Chapter 1

Chapter 1: Introduction
In the 21st century, education is very important to almost everyone in this world. As the technologies improve from time to time, there are some technologies had also been integrated into the classroom in order to improve the quality of the education and study’s environment. This classroom is also known as smart classroom. The first technology that had been integrated into the classroom is the Smart Board interactive whiteboard. The Smart Board interactive whiteboard operates as part of a system that includes the interactive whiteboard, a computer, a projector and whiteboarding software. This technology is still being used worldwide.
Recently, according to a survey which done by Phil Sharp in US, it was found that 80% of the teachers agree that the usage of technology shows positive result in the classroom. As for now, the most popular technology that used in the smart classroom is the small laptops and tablets due to its easy interface and. For tablet such as iPad, students who have disabilities show positive attitude in learning when they use the tablet. For small laptops such as Chromebooks, it has a simple web-based operating system which allow the students to use it easily during study.

However, in this project, the aim is not to use these advance technologies equipment to build the smart classroom. The aim of this smart classroom project is to build a smart classroom that able to reduce the usage of electricity as well as implement an automated attendance taking system to record the attendance of students systematically. Other than that, an electromagnetic lock will be install at the door of the classroom as well for security purposes.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

Nowadays, there are some non-profit organisations encourage the society to reduce the usage of energy to produce a green environment. Since the wastage of electricity is also considered as wastage of energy, thus the team decided to build the smart classroom that able to reduce the wastage of electricity. Next, Proper attendance recording and management has become very important in today’s world. Most of the educational institutions in our country still using paper based attendance method for maintaining the attendance records. This method is not systematic as there are times the lecturers forgot to bring the attendance list to the class or lost it unknowingly. Moreover, it is also time consuming which the lecturer need to call out student’s name to take the attendance. In order to solve this problem, the team decided to implement an automated attendance taking system.
Overview
In this smart classroom project, the 2 main problems that needed to be solve is the wastage of electricity and the attendance taking method. The problem of wastage of electricity is vital as the wastage of electricity causes an increase the amount in electricity bill. Furthermore, wastage of electricity is also shows that the energy is wasted. This problem can be solved by controlling the electrical appliances in the classroom automatically. When there is no one in the classroom, the electrical appliances in the classroom will be switched off and vice versa. Next, the current attendance taking method is not systematic as there is times when lecturers forgot to take the attendance list or lost it unknowingly. Therefore, automated attendance taking system will be implemented in the classroom. This automated attendance taking system will be using RFID technology to record the student’s attendance and store the data into a cloud.
Project Objective
The objectives of this project are such as:
To reduce the wastage of electricity.

To be able to record the attendance in a systematic way by using RFID system.

To minimise the project cost.

Problem statement
The problem statement that is to solve in this project are such as:
What is the improvement that the current smart classroom can be done.

How much is the energy waste can be saved in this project.

How efficient can the data logging can be done compare to the manual way.

How fast can the data write into the cloud.

Chapter 2: Literature Review
INTERNET OF THINGS
Internet of things (IoT) has emerged as a new network paradigm which allows a lot of physical objects in the world to connect with each other. IoT was first proposed in 1999 by Kevin Ashton, who is the co-founder of Auto-ID center at the Massachusetts Institute of Technology (MIT). CITATION Kev09 l 1033 (Ashton, 2009) One of the most common IoT technology is Radio Frequency Identification (RFID) technology. Through RFID technology, the physical objects can be identified, tracked and monitored automatically. CITATION XJi12 l 1033 (X. Jia, 2012) Another common technology of IoT is Wireless Sensor Networks (WSNs), which the intelligent sensors are interconnected to periodically sense the monitored environment and send the information to the sink (or base station), at which the collected information can be further processed for end-user queries. CITATION JHe14 l 1033 (J. He, 2014)SMART CLASSROOM
Ciaran O’Driscoll defines a smart classroom is a pseudo intelligent room that can reconfigure itself and its resources automatically based on predefined profiles for specific user groups. CITATION ODr09 l 1033 (O’Driscoll, 2009) Furthermore, Ciaran O’Driscoll also stated that the smart classroom, in simple terms, are interactive classroom that provides an additional level of automated response based on specific situation and are a subset of Smart Spaces. CITATION ODr09 l 1033 (O’Driscoll, 2009) In the future, Ciaran O’Driscoll proposed to develop an interactive response system that can use mobile phones to permit peer instruction at any classroom. CITATION ODr09 l 1033 (O’Driscoll, 2009)Anurag Chaudhary, Gaurav Agrawal and Meghna jharia think that the importance of smart classroom is a new generation educational product which helps students gain more marks and is a step to the future of education. CITATION Anu14 l 1033 (Anurag Chaudhary, 2014) Anurag Chaudhary, Gaurav Agrawal and Meghna jharia also stated that the smart classroom also aim to develop students learning ability as the entire chapters become more interesting to study and hence improve the results of the students. CITATION Anu14 l 1033 (Anurag Chaudhary, 2014)Maheshwari thinks that a smart classroom able to improve the education quality to the students. The students able to learn better concept formation, concept elaboration, improvement in reading skills and academic achievement. CITATION VKM16 l 1033 (V.K.Maheshwari, 2016)
Recently, Uskov and Heinemann found that the smart classroom (SmC) had become a hot topic for discussion internationally. In several recent years, the ideas of smart education (SmE), smart university (SmU), smart classroom (SmC), smart learning environments (SLE), and related topics became the main themes of various pioneering international and national events and projects, governmental and corporate initiatives, institutional agendas and strategic plans. CITATION Usk17 l 1033 (Uskov, 2017)Davar Pishva and G. G. D. Nishantha proposed to design smart classrooms that will integrate voice-recognition, computer-vision, and other technologies, collectively referred to as intelligent agents, to provide a tele-education experience similar to a traditional classroom experience. CITATION Nis08 l 1033 (Nishantha, 2008)-3175127000Figure I: Classroom architecture designed by Davar Pishva and G.G.D. Nishanta CITATION Nis08 l 1033 (Nishantha, 2008)
Jungwoo Lee, Yongki Park and Myung Suk Cha proposed a new smart classroom system through the combination of smart pedagogies, smart content and smart information technologies. “a new classroom environment that is created by the convergence of advanced pedagogies, educational content getting smart, and information technologies and derive the classroom system’s architecture and functionality from the analysis of scenario-based requirements.” CITATION Jun13 l 1033 (Jungwoo Lee, 2013)
At Dublin Institute of Technology (DIT), the Institute had several classrooms equipped with the interactive smartboards. The function of the interactive smartboard allows user to blend computer graphic with the traditional white board for a truly interactive digital learning experience. CITATION Dub17 l 1033 (Anon., n.d.)
Stephen S. Yau, Sandeep K. S. Gupta, Fariaz Karim, Sheikh I. Ahamed, Yu Wang, and Bin Wang proposed to build a smart classroom that facilitates collaborative learning using (Reconfigurable Context-Sensitive Middleware) RCSM which is a middleware for pervasive computing applications. CITATION Ste13 l 1033 (Stephen S. Yau, 2013) 11 Stephen S. Yau, Sandeep K. S. Gupta, Fariaz Karim, Sheikh I. Ahamed, Yu Wang, and Bin Wang also stated that the smart classroom is divided into 2 categories, infrastructure-device which consist of PCS and PDAs with the capabilities of location and light detection and mobile-device which is using the PDAs. CITATION Ste13 l 1033 (Stephen S. Yau, 2013) CITATION Ste13 l 1033 (Stephen S. Yau, 2013)
Figure II: The layout of smart classroom proposed by Stephen S.Yau and his team.

CITATION Ste13 l 1033 (Stephen S. Yau, 2013) 11
Figure III: The architecture of the smart classroom proposed by Stephen S.Yau and his team.

Kirti Tanwar and Stuti Gupta proposed to implement a smart classroom using the Li-Fi technology instead of using the Wi-Fi technology. This is because Wi-Fi technology uses the radio waves and radio frequency communication requires radio circuits, antennas and complex receivers which are also harmful for the human being. CITATION Kir14 l 1033 (Kirti Tanwar, 2014) They also stated that the Li-FI technology is much simpler and uses direct modulation methods similar to those used in low-cost infra-red communications devices such as remote-control units. CITATION Kir14 l 1033 (Kirti Tanwar, 2014).

Chien-Wen Shen, Yen-Chun Jim Wu and Tsung-Che Lee proposed to design a smart classroom by using the near field communication (NFC) technology that able to automated attendance system, locate students, and provide real-time student feedback. CITATION Chi14 l 1033 (Chien-Wen Shen, 2014) CITATION Chi14 l 1033 (Chien-Wen Shen, 2014)Figure IV: The layout of smart classroom proposed by Chien-Wen Shen and his team.

Jeffrey P. Bakken, Vladimir L. Uskov, Archana Penumatsa and Aishwarya Doddapaneni proposed to design a smart classroom that will be able to benefit the students with disabilities. The disabilities are such as learning disabilities, speech and language disabilities, visually impaired or blind and hearing impaired or deaf. CITATION Jef16 l 1033 (Jeffrey P. Bakken, 2016)Paul Morrison compiled 6 key themes of future smart classroom and expect to see it happens in the near future. The 6 key themes are:
IoT spreading across the Institution
Always-on experiences
Intelligent spaces
Wearable and location-awareness solutions
Virtual Reality (VR) and Augmented Reality (AR) for teaching
Multiplication of dense environments
CITATION Mor17 l 1033 (Morrison, 2017)Chapter 3: Product Design
In this project, it is required to design a smart classroom which is to achieve the aim to transform Tunku Abdul Rahman University College (TARUC) into smart and green campus. Before designing the smart classroom, there is some constraint and problems need to be identified first. The constraints and problems will be identified in point forms as shown below.

CONSTRAINTS
The modification works should be as few as possible to ease the college wide implementation
The overall implementation cost must be as low as possible to make it happens to all classroom
PROBLEMS
Classrooms in TARUC are always left unattended without the electrical appliances being switched off which results in high electrical bill and wastage of energy.

Classrooms remain in its conventional appearance without much improvement for the past few decades.

In order to solve the problems with the constraints, an initial solution is proposed. The proposed solution will be:
A sensor will be placed in the classroom to sense whether any students left in the class. If there is none, the electrical appliances in the classroom will be switched off.
An automated attendance taking system will be implemented in the classroom. This allows the lecturer to save time by taking attendance of students.

A magnetic lock will be installed at the entrance door of the classroom. This solution able to improve security.

Upon the solutions, the outcomes are:
College’s electricity can be cut down as electrical appliances are not used and forcefully shut down if there is no class in the schedule.

Classroom is protected from time to time as the door will be locked from a period of time to another time.

Lecturer’s beneficial of need no to print, bring and collect the attendance from the students as the attendance taking system is introduced and used, which also allows student no need to sign and pass the attendance list around the class, and recollect by lecturer again.

Improving the attendance rate of the student.
The designs are to divide to 3 parts, that is:
Electronic hardware part which the sensors controlling the current availability to the electrical appliances
Main core software part which the attendance taking system can be executed and signal send and receive by the sensor for controlling the electrical appliances
Scanning and safety hardware and software which controls the safety of the classroom and the happening of the attendance taking system.
Overview Block Diagram

Figure V
Centralized Monitoring System is the desktop computer which allows the uploading, changing and scheduling the information through accessing the database. The information such as student’s information, lecturer/tutor’s information and classes schedule from time to time are updated through this system. If the schedule such as tutor/lecturer is on medical leave or cancel classes or festive, the changes upon the schedule can be immediately perform and upload to the database. Database is the platform where the Centralized Monitoring System are to upload in the information and store into it as well allowed to change. The database will serve and connected to the microcontroller through the Wi-Fi module.

Wi-Fi module act as a pathway and allows the communication between database and the microcontroller’s RX-TX system. Microcontroller will receive the information from database through Wi-Fi module as signal, allows its operation to control the classroom by sending signals to the sensors, hardware systems. The connection between the microcontroller and RFID system allows the changes and updates of the signal to be sent to the database for the Attendance Rubrics.

Sensors are functioned to sense if, any movements are present for the energy saving purposes. Sensors will send signal to the microcontroller when sensed any movement, and allows the electrical appliances to function through the relay switches, as well to switch off if no sensing any movement in the next period of time.

