abstract book - worldconferences.networldconferences.net/proceedings/aics2015/abstrac… · ·...

3rd International Conference on Artificial Intelligence and Computer Science (AICS2015), 12 - 13 October 2015, Penang, MALAYSIA. (e-ISBN 978-967-0792-06-4). Organized by http://worldconferences.net 2

ABSTRACT BOOK

3rd INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND COMPUTER SCIENCE 2015

AICS2015

“The importance of Intelligent Machine”

Penang, MALAYSIA

12 & 13 October 2015

e-ISBN 978-967-0792-06-4

The Secretariat would like to express their heartfelt appreciation for the contributions made by the authors, co-authors, reviewers and all who involved in this conference.

Organized and Published by

WorldConferences.net

Koperasi KOKISDAR

Kolej Universiti Islam Antarabangsa Selangor

Bandar Seri Putra, 43600 Kajang, Selangor, MALAYSIA

E-mail: [email protected]

Phone: +6019-347-2420

Copyright © 2015 WorldConferences.net

All rights reserved. No part of this publication may be reproduced in any form or any means without prior permission from the copyright holder.

All articles in this proceeding are openly accessible at WorldConferences.net

mailto:[email protected]


ABOUT THE CONFERENCE The AICS2015 conference is a platform to bring together researchers, developers and practitioners from academia and industry working in all interdisciplinary areas of Artificial Intelligence and Computer Science. The conference is hosted by WorldConferences.net, KOKISDAR (in collaboration with Faculty of Information Science and Technology (FSTM), International Islamic University College Selangor (KUIS), MALAYSIA) .

Venue Bayview Beach Resort Hotel, PENANG, MALAYSIA

Conference Dates 12 & 13 October 2015

Theme “The importance of Intelligent Machine”

Sub-themes Natural language processing

Machine Translation

Machine Transliteration

Computer Science

Computer Intelligence

Algorithm and Programming

Software Engineering

Fuzzy logic and soft computing

Software tools for AI

Expert systems

Decision support systems

Automated problem solving

Knowledge discovery

Knowledge representation

Knowledge acquisition

Knowledge-intensive problem solving techniques

Knowledge networks and management

Intelligent information systems

Intelligent web-based business

Intelligent agents

Intelligent networks

Intelligent databases

Intelligent user interface

AI and evolutionary algorithms

Intelligent tutoring systems

Reasoning strategies

Distributed AI algorithms and techniques

Distributed AI systems and architectures

Neural networks and applications

Heuristic searching methods

Languages and programming techniques for AI

Constraint-based reasoning and constraint programming

Intelligent information fusion

Search and meta-heuristics

Swarm Optimization

Integration of AI with other technologies

Evaluation of AI tools

Social intelligence (markets and computational societies)

Social impact of AI

Emerging technologies

AI Applications (including: computer vision, signal processing, pattern recognition, face recognition, finger print recognition, education, emerging applications, …)

Machine Learning


EDITORIAL BOARD Reviewers Professor Dr. Abdul Hanan Bin Abdullah Universiti Teknologi Malaysia (UTM), MALAYSIA. Professor Dr. Siti Mariyam Shamsuddin Universiti Teknologi Malaysia (UTM), MALAYSIA. Professor Dr. Mohd Lazim Abdullah Universiti Malaysia Terengganu (UMT), MALAYSIA. Professor Dr. Abhay Saxena Dev Sanskriti Vishwavidyalya, Hardwar, Uttrakhand, INDIA Professor Dr. P.Raviraj Kalaignar Karunanidhi Institute of Technology, Coimbatore, Tamilnadu, INDIA. Professor Dr. Utpal Roy, Siksha-Bhavana, Visva-Bharati(Central University), Santiniketan, INDIA Associate Professor Ir. Dr. Sivarao Subramonian Universiti Teknikal Malaysia Melaka (UTeM), MALAYSIA. Associate Professor Dr. Md. Asri Ngadi Universiti Teknologi Malaysia (UTM), MALAYSIA. Associate Professor Dr. Sushil Kulkarni University of Mumbai, INDIA. Associate Professor Dr. Faieza Abdul Aziz Universiti Putra Malaysia (UPM), MALAYSIA. Associate Professor Mohd Hasan Selamat Universiti Putra Malaysia (UPM), MALAYSIA. Assistant Professor Nisheeth Joshi Apaji Institute, Banasthali University, Rajasthan, INDIA. Assistant Professor Dr. Ashutosh Kumar Bhatt Birla Institute of Applied Sciences, Bhimtal, Uttarakhand, INDIA. Dr. Ho Pei Yee Universiti Malaya (UM), MALAYSIA.


