-37338080645DECLARATION OF THESIS / UNDERGRADUATE PROJECT REPORT Author’s full name

-37338080645DECLARATION OF THESIS / UNDERGRADUATE PROJECT REPORT
Author’s full name :
Date of Birth:
Title:
Academic Session: 2016/2017
I declare that this thesis is classified as:
CONFIDENTIAL (Contains confidential information under the Official Secret Act 1972)*
RESTRICTED (Contains restricted information as specified by the organization where research was done)*
OPEN ACCESS I agree that my thesis to be published as online open access (full text)

I acknowledged that Universiti Teknologi Malaysia reserves the right as follows:
The thesis is the property of Universiti Teknologi Malaysia
The Library of Universiti Teknologi Malaysia has the right to make copies for the purpose of research only.

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


order now

The Library has the right to make copies of the thesis for academic exchange.

Certified by:
SIGNATURE SIGNATURE OF SUPERVISOR MARINA BINTI MD ARSHAD (NEW IC NO/PASSPORT) NAME OF SUPERVISOR Date: 20 JUNE 2016 Date: 20 JUNE 2016
00DECLARATION OF THESIS / UNDERGRADUATE PROJECT REPORT
Author’s full name :
Date of Birth:
Title:
Academic Session: 2016/2017
I declare that this thesis is classified as:
CONFIDENTIAL (Contains confidential information under the Official Secret Act 1972)*
RESTRICTED (Contains restricted information as specified by the organization where research was done)*
OPEN ACCESS I agree that my thesis to be published as online open access (full text)

I acknowledged that Universiti Teknologi Malaysia reserves the right as follows:
The thesis is the property of Universiti Teknologi Malaysia
The Library of Universiti Teknologi Malaysia has the right to make copies for the purpose of research only.

The Library has the right to make copies of the thesis for academic exchange.

Certified by:
SIGNATURE SIGNATURE OF SUPERVISOR MARINA BINTI MD ARSHAD (NEW IC NO/PASSPORT) NAME OF SUPERVISOR Date: 20 JUNE 2016 Date: 20 JUNE 2016
-3733808415020NOTES: *If the thesis is CONFIDENTAL or RESTRICTED, please attach with the letter from the organization with period and reasons for confidentiality or restriction.

020000NOTES: *If the thesis is CONFIDENTAL or RESTRICTED, please attach with the letter from the organization with period and reasons for confidentiality or restriction.

4217670-414655PSZ 19:16 (Pind. 1/07)
00PSZ 19:16 (Pind. 1/07)
-373380-233045UNIVERSITI TEKNOLOGI MALAYSIA
00UNIVERSITI TEKNOLOGI MALAYSIA

“Saya akui telah membaca karya ini dan pada pandangan saya,
karya ini adalah memadai dari segi skop dan kualiti untuk tujuan penganugerahan
Ijazah Sarjana Muda Sains Komputer (Rangkaian dan Keselamatan Komputer)”
Tandatangan:…………………………………

Nama Penyelia :Marina Binti Md Arshad
Tarikh:………………………………..

PROTOTAIP PENAMBAIKAN MODUL PENEMPATAN SISTEM LATIHAN INDUSTRI FAKULTI KOMPUTERAN
NURUL ASYIKIN ZAMRI TAN
Laporan ini dikemukakan sebagai memenuhi
sebahagian daripada syarat penganugerahan
Ijazah Sarjana Muda Sains Komputer (Rangkaian dan Keselamatan Komputer)
Fakulti Komputeran
Universiti Teknologi Malaysia
JUN 2016
Saya akui tesis yang bertajuk “Prototaip Penambahbaikan Modul Penempatan Sistem Latihan Industri Fakulti Komputeran” adalah hasil kerja saya sendiri kecuali nukilan dan ringkasan yang tiap-tiap satunya telah saya jelaskan sumbernya.

Tandatangan: …………………………………………….

Nama Penulis : NURUL ASYIKIN ZAMRI TAN
Tarikh : 20 JUN 2016

“My dearest mum, family, Miss Marina and friends”
This is for all of you
ACKNOWLEDGEMENT
All praise, honour and glory to God for his richest grace and mercy for my accomplishment of this report.

This thesis would not be competed without the following important people who willing to give their time to help me. Firstly, I would like to express my sincere appreciation to my supervisor, Dr. Haslina Hashim for helping me finishing my final year project. Her guidance, encouragement and incredible help throughout my journey doing this project gave me strength to finish this thesis.
Then, for my family thank you for always be there when I need support through my hardest time, keeps reminding me that I can do it and always believe in me. Also, for my friends close or distant, I always thankful because you guys help me whenever I need someone to listen for my problems and giving me encouragement for us together finishing our study. For this people I am forever and always thankful.
ABSTRACT
Awareness of autism has grown dramatically in recent years, which reflects both an increase in diagnoses and in the public’s understanding that, even late in life, a diagnosis can offer major benefits and relief. This study examines the symptoms of ASD in adults and predicting result based on AQ questionnaires. Although early ASD research focused primarily on children, there is increasing recognition that ASD is a lifelong neurodevelopment disorder. Research is required to better understand the needs of adults with ASD including on how to detect ASD using machine learning. Existing screening tools for early identification of a mental imbalance are costly, tedious and at times miss the mark in prescient esteem. Here, we apply machine learning figuring out how to make low-cost, quick and simple to apply screening tools that perform better. Current approaches for diagnosing autism have high diagnostic validity but are time consuming and can contribute to delays in arriving at an official diagnosis.
ABSTRAK
Your text begins here.