Hardware Control Overview Block Diagram

Figure VI
Upon the setting from the microcontroller with the data from the database which created by the centralized monitoring system:
Relay system will be acted as the allowing or cut-off when either> a certain period of time before the class starts, allows the electrical appliances to be switched on> Scanning system is proceeded and sensors sensed the movement, the relay system will allows the current to flow through certain of the electrical appliances (for no classes in schedule cases)> forever cut off when there is no signal triggered from sensors, not in the schedule AND no power supplyAutomatic Door System which uses Electromagnetism device which attach to the door for allowing the entering when is in the schedule and working hours. It is controlled by the microcontroller by setting the odds of the time interval and the scheduling of the class upon the databases. The signal pulse will be sent from microcontroller, and allows the discharging of the electricity for disabling the electromagnetism which happens between the device on the door.Scanning System Overview Block Diagram

Figure VII
Scanning system is functioned for the attendance taking purpose, allows the information and signal sends to the database through the Wi-Fi module from the microcontroller. When scanning system is executed, it will send signal to the microcontroller and the signal will then communicate to the Wi-Fi module, and overwrite or mark the attendance of that particular in database.
Parts ComparisonMicrocontroller
Microcontroller is an important item in this project. This is because microcontroller will be the brain of the smart classroom as it will control all the sensors and process the data then transfer to the cloud or retrieve data from the cloud. There is a lot of microcontrollers available in the market. However, we decided to choose 3 types of common microcontroller that most of the user will choose to use to do a comparison. The 3 types of microcontroller are:
Arduino UNO
Raspberry Pi 3
ARM Mbed NXP LPC1768
Arduino UNO
Figure VIII
Arduino UNO is a microcontroller board based on the ATMega328P. Arduino UNO consists of 14 digital I/O ports, 6 analog input ports, 16 MHz quartz crystal, a USB connection, a power jack, an ICSP header and a reset button. 6 PWM digital I/O pins can be found as well on the Arduino UNO. The operating voltage of Arduino UNO is at 5V. Regarding to memory, Arduino UNO has 3 types of memory built-in. The 3 types of memory are:
Flash Memory (32KB)
SRAM (2KB)
EEPROM (1KB)
To write a program into Arduino UNO, a compiler produced by Arduino company need to be downloaded. The compiler is known as Arduino IDE. Arduino IDE supports with C / C++ language which also means that programmer need to have the knowledge of C / C++ in order to write a program and upload into Arduino UNO. Since Arduino is an open source platform, there is a lot of examples and source codes can be found on the Internet. The price of an Arduino UNO will be around RM 30.

Raspberry Pi 3
Figure IX
Raspberry Pi is a series of small single-board computers. Raspberry Pi can runs on non Linux-based operating system or Linux-based operating system. Raspberry Pi 3 is the latest version of Raspberry Pi microcontroller. Raspberry Pi 3 microcontroller is using the architecture of ARMv8-A. The CPU in the Raspberry Pi 3 is running a 1.2 GHz 64-bit quad-core ARM Cortex-A53. A 1GB RAM is included in the Raspberry Pi3. There is 40 GPIO extend pin on the Raspberry Pi 3. For additional feature, Raspberry Pi 3 also consists of BCM43438 wireless LAN and Bluetooth Low Energy (BLE) on board. Besides that, HDMI port also included on the board to connect the Raspberry Pi 3 to a LCD or LED TV screen. usually used for complicated projects. Raspberry Pi 3 are usually used for a complicated project as it has a powerful processor that able to do multiple of tasks at once.

There are a lot of compilers available for programmer to write program and upload into the Raspberry Pi 3. Different compilers use different type of language. Therefore, Raspberry Pi 3 are not suitable for beginner programmer as it requires to understand a lot of programming language. One of the most common language that Raspberry Pi 3 used is Phyton. The cost of a Raspberry Pi 3 is around RM 180.

ARM Mbed NXP LPC1768
Figure X
The ARM Mbed microcontrollers are a series of ARM microcontroller development boards designed for rapid prototyping. ARM Mbed NXP LPC1768 is running with a 32-bit ARM Cortex-M3. Regarding to memory, it includes 512KB of FLASH and 32KB RAM. The ARM Mbed NXP LPC1768 also includes built-in Ethernet, USB Host and Device, CAN, SPI, I2C, ADC, DAC, PWM and other I/O interfaces. 26 digital I/O pins can be found on the ARM Mbed NXP LPC1768.
As for the compiler, ARM Mbed NXP LPC1768 is usually program with µVision compiler. Online compiler also allow user to write their program and upload to the microcontroller. µVision compiler and online compiler for ARM Mbed NXP LPC1768 used C language for programming. Moreover, source code and example also can be found on the ARM Mbed community forum. The price of ARM Mbed LPC1768 microcontroller is about RM350.

A table is produced to summarise the 3 types of microcontrollers.
Arduino UNO Raspberry Pi 3 ARM Mbed LPC1768
CPU ATMega328P quad-core ARM Cortex-A53ARM Cortex-M3
Digital I/O 14 17 26
Analog I/O 6 0 6
RAM 2KB 1GB 32KB
Memory 32KB Used Micro-SD card 512KB
Programming language C / C++ C / C++ / PhytonC / C++
Price RM 30 RM 180 RM 350
Additional feature Extension I/O ports HDMI Port / BCM43438 wireless LAN / Bluetooth Low Energy (BLE) Built-in Ethernet / LCD / LED / Buzzer / Potentiometer / Joystick
Table I
Automated attendance taking systemAutomated attendance taking system is a system whereby the attendance of students will be taken automatically using technologies. There are a few technologies can be use to build this automated attendance taking system. The technologies are such as:
RFID
Biometric fingerprint
Facial recognition
RFID
Figure XI
RFID, which also known as Radio Frequency Identification uses the electromagnetic field to identify and track tags attached to objects. The working principle of the RFID system is the reader coil will generates an electromagnetic field, which couples into the coil on the RFID tag which also known as RFID-Transponder. The field generates a current in the transponder, which powers it, and also contains the transmitted data.
Figue XII
The tags are storing with electronic information. RFID system can be classified by the type of tag and reader. There are 3 classification of RFID systems which are:
Passive Reader Active Tag (PRAT)
This system consists of passive reader which only receives radio signal from the active tag. The active tag is operating with battery.
Active Reader Passive Tag(ARPT)
This system has an active reader, which transmit interrogator signal and receives reply from the passive tag.

Active Reader Active Tag(ARAT)
This system uses active tag awoken with an interrogator signal from the active reader. Besides that, this system could also use a Battery-Assisted Passive (BAP) tag which acts like a passive tag but has a small battery to power the tag’s return reporting signal.

As this RFID system requires a RFID tag to identify an object. Thus, this system consists 3 types of RFID tag. The 3 types of RFID tag are:
Active tag
Active tag consists of a battery and transmit signal periodically.
Passive tag
Passive tag does not consist of battery to transmit signal. However, it uses the radio energy transmitted by the reader to transmit signal.

Battery-Assisted Passive (BAP) tag
Battery-Assisted Passive (BAP) tag has a small battery on board and is activated when in the presence of a RFID reader.

Biometric fingerprint
Biometric fingerprint technology is an automated system that able to recognize a person based on his or her fingerprint’s characteristics. The fingerprint of a person stores his or her personal information. This personal information cannot be stolen and used to access personal information as biometric template cannot be reverse-engineered to recreate personal information. To read the personal information of a person, a fingerprint scanner is needed.

A fingerprint scanner system has 2 jobs which are getting image of your fingerprint and determine the image of fingerprint matches the pre-scanned image. Every fingerprint has its own specific characteristics. These specific characteristics are filtered and saved as an encrypted biometric key. This biometric key will convert into binary code which will be saved for verification purpose. The algorithm cannot be reconverted to an image. Thus, the fingerprint cannot be duplicated.

Figure XIII
Facial Recognition
Face recognition technology measures and matches the unique characteristics of a face for the purposes of identification or authentication. This is similar to the biometric fingerprint technology as it also identifies a person’s information based on physical characteristic. This technology is often leveraging a digital or connected camera, facial recognition software can detect faces in images, quantify their features, and then match them against stored templates in a database.

Figure XIV
RelayRelay are mainly an electricity operated switch and mostly use electromagnet to mechanically operate the switch. When electric current is passed through the coil inside the relay, it generates a magnetic field that activates the movement either connects or breaks the connection with a fixed contact. However, if the current rating of the relay is driven by large current which exceed the current rating, the relay will forcefully malfunction and results overloading.
The types of relay can be divided among mechanical comparison and energy transforming comparison. For mechanical comparison, it is usually to be seen that the relay works with spring operated, or by pneumatic. However, for household and academic places such as school or college, it is usual to use the spring operated relay. While the pneumatic relay is used in the heavy duty area or factory.

Figure XV: Electromagnetic spring operated relay
The spring operated relay are usually perform the operation under the electromagnetism, where when the current is passed through the magnet coil inside, the electromagnet will be energized and actives the electromagnetism between the coil and the steel plate. As the result, the spring will hold the steel plate when electromagnetism is occur, and is release the steel plate when the electromagnet is de-energized, thus switching the current to ON or OFF depends on the connection.

Figure XVI: Pneumatic relay using air flow control
Pneumatic relay is connected to circuits that conduct compressed air rather than flow of electrons by using the same principle. The difference is that when the presence of the compressed air is flowing through one circuit, the force of that energy opens up switch and begin to flow to second circuit. The sensor needs to be present so that to make the switching to occur.

Motion sensors The device that detects moving objects. The device is often integrated as a component of a system that automatically performs a task in its area. Sensors are mostly passive with their sensing a signature only from the moving object via emission or reflection. They are commonly found wide use in domestic and commercial applications.Passive Infrared (PIR) SensorAn electronic sensor that measure infrared light radiating from objects in its field of view. All the objects with a temperature above absolute zero emit heat energy in the form of radiation. These radiation is not visible to human eye because of the wavelength is not visible wavelength but infrared wavelength, but the detection is possible by electronic devices as they designed for this purpose. Passive in this terms meaning that it does not emit or generate energy for detection purposes, but detection the infrared that is emitted or reflected FROM the object.

Figure XVII (left: sensor block diagram; right: PIR sensor)
Ultrasonic sensorAlso as ultrasonic transducer. It divides into 3 boards that is transmitters, receivers and transceiver. The transmitter converts electrical signals into ultrasound, receiver converts ultrasound into electrical signals and transceiver can both transmit and receive ultrasound. It used in systems which evaluate targets by interpreting the reflected signals.
Figure XVIII: Ultrasonic Sensor
Design choices for Smart Classroom
Functionality Choices
Microcontroller model used ARM Cortex M-Bed LPC-1768 -4201517335600Raspberry Pi-3 42013938452100Arduino UNO MEGA
Types of Wi-Fi module used
45351922402600Ethernet -290308-55723000574745-56280500
46151622582000BLE ESP-8266
Protection of electronic part(cut off current when no detection or out schedule) 127052147943005V/ 3.3V input 1 channel 10A Relay
4370542124400 Circuit breaker devices
Types of Motion Sensor used
1249391-35698600
46863045246800Passive Infrared (PIR) 589268-47180600
48260025781000Ultrasonic Type of reading way RFID System Face Recognition Fingerprint
Materials for the system covering (Packaging)
434028-12890500
Plastic 1285280-409258001213663-48002500
Aluminium Glass
Table II: Design Choice Path
100584026479500
100584027368500Design 1
100584029337000Design 2
Design 3
Types of reading frequency for RFID System division:> Low> High> Ultra-high

Weightage Distribution
Performance Weightage Rating: 30%Performance criteria is weighted the highest rating of 30% due to the involving of programming, reading and recording and changing of data, sensing operation and relay operations. The programming for the main core will decide the operations and outcome of the product. Programming of microcontroller:C programmingWi-Fi module connection:Cloud / Drive Operation for relay: switch when detection of sensors and scheduleOperation for sensing:disable if no motion detected after 5 minutesRecording of data:Cloud / Drive uploadChanging of data:Cloud / Drive upload
Cost Weightage Rating: 20%Cost of the product is medium weighted due to the processors and operations availability of the product. Microcontroller in this criteria is used for the main core, will decide the available operations as well the simplicity of the connections. The hardware part, as well is concerned due to the usage of the sensors and the relays as well the protections. The sensor is suggested to install more than one if the space of the installed area is large. Furthermore, the relay module is suggested to install number as because relay is a switch for functioning to cut off or connect for the certain signal given. While the scanning system (feature) will be decide if to or not for the installations because it is a feature that is for the user to decide.Arduino cost:CostAvailable I/O pins> ARM-CortexRM 35070`> Arduino UNO RM 3054> Raspberri Pi-3RM180 14
Safety Weightage Rating: 20%The reason why safety is slightly more important than durability criteria because this system is involving of the connection, especially the relay connection and operations, which if the relay support is not enough to sustain the current needed in the operating area, the worst case scenario of current overflowing will occur and destroy the relay as well the wiring connection of the both hardware part on product and operating area. Circuit breaker or multiple relay control is strongly advised for preventing the worst case scenario to be happened.
Durability Weightage Rating: 12.5%The product is mostly dealt with the electronic parts and the programming interface, therefore the connections of the whole system for the product must assure to be correct and exact position. The lifespan for the product is unpredictable if the operating area having unstable power supply.