Dr. Mokmin Basri Kolej Universiti Islam Antarabangsa Selangor (KUIS), MALAYSIA. Dr. Serkan Dincer, University of Cukurova, TURKEY. Dr. Mohd Zaki Ayob, British Malaysian Institute, Universiti Kuala Lumpur (UNIKL), MALAYSIA. Mr. Jitender Grover, Assistant Professor, M.M. University, Sadopur, Ambala (Haryana), INDIA. Mr. Leon Andretti Abdillah, Senior Lecturer, Bina Darma University, INDONESIA Mr. Khirulnizam Abd Rahman, International Islamic University College Selangor (KUIS), MALAYSIA. Editors DR. MOKMIN BASRI KHIRULNIZAM ABD RAHMAN CHE WAN SHAMSUL BAHRI CW AHMAD


PRESENTATION SCHEDULE 12 OCTOBER 2015 – Monday

8.00am -

9.00am

9.00am -

10.30am

10.30am-

11.00am

11.00am -

1.00pm

1.00pm-

2.00 pm

2.15pm -

4.30pm

4.30pm

Registration PARALLEL SESSION 1

Morning Break

PARALLEL SESSION 2

Lunch and

Prayer

PARALLEL SESSION 3

Coffee / Tea

Break

Prayer Room : G Floor

Lunch :La Veranda Coffee House (G Floor)

There will be no presentation on the second day of the conference. However, participants are still entitled for lunch on the second day of the conference.

The 1st draft of AICS 2015 presentation schedule is published at the AICS 2015 website.

1. If you have paid the registration fee and your papers are not available at the

presentation schedule, please email to us your registration fee documentation. 2. Please remember your ID No. during the registration session. 3. Please bring your registration fee documentation during the registration session

Rules for Presentation

1. The presentation duration is 15 minutes.

2. No standard format for the presentation slides. The number of slides is use to be suite with the 15 minutes presentation.

Thank you & best regards.


DAY 1 - PARALLEL SESSION 1

(9.00AM – 10.30PM) AICS 2015

MODERATOR

A012

ELICITING EXPERT KNOWLEDGE IN QUANTIFYING THE HUMAN BEHAVIOUR DURING AN EMERGENCY

USING EBBN PROCEDURE MRS. NURULHUDA RAMLI, NORAIDA ABDUL GHANI, INTAN HASHIMAH MOHD HASHIM AND ZULKARNAIN AHMAD HATTA

A018

MINDMAP SHEET: SATU KAEDAH UNTUK MENINGKATKAN PENGUASAAN DAN KEMAHIRAN SUBJEK

APLIKASI KOMPUTER MENGGUNAKAN TEKNIK PETA MINDA DI KALANGAN PELAJAR BERMASALAH

PEMBELAJARAN DI KOLEJ KOMUNITI BAYAN BARU NOOR SARENA MOHD ZAHID, ROHANI M.M YUSOFF, NORHAFIZAH ABDUL RAHMAN, ABDA HAMIDA D ABDUL HAMEED