TABLE OF CONTENTS
CHAPTER TITLE PAGE
TOC f h z “Heading 2,3,Heading 3,4,Heading 4,5,Chapter Title,2,Title,1,Reference Heading,6” ACKNOWLEDGEMENT PAGEREF _Toc483907978 h ivABSTRAK PAGEREF _Toc483907979 h vABSTRACT PAGEREF _Toc483907980 h viKANDUNGAN PAGEREF _Toc483907981 h viiSENARAI JADUAL PAGEREF _Toc483907982 h xSENARAI RAJAH PAGEREF _Toc483907983 h xiSENARAI SINGKATAN PAGEREF _Toc483907984 h xiiSENARAI SIMBOL PAGEREF _Toc483907985 h xiiiSENARAI LAMPIRAN PAGEREF _Toc483907986 h xiv1INTRODUCTION PAGEREF _Toc483907987 h 11.1Pengenalan PAGEREF _Toc483907988 h 11.2Research Background PAGEREF _Toc483907989 h 11.3Problem Statement PAGEREF _Toc483907990 h 21.4Research Objectives PAGEREF _Toc483907991 h 21.5Research Scopes PAGEREF _Toc483907992 h 21.6Research Significance PAGEREF _Toc483907993 h 31.7Thesis Organization PAGEREF _Toc483907994 h 32KAJIAN LATAR BELAKANG PAGEREF _Toc483907995 h 42.1Introduction PAGEREF _Toc483907996 h 42.2Autism Spectrum Disorder PAGEREF _Toc483907997 h 42.3Classification PAGEREF _Toc483907998 h 52.3.1ITS UTM PAGEREF _Toc483907999 h 62.3.1.1Analisis Masalah Dalam ITS UTM PAGEREF _Toc483908000 h 62.3.2Sistem Latihan Amali dan Industri Universiti Kebangsaan Malaysia (SLAI UKM) PAGEREF _Toc483908001 h 72.4Perbandingan Antara Sistem PAGEREF _Toc483908002 h 72.5Kajian Latar Belakang Teknologi yang Digunakan PAGEREF _Toc483908003 h 72.6Heading 2 PAGEREF _Toc483908004 h 82.6.1Heading 3 PAGEREF _Toc483908005 h 82.6.1.1Heading 4 PAGEREF _Toc483908006 h 82.7Kesimpulan PAGEREF _Toc483908007 h 83METODOLOGI PAGEREF _Toc483908008 h 93.1Pengenalan PAGEREF _Toc483908009 h 93.2Metodologi Projek dan Justifikasi PAGEREF _Toc483908010 h 93.3Fasa Pembangunan Sistem PAGEREF _Toc483908011 h 103.4Teknologi dan Peralatan yang Digunakan PAGEREF _Toc483908012 h 103.5Analisis Keperluan Sistem: Perkakasan dan Perisian PAGEREF _Toc483908013 h 103.6Kesimpulan PAGEREF _Toc483908014 h 104ANALISIS KEPERLUAN DAN REKA BENTUK PAGEREF _Toc483908015 h 114.1Pengenalan PAGEREF _Toc483908016 h 114.2Analisis Keperluan PAGEREF _Toc483908017 h 114.3Reka Bentuk Seni Bina Sistem PAGEREF _Toc483908018 h 114.4Reka Bentuk Pangkalan Data PAGEREF _Toc483908019 h 124.5Reka Bentuk Antara Muka Sistem PAGEREF _Toc483908020 h 124.5.1Reka Bentuk Menu dan Paparan PAGEREF _Toc483908021 h 124.5.2Reka Bentuk Kandungan dan Navigasi Sistem PAGEREF _Toc483908022 h 134.5.3Navigasi Halaman Web PAGEREF _Toc483908023 h 134.6Kesimpulan PAGEREF _Toc483908024 h 135RESULT ; DISCUSSION PAGEREF _Toc483908025 h 145.1Introduction PAGEREF _Toc483908026 h 145.2Pengekodan Fungsi Utama Sistem PAGEREF _Toc483908027 h 145.3Antara Muka Fungsi Utama PAGEREF _Toc483908028 h 145.4Pengujian PAGEREF _Toc483908029 h 155.4.1Pengujian Kotak Hitam PAGEREF _Toc483908030 h 155.4.2Pengujian Kotak Putih PAGEREF _Toc483908031 h 155.4.3Pengujian Pengguna PAGEREF _Toc483908032 h 155.5Kesimpulan PAGEREF _Toc483908033 h 166CONCLUSION PAGEREF _Toc483908034 h 176.1Introduction PAGEREF _Toc483908035 h 176.2Pencapaian Projek PAGEREF _Toc483908036 h 176.3Cadangan Penambahbaikan Projek PAGEREF _Toc483908037 h 176.4Cadangan Penambahbaikan Sistem untuk Masa Hadapan PAGEREF _Toc483908038 h 18REFERENCES PAGEREF _Toc483908039 h 19Lampiran A – Y 20 – 30
LIST OF TABLES
TABLE NO. TITLE PAGE
TOC h z c “Jadual” 2.1 Sistem LI universiti-universiti di Malaysia PAGEREF _Toc459739283 h 3
LIST OF FIGURES
NO. FIGURE TITLE PAGE
TOC h z c “Rajah” 2.1Antara muka fungsi penempatan. PAGEREF _Toc459739285 h 3
LIST OF ABBREVIATIONS
ASD – Autism Spectrum Disorder
SLAI – System Latihan Amali dan Industri
UTM – Universiti Teknologi Malaysia
LIST OF APPENDIX
LAMPIRANTAJUK HALAMAN
TOC c “LAMPIRAN” ABorang permohonan atas talian PAGEREF _Toc483911564 h 20
BShift-Enter selepas lampiran B PAGEREF _Toc483911565 h 21