Standard Parts Weightage Rating: 12.5%Standards Part is weighted 12.5%. The standard parts for the product can be easily found in robotic or electronic shops for the both hardware parts and scanning system parts. However, it is recommended to use the same model of the product as the configuration in the microcontroller are fixed for all the operations.

Portability Weightage Rating: 5%Portability is rated the lowest of 5% because the product will be packaged as a device which looks like a small box, meaning it can placed no matter where it is. But it is recommended to place them at a fixed position so that the wiring connection can be configured with fixed.

Criteria Rating Matrix
Criteria Weight (%) Design 1
Design 2 Design 3
Rating (0 – 10)
Rating (0 – 10) Rating (0 – 10)
Rate
Weight Rate Weight Rate Weight
Performance
30.0 8.0 0.24000 8.5 0.25500 7.0 0.21000
Cost
20.0 3.0 0.06000 8.5 0.17000 5.5 0.11000
Safety
20.0 6.5 0.13000 7.0 0.14000 4.5 0.09000
Durability
12.5 6.5 0.08125 7.5 0.09375 6.0 0.07500
PartsAvailability
12.5 3.5
0.04375 9.5 0.1185 3.5 0.04375
Portability
5.0 4.0 0.02000 9.0 0.04500 2.0 0.10000
Total
100.0
0.57500 / 57.50% 0.82225 / 82.23% 0.62875 / 62.88%
Table III: Rating Matrix of designs
Through the matrices, design 2 has the highest scoring compare to the other designs, so design 2 is selected.

Explanation Selection of Conceptual Design
Performance
-Design 1 (8.0/10.0)-It earned 8.0 out of 10 because of the functionality of the microcontroller is better but complex as well the program for it are hard to understand and perform. While the Wi-Fi module are ease by just connecting pins to the microcontroller. PIR sensors are great to detect any movement.
-Design 2 (8.5/10.0)-It earned 8.5 out of 10 because of the functionality of the microcontroller is easy to use and performed, as well the I/O pins are greater. The Wi-Fi module are easy to connect and programmed, as well common to get the source code.

-Design 3(7.0/10.0)-It earned 7.0 out of 10. The microcontroller are same as the design 2 but the I/O pins are lesser. The ultrasonic sensor as sensing are not effective range as Passive Infrared.

Cost
-Design 1 (3.0/10.0)It rated 3.0 out of 10.0 only because the cost of the microcontroller is among the highest, the way for reading in extra feature is among the highest, and the device for the protection of the electronic parts is the highest as well.

-Design 2 (8.5/10.0)It earned 8.5 out of 10 because the Wi-Fi module is the most affordable among the choice, the device for the protection of the electronic parts is the most affordable, the way for reading in extra feature is the lowest cost as well the packaging.
-Design 3 (5.5/10.0)It earned 5.5 out of 10 because the cost of microcontroller is among the lowest. The cost of the choice in the motion sensor is affordable as well.

Safety-Design 1 (6.5/10.0)It earned 6.5 out of 10 because it is safe for using the circuit breaker and this allow the immediate cut-off if over current is detected. But for the material, the aluminium might having sharp edge when manufactured and packaged, which will lead to the physical injuries. Also the risk of the privacy when using fingerprint because it is easy to obtain a particular’s fingerprint through some way and possible to steal the information of the particular’s identity.

-Design 2 (7.0/10.0)It earned 7.0 out of 10. Although relay is not as powerful as the circuit breaker, but relay are used as an external control switch and could be use in numbers for the control if it is not needed on the particular electronic devices. The material is plastic and it is assure that is safer than design 2’s material.-Design 3 (4.5/10.0)It rated 4.5 out of 10 because the material used for packaging are glass, which is quite heavy and ease to break if any external force applied.
Durability-Design 1 (6.5/10.0)It earned 6.5 out of 10 because the usage of the aluminium as packaging, where the oxidation and aging will happens on the surface, also the heat transverse will happen under the hot weather, which will damage the board in the system.
-Design 2 (7.5/10.0)It earned 7.5 out of 10 because of the usage of the plastic as packaging. The colour of the plastic can be selected and it is better to use light colour such as white, yellow or light grey for the heat reflecting purpose so that the internal circuit can be protected when hot weather.
-Design 3 (6.0/10.0)It rated 6.0 out of 10 because of the usage of glass as packaging. It is not just light, but transparent or translucent which allows the sunlight under hot weather as well the heat easily pass through and damage the board in the system (depends on the position where user is placed)

Standard Parts-Design 1 (3.5/10.0)It rated 3.5 out of 10 because parts in used in the design are not easily to obtained, such as the aluminium in packaging, circuit breaker, and the usage of the scanning way of fingerprint which it needs authorized agent’s approval. As well the Wi-Fi module and microcontroller and not easily to obtained if any changed or damaged is seen.

-Design 2 (9.5/10.0)It earned 9.5 out of 10 because the parts used in the design are easily to obtain, such as the microcontroller, Wi-Fi module, parts for protecting the electronic devices and parts used for the reading way are easily found in electronic shops if damaged or changed is needed. As well material for the packaging are common to obtained and shaping too.

-Design 3 (3.5/10.0)It rated 3.5 out of 10 due to the packaging part of using glasses are rare to get for replacing, as the usage of the scanning way of face recognition which it needs authorized agent’s approval like design 1.

Portability-Design 1 (4.0/10.0)It rated 4.0 out of 10 because of the usage of circuit breaker, which it is to fixed its position near the power supply.

-Design 2 (9.0/10.0)It earned 9.0 out of 10 because the relay can be used severally and control the connection, as well the product which use product as packaging can be install in anywhere as it is light weight.

-Design 3 (2.0/10.0)It rated 2.0 out of 10 because of the material used for packaging is glass which is the heaviest and risked among the design and not safe to hang in anywhere but supporting.

Flow chart of the product working
Figure XIX: Flow chart
Positioning Definition> Outside of Classroom
Figure XX
The planning of the whole Smart Classroom will have the setting of the position for Microcontroller and the Wi-Fi Module. It is advised to place them on the ceiling and the central site among the classroom as shown in the diagram. This is because it can be balance the usage of the wiring to every scanning devices that will place in front of every room (if, possible). The scanning devices will allow the attendance procedure to be execute and the automated magnetic door will open as safety purpose as well in the schedule where class will be having in. Wi-Fi router is allowed to connect with centralized monitoring system and receive and send data and signal to the microcontroller through Wi-Fi module. Which first its operation is to check if the classroom is in the schedule. >Inside of ClassroomUpon the connection of the microcontroller and the Wi-Fi model is placed outside of the rooms, the relay that controls the electrical components. The advices of the usage of relay to control divides to 3 sets.> 1st set: controlling lamp and fan> 2nd set: computer and projector (ignore if power source is installed inside for the purpose)> 3rd set: switching on/off the purpose usage of air conditioner (this is because air conditioner drained much more than other appliances)The scanning devices is the purpose for the attendance taking. It depends to user where it placed would be better.The sensors are advised to install with this setting IF there is a ceiling block which is same height of the fan in the room. This is because the sensor will still sense the movement of the fan even there is no one in the classroom, results it will still continue to send signal that there is still movement inside and allows the electrical appliances to continue to supply, and thus energy waste.
Figure XXI
Figure XXII: Sensor sensing area (Top view)

Figure XXIII: Sensor sensing area (Side view)
For the case that there is no ceiling block, it is advised that the sensors are to install in this way. This is because the sensor will still sense the movement of the fan even there is no one in the classroom, results it will still continue to send signal that there is still movement inside and allows the electrical appliances to continue to supply, and thus energy waste.

Figure XXIV

Figure XXV: Sensor sensing area (Top view)

Figure XXVI: Sensor sensing area (Side view)

Chapter 4: Impact on society
Smart classroom is getting used in the school and college world-widely. By defining the ‘smart’ in the smart classroom, we are commonly see the smart classroom are used when having lecture or tutorial classes, by using the computer, projector, screen and the whiteboard. Lecturer or tutor will have the slides file which contains the material of the subject, stream them slide by slides through projector projects them on the screen. This ‘smart’ defines as the smart teaching. Through the eras, the ‘smart’ defines more crucial as it defines not just smart in teaching way but save power and increase the efficiencies. Therefore, smart classroom is redefined to have smarter teaching way, saving power and getting more efficient.
HealthSmart classroom consists of electrical components and sensors. The health issues are mostly regarding on the radiation such as electromagnetic field radiation. The radiation that is emitted from the devices and sensors are commonly in wave frequency which is the non-ionizing electromagnetic radiation. Such radio frequency radiation, low frequency radiation. These radiations do not exceed the harmed level and the effect on body are mostly after accumulation or long-time contact of these radiation. The radio frequency will affects the heating of body tissues when in exposed long time, low frequency will have the cumulation of change on body surfaces such as disturbance of nerve and muscle responses. But as mentioned, these effects are only actives after a long time accumulations.
If or unless, the individual suffers disabilities ‘Electromagnetic Hypersensitivity’ or if the individual suffers heart chronic and using device in body ‘pacemaker’, these electromagnetic radiations are fatal to them. For the disabilities ‘Electromagnetic Hypersensitivity’, the individual possibly experiences symptoms such as headache, fatigue, stress, sleep disturbances, pain and ache in muscles and various health problem; for the device in body ‘pacemaker’, these frequencies will develop adverse effect as Electromagnetic interference, which defined as interference of pacemaker function by the signals generated by external source.

Safety and Privacy
The safety concern is assured as the smart classroom in this project are in the objective of safety purpose, which is the reason of the automatic lock system are introduced and involve in this project. While the privacy, the lost of the ID on the scanning object would be a risk or threat because the ID consists of all the information which is similar to personal identification card. To prevent the information leakage, the individual is advice to report and deactivate the lost scanning object and re-do a replacement of it when they lost their ID.

Certification and Legal
Upon the certification to legalize and permit for smart classroom, ISO, which defines standard of the product which includes product design requirement, test methods, product specification, performance requirement, classifications and practises, are to apply by submitting the completed Questionnaire to the SIRIM QAS. The quotation will be issued after feasibility for certification is examined with respect to the standards and availability of testing facilities. After the acceptance of quotations, document evaluation and factory audits, SIRIM QAS issues Product Certification License and will categorize as Trading Company with the product manufactured locally by a Certified Manufacturer. For the certification renewal, it is valid for one year from the date of approval and it is renewable on yearly basis subject to terms and condition. It is understood that this certification allows an independent assurance that the product is manufactured / made under an effective system of testing, supervision and control, safety and reliability, protection against competition from substandard products and misrepresentation,as well as improve efficiency in production and reduce wastage and reject.

Authority of College/ School’s view
For the saving electricity purpose, the unwanted usage can be cut down drastically and therefore save money for the bills.

The usage of the scanning for attendance taking system will have a great impact of changing to the authorities. For instance, the lecturer saves lots of work than before as they need to print the attendance list, passes to students for the signature as present and recollect from them (or call name by name to check if student is present and this takes lots of time), as well they need to bring them every lecture as well to hand in every end of month and does the same again in the following month. For authorities, they will need to collect and check the percentage of the presence for the students one by one. This attendance taking system will save lots of work by just checking the list through the database whether students are present or not. The saving of printing of ink and papers for the attendance list can greatly reduce as well.

While the safety and security purpose, all the aspects in the college or school can save their worries as the classroom will automatically lock when the designated time is reach and unlocked vice versa.

Student’s view
The greatest impact will be feature of the attendance taking system, which they will have high discipline and punctuality to attend the classes in order to gain the attendance. Although it is not fair for some cases that having bad weather happens and students or lecturers that stay at the area which is far away from the college or school, but their willpower on academy will gained. This risk they will face is the misuse of identity if losing scanning object as it is because the primary identity almost similarly to the identification card.
Parent’s view
It has not much impact to parents, but the concerning of their children’s lifestyle and discipline are greatly affected. By introducing the smart classroom, the attendance taking system and security system will ensure and let the parents to be less worry.