A027

AGENT BASED TWO BUFFER HIERARCHICAL SCHEDULING ALGORITHM FOR MULTICORE ARCHITECTURE

G.MUNEESWARI AND E.M.MALATHY

A028

THREE METHODS OF ARTIFICIAL EVOLUTION FOR AUTOMATED & SEMI-AUTOMATED SYNTHESIS OF FREE-

FORM 3D PRINTABLE AESTHETIC OBJECTS

JASON TEO, ONG JIA HUI, HALIMAH MANJA AND LEE CHIN KUAN

A077

ONTOLOGY BASED FUZZY INFORMATION RETRIEVAL WITH AN EYE ON FUZZINESS

DR. SRABANI SARKAR

A036

IMPROVED FUZZY-PI CONTROL SCHEME FOR POWER FLOW OF DISTRIBUTED GENERATION

AZUKI ABDUL SALAM, NIK AZRAN AB HADI, FATIMAH ZAHARAH HAMIDON AND ISMAIL ADAM



(11.00PM – 1.00PM)

AICS 2015

MODERATOR

HUDA ZAKI NAJI

A039

SYSTEM TO AUTOMATICALLY CALCULATE THE ACCURACY (SACA)

MUHAMMAD AWIS JAMALUDDIN JOHARI, AMRU YUSRIN AMRUDDIN AND DR. CHEW YEW CHOONG

A043

NEURAL NETWORK MODEL USING BACK PROPAGATION ALGORITHM FOR CREDIT RISK EVALUATION

DIONICIO D. GANTE

A065

THE POSSIBILITY OF STUDENTS’ COMMENTS AUTOMATIC INTERPRET USING LEXICON BASED SENTIMENT

ANALYSIS TO TEACHER EVALUATION

PHURIPOJ KAEWYONG, ANUPONG SUKPRASERT, PROF. DR. NAOMIE SALIM AND ASSOC. PROF. DR. FATIN

ALIAH PHANG

A067

UTILIZING PAST EXPERIENCES OF INCIDENT HANDLERS FOR REALIZING A CBR RECOMMENDER IN

INCIDENT RESPONSE

WIRA ZANORAMY ANSIRY ZAKARIA, KILAUSURIA ABDULLAH AND FAISZATULNASRO MOHD MAKSOM

A026

DIAGNOSTIC FEATURES SELECTION METHODS FOR SOIL PROFILE CLASSIFICATION SYSTEM BASED ON DMT

AND CPT DATA

JAROSLAW KUREK, MICHAL KRUK, PIOTR BILSKI, OGUZ AKPOLAT AND SIMON RABARIJOELY

A023

DYNAMIC REDEPLOYMENT MANAGEMENT FOR EMERGENCY MEDICAL SYSTEMS WITH TWO TYPES OF

SERVERS HUDA ZAKI NAJI AND NORAIDA ABDUL GHANI

A073

MYABISO: A MOBILE APPLICATION FOR STUDENT ORGANIZATION EVENT MANAGEMENT AND

INFORMATION DISSEMINATION

LANDICHO, JUNAR A.*, BACULIO , RYAN DYL B. , GABALES , RHYAN JAY B. , GEÑOSO,EARL HANS P. ,

MARTINEZ AND

A074

WEB - BASED INTERACTIVE CAMPUS MAP

MARYLENE S. EDER, CATHERINE JEAN L. NOCETE, GEMELYN L. RANCES, ETHYL M. TARROSA AND JENILYN N.