INTRODUCTION
Introduction
Awareness of autism has grown dramatically in recent years, which reflects both an enlarge in diagnoses and in the public’s grasp regarding experienced for families or individual that faced limitation on getting early diagnosis. Many children with autism are put on waiting list and miss out early behavioural interventions and other benefits because health professionals are reluctant to diagnose autism early out of fear of labelling young children ADDIN EN.CITE <EndNote><Cite><Author>Dillenburger</Author><Year>2014</Year><RecNum>43</RecNum><DisplayText>(Dillenburger, 2014)</DisplayText><record><rec-number>43</rec-number><foreign-keys><key app=”EN” db-id=”fp5z9wsfaf2fxgedvp8pftx30w520tza0s5t” timestamp=”1524535044″>43</key></foreign-keys><ref-type name=”Web Page”>12</ref-type><contributors><authors><author>Karola Dillenburger</author></authors></contributors><titles><title>Why early diagnosis of autism in children is a good thing</title></titles><number>28 october</number><dates><year>2014</year></dates><pub-location>Australia</pub-location><urls><related-urls><url>https://theconversation.com/why-early-diagnosis-of-autism-in-children-is-a-good-thing-33290</url></related-urls></urls><custom1>2018</custom1><custom2>24 april</custom2></record></Cite></EndNote>(Dillenburger, 2014). Due to the significant quantity of genetic heterogeneity that underlies autism spectrum disorder (ASD), autism is particularly recognized via behavioural evaluations. Physician still did not fully utilized function of machine learning for early detection of ASD. The diagnostic services and trained clinicians tend to be geographically clustered in major metropolitan areas and far outnumbered by the individuals in need of evaluation PEVuZE5vdGU+PENpdGU+PEF1dGhvcj5EdWRhPC9BdXRob3I+PFllYXI+MjAxNDwvWWVhcj48UmVj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ADDIN EN.CITE PEVuZE5vdGU+PENpdGU+PEF1dGhvcj5EdWRhPC9BdXRob3I+PFllYXI+MjAxNDwvWWVhcj48UmVj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ADDIN EN.CITE.DATA (Duda, Kosmicki, & Wall, 2014). Diagnostic evaluations regularly require referrals from child’s primary care physician, and due to time and resource limitations, existing autism screening cannot be conducted consistently. Families may face long waiting periods between initial screening and clinical diagnosis, or even longer for the minority population or lower socioeconomic status.

From to this matter, there is a population of adult that facing this problem but did not receive any treatment from the start. Here we would like to provide a solution on difficulty getting diagnosis for further treatment. This will solve that even late diagnosis can help adults to understand their behavioural. Also, can provide main advantages and relief for their life.

Thus, this research focuses on how to improve classification algorithm performance for ASD prediction using fewer features and to execute feature selection method for Autism Spectrum Disorder classification based on behavioural. Applying machine learning techniques to this dataset to analyse data specific to ASD, with the goal to evaluate the predictive power of this techniques.
Research Background
Autism Spectrum Disorder is now recognized as a common lifelong neurodevelopmental disorder that affects 1% of both the children and adult populationPEVuZE5vdGU+PENpdGU+PEF1dGhvcj5NdXJwaHk8L0F1dGhvcj48WWVhcj4yMDE2PC9ZZWFyPjxS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==
ADDIN EN.CITE PEVuZE5vdGU+PENpdGU+PEF1dGhvcj5NdXJwaHk8L0F1dGhvcj48WWVhcj4yMDE2PC9ZZWFyPjxS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==
ADDIN EN.CITE.DATA (Murphy et al., 2016). This percentage shows that there is a growth rate in number of people with ASD. Due to that, a facility for both generations should be produce, which is simple, quick and easy for easier diagnosis for every people. Presently, very limited autism datasets associated with clinical or screening are available and most of them are genetic in nature. By using behavioural traits to diagnosis autism spectrum disorder, we can provide methods to quickly and accurately diagnosis ASD. Beside that to shorten diagnosis time for ASD, thus avoid patient diagnosis late.

Due to that, machine learning could be a new approach to diagnosis a person having ADS or not. The primary purpose of the machine learning studies on ASD was to improve diagnosis time of a case in order to provide quicker access to health care services using electronic and digitized applications, improve diagnosis accuracy, and reduce the dimensionality of the input dataset as to identify the highest ranked features of ASD. A screening tools should consist of only a few items and have good accuracy in classifying cases and non-cases.

The development of new method for ASD diagnoses based on machine learning. Therefore, in this research, machine learning is used and implemented as a screening tool to detect adult with autism more easy and quick. Using machine learning we can predict person condition either they have ASD or not, by referring to their behavioural. This shortened the time consuming for traditional diagnosis of ASD. Avoid late.

.

Problem Statement
The main goal of this research is focused on by using computational method. The amount of data being collected up until now beyond the limit of our ability to traditionally analyse without any computational methods. The following research questions that could be started to achieve the goal of this research:
How to increase the classification accuracy of ASD prediction?
What is classification methods that could be used for predicting ASD?
How to select relevant features methods which accurately represent Autism Spectrum Disorder for classification purpose?
Research objectives
The goal of this research is to evaluate the effectiveness of computational classification method for prediction of autism spectrum disorder. Fast screening by minimizing the features used by machine learning. Therefore, the objectives are as follows:
To investigate the computational classification method on prediction of ASD based on behavioural.

To employ SVM, Random forest, Naïve Bayes, Random Forest and Decision Tree for ASD Prediction.
To enhance accuracy, sensitivity, and specificity of the classification methods.

To compare the performance of classification between SVM, Random forest, Naïve Bayes, Random Forest and Decision Tree for ASD prediction.

Research Scopes
The scope for this research are as follows:
Datasets used are from UCI and based on behavioural (AQ10 question are)
The classification experiments performed using WEKA (SVM, Random forest, Naïve Bayes, Neural Network and Decision Tree)
The feature selection used is method only.

Research Significance
This research aims to help reduced time for ASD diagnosis by using computational classification method. The result of classification will help researchers/psychologists to make quicker and simple diagnosis on people with ASD or no for further treatment.

Thesis Organization
This thesis outline is divided into 6 chapters. First, Chapter 1 gives the introduction of this study, background and objectives on what is needed to achieved in this research. Chapter 2 provides the literature review of previous and current works and methods relating to the research. Then in Chapter 3 presented the research methodology. Chapter 4 shows the process taken to achieved the objectives of this study. The result and discussion are describe at Chapter 5 and lastly, the thesis concluded at Chapter 6.