Chapter 5: Financial analysis
Company description
SMARTS SDN BHD is a newly established company which provides efficient and reliable services to build a smart classroom in Malaysia. SMARTS SDN BHD owned and operated by partners, Cheng Guan Jie, Teoh Khy Jun and Gan Ji Sheng. SMARTS SDN BHD is set to start its business on 8/1/2018.

Management Directory
Mr Cheng Guan Jie, Chief Executive Officer (CEO)
Mr Cheng studied Bachelor of Engineering (Hons) Mechatronics Engineering at Tunku Abdul Rahman University College (TARUC). Recently, Mr Cheng did his research on the smart classroom system. Besides that, he possesses a good leadership skill in leading a team. Thus, Mr Cheng is recommended to become the CEO of the company.

Mr Teoh Khy Jun, Chief Operating Officer (COO)
Mr Teoh studied Bachelor of Engineering (Hons) Mechatronics Engineering at Tunku Abdul Rahman University College (TARUC). Mr Teoh has a high interest in smart classroom system. Furthermore, he has a very good project management skills and knowledges which is the reason he is the Chief Operating Officer (COO) of the company.

Mr Gan Ji Sheng, Chief Technology Officer (CTO)
Mr Gan studied Bachelor of Engineering (Hons) Mechatronics Engineering at Tunku Abdul Rahman University College (TARUC). Mr Gan has various experiences on building and design of the technology item. Moreover, his also did a lot of research on new technology which we believe that he can hold the position of Chief Technology Officer (CTO).

Product and services
The purpose of the company is to build a smart classroom which will improve the quality of education. As now we are in the 21st Century, students nowadays expose to a lot of smart technology which they find it convenience as well as comfortable to use it at the same time. The design of the traditional classroom had not been changed for a few decades. Therefore, we are now providing the services to build a smart classroom which we believe that the students will feel happy to study in a smart classroom and at the same time the quality of education will improve as well. The product that we have created are such as automated attendance taking system, magnetic door lock and automated electrical appliances control system.

Mission statement
To invent smart technology into a classroom.

To improve the quality of education.

To reduce the usage of electricity of a classroom
To implement automated attendance taking system into a classroom.

Business location and contact details
Location
20A, Jalan Prima Setapak 1,
Setapak, 53300 Kuala Lumpur,
Wilayah Persekutuan Kuala Lumpur
Contact details
Mr Cheng Guan Jie (012-3059753)
Mr Teoh Khy Jun (017-2960663)
Mr Gan Ji Sheng (016-6288398)
Email: [email protected] projection
Products Price (RM)
Arduino UNO 30
ESP 8266 Wi-Fi Module 15
PIR sensor 42
Relay 1 channel 10A 12
RFID receiver 30
Electromagnetic lock 60
Table IV: Price for product that need to purchase
In this project for 1 classroom, 1 Arduino Mega, 1 ESP 8266 Wi-Fi module, 2 PIR sensor, 4 Relay, 2 electromagnetic lock and 1 RFID receiver is needed. The total price will be:
Total price = 30(1) + 15(1) + 42(2) + 12(4) + 30(1) + 60(1) = RM 267
Investment’s sources Amount (RM)
Cheng Guan Jie20,000
Teoh Khy Jun 20,000
Gan Ji Sheng 20,000
Term loan and Overdraft 200,000
Total 260,000
Table V: The initial fund of company.

Expenses Year 1 (RM) Year 2 (RM) Year 3 (RM)
Accounting, Audit & secretarial fees 6,000 6,000 6,000
Insurance 3,600 4,800 6,000
Rental 30,000 30,000 30,000
Company purchases 15,000 3,000 3,000
Utilities 20,000 20,000 20,000
Advertisement 3,600 3,600 3,600
Miscellaneous overheads 15,000 17,500 20,000
Staff salaries 32,400 32,400 32,400
EPF & SOSCO 4,220 4,220 4,220
Depreciation 3,840 3,840 3,840
Loan repayment (Included interest) 37,699 34,799 32,460
Total 168,460 160,159 161,520
Table VI: Estimated expenses in 3 years.

Pro forma income statement
Year 1 (RM) Year 2 (RM) Year 3 (RM)
Sales revenue 250,000 300,000 350,000
Cost of sales 40,000 80,000 120,000
Gross profit 210,000 220,000 230,000
Expenses 168,460 160,159 161,520
Net profit / loss before tax 41,540 59,841 68,480
Tax (20% of profit) 8,308 11,968.20 13,696
Net profit 33,232 47,872.80 54,784
Cumulative net profit 33,232 81,104.80 135,888.80
Profit of each holder 11077.30 15,957.60 18,261.30
Table VII: Income statement table
Pro forma cash flow
Cash inflow Year 1 (RM) Year 2 (RM) Year 3 (RM)
Cumulative cash from previous year – 410,232 517504.80
Start-up capital 60,000 – –
Term loan and overdraft 300,000 – –
Sales revenue 250,000 300,000 350,000
Total cash inflow 610,000 710,232 867,504.80
Cash outflow Total expenses 168,460 160,159 161,520
Tax (20% of profit) 31,308 32,568.20 34,296
Total cash outflow 199,768 192,727.20 195,816
Net cash flow 410,232 517,504.80 671,688.80
Table VIII: cash flow table
Assumption
In this financial projection, few assumptions had been made. The assumptions are such as:
Bank Term Loan of RM 150,000 with an interest rate of 2.5% per annual.

Overdraft Loan of RM 50,000 with an interest rate of 2.5% per annual.

Employee Provident Fund (EPF) with a constant rate of 12%.

SOSCO rate based on contribution table produced by PERKESO.

Depreciation rate with a constant rate of 12%.

The tax is 20 % of the amount of profit.

Figure XXVII
Based on chart above, the profit of each holder in Year 1 is RM 15,077.30. During Year 2, the profit of each holder increases to RM 16,757.60. In Year 3, the profit of each holder is about RM 19,061.30

Figure XXVIII
In year 2017, the cash inflow is RM 610,000. This amount of cash inflow included the start-up capital, sales revenue, term loan and overdraft. The cash outflow is RM 199,768. The cash outflow included the total expenses of company and tax. Finally, the net cash flow of SMARTS SDN BHD is RM 410,232. The net cash flow will bring into next year.

In year 2018, the cash inflow is RM 710,232. This amount of cash inflow included the net cash flow of Year 2017 and sales revenue. Next, the cash outflow is slightly lower compared to Year 2017. The amount of cash outflow is RM 192,727.20. The net cash flow is RM 517,504.80.

In year 2019, the cash inflow is RM 867,504.80. The amount of cash outflow increases to RM 195,816. Lastly, the net cash flow is RM 671,688.80.

As shown in the chart, 3 years of net cash flow show a positive value. This also means that the company did not loss and got earning in all 3 years.

Chapter 6: Marketing Analysis
In recent years, high growth in the education sector has been observed. Ongoing technological advancement in educational sector has given rise to education technology and smart classrooms that are replacing the traditional classroom. Our main focus in the smart classroom will be replacing paper based attendance system to automated attendance system.

Economical
In our product and services, we decided to build the smart classroom with the easiest and cheapest way. Before selling our product and services, we decided to build a prototype to ensure that nothing will goes wrong when implementing the product into a real classroom and also at the same time reduce the loss to minimum. In our product, an automated electrical appliances control system is the one that will cause troubles if anything goes wrong. This is because this system requires to turn on and off the electrical appliances. Changing the circuit of the electrical appliances will cost a lot. Therefore, we decided to use a relay module to control the electrical appliances. This module will cost about RM 10. A microcontroller is the main components of this smart classroom system. Since our prototype is to build one smart classroom, so we decided to use Arduino UNO which is the cheapest microcontroller. Lastly, the solution for the connection between microcontroller and PC is to use a Wi-Fi module. The reason is because Wi-Fi module is cheap and there will be no wire required to connect the microcontroller and PC.

Product, Price, Promotion
Product strategy
We ensure the customers will feel satisfaction by using our product and services. Besides that, we will ensure to deliver product and services with high quality to the customers. Warranty will be provided as well to the customers if the smart classroom system found faulty.

Pricing strategy
The products and services are reasonably priced to ensure customers able to afford to purchase our product and services. The price list of the products and services will be updated from time to time. Furthermore, a comparison of price with different company will also be provided to the customer to allow customer to choose the cheaper price for the particular products and services.

Promotion strategy
As for promotion, advertisement of the company will be done by using the social media such as facebook. Besides using social media, we will also produce flyer and distribute to potential customers as well. Next, we will also provide discount of products and services from time to time as well. Reviews from the customers will also be part of our promotion strategy as well. A good review by a customer will be spread to other people unknowingly. These good reviews will help the company to sell the products and services to more customers.

Target Market
1. Educational Institutions
This is one of our main target since there are a lot of classroom that still use traditional method to take and maintain the attendance records. This method is by passing the attendance sheet around the class for the student to sign. Some of the students take advantage of it by having their friends to sign for them. Even if the lecturer decides to call out student’s name to take attendance, it will be time consuming and troublesome at the same time if the class size is big. That is why we are here to provide an automated attendance system for them.

2. Building Office
We put less priority on this market but it is still included in our target market. Automated attendance systems help to track employees and their presence within an organization. By monitoring the attendance, organizations can understand the behavior of their employees, such as their arrival and departure times, vacation and sick days, and leaves of absence. The prospects for growth in this market will be impelled by the growing need for higher employee efficiency and better time management in organizations. Organizations use attendance systems management solutions to manage their workforce efficiently. The effective deployment of this system helps organizations to monitor the real-time performance of their employees and also enables easy planning and scheduling of work.

Marketing Plan
We started by providing the automated attendance system in the classroom at Tunku Abdul Rahman University College. We will be designing a system that will suit the need for the students and lecturers and additional features and improvement will be made to further improve the quality of life of the user. Maintenance will be made from time to time to ensure the quality of the system does not degrade. After we have sufficient knowledge and experience in this system we will start to aim for other educational institutions and building office.

Competition
1) MAGNET Security & Automation SDN. BHD.

It is located at Pandan Jaya in Kuala Lumpur. They offer different types of access control but their automated attendance system is mainly based on fingerprint type only.

2) FLEXI Team System SDN. BHD.

It is located at Johor Bahru and their branch is at Melaka and Kuala Lumpur. The service they offer is mainly based on RFID based attendance system.

3) ANVIZ
It is located at Butterworth in Pulau Pinang. They provide different types of attendance and door access system such as fingerprint based, RFID based, facial recognition, iris recognition. However, the service they provide are mostly targeted towards international market.

4) ITS Office Appliance SDN. BHD.

It is located at Puchong in Selangor. It offers different types of office automation but their automated attendance system is mainly based on fingerprint type only.

The market will look our technological advantage as our strength. We have the knowledge and skills to operate the system in a skillful and professional way. We have engineer team ready to ensure that the system runs smoothly. With the knowledge on the latest technology which helps us to improve, we will have the strength to be one of the major competitor in the market.

However, the lack of experience in running the service might be our weakness in the market. Some of the rival companies have the brand trust within the consumers. Their companies have operated for a long period that they have the experience in handling different kinds of service. They have more data and analysis on the market. We might not be more experienced compare to our rival company. However, we have an intense and comprehensive planning. We will slowly upgrade and keep on improve when we get involved in the market and by time to time we will make our system more efficient.

Marketing Survey
To improve our market analysis, a survey of 60 respondents is created which consists of 11 questions to gather information about people’s idea opinions in order to help us in our design.

1. Are you a student or lecturer?
Figure XXIX
Based on the data above, all 60 respondents are student.

2. Have you ever used a smart classroom before?
Figure XXX
Based on the data above, there are only 33.3% (20) of students use a smart classroom before while 66.7% (40) of students never use it before. It is because most of the educational institutions in our country still using paper based attendance system.

3. Do you think it is great to have a smart classroom?
Figure XXXI
Based on the data above, there are 90% (54) of students think it is great to have a smart classroom while 10% (6) of students thinks the other way round. It shows that most of the respondent want to have smart classroom because it has a lot of advantages over normal classroom such as automated attendance recording, energy saving and so on.