YANSON



(2.30AM – 4.30PM)

AICS 2015

MODERATOR

A048/050

GENDER CLASSIFICATION USING GLOBAL LEVEL FINGERPRINT FEATURE IN MALAYSIA

SITI FAIRUZ ABDULLAH, AHMAD FADZLI NIZAM ABD RAHMAN AND ZURAIDA ABAL ABAS

A049/050

DISCRETE WAVELET PACKET TRANSFORM FOR ELECTROENCEPHALOGRAM-BASED EMOTION

RECOGNITION IN THE VALENCE-AROUSAL SPACE

FARZANA KABIR AHMAD AND OYENUGA WASIU OLAKUNLE

A051

OPTIMIZING ATTACK PATH SELECTION FOR ENTERPRISE NETWORK SECURITY

ABDULLAH SANI ABD RAHMAN AND MOHD KHALIT OTHMAN

A054

PROPOSED CONCEPTUAL FRAMEWORK OF DENGUE ACTIVE SURVEILLANCE SYSTEM IN MALAYSIA

MOHD KHALIT OTHMAN AND MOHD SHAHRUL NIZAM MOHD DANURI

A072 - CROWDALERT: AN ANDROID APPLICATION FOR INCREASING THE AWARENESS AND RESPONSE

INITIATIVES OF THE CITIZENS THROUGH CROWDSOURCING

JOHN BENEDICT L. BERNARDO, MIT*, KATHLYN M. HUAVAS, GREMEIR MITZ O. OCIONES, RICKY A. PANTUAN,

JESSA MAE P. VASALLO

A055

A FRAMEWORK FOR SEMANTIC BASED ANOMALY DETECTION IN TEXT

MOHAMMED AHMED TAIYE, SITI SAKIRA KAMARUDDIN AND FARZANA KABIR AHMAD

A057

MODIFIED A5/1 STREAM CIPHER FOR SECURE GLOBAL SYSTEM FOR MOBILE (GSM) COMMUNICATION

SITI YOHANA AKMAL MOHD FAUZI, DR. MARINAH OTHMAN, FARRAH MASYITAH MOHD SHUIB AND PROF.

DR. KAMARUZZAMAN BIN SEMAN

A059

AN EFFICIENT METHOD TO PREDICT DENGUE OUTBREAKS IN KUALA LUMPUR

DUC NGHIA PHAM1, TARIQUE AZIZ

1, ALI KOHAN

1, SYAHRUL NELLIS

2, JURAINA BINTI ABD. JAMIL

2, JING JING

KHOO2, DICKSON LUKOSE

1, SAZALY BIN ABU BAKAR

2 AND ABDUL SATTAR

3

A068

ADVANCED THRESHOLD SENSITIVE STABLE ELECTION PROTOCOL FOR CLUSTERED HETROGENEOUS

WIRELESS SENSOR NETWORKS: ATSEP

PRIYANKA SHARMA AND INDERJEET KAUR


A075 - FUSION OF MULTIPLE ECHOCARDIOGRAPHY SEQUENCES THROUGH A HYBRID METHOD

SAMANEH MAZAHERI, PUTERI SUHAIZA SULAIMAN, RAHMITA WIRZA, MOHD ZAMRIN DIMON, FATIMAH

KHALID AND ROHOLLAH MOOSAVI TAYEBI

A070

TSADA-MOBIMINDER (A LOCATION BASED ALARM MOBILE REMINDER)

MARYLENE SALDON-EDER

A071

SENTIMENT ANALYSIS OF GOVERNMENT SOCIAL MEDIA TOWARDS AN AUTOMATED CONTENT ANALYSIS

USING SEMANTIC ROLE LABELING

SITI SALWA HASBULLAH1 AND RITA ZAHARAH WAN-CHIK

2

A053

MAPREDUCE BASED PARTICLE SWARM OPTIMIZATION FOR LARGE SCALE PROBLEMS

SAEED MEHRJOO AND SAMAN DEHGHANIAN

A025

SOILS CLASSIFICATION SYSTEM ON THE BASIS OF DMT AND CPT DATA MICHAL KRUK, JAROSLAW KUREK, PIOTR BILSKI AND OGUZ AKPOLAT

A030

APPLICATION OF THE RULE-BASED SYSTEM FOR THE CLASSIFICATION OF SOIL LAYERS

PIOTR BILSKI AND SIMON RABARIJOELY


TABLE OF CONTENTS