LITERATURE REVIEW
Introduction
Awareness of autism has grown dramatically in recent years, which reflects both an increase in diagnoses and in the public’s understanding that, even late in life, a diagnosis can offer major benefits and relief. More severe forms of ASD are often diagnosed in the first two years of a child’s life, but less severe forms may be diagnosed much later in life. Late diagnosis can help adults to understand their behavioural. It is not unusual for people on the autism spectrum to have reached adulthood without a diagnosis. This research is required to determine a better understanding of the needs of adult with ASD. Many adults with autism spectrum disorder(ASD) remain undiagnosed. ASD mainly diagnosed utilizing behavioural indicators such as social interaction, imaginative ability, repetitive behaviours, and communication among others ADDIN EN.CITE ;EndNote;;Cite;;Author;Thabtah;/Author;;Year;2018;/Year;;RecNum;36;/RecNum;;DisplayText;(Thabtah, 2018);/DisplayText;;record;;rec-number;36;/rec-number;;foreign-keys;;key app=”EN” db-id=”fp5z9wsfaf2fxgedvp8pftx30w520tza0s5t” timestamp=”1524057542″;36;/key;;key app=”ENWeb” db-id=””;0;/key;;/foreign-keys;;ref-type name=”Journal Article”;17;/ref-type;;contributors;;authors;;author;Fadi Thabtah;/author;;/authors;;/contributors;;titles;;title;Machine learning in autistic spectrum disorder behavioral research: A review and ways forward;/title;;/titles;;dates;;year;2018;/year;;/dates;;isbn;1753-8157;/isbn;;urls;;/urls;;electronic-resource-num;10.1080/17538157.2017.1399132;/electronic-resource-num;;/record;;/Cite;;/EndNote;(Thabtah, 2018).
To improve the diagnosis process of ASD, researchers have recently started to adopt machine learning intelligent methods ADDIN EN.CITE ;EndNote;;Cite;;Author;Thabtah;/Author;;Year;2018;/Year;;RecNum;36;/RecNum;;DisplayText;(Thabtah, 2018);/DisplayText;;record;;rec-number;36;/rec-number;;foreign-keys;;key app=”EN” db-id=”fp5z9wsfaf2fxgedvp8pftx30w520tza0s5t” timestamp=”1524057542″;36;/key;;key app=”ENWeb” db-id=””;0;/key;;/foreign-keys;;ref-type name=”Journal Article”;17;/ref-type;;contributors;;authors;;author;Fadi Thabtah;/author;;/authors;;/contributors;;titles;;title;Machine learning in autistic spectrum disorder behavioral research: A review and ways forward;/title;;/titles;;dates;;year;2018;/year;;/dates;;isbn;1753-8157;/isbn;;urls;;/urls;;electronic-resource-num;10.1080/17538157.2017.1399132;/electronic-resource-num;;/record;;/Cite;;/EndNote;(Thabtah, 2018).

This study is to reduce the input dimensionality and minimize the time taken to build the model, thus diagnosis efficiency with respect to time improves.

Binary classification.

Autism Spectrum Disorder(ASD)
Autism spectrum disorder(ASDs) are divesting neurodevelopmental disorders characterized by deficits in social communication and interaction across multiple contexts as well as restricted, repetitive patterns of interests and behaviour ADDIN EN.CITE ;EndNote;;Cite;;Author;Oh;/Author;;Year;2017;/Year;;RecNum;12;/RecNum;;DisplayText;(Oh, Kim, Kim, ;amp; Ahn, 2017);/DisplayText;;record;;rec-number;12;/rec-number;;foreign-keys;;key app=”EN” db-id=”fp5z9wsfaf2fxgedvp8pftx30w520tza0s5t” timestamp=”1522030325″;12;/key;;key app=”ENWeb” db-id=””;0;/key;;/foreign-keys;;ref-type name=”Journal Article”;17;/ref-type;;contributors;;authors;;author;Oh, D. H.;/author;;author;Kim, I. B.;/author;;author;Kim, S. H.;/author;;author;Ahn, D. H.;/author;;/authors;;/contributors;;auth-address;Institute for Health and Society, Hanyang University, Seoul, Korea. Translational Neurogenetics Laboratory, Graduate School of Medical Science and Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea. Department of Psychiatry and Institute of Mental Health, Hanyang University College of Medicine, Seoul, Korea.;/auth-address;;titles;;title;Predicting Autism Spectrum Disorder Using Blood-based Gene Expression Signatures and Machine Learning;/title;;secondary-title;Clin Psychopharmacol Neurosci;/secondary-title;;/titles;;periodical;;full-title;Clin Psychopharmacol Neurosci;/full-title;;/periodical;;pages;47-52;/pages;;volume;15;/volume;;number;1;/number;;keywords;;keyword;Autism spectrum disorder;/keyword;;keyword;Blood;/keyword;;keyword;Decision support techniques;/keyword;;keyword;Machine learning;/keyword;;keyword;Microarray analysis;/keyword;;keyword;Transcriptome;/keyword;;/keywords;;dates;;year;2017;/year;;pub-dates;;date;Feb 28;/date;;/pub-dates;;/dates;;isbn;1738-1088 (Print) 1738-1088 (Linking);/isbn;;accession-num;28138110;/accession-num;;urls;;related-urls;;url;https://www.ncbi.nlm.nih.gov/pubmed/28138110;/url;;/related-urls;;/urls;;custom2;PMC5290715;/custom2;;electronic-resource-num;10.9758/cpn.2017.15.1.47;/electronic-resource-num;;/record;;/Cite;;/EndNote;(Oh, Kim, Kim, ; Ahn, 2017). ASD was initially described as a rare disorder of childhoodPEVuZE5vdGU+PENpdGU+PEF1dGhvcj5NdXJwaHk8L0F1dGhvcj48WWVhcj4yMDE2PC9ZZWFyPjxS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==
ADDIN EN.CITE PEVuZE5vdGU+PENpdGU+PEF1dGhvcj5NdXJwaHk8L0F1dGhvcj48WWVhcj4yMDE2PC9ZZWFyPjxS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==
ADDIN EN.CITE.DATA (Murphy et al., 2016). In 1966, the prevalence of autism was estimated to be just four cases per 10,000 people. However, ASD is now recognized as a common lifelong neurodevelopmental disorder that affects 1% of both the child and adult populationPEVuZE5vdGU+PENpdGU+PEF1dGhvcj5NdXJwaHk8L0F1dGhvcj48WWVhcj4yMDE2PC9ZZWFyPjxS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==
ADDIN EN.CITE PEVuZE5vdGU+PENpdGU+PEF1dGhvcj5NdXJwaHk8L0F1dGhvcj48WWVhcj4yMDE2PC9ZZWFyPjxS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==
ADDIN EN.CITE.DATA (Murphy et al., 2016). An older adult with ASD may impact on their mental health and ability to live independently. Behavioural difficulties
ASD symptoms
Every person on the autism spectrum is different but some of the more common characteristics include difficulties with high-level language skills such as verbal reasoning, problem solving, making inferences and predictions. Also in counter problems with understanding another person’s point of view, difficulties initiating social interactions and maintaining an interaction and may not respond in the way that is expected in a social interaction, a preference for routines and schedules disruption of a routine can result in stress or anxiety and specialised fields of interest or hobbies. After reviewing so many papers, a few of them.
Moreover, people with ASD can have specific cognitive anomalies, including poor planning, decision making, timing, and motor skills, which will affect their everyday living skillsPEVuZE5vdGU+PENpdGU+PEF1dGhvcj5NdXJwaHk8L0F1dGhvcj48WWVhcj4yMDE2PC9ZZWFyPjxS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==
ADDIN EN.CITE PEVuZE5vdGU+PENpdGU+PEF1dGhvcj5NdXJwaHk8L0F1dGhvcj48WWVhcj4yMDE2PC9ZZWFyPjxS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==
ADDIN EN.CITE.DATA (Murphy et al., 2016).