4. Have you ever forgot to sign on paper of attendance list during class? (answer this question only if you are a student)
Figure XXXII
Based on the data above, there are 81.7% (49) of students have forgot to sign on paper on attendance list during class before while 18.3% (11) of students are not. This data proves the disadvantages of using paper based attendance system and a new replacement of system is needed.

5. Which attendance system do you think is faster and easier to use?
Figure XXXIII
Based on the data above, there are 86.7% (52) of students think that automated attendance system is faster and easier to use while 13.3% (8) of students think it is not.

6. What type of automated attendance system you think have the least invasion of privacy?
Figure XXXIV
Based on the data above, there are 56.7% (34) of students think RFID based system have least invasion of privacy followed by fingerprint based system which has only 23.3% (14) of students. The last one is facial recognition system which has only 20% (12) of students. This data collected will be one of the factor that RFID based system is used instead of fingerprint and facial recognition system.

7. Do you think an automated attendance system will improve the student’s attendance rate?
Figure XXXV
Based on the data above, there are 80% (48) of students think that automated attendance system will improve student’s attendance rate while 20% (12) of students think it will not improve it. Some student takes advantage of paper based attendance system by having their friend to sign for them and many respondents think that it can improve the attendance rate if change to automated attendance system.

8. Do you want the classroom to turn on power automatically when there are people inside it?
Figure XXXVI
Based on the data above, there are 91.7% (55) of students wish to have the classroom to turn on power automatically when there are people inside it while the other 8.3% (5) students are not. This data further supports our idea by adding sensors that can detect motion in the classroom.

9. Do you think that leaving the electrical appliances turn on when no one is in the classroom is a waste of energy?
Figure XXXVII
Based on the data above, there are 95% (57) of students think that leaving the electrical appliances turn on when no one is in the classroom is a waste of energy while the other 5% (3) of students think the other way round. This data further supports our idea by adding sensors that can detect motion in the classroom.

10. Do you think it is good to implement a classroom that can save energy?
Figure XXXVIII
Based on the data above, all of the students think it is good to have a classroom that can save energy.

11. Do you want a classroom to have security feature?
Figure XXXIX
Based on the data above, there are 91.7% (55) of students want to have a classroom that have security feature while the other 8.3% (5) of students do not want it. This data further supports our idea by open or lock the door automatically depends on the class schedule.

Conclusion
Based on the marketing survey, it is known that they wish to have a smart classroom over a traditional classroom. They also prefer RFID based over fingerprint and facial recognition attendance system because of privacy issue. Information obtained on fingerprint and facial recognition might be hacked or sold to other companies without consent of the individual for illegal purposes. This is why RFID based is still consider as the safest among the three. Besides that, based on the marketing survey we will be undergo further improvement and modification such as turn on and off the power automatically depends whether there are people inside the classroom or not. With this feature energy saving is achieved. Theft is one of the issue to the educational institutions and based on the survey we decided to add modifications on the door that can locked and open automatically depends on the class schedule.

Chapter 7: Project Management
Scope baseline
To design a smart classroom system that will turn on or off the electrical appliances automatically in a classroom depending the presence of students.

To implement an automated attendance taking system in the classroom.

To deliver and demonstrate the product prototype.

Project goals and objectives
At the end of the project, the team should be able to deliver and demonstrate the product prototype without errors.

Project milestone
Programming of the smart classroom system
In this project, it is targeted to be able to write a software program for the smart classroom system without error.

Building hardware of the smart classroom system
In this project, it is targeted to be able to connect the device and sensors without error.

Implement the system into the classroom
In this project, it is targeted to be able to integrate the software parts and hardware parts of the system into the classroom and turn the classroom into a smart classroom.

Monitoring the smart classroom system
In this project, it is targeted to observe the smart classroom system functionality after the implementation of the system into the classroom. Data will also be collected for study purposes.

Project phase
This project had divided into 4 phases:
Planning
In this phase, the team had discussed about the task allocation, budgeting of the project and the conceptual design of products. Planning stage takes about 12 weeks to be done.
Execution
In this phase, the team will start the project. Task such as programming, wiring, debugging and others will be done in this phase.

Monitoring
In this phase, the team will monitor the final product to ensure nothing will goes wrong for the product.

Closing
In this phase, the project will be called as done. The project will close after the products had been delivered successfully.

Work breakdown structure (WBS)
To assign tasks to the team member, work breakdown structure is applied to ensure each task can be handle by each team member.

Figure XL: Work Breakdown Structure
Estimated duration of activity
WBS number Activity list Expected time (days)
1.1 Product Design 3
1.2 Cost and Budgeting 1
1.2.1 Purchase components 1
2.1.1.1 Device programming 21
2.1.1.2 Cloud setup 21
2.1.2.1 Wiring circuit connection 7
2.2.1 Debug software programming 7
2.2.1.1 Modification 7
2.2.2 Identify error in circuit connection 7
2.2.2.1 Modification 7
2.3 System installation 3
3.1.1 Monitoring the product 14
3.2 Collect data 14
Table IX
The table above is to show the estimated time of the project activities to be done.

CPM SCHEDULE
Description Duration (Day) Predecessors
Product Design 3 –
Cost and Budgeting 1 Product Design
Purchase Component 3 Cost and Budgeting
Device Programming 21 Purchase Component
Cloud Setup 21 Device Programming
Wiring circuit connection 7 Purchase Component
Identification error and modification in circuit connection 7 Wiring circuit connection
Debug software programming and modification 7 Cloud Setup , Identification error and modification in circuit connection
System installation 3 Debug software programming and modification
Collect data and monitoring product 7 System installation
Table XCPM = Product Design > Cost and Budgeting > Purchase Component > Device Programming > Cloud Setup > Debug software programming and modification > System installation > Collect data and monitoring product = 3 + 1 + 3 + 21 + 21 + 7 + 3 + 7 = 66 (days)

References and Appendix
BIBLIOGRAPHY Anon., n.d. Dublin Institute of Technology. Online Available at: http://www.dit.ie/is/mediaservices/classroomtechnology/Accessed 19 12 2017.

Anurag Chaudhary, G. A. M. J., 2014. A Review on Applications of Smart Class and. International Journal of Scientific Engineering and Research (IJSER), 2(3), pp. 77-80.

Ashton, K., 2009. That Internet of Things Thing. RFiD journal, Volume 22, pp. 97-114.

Chien-Wen Shen, Y.-C. J. W. a. T.-C. L., 2014. Developing a NFC-equipped smart classroom: Effects on attitudes. Computers in Human Behavior, Volume 30, pp. 731-738.

J. He, S. J. Y. P. a. Y. L., 2014. Constructing Load-Balanced Data Aggre- gation Trees in. IEEE Transactions on Parallel and Distributed Systems, 25(7), pp. 1681-1690.

Jeffrey P. Bakken, V. L. U. A. P. a. A. D., 2016. Springer. Online Available at: https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&uact=8&ved=0ahUKEwia4NfitJbYAhWMRY8KHbmOCGYQFggqMAA&url=http%3A%2F%2Fwww.springer.com%2Fcda%2Fcontent%2Fdocument%2Fcda_downloaddocument%2F9783319396897-c2.pdf%3FSGWID%3D0-0-45-1568387Accessed 19 12 2017.

Jungwoo Lee, Y. P. M. S. C., 2013. Smart Classroom: Converging Smart Technologies, Novel Content and Advanced Pedagogies for Future of Education. Journal of Education and Vocational Research Vol. 4, 4(1), pp. 5-9.

Kirti Tanwar, S. G., 2014. Smart Class Using Li-Fi Technology. The International Journal Of Engineering And Science (IJES), 3(7), pp. 16-18.

Morrison, P., 2017. Education Technology. Online Available at: http://edtechnology.co.uk/Article/the-future-of-smart-classroomsAccessed 19 12 2017.

Nishantha, D. P. a. G. G. D., 2008. Smart Classrooms for Distance Education and their. JOURNAL OF NETWORKS, 3(5), pp. 54-63.

O’Driscoll, C., 2009. Advance in Technology, Education and Development. s.l.:InTech.

Stephen S. Yau, S. K. S. G. F. K. S. I. A. Y. W. a. B. W., 2013. DPSE Laboratory. Online Available at: http://dpse.eas.asu.edu/papers/SmartClassroom.pdfAccessed 19 12 2017.

Uskov, C. H. a. V. L., 2017. Smart University: Literature Review and Creative Analysis. In: J. P. B. R. J. H. L. C. J. Vladimir L. Uskov, ed. Smart Universities: Concepts, Systems, and Technologies. Peoria: Springer International Publishing, p. 11.

V.K.Maheshwari, D., 2016. THE CONCEPT OF SMART CLASSROOM. Online Available at: http://www.vkmaheshwari.com/WP/?p=2352Accessed 18 12 2017.

X. Jia, O. F. T. F. a. Q. L., 2012. RFID technology and its applications in internet of things. IEEE conference on Consumer Electronics, Communications and Networks, pp. 1282-1285.

CHAPTER 1:
INTRODUCTION.
In the last few decades, the smartphones have become an essential part of every human daily life, the smartphone equipped with high computational capabilities, easy access to the internet, storage capacity and portability has led to the surge use of the devices for important transactions. Smartphone usage has increased in day-to-day activities. (Jeroen, Elke den, Yuan, 2008). Some of the important transactions include inputting valuable sensitive information such as, social security numbers, passwords, PINS and credits card information by interacting or touching of the soft keyboard of the smartphone. These smartphones devices are equipped with various hi-tech tools such as, the camera, the various on-board sensors and navigational tools that helps in enhancing the user experience. These hi-tech tools are sensitive to any action done on the phone by the user and have the ability to record data readings in regard to specific actions. For example, interacting with the smart phone soft touch screen keyboard to type or input information, these sensors can detect the action being done and capture data readings variations in respect to the action or the device’s camera ability to capture the location coordinates of a picture when it was taken. These smartphone capabilities to capture different sensitive readings and information, have given rise to the question of privacy and security gap in regard to the device’s capturing abilities.
Problem statement.
In this era of smartphone devices, privacy and security of user’s information stored on the phone has become paramount, even though smartphone companies have offered such mechanism to protect user’s valuable information when it comes to some on-board sensors. With today’s smartphone on-board set of cheap implanted sensors number keeps growing, getting smarter and much more sensitive, such as an accelerometer, digital compass, gyroscope, GPS, microphone, and camera, these tools are enabling the emergence of personal, group, and community-scale sensing applications. (Nicholas, et al., 2010).
The variation readings from these on-board sensors from these devices are left unsecured, even though there is a restriction of third party application from having access to some sensitive tools variations, like the camera and microphone, there exist no such restrictions when that said third-party application is being used. As such, an attacker can develop an application that would appear innocent but, in the back, the application is transferring these sensor variation readings to the attacker without the knowledge of the user as proven by (Chen ; Cai, 2011) in their research work. They developed a third-party application TouchLogger, which capture the orientation sensor reading variation of the smartphone to infer the user’s keystrokes. Their application works when the third-party application Touchlogger is in use. The ability of the smartphones’ sensors readings to be able to infer keystrokes or to infer the location of a user has a great privacy and security concern because it can lead to government official to spy on their citizen, or love ones to spy on one another or even the theft of user’s personal information like the PIN.
Research Questions.
There are many research questions within the smartphone sensors and tools, for these research work, the analysis will be conducted on a full QWERTY keypad. The focus will be on the motion sensors (accelerometer and gyroscope) Below are questions that this research paper seeks to answer:
Is there feasibility of carrying a side channel attack to infer user keystrokes based on the sensor (accelerometer and gyroscope) readings on a full QWERTY keypad?
Which statistical model will best infer the keystroke?
Which sensor among the motion sensor is most effective?
How do you use the sensor readings to predict tap event and non-tap event?
Is there a different in individual’s keystrokes pattern?
Is there a similarity in keystrokes pattern among people from the same nation?
Objectives.
The objectives of this research work are to expose the weakness of security in a smartphone concerning motion sensors reading variation from different gesture and keystrokes pattern analysis.
Inferring keystrokes on a QWERTY keypad on a smartphone.
Tap event inferencing.
Find the best model in terms of keystrokes inference.
Analysis of keystrokes pattern base on individuality and base on nationality.