Diagnosis
ASD is defined and diagnosed on the basis of behaviour. The diagnosis of ASD has been revised over the last 35 years, and early brain imaging, as well as genetic and behavioural investigations of ASD, have contributed to significant advances in our understanding of ASDPEVuZE5vdGU+PENpdGU+PEF1dGhvcj5NdXJwaHk8L0F1dGhvcj48WWVhcj4yMDE2PC9ZZWFyPjxS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==
ADDIN EN.CITE PEVuZE5vdGU+PENpdGU+PEF1dGhvcj5NdXJwaHk8L0F1dGhvcj48WWVhcj4yMDE2PC9ZZWFyPjxS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==
ADDIN EN.CITE.DATA (Murphy et al., 2016). Targeted treatment thus improved services for people with ASD.

Machine Learning
Machine learning is a field of computer science that uses statistical technique to give computer science the ability to “learn” with data, without being explicitly programmed. The term machine learning was coined in 1959 by Arthur Samuel. There are four types of machine learning, supervised learning, unsupervised learning, semi-supervised learning and reinforcement learning. Majority of practical machine learning uses supervised learning.
Supervised learning is where you have input variables and output variable and use an algorithm to learn the mapping function from the input to the output. The goal from this is to learn the model from labelled data and make accurate output prediction on the new input. The supervised learning can be further grouped into regression and classification problems. A classification problem is when the output variable is a category, such as “cancer” or “no cancer” (have class). A regression problem is when the output variable is real value, such as “weight”. List of common algorithms is Support Vector Machine(SVM), Neural Network, Decision Trees, Linear Regression, Random Forest, Naive Bayes and Nearest Neighbour.

Unsupervised learning is where only input data without no corresponding output variables. The goal is to model the underlying structure or distribution in the data in order to learn more about the data. Unlike supervised learning, there is no correct answer for this learning. Algorithm needs to discover and present the structure in the data. Unsupervised learning can be further grouped into clustering and association problems. A clustering problem is where you want to discover the inherent groupings in the data, such as grouping customers by purchasing behaviour. An association rule learning problem is where you want to discover rules that describe large portions of your data, such as people that buy X also tend to buy Y. Mainly used in pattern detection and descriptive modelling. Some popular example of unsupervised learning algorithms are k-means(c) and apriori algorithm for (association rule learning). In short, supervised learning all data is labelled and the algorithms learn to predict the output from the input data. Unsupervised learning all data is unlabelled and the algorithms learn to inherent structure from the input data. Semi-supervised some data is labelled but most of its unlabelled and both supervised and unsupervised techniques can be used.

Classification
This process is employed to classify data into predefined categorical class labels. Classification can be a two step process consisting of training data and testing data. Classification rule techniques are applied on training data to form the model.

Random Forest
Naive Bayes
Support Vector Machine (SVM)
Decision Tree
A supervised learning algorithm that is mostly used for classification problems. Can handle both categorical and continuous dependent variables. Requires reshaping the entire classifier in case of any addition and removal to features.

Neural Network
Autism-Spectrum Quotient
There are two different types diagnosis methods for ASD, clinical and non-clinical type. Autism Diagnostic Observation Schedule-Revised (ADOS-R) and Autism Diagnostic Interview (ADI) is an example of clinical diagnosis method, whereas for non-clinical methods are Autism Quotient Trait (AQ) and Social Communication Questionnaire (SCQ). A self-report questionnaire measure of autistic traits. However, the capability of the AQ to predict who will go on to acquire a diagnosis of ASD in adults is unclear.