CHAPTER 2:
LITERATURE REVIEW
The smartphone on-board motion sensors are enabling new applications across a wide variety of domains, such as healthcare, social networks, safety, environmental monitoring, and transportation. (Nicholas, et al., 2010). With this technological advancement, however, come new security and privacy challenges. Like their computers and other personal electronics, smartphones are not immune to the data theft ravaging the digital world. Due to the assumption that these sensors reading is not sensitive, third party applications have access to the data without any security restrictions or privileges on all the major smartphone platforms, Android (specification, 2018) and IOS (Library:, 2018).
Attacks on smartphone
Several attacks have been proposed to get user’s information on a smartphone device based on the tools and motion sensors. One of the earliest attacks was the ‘Touch Event hijacking’ (Hijacking, 2010). TapJacking occurs when an attacker creates a fake user interface that seems like it can be interacted with, but actually, passes interaction events such as finger taps to a hidden user interface behind it. Using this technique, an attacker could potentially trick a user into making purchases, clicking on ads, installing an application, granting permissions, or even wiping all of the data from their phone, this type of attack is easy to detect, and with an improve in awareness and security in the operating system, this type of attack is no longer feasible.
Another type of attack proposed was by (Aviv, et al., 2010), they explored the feasibility of pinpointing of lock pattern based on smudges left by fingers on the touchscreen. They investigated the feasibility of capturing such smudges and analysis was done by snapping the screen of the smartphone from different angles and variety of lighting, by changing the contrast of the image they were able to that partial pattern password recovery was possible. As smartphone users tends to favour the characters and numbers type of passwords, also there exist the possibility of the smudges being wiped out off the screen as the victim put his smartphone in his pockets and there is the case of the attacker must be in the possession of the victim’s device, these difficulties have rendered this type of attack nonetheless totally infeasible.
Video-based attacks
More sophisticated attacks are proposed, one of the those attacks was by (Federico, et al., 2011; Krumm, 2007) and (Rahul, et al., 2011), they proposed a more feasible type of attack ‘shoulder surfing attacks’ which an attacker monitor user’s actions by spying on users with a camera (taking pictures or videos) or from a reflection (e.g. from sunglasses), focusing on the key magnifying of touchscreen to infer user’s inputs. Smartphone soft keyboard are created with a feature that magnifies each tap keys, after capturing the pictures, they analysed each frames of the picture/videos and were able to infer user keystrokes. Even their proposed type of attack is still feasible nowadays, there is still some limitations with the proposed type of attack are, which are; (1) smartphones from different companies have different keyboard layout, thus, to make it feasible, the attacker has to buy the same type of smartphone as the victim. (2) The attacker has to follow the victim, this will make the victim suspicious. (3) Due to movement and light intensity, the captured video/pictures may be distorted. Another video type of attack was proposed by (Yi, et al., 2013) for keystrokes inferencing, where they used an extended computer vision processing to cover the challenges face by low-resolution images in the previous attack. They also took into consideration, the fingertip movement, this counter the challenges of low quality images faced by (Federico, et al., 2011) and (Rahul, et al., 2011). Similar video attack was proposed by (Qinggang, et al., 2014), they showed the feasibility of keystrokes inference by observing the shadow of the fingertips on a touchscreen, using machine-learning algorithm to predict the touch pattern. Planar homograph is then applied on the touch pattern to infer the keystrokes. Planar homograph is the process of analysing of an image/video where the video is recreated to make precisely or near precise the first image/video. Another video attack was proposed by (Yimin, et al., 2018), their work was based on the movement of the eyes when the victim is typing on his touchscreen. Their theory was that the human eyes focus on and follow the keys that is intended to tap on a touchscreen, the eyes movement results in a unique pattern of the movement. Using the unique movement pattern also captured with a video recorded, they were able to deduce the keystrokes by analysing each frames of the video and recreating the frames.
More of video attack by (Jingchao, et al., February 2016) was suggested, they moved away from the eyes movement, reflections and finger shadows and movement, they focused on the tablet backside motion when a user is typing. They noticed that each typed key causes the backside of the tablet to move in unique pattern. Using a video recording from VISIBLE; an application they developed, they used complex steerable pyramid decomposition to detect and quantify the subtle motion patterns. They analyse the frames, using SVM to classify the frames. They then differentiate the motion patterns and then use dictionary and linguistic relationship to increase the inference accuracy.
Cons of video-based attacks
There are many feasible keystrokes inference video-based attacks proposed on the smartphone device, even though they are feasible, they are faced with one or more of the below challenges;
Smartphones from different companies have different keyboard layout.
Inference is not feasible when the video recording is not available or in low quality.
The attacker has to follow the victim; this will make the victim suspicious.
Being (the attacker and the victim) in the same place all the time is highly unlikely.
Environment may obstruct the attacker video recording.
Attacks based on sensitive tools/sensors
The privacy and security concern with regards to mobile tools/sensors data have been in the spotlight for sometimes. Research works from (Nicholas, et al., 2010) and (Liang, et al., 2009) have shown how mobile tools/sensors data are sensitive. Liang et al., 2009 studies the vulnerability of the mobile tools such as the microphone, GPS and camera, they show that current mobile phone platforms inadequately protect their users from this threat. (Nicholas et al., 2010) highlighted the importance of the sensor-equipped smartphones and how the sensors will revolutionize many sectors in the world. They also explore the challenges of open issues and challenges emerging in the new area of mobile phone sensing research. Both research works highlighted the privacy and security issues relating to the smartphone mobile sensors, ranging from keystrokes inferencing, hijacking of camera, exploiting the GPS sensor for location and tapping of the microphone to eavesdrop.
An earlier proposed attack related to tools was done by (Krumm, 2007). His work was based on the GPS location data of some volunteers, where he was able to infer the subject’s location using the last know GPS coordinates, the amount of time they spent in a particular place (the subject spent more time at home) and coordinates level of clusters of GPS readings.
(Nan, et al., 2009) proposed attack was based video camera of the 3G smartphone device. They created a spyware that turn on the camera to stealthy record information without the knowledge of the victim; it is perfect for spying on the victim. This type of attack can also be used to stealthy record environment/building with camera restriction.
An attack on the smartphone microphone has being exploited by (Schlegel, et al., 2011) in their work, they created a trojan called ‘Soundcomber’ that can record victim’s sensitive information such as credit and PIN numbers from both tone and speech-based interaction with phone menu systems. Their theory was that each key tap makes a distinct sounds/tune, by recording the tunes they were able predict the keystrokes. More proposed attack on the microphone was by (Laurent ; Ross, 2013), they exploited the feasibility of attack based on the microphone and the camera’s orientation sensor. They used a malicious application ‘PIN Skimmer’ that has access to the microphone and camera’s orientation sensor to collect the variation reading of the sensor. The microphone is used to detect touch event while the orientation sensor reading is used to deduce the keystrokes. When the application is in used, it stealthily video record the user’s activities and each time the user taps the touchscreen, the microphone detects a tap and the camera takes a picture frame with the orientation sensor variation readings. Another work focusing on the microphone was done by (Sashank, et al., 2014), their work was based on the microphone and gyroscope sensor and the combination of the two. The microphone measures the sounds decibels and the gyroscope measures the variation readings. Their work shows that the data from microphone has a higher accuracy than the data from gyroscope but the combination of both has a higher accuracy. Using the Weka tool, they tested different machine algorithms to find the best performing algorithm.
Cons of sensitive based sensor attack
All these proposed attacks are feasible, but they depend on sensitive sensors of the smartphone, like the GPS, camera and microphone, accessing these sensitive sensors requires permissions grant from the user, without permission, these attacks are infeasible.
Attack based on motion sensors
Research have shown that motion sensors (e.g. accelerometer, gyroscope) which are considered insensitive sensors, are highly vulnerable just like their sensitive sensor counterparts (camera, microphone). (Jun Han, 2012) gave a feasibility of location inferencing focusing on the accelerometer sensor readings on a smartphone, since the accelerometer measures the non-gravitation velocity, using the accelerometer trajectory variation readings, they were able to narrow down the possible movement of the user with the smartphone.
One of the first research work that focuses on the smartphone motion sensors variation readings was by (Philip, et al., 2011.), they developed an application (sp)iPhone which uses motion sensors in an iPhone 4 placed on a table to infer the keystrokes of a nearby laptop, as the user was typing, the tapping caused vibrations, the motion sensor (accelerometer) is rattled by the vibration and it caused variation.
Another attack was proposed by (Chen & Cai, 2011). They stated since typing on touchscreen causes changes on the orientation sensor position due to the force of the finger on the touchscreen, they developed an application TouchLogger that captures the orientation sensor readings to infer keystrokes. They used a number-only keyboard on a landscape mode on a smartphone. Using machine learning, they were able to successfully infer more than 70% of the keys typed. Similarly, (Emmanuel, et al., 2012) in their work ACCessory: Password Inference using Accelerometer on smartphone shows that accelerometer sensor readings in a smart phone are a powerful side channel attack feature in inferring user’s password. They divided the smartphone screen into 60 region grids and studied the feasibility of inferring the touch zones. Their work shows that with the accelerometer sensor readings, they were able to predict a 6-character password in 4.5 trials (median) and they were able to successfully break 59 out of 99 passwords using the accelerometer readings.
Further work by, (Zhi, et al., 2012), they took a different approach to the problem; he proposed another type of attack that utilizes the accelerometer and the orientation sensor readings by creating an application the TapLogger, which does all the other applications does, capture the accelerometer and orientation sensor variation readings. The application has two features; (1) Tap feature is used to collect training data while the user is interacting with the application and the (2) Logging feature is to stealthily send the sensor readings when the user is inputting important information on other third-party applications. The logging feature of the TapLogger, detect when the user is inputting information on a third-party application like the browser, the application stealthy sends the data via the network to the attacker. Lastly, their work also shows the feasibility of inferencing is based on how the user uses his device and the type of device.
(Adam, et al., 2012) research work was based on the accelerometer sensor readings where data was collected in two scenarios; a controlled (while sitting) and uncontrolled (while walking). In a controlled scenario, they had 43% accuracy while in an uncontrolled scenario; a 20% accuracy was achieved. They showed that keystroke inferencing in an uncontrolled scenario is quite challenging due to movement. (Liang ; Hao, 2012) in their work, answers the question, is the keystrokes pattern universal for everyone, all the type of phone. Their work showed that keystrokes inference depends on the type of device, screen dimension, the keyboard layout and the user.
(Ahmed, et al., 2013) research work focused on addressing the question, which available sensors can perform best in the context of the inference attack. They considered all the available sensors and the integration of all the sensors data in a single dataset and compared each sensors performance in relation to inference keystrokes attack. They found out that the gyroscope has the highest accuracy and the least performing accuracy is the accelerometer sensor. the research was conducted on number keypad layout while (Emiliano, et al., 2012) went further to address the question, which sensors has better accuracy. Their work was thus focus on the QWERTY keyboard layout rather than the number keypad layout. Result showed that the combination of the accelerometer and gyroscope reading have the higher accuracy rather than standalone sensor readings.
(Xiangyu, et al., 2015) took a different approach. They explored the possibility of keystrokes inferencing based on the accelerometer on the smartwatch of the user. Their theory was that the accelerometer of the smartwatch could detect the user’s hands movement when tapping the touchscreen. They focused on the number and QWERTY keyboard pattern; they had a success rate of 65%. Irregular hand movement was one the challenge they faced in their approach. Even though this attack is feasible, it is highly unlikely for an attack because the attacker has to be in possession of victim’s smartwatch.
This Experiment setup
Most of the research above were based on number keypad instead of the QWERTY keyboard layout and furthermore, as the smartphones are getting light in weight, it is now easy to interact with one hand even while standing. This research is focused on a controlled scenario where each user is standing and using the smartphone with one hand (right hand). The project is solely relied on motion sensors which is easily assessible through an APIs on the device. Previous works mostly are based on a single user, this research explores the keystrokes inference feasibility with from a number of users.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

Chapter 3:
RESEARCH METHODS
This dissertation begins with introducing a smartphone device and its on-board sensors, the privacy and security concern based on the on-board sensors and an extensive literature review of feasibility of security and privacy different possible attacks, which would help answer this research questions.
This research project involves the designing of a malicious application that can capture the motion sensors data readings based on keystrokes events on a QWERTY keyboard layout, the variation sensors readings extracted along with other features from the data and developed a machine learning algorithm to classify the data into different classification for analysis.
Tools and models
The range of tools to be use for this project include:
An htc one A9s Android smartphone with an on-board motion sensor. For this project, I used the accelerometer and gyroscope sensors.
An application: an android application is created with interfaces that allow users to type the inputs. The application captures the sensors variation readings of the accelerometer and gyroscope in the background; it saves the data to be transferred into a workstation.

Figure 3 1 user interaction of the application.
Weka machine learning suite tool: is a suite of machine learning software written in Java, developed at the University of Waikato, New Zealand. It is a free software licensed under the GNU General Public License. It contains many machine learning algorithms and visualisation tools. It is used for data mining, classification, regression and feature selections. (Weka, 2018).
Statistical models: the models used for this project include the clustering K-NN model, Naive Bayes, Random Forest and the Multilayer perceptron classification.
K means clustering model: is an algorithm that aims to cluster n-data reading into k clusters, each element of n-data is clustered nearest to the mean, serving as the center of the cluster. (Hartigan ; Wong, 1979).
Naïve Bayes classification: A Naïve Bayes classifier is a classification based on (naïve) independence features probability assumption; that is, a particular feature in a class is unrelated to the presence of any other feature. It is derived from the Bayes theorem. (Tina ; Sherekar, 2013). Due to the naïve (independency) feature of the classifier, this classifier gives the better accuracy for each keystroke inference without compromising the other characters accuracy. From Naïve Bayes theorem;
P(H/D)=P(H)P(D/H)/(P(D))
P(H/D) is the probability of H given that the D have already occurred is the
P(H) probability of H.
P(D/H) probability of D given the H occurred.
P(D) probability of D.
P(character/(all_characters ))=P(character)P((all_characters)/character)/p(all_characters )
The Naïve Bayes classification uses the Naïve Bayes theorem in terms of each probability, the probability with the highest value is chosen as the likely classification.
Random forest: random forest is a supervised ensemble machine algorithm that build multiple decision trees to get better accuracy (Ho, 1995). The decision trees node is selected at random, in the end, the highest number of outcomes from all the decision trees in the forest is voted as the most likely class.

Figure 3 2 Random Forest algorithms with multiple decision trees.
Source: (Niklas, 2018)
Randomly select a feature “K” among all the features of 26 characters.
From the “K” feature, calculate the nodes “best separation” of the feature.
Split the nodes into other nodes using the best separation.
Repeat the A to C steps until all the other features nodes has been created.
Build the forest by repeating steps A to D for “n” number times to create “n” number of trees.
Multilayer perceptron: is a feedforward type of artificial neural network algorithm. It is a classification model that consist of at least a layer, a hidden layer and nodes. It is a simple algorithm intended to perform binary classification; i.e. it predicts whether input belongs to a certain category of interest or not. (Rohit ; Suman, 2012) in their research work on Weka machine suite showed that multilayer perceptron works well in most cases. It is activated by an activation function. Backpropagation is used to fine-tune the classifier to get the best accuracy. This model gives importance to instances in terms of weights. Any character instance that is closer to a specific class will be giving more importance than other instances, this will aid in the classification accuracy. The disadvantage of this algorithm is, the computational power is very high.

Figure 3 3: multilayer perceptron.
Source: (Vikas, 2017).
Type of data
The type of data used for this dissertation are:
Accelerometer sensor: monitors the acceleration of the device when the device is in motion in three axes: left-right(x-axis), forward-backward(y-axis) and the up-down(z-axis). For example, the readings will be positive when the device is accelerating in each of the directions.
The gyroscope sensor: monitors the rotation or twisting of a smartphone with respect to gravity. It is calibrated in three axes. It measures angular velocity. It has three axes: When the device rotates along the Z-axis (perpendicular to the screen plane) azimuth angle changes in 0,360, when the device rotates along the X-axis (pitch angle) changes in ?180,180), when the device rotates along the Y-axis (roll angle) changes in ?90,90). (Liang ; Hao, 2012)

Figure 3 4: Accelerometer ; Gyroscope sensors.
Source: (Liang ; Hao, 2012)
Both sensors reading changes when the smartphone is being interacted with due to the force of the tapping force. The sensor reader application is used to capture the sensors reading and then store the readings for further analysis.
Data collection
The data collection is done in a controlled manner that is standing and holding the smartphone with the right hand. For this project the focused is placed on the right-handed people.
Tap-event data collection
For tap event data collection, the user holds the smartphone without tapping to get the sensor readings for 20 seconds to get the data for not tapping event, after that, the user is allowed to tap some few alphabets to get the sensor readings for tapping.
Data collection for keystrokes inferencing
The sensor reader application allows the user to input all the 26 alphabets 20 times making a total of 520 inputs. As the user is typing, the application is capturing the sensors readings for each tap event.
Data collection from other users
Data was collected from six (6) users for further to analysis. Each user is asked to input some random words into the application in the controlled manner. The random words contain 114 words making up of 626 characters. The volunteers are from different nationalities, three are from the China and the rest making up of different nations.

Figure 3 5: Word Counts.
Each character frequencies are taking into consideration.

Figure 3 6: Character frequencies.
Data analysis
Tap event: Since the accelerometer measures the acceleration of the mobile, I used the accelerometer three (x,y,z) axes coordinates sumsquare to predict when the user is tapping or not.
Hierarchical method: I divided the keyboard alphabets into two sides that is, the right side and left side of a keyboard layout and related each sides’ characters with the sensor readings. Then I tested the clustering K means model to infer which side of the hierarchy a keystroke belongs.
Classification Model Generation: I used the Weka machine-learning suite to try different machine algorithms mentioned above and check the level of accuracy. In the process of testing, three algorithms were involved and Keystrokes inferencing and to answer other objectives of this project.
Performance Valuation
The classification model function will analyse accuracy of keystrokes inference. I checked the most the effective motion sensors and the combination of variation readings from both sensors. The higher accuracy of the classification model defines the accuracy of the model for inferencing. The difference in keystrokes pattern of each user. The exact characters that differentiate between people from the same with people from other nations with higher classification accuracy.

CHAPTER 4:
FINDINGS
After data collection, Raw sensor reading data needs to be processed before applying the machine learning algorithms to it. To proceed with the inferencing, specific section relating to keystrokes/tap event has to be extracted from the data set. Taking the sumsquare of the three xyz coordinates, it shows that there is a distinction in the pattern of the different actions.
Figure 4 1: This is the square of each coordinates of the accelerometer depicting different actions while holding the phone. (a) Walking (b) Running (c) Standing/no tap (d) Tapping.

Pre-processing
Raw data readings are not that important in keystrokes inferencing because tap span multiple readings, to get the specific sections concerning tap event, some unique features have to be extracted from the sensor reading data set.
The data set consist of the three output (x, y, z) values along the three axes. In the cause of the research. On average, each tap event consists of three different reading values. That is, at my tapping rate, the difference between a tap event and another are three sensor different readings.
Due to the group of sensor readings spanning each keystroke, features are extracted. Some of the previous work focused on different unique features. For this project, I focused on six statistics features, the minimum, maximum, median, average, standard deviation and the skewness.
Minimum m: these are the minimum values for each of the three output (x, y, and z) along the three axes.
Maximum mx: these are the maximum values for each of the three output (x, y, and z) along the three axes.
Average ?: the average of each three-sensor output (x, y, and z) values along the three axes.
?=?n/n
For each tap, the x1+x2+x3/3 for x coordinate. That is, x1 is the value before the tap, x2 the value at the tap reading and x3 is the value after the tap.
Median M: is the middle of the three output along the corresponding coordinates (x, y, and z) in an ascending order. M=(N+1)th/2.
Standard deviation SD: is the amount of variation of each output along the coordinates from the corresponding average.
SD=(?(?(xi-mean))^2)/n
Skewness: is a measure of the asymmetry of the probability distribution of a real-valued random variable about its mean.
skewness=3(mean-median)/(standard deviation)
The raw data consists of three values along the three (x, y, and z) coordinate, each tap event has 18 features. These final features are the final input used for the machine learning analysis. For example, for x coordinate, the six (6) features will be xminA, xmaxA, xmeanA, xmedianA, xSDA, xSkewA. The first ‘x’ is the corresponding coordinate, the second is the unique feature and the ‘A’ is the sensor (accelerometer) from which the sensor data was driven. Each feature is used to distinguish a different keystroke.
Evaluation
In this section l evaluated the different keystrokes inferencing accuracy of the different classification model used, the tap event and the keystroke inference accuracy, the different and similarities among different of the users,
The sensor reader application is configured on an htc one A92 Android smartphone; the device can generate sensors reading at the default frequency of 100Hz. I used the ten-fold cross validation approach for the analysis. This type of methods where the dataset is divided into 10 folds, where one-fold is used as a training set and the other folds are used for testing set. The process is repeated until all instances of the dataset serve as the training set and testing set. This method of analysis makes sure each part of the dataset is taken into considerations.
Tap event
To infer the keystrokes, there is a need to predict between tap event and non-tap event. To do this, I based the analysis on the accelerometer sensor readings. Using the sum square of the three coordinates, the standard deviation and the mean.
sumsquare=x^2+y^2+z^2
From the figure below, there is a clear distinction between tap event and not tap event. I held the phone without tapping for a while to get the statistical mean and standard deviation for non-tap event to compare it to the tap event. I got the mean to be 98.88 and the standard deviation to be 7.10. The difference between the mean and standard deviation is 91.77 and the addition of the mean and standard deviation is 105.98. Using the 68.2% level of a normal distribution curve, I applied the non-tap mean value and up and down limit level to a tap sensor reading to distinguish between tap event and non-tap event.
Figure 4 2: (a) Non-tap event, it shows must of the sensor readings fall between the 68.2% of a normal distribution curve. (b) Any value outside the 68.2% is considered a tap event.

Using the sum square of the three coordinates xyz of the accelerometer sensor, I built a model that extract all the sum squared values that are outside the threshold level (68.2%) of a normal distribution and the corresponding xyz coordinates. The xyz values are labelled as tap event. Any sum squared values that are between the threshold levels (68.2), the corresponding xyz values are labelled as non-tap. I then trained a random forest classifier for tap event and non-tap event. The result is nearly 90%, producing nearly no false positive or false negative. A close look at the figure 8, there is a clear a distinction between the sum squares of a tap event and non-tap event.
Keystroke inference
The sensor reader application captures the data of both the accelerometer and gyroscope sensors. I analyzed the keystrokes inference based on each sensor and the amalgamation of both sensors. The inference probability of all the 26 alphabets is 1/26=0.38, after collecting the sensor readings of 520 instances (20 of each alphabet) and applying the different machine learning algorithms mentioned above, I now present the results.

No tap
Data discarded

Classification Result classification result classification result
Figure 4 3: The process blue print.
After the testing the correlations of all the features, I found the skewness feature has no correlation to the inference accuracy. The skewness feature was removed and take inot consideration only the remaining features, the max, min, mean, median and standard deviation, making the total of 15 features for the three xyz axes.
Keystroke inference based on the accelerometer
Using the accelerometer sensor variation readings, I was able to get an accuracy of 31.92% for the Random Forest algorithm, 22.11% for Multilayer Perceptron algorithm and 28.46% for the Naïve Bayes algorithms. The confusion matrixes for the three models are as follows:

Figure 4 4: The Keystroke inference accuracy levels of the three machine learning algorithms based on the accelerometer sensor data.

Table 4 1: confusion matrix for the random forest algorithms for accelerometer sensor data. The first column is the specific key accuracy, 2nd, 3rd, 4th, and 5th columns shows the accuracy of the immediate neighbors.
key acc % 1st % conf. 2nd %
conf 3rd % conf 4th % conf
Total acc %
A:80
B:20
C:20
D:35
E:30
F:30
G:15
H:5
I:45
J:30
K:35
L:20
M:70
N:5
O:20
P:60
Q:15
R:35
S:25
T:60
U:15
V:55
W:30
X:35
Y:25
Z: 15 D:5
N:5
V:5
F:15
F:5
G:5
H:10
G:10
K:5
K:15
L:5
M:15
N:5
M:15
I:5
O:5
Z:10
T:20
W:10
R:30
I:10
B:0
A:10
S:5
U:15
X:0 S:10
H:0
F:0
W:10
D:0
D:5
F:10
J:25
O:10
U:10
J:10
U:5
L:0
H:5
P:10
L:0
S:5
E:0
Z:0
Y:0
J:10
C:0
D:5
D:10
T:5
A:5 Z:0
G:5
V:5
S:0
W:5
S:10
B:5
U:0
U:5
H:10
O:5
P:10
J:0
J:0
J:5
M:10
D:10
D:0
A:10
G:5
K:0
F:0
Z:15
Z:0
J:5
S:0 Q:0
F:0
X:0
X:5
R:0
R:0
C:5
Y:0
M:0
I:0
M:0
O:0
K:0
B:10
M:0
K:5
A:5
F:5
D:10
F:0
L:5
G:0
Q:5
C:0
H:0
D:5 95
30
30
65
40
50
45
40
65
65
55
50
75
35
40
80
45
60
55
95
40
55
65
50
50
25

From the table above, the inference accuracy based on the accelerometer sensor data varies from 80% for letter ‘A’ to 5% for letters ‘N’ and ‘H’.