To enable medical care staff, including physicians, nurses, and other clinical staff, to utilize at most ten features/question as a form for quick clinical referrals of potential ASD cases ADDIN EN.CITE <EndNote><Cite><Author>Thabtah</Author><Year>2018</Year><RecNum>36</RecNum><DisplayText>(Thabtah, 2018)</DisplayText><record><rec-number>36</rec-number><foreign-keys><key app=”EN” db-id=”fp5z9wsfaf2fxgedvp8pftx30w520tza0s5t” timestamp=”1524057542″>36</key><key app=”ENWeb” db-id=””>0</key></foreign-keys><ref-type name=”Journal Article”>17</ref-type><contributors><authors><author>Fadi Thabtah</author></authors></contributors><titles><title>Machine learning in autistic spectrum disorder behavioral research: A review and ways forward</title></titles><dates><year>2018</year></dates><isbn>1753-8157</isbn><urls></urls><electronic-resource-num>10.1080/17538157.2017.1399132</electronic-resource-num></record></Cite></EndNote>(Thabtah, 2018).

Weka
Weka was developed at the University of Waikato in New Zealand, the name stands for Waikato Environment for Knowledge Analysis. The Weka GUI Chooser lets you choose one of the Explorer, Experimenter, Knowledge Explorer and Simple CLI. Weka provides features like data filtering, clustering, association rule extraction, and visualization ADDIN EN.CITE <EndNote><Cite><Author>al</Author><Year>2016</Year><RecNum>10</RecNum><DisplayText>(al, 2016)</DisplayText><record><rec-number>10</rec-number><foreign-keys><key app=”EN” db-id=”fp5z9wsfaf2fxgedvp8pftx30w520tza0s5t” timestamp=”1521875313″>10</key><key app=”ENWeb” db-id=””>0</key></foreign-keys><ref-type name=”Book”>6</ref-type><contributors><authors><author>Witten. et al</author></authors></contributors><titles><title>The Weka Workbench</title></titles><edition>4</edition><dates><year>2016</year></dates><urls></urls></record></Cite></EndNote>(al, 2016).Usually, dataset in Weka using ARFF format, but there also other format that supported in Weka for example cvs. format. When using Weka, you need to change the data type to format that compatible with weka. Weka’s main graphical user interface, the Explorer, gives access to all of its facilities using menu selection and form filling. There is disadvantage of the of the Explorer is that it holds everything in main memory, so when you open a dataset, it immediately loads it all in. This means that it can only be applied to small and medium problems. There are three other GUI to Weka. The experimenter enables you to set up large-scale experiments, you just can set up big experiments and just leave them to run. It allows user to distribute the computing load across multiple machines using java RMI. The Experimenter transcends limitations of the time. The knowledgeFlow help to visualizing the flow of the data. Transcends limitations of space by allowing machine learning runs that do not load in the whole dataset at once.

Dataset
Presently, very limited autism datasets associated with clinical or screening are available and most of them are genetic in nature. In this dataset, data was record ten behavioural features (AQ-10-Adult) plus ten individual’s characteristics that have proved to be effective in detecting the ASD cases from controls in behaviour science. Containing 515 positive set and 189 negative set.Autism Screening Adult data collected from UCI Repository by Fadi Thabtah.

It consisted of 200 individuals with ASD and 215 with non ASD. The data only have two class labels, ASD or non-ASD.

Majority of the research which involving ASD and machine learning, uses dataset containing two class labels, ASD and Non-ASD.

Feature selection
Tries to eliminate features that are irrelevant or not important for the classification, thereby decreasing the complexity of the model. Reduce dimensionality. The current research using feature selection to reduce dimensionality data of ASD and applying machine learning to the selected features.
Two main categories of feature selection is filter and wrapper models. A filtering methods like, usually produces a ranked set of features quickly and hence filtering methods are time efficient. On the other hand, wrapping methods normally
Feature selection plays significant role in the success or failure of the machine learning algorithm().
Evaluation method
Evaluation metrics normally recommended for evaluating the classifier’s performance are accuracy, sensitivity or recall, specificity, Balanced Classification Rate (BCR), F-Value, Matthews Correlation Coefficient(MCC) and Area Under Receivers Operating Characteristic(auROC) curve ADDIN EN.CITE ;EndNote;;Cite;;Author;Jagga;/Author;;Year;2014;/Year;;RecNum;17;/RecNum;;DisplayText;(Jagga ;amp; Gupta, 2014);/DisplayText;;record;;rec-number;17;/rec-number;;foreign-keys;;key app=”EN” db-id=”fp5z9wsfaf2fxgedvp8pftx30w520tza0s5t” timestamp=”1523377141″;17;/key;;key app=”ENWeb” db-id=””;0;/key;;/foreign-keys;;ref-type name=”Journal Article”;17;/ref-type;;contributors;;authors;;author;Jagga, Z.;/author;;author;Gupta, D.;/author;;/authors;;/contributors;;auth-address;Bioinformatics Facility, Structural and Computational Biology Group, International Centre for Genetic Engineering and Biotechnology, Aruna Asaf Ali Marg, New Delhi, India.;/auth-address;;titles;;title;Supervised learning classification models for prediction of plant virus encoded RNA silencing suppressors;/title;;secondary-title;PLoS One;/secondary-title;;/titles;;periodical;;full-title;PLoS One;/full-title;;/periodical;;pages;e97446;/pages;;volume;9;/volume;;number;5;/number;;keywords;;keyword;Algorithms;/keyword;;keyword;Amino Acids/genetics;/keyword;;keyword;Bayes Theorem;/keyword;;keyword;Plant Diseases/virology;/keyword;;keyword;Plant Viruses/*genetics</keyword><keyword>Plants/virology</keyword><keyword>RNA Interference/*physiology</keyword><keyword>RNA, Viral/*genetics</keyword><keyword>Viral Proteins/genetics</keyword></keywords><dates><year>2014</year></dates><isbn>1932-6203 (Electronic) 1932-6203 (Linking)</isbn><accession-num>24828116</accession-num><urls><related-urls><url>https://www.ncbi.nlm.nih.gov/pubmed/24828116</url></related-urls></urls><custom2>PMC4020838</custom2><electronic-resource-num>10.1371/journal.pone.0097446</electronic-resource-num></record></Cite></EndNote>(Jagga & Gupta, 2014). The predictive model derived by machine learning is assessed with a number of evaluation measures. For a binary classification problem (ASD, No-ASD) as a basic form of the classification problem.
Cross-validation is a testing method existing in machine learning to examine the predictive models and to assess its effectiveness. Normally k used is 10.

Accuracy
This is the most common evaluation measures. This measures to identify the number of test case that have been correctly classified from the total number of test cases.
Accuracy=TP+TNTP+TN+FP+FN×100F-Measure
F-Measure combines recall and precision by harmonic mean(?). Standard evaluation metric, in the case of class imbalance.

F-value=2×TP2×TP+FP+FNSensitivity and Recall
Determines classifier effectiveness to identify positive class labels.Identifies the ratio of the test cases that have truly ASD(true positive rate). Correctly identify those who have ASD.

Sensitivity/ Recall=TPTP+FN×100Precision
Precision is
4246245167640…(2.4)4)
00…(2.4)4)

Precision=TPTP+FP×100Specificity
Specificity calculates the classifier effectiveness to identify negative class labels. Ratio of the best test cases who do not have ASD(true negative rate). Correctly identify those who do not have ASD.

Specificity=TNTN+FP×100MCC
MCC value ranges from 0 to 1, where 1 is the perfect prediction and 0 is random prediction ADDIN EN.CITE <EndNote><Cite><Author>Jagga</Author><Year>2014</Year><RecNum>17</RecNum><DisplayText>(Jagga &amp; Gupta, 2014)</DisplayText><record><rec-number>17</rec-number><foreign-keys><key app=”EN” db-id=”fp5z9wsfaf2fxgedvp8pftx30w520tza0s5t” timestamp=”1523377141″>17</key><key app=”ENWeb” db-id=””>0</key></foreign-keys><ref-type name=”Journal Article”>17</ref-type><contributors><authors><author>Jagga, Z.</author><author>Gupta, D.</author></authors></contributors><auth-address>Bioinformatics Facility, Structural and Computational Biology Group, International Centre for Genetic Engineering and Biotechnology, Aruna Asaf Ali Marg, New Delhi, India.</auth-address><titles><title>Supervised learning classification models for prediction of plant virus encoded RNA silencing suppressors</title><secondary-title>PLoS One</secondary-title></titles><periodical><full-title>PLoS One</full-title></periodical><pages>e97446</pages><volume>9</volume><number>5</number><keywords><keyword>Algorithms</keyword><keyword>Amino Acids/genetics</keyword><keyword>Bayes Theorem</keyword><keyword>Plant Diseases/virology</keyword><keyword>Plant Viruses/*genetics</keyword><keyword>Plants/virology</keyword><keyword>RNA Interference/*physiology</keyword><keyword>RNA, Viral/*genetics</keyword><keyword>Viral Proteins/genetics</keyword></keywords><dates><year>2014</year></dates><isbn>1932-6203 (Electronic) 1932-6203 (Linking)</isbn><accession-num>24828116</accession-num><urls><related-urls><url>https://www.ncbi.nlm.nih.gov/pubmed/24828116</url></related-urls></urls><custom2>PMC4020838</custom2><electronic-resource-num>10.1371/journal.pone.0097446</electronic-resource-num></record></Cite></EndNote>(Jagga & Gupta, 2014)
MCC=TP×TN-(FP×FN)TP+FN×TN+FP×TP+FP×TN+FN Cross Validation
Cross-validation, is a model validation technique for assessing how the results of a statistical analysis will generalize to an independent data set. It is mainly used in settings where the goal is prediction, and one wants to estimate how accurately a predictive model will perform in practice. In a prediction problem, a model is usually given a dataset of known data on which training is run (training dataset), and a dataset of unknown data (or first seen data) against which the model is tested (testing dataset). (This from dr roha slide).

This start with splitting the data into n partitions, for example n often set to 10.
Summary
This chapter described the detail on the definition and meaning of every term used as a part in this research.

METHODOLOGY
Introduction
This chapter discusses the methodology that implemented in this research. Basic requirements to perform diagnostic using machine learning are dataset as in input, also machine learning algorithm either new or existing embedded in a diagnostic tool to help build a predictive model for ASD classification. Lastly, an output form the classification. Then we also can add steps such as feature selection and noise minimization for the input dataset, this may help in the output quality or improve process efficiency of the classification.
Research methodology
center16510Dataset using Autism adult screening from UCI repository
00Dataset using Autism adult screening from UCI repository

center405765Processed data
Test data
0Processed data
Test data
center20002500
769620289560Feature selection
Defining which attributes most useful for classification
00Feature selection
Defining which attributes most useful for classification
center10985500
center192405Classification using 5 different machine learning run using Weka.

(J48, Naïve Bayes, SVM, Random forest, Neural Network)
00Classification using 5 different machine learning run using Weka.

(J48, Naïve Bayes, SVM, Random forest, Neural Network)
center1016000
center35877500
center40005Evaluation Methods performance
And comparison between all machine learning
0Evaluation Methods performance
And comparison between all machine learning

1760220407669Analyze classification result
00Analyze classification result
center20764500
Figure 3.1: A research framework of the proposed study.

In order to carry out this research, there are six phases of the methodology with each of the phases consist of their own processes in order to complete this research effectively. The following steps outline the research methods employed in this study.

Collect and gather dataset
Dataset collected from UCI Repository. Containing 515 positive set and 189 negative set. The after balancing the data by removing data from majority class, it containing 205 positive and 205 negative.

Perform data preprocessing
Remove the noise and impute missing value in the data. Due to that, it leads to better classification process and upgrades classifier’s performance.