Figure 4 5: keystrokes inference accuracy from 20 instances of each keys on the keyboard based on the accelerometer sensor.

Figure 4 6: confusion probabilities of ‘S’, ‘G’ and ‘K’ based on accelerometer sensor. The keys belong to the left, middle and right side on the keyboard. The main keys are in dark color with their accuracies, the keys in light color represent misclassification accuracies for each neighboring character.

Keystroke inference based in the gyroscope sensor
Using the gyroscope sensor reading, I was able to get an accuracy of 39.23% for the random forest algorithm, 24.42% for multilayer perceptron algorithm and 27.69% for the Naïve Bayes algorithms. The confusion matrixes for the three models are as follows:
Figure 4 7: The keystroke inference accuracy levels of the three machine learning algorithms based on the gyroscope sensor data.

Table 4 2: confusion matrix for the random forest algorithms for accelerometer sensor data. The first column is the specific key accuracy, 2nd, 3rd, 4th, and 5th columns shows the accuracy of the immediate neighbors.
key acc % 1st % conf. 2nd %
conf 3rd % conf 4th % conf TOTAL ACC %
A:60
B:25
C:50
D:30
E:15
F:50
G:40
H:15
I:60
J:20
K:30
L:35
M:45
N:25
O:45
P:60
Q:30
R:75
S:35
T:70
U:40
V:45
W:30
X:30
Y:20
Z: 40 Q:5
N:10
V:10
F:20
F:0
G:0
H:10
G:5
K:5
K:10
L:10
M:25
N:0
M:0
I:0
O:10
Z:10
T:10
X:10
R:20
I:0
B:15
A:10
S:0
U:5
W:5 S:25
V:15
F:5
W:10
D:0
D:10
F:10
J:10
O:0
U:5
J:10
U:0
L:20
Y:5
P:5
L:0
S:0
E:0
Z:0
Y:0
J:0
C:0
D:5
D:20
T:10
A:5 W:10
G:5
V:5
S:10
W:10
S:5
V:0
U:0
U:0
H:15
O:5
P:10
J:0
J:5
J:0
M:5
D:5
D:0
A:25
G:0
k:0
F:0
Z:15
Z:5
G:5
S:5 Q:0
F:0
X:0
X:5
Z:10
T:5
T:5
Y:0
M:0
N:10
N:5
N:10
U:15
B:5
M:0
K:0
A:15
F:0
D:15
F:0
M:20
G:0
Q:5
C:10
H:5
D:10 100
55
70
75
35
70
65
30
65
60
60
70
80
40
50
75
60
85
85
90
60
60
75
65
45
65

From the table above, the inference accuracy based on the gyroscope sensor data varies from 75% for letter ‘E’ to 15% for letters ‘E’ and ‘H’.

Figure 4 8: keystrokes inference accuracy from 20 instances of each keys on the keyboard based on the gyroscope sensor.

Figure 4 9: confusion probabilities of ‘S’, ‘G’ and ‘K’ based on gyroscope sensor. The keys belong to the left, middle and right side on the keyboard. The main keys are in dark color with their accuracies, the keys in light color represent misclassification accuracies of neighboring characters.
Keystroke inference based on the amalgamation of the two sensors
Using the combination of both the gyroscope and accelerometer sensors reading, the models gave an accuracy of 42.69% for the random forest algorithm, 31.73% for multilayer perceptron algorithm and 33.07% for the Naïve Bayes algorithms. The confusion matrixes for the three models are as follows:

Figure 4 10. this is the keystroke inference accuracy levels of the three different machine learning algorithms based on the amalgamation of the two motion sensors data, with random forest having a better accuracy than the other two algorithms.

Table 4 3: confusion matrix for the random forest algorithms for accelerometer sensor data. The first column is the specific key accuracy, 2nd, 3rd, 4th, and 5th columns shows the accuracy of the immediate neighbors.
key acc % 1st % conf. 2nd %
Conf 3rd % conf 4th % conf TOTAL ACC %
A:75
B:25
C:30
D:35
E:20
F:50
G:40
H:20
I:65
J:35
K:50
L:25
M:80
N:15
O:35
P:60
Q:25
R:70
S:40
T:70
U:35
V:45
W:40
X:35
Y:45
Z: 45 E:5
N:10
V:10
F:15
F:5
G:0
H:5
G:10
K:10
K:15
L:5
M:25
N:10
M:10
I:15
O:5
Z:5
T:20
X:5
R:20
N:5
B:10
A:0
S:5
U:0
W:5 S:15
V:10
F:0
W:10
D:5
D:15
F:10
J:5
O:0
U:5
J:5
U:0
L:10
Y:0
P:5
L:0
S:5
E:0
Z:0
Y:0
J:5
C:5
D:25
D:15
T:5
A:5 W:0
G:0
E:5
S:5
W:0
S:5
V:0
U:5
U:0
H:10
O:5
P:5
J:0
J:5
J:0
M:10
D:5
D:0
A:10
G:0
Y:10
F:0
Z:5
Z:5
G:0
S:0 D:5
F:0
X:5
W:10
Z:10
T:5
T:5
Y:0
L:5
N:5
N:5
N:15
U:0
B:5
M:0
K:5
A:5
F:0
W:15
F:0
M:15
G:0
Q:5
C:5
H:5
D:0 100
45
50
75
40
75
60
40
80
70
70
75
100
35
55
80
45
90
70
90
70
60
75
65
55
55

From the table above, the inference accuracy based on the gyroscope sensor data varies from 80% for letter ‘M’ to 15% for letter ‘N’.

Figure 4 11: keystrokes inference accuracy from 20 instances of each keys on the keyboard based on the gyroscope + accelerometer sensors.

Figure 4 12: confusion probabilities of ‘S’, ‘G’ and ‘K’ based on gyroscope sensor. The keys belong to the left, middle and right side on the keyboard. The main keys are in dark color with their accuracies, the keys in light color represent misclassification accuracies for neighboring characters.
Character ‘A’ inference accuracy is high in all three scenarios due to its extreme position on the keyboard, tapping on ‘A’ created a more gesture, which caused more variation to the motion sensors. Letters ‘N’ and ‘H’ has the very low accuracy in all the three scenarios due their positions on the keyboard and the position of the hand on the back of the phone. Holding the phone with one-hand places the two keys in the middle of the hand grip which gives more support to phone on both sides, a tap on both keys wouldn’t give a much gestures to cause much variations to the motion sensors.
The most effective sensor and algorithms
From the analysis above, it shows based on the features extracted, the amalgamated sensor readings from accelerometer and gyroscope have the higher inference accuracy, followed by the gyroscope and the accelerometer has the least inference accuracy. The accelerometer adds only a 3.46% on accuracy to the gyroscope accuracy result using the best performing algorithm (Random Forest algorithm). It adds a 5.38% and 7.31% for the other two algorithms Naïve Bayes and Multilayer perceptron respectively. Due to angular calibration of the gyroscope along the three axes, this made the gyroscope to have more inference accuracy than the accelerometer.
Figure 4 13: (a). multilayer perceptron inference accuracies (b). Naïve Bayes inference accuracies (c) Random forest inference accuracies.

Conclusion: The gyroscope is the most effective sensor between the two and the most effective machine algorithms is the random forest algorithms with the highest accuracy of 42.69%, this is due to the fact that the decision trees node is selected at random. This helped in giving equal importance to each feature of the dataset.
Keystroke inference per-user
Six (6), (four (4) male and two (2) female) users across different nationalities were asked to enter some 114 words consisting of 626 characters in a controlled setting. This is done to check if there is a distinction of typing pattern between different users and to check the if there is similarity and difference keystrokes pattern with regards to nationality.
The best perfuming algorithms and the most effective sensor is already established. For this exercise, my focused was on the Random Forest algorithms and the acc + gyro sensor readings. Due to the differences in the number of instances for each key, the keys with the highest number of frequencies were taking into consideration.
Table 4 4: confusion matrix per user inference accuracies for highest frequencies characters.
User Key inference accuracy Two neighboring key accuracy %
User 1 A(11/56)
E(23/62)
O(13/40) E,S(19/56)
R,S(9/62)
I,P(4/40) 53.57
51.61
42.50
User 2 A(16/56)
E(27/62)
O(10/40) E,S(14/56)
R,S(13/62)
I,P(8/40) 53.57
64.51
45
User 3 A(11/56)
E(24/62)
O(13/40) E,S(18/56)
R,S(9/62)
I,P(5/40) 51.78
53.22
45
User 4 A(8/56)
E(20/62)
O(19/40) E,S(14/56)
R,S(17/62)
I,P(11/40) 39.28
59.67
75
User 5 A(15/56)
E(24/62)
O(6/40) E,S(13/56)
R,S(17/62)
I,L(9/40) 50
66.12
37.5
User 6 A(14/56)
E(22/62)
O(16/40) E,S(22/56)
R,S(12/62)
I,P(14/40) 64.28
54.83
75

Figure 4 14: per-user inference accuracy for the letters (‘A’, ‘E’, ‘O’) and their closest neighboring keys on the keyboard.

Classification of users based on each user
In this section, I tried to check if there is a difference between how each user type, using the data from the six (6) volunteers’ dataset making up of four (4) male and two (2) female. I used the Random Forest algorithms and the dataset from the amalgamation of the two sensors (accelerometer and gyroscope). Using the 10-cross validation on the dataset, the confusion matrix is as follows:

Figure 4 15: confusion matrix using the random forest algorithm with an accuracy of 96%.

From the confusion matrix, figure 21, it shows the nature of keystrokes pattern depends on the user. Each user has a unique way of typing on the smartphone. This is due to each individual way of holding the phones and the force of the keystrokes.
Classification of users based on nationality
There is a misclassification between the last three volunteers, where some of their data overlap each other. The last three volunteers are from the same country. This misclassification among three users from the same nationality suggest that there is a similarity in the way people from the same nationality type on their smartphone. Giving that I have 50% of my data from people from China, I decided to divide the dataset into groups, China and non-China; using the 66% of the dataset consisting of data from two Chinese and two non-Chinese to create a model and the remaining 44% is used for testing. I then trained the data random forest algorithm; I got a confusion matrix as below;

Figure 4 16: confusion matrix for classification model based on Nationality.
After testing the model on the remaining 44% dataset, I got a confusion matrix below:

Figure 4 17: confusion matrix after testing the dataset on remaining 44% of the dataset with a 71% accuracy.

The confusion matrix shows a 100% accuracy for the user from China and 45% for the user from non-China nation. This suggests that, there are some specific characters among the 26 characters that distinguished the nature of how people from the same nation type with other people from different nation, in this case, the people from China and the people from non-China. I decided to find the unique characters with higher frequencies that are classified the two class to some accuracies accurately from the confusion matrix above. I found the unique characters that successfully classified between the two classes are letters ‘I’, ‘N’, ‘O’, ‘P’, ‘T’, ‘U’ and ‘M’. I created another model using only those characters, using the 66% of the main data. The model has an accuracy of 93.76%,

Figure 4 18. The confusion for the new model using the new unique characters.

I extracted the unique characters from the remaining 44% of dataset and used it as a test set. I was able to get 86.61%. This clearly shows that there is a distinction between how people from the countries typed on the smartphone.

Figure 4 19: the confusion matrix for the test set with an 86.62% accuracy.

I decided to collect another set of sensors reading from a one non-Chinese person to further test the created model using the only the unique characters. I asked the person to enter the unique characters 20 times each making a total of 140 instances. I added the new data to a Chinese person to make two classes of a China and non-china class. After testing the model on the new dataset, I was able to get an accuracy of 99.69%.

Figure 4 20: the confusion matrix for the new dataset with an accuracy of 99.69% after testing the model.

This diversity analysis shows the possibilities of division of how people type on the smartphone screens due to some factors like the length of fingers, how consistent different people use certain characters, like in English, the most common used characters are the vowels (A E I O U). This is open for further research.

x

Hi!
I'm Alfred!

Would you like to get a custom essay? How about receiving a customized one?

Check it out