Perform feature selection
There are basically two methods of feature selection wrapper method and filter method. Using wrapper method. The reason why we applied feature selection is to reduce the dimensionality of data.
A feature selection technique that used in this research is method.
Perform Classification
At classification phase, the tool that will be uses is a Waikato Enviroment for Knowledge Analysis(WEKA). It could be accessed or downloded through the link(WEKA link). The WEKA workbench is a collection of machine learning algorithm and data preprocessing tools that includes virtually many algorithm. Here the function that will be used are for the data pre-processing, feature selection and classification experiment. Machine learning techniques such as Naive Bayes, Support Vector machines, J48, Random Forest, and Neural Network, have been applied to datasets related to autism in order to construct predictive models. These models claim to enhance the ability of clinicians to provide robust diagnoses and prognoses of ASD. Using explorer workbench.

The classification was performed to both training and testing dataset. Using 10 cross validation because reduces this variance by averaging over k different partitions, so the performance estimate is less sensitive to the partitioning of the data.

By loading the processed dataset and then choosing the machine learning algorithm which in this study I choose (SVM, Random forest, Decision tree, Naïve Bayes and NN) this is common algorithm used to classify the dataset. Then the outcome of this phase evaluated to determine the effectiveness of the chosen machine learning method.

Analyze the Classification Result
The result from the experiment conducted using WEKA then calculated for evaluation method accuracy, precision, specificity, sensitivity/recall and F-Measure. The comparison between the result using or without using feature selection method can be seen after the evaluation of the classification result. The result is discussed in Chapter 5.

Summary
This chapter discussed the methodology which will be used in this research. It includes six phases starting with. Each of these phases have an integral role in achieving the main objective in this research. Also all the details of the framework were discussed in this chapter.

EXPERIMENTAL RESULT
Introduction
This chapter discussed the activities on how to get experimental result. The activities involve in data pre-processing phase, which feature selection. Show classification using WEKA tool.

Data pre-prosessing
Consist of.

Feature selection
Perform classification
Summary
RESULT AND CONCLUSION
Introduction
This chapter explains more on classification result and performance measurement analysis. Those Result get from WEKA.

Analyze the classification result (without feature selection)

Figure 5.1 The classification performance based on accuracy.

The highest accuracy is 96.87% for SVM classification.

Figure 5.2 The classification performance based on precision

Figure 5.3 The classification performance based on sensitivity/recall

Figure 5.4 The classification performance based on specificity

Figure 5.5 The classification performance based on F-Measure
Analyze the classification result (with feature selection)
Discussion
The purpose of this study was to validate the classifier aimed at decreasing the time consume for diagnosis and detection of ASD based on behaviour using small number of features. The result from five different machine learning with feature selection and without feature selection. The classifier performed with statistical accuracy and shows high positive and negative predictive values when compare to what classifier. Although more testing and experiment is needed to determine if and how the approaches describe here can have clinical value, there is little doubt that the field needs novel methods for initial screening, diagnosis and monitoring that can reach a larger percentage of rising autism population.
Summary
CONCLUSION
Introduction
This chapter explains more on conclusion based on the experiment and result obtained throughout the process. Also, the problem faced during the process of this research and suggestion on future works discussed here. There has been a considerable increase in ASD research over the past years but much remains to be done in health services research for people with ASD.

In conclusion, from the result of this experiment, enhance and improvements are needed for future works if this research is to be continued. Firstly.

Problem and Limitation of Research
There are several problems and limitations when doing this research, such as:
Time needed.

Future Works
In addition, from the result of this experiment,….improvement are needed for future works. Firstly, providing different class for example “light autism” or “severe autism”, etc. Also, for different cases that may have common features with other PDD categories for example ADHD and Asperger Syndrome. Discovering how to differentating this cases.

Summary
In overall, this research has achieved the objectives and meet the proposed scope of the research. This research offers the solution to the problem that happens nowdays, which is the time to diagnosis individual having ASD or not.

RUJUKANADDIN Mendeley Bibliography CSL_BIBLIOGRAPHY Mohammed, N., Munassar, A. & Govardhan, A., 2010. A Comparison Between Five Models Of Software Engineering. IJCSI International Journal of Computer Science Issues ISSN, 7(5), pp.1694–814.

LAMPIRAN SEQ LAMPIRAN * ALPHABETIC ABorang permohonan atas talian
LAMPIRAN SEQ LAMPIRAN * ALPHABETIC BShift-Enter selepas lampiran B
Gunakan Insert Caption “Lampiran”
REFERENCES
ADDIN EN.REFLIST al, W. e. (2016). The Weka Workbench (4 ed.).

Dillenburger, K. (2014). Why early diagnosis of autism in children is a good thing. Retrieved from https://theconversation.com/why-early-diagnosis-of-autism-in-children-is-a-good-thing-33290Duda, M., Kosmicki, J. A., & Wall, D. P. (2014). Testing the accuracy of an observation-based classifier for rapid detection of autism risk. Transl Psychiatry, 4, e424. doi:10.1038/tp.2014.65
Jagga, Z., & Gupta, D. (2014). Supervised learning classification models for prediction of plant virus encoded RNA silencing suppressors. PLoS One, 9(5), e97446. doi:10.1371/journal.pone.0097446
Murphy, C. M., Wilson, C. E., Robertson, D. M., Ecker, C., Daly, E. M., Hammond, N., . . . McAlonan, G. M. (2016). Autism spectrum disorder in adults: diagnosis, management, and health services development. Neuropsychiatr Dis Treat, 12, 1669-1686. doi:10.2147/NDT.S65455
Oh, D. H., Kim, I. B., Kim, S. H., & Ahn, D. H. (2017). Predicting Autism Spectrum Disorder Using Blood-based Gene Expression Signatures and Machine Learning. Clin Psychopharmacol Neurosci, 15(1), 47-52. doi:10.9758/cpn.2017.15.1.47
Thabtah, F. (2018). Machine learning in autistic spectrum disorder behavioral research: A review and ways forward. doi:10.1080/17538157.2017.1399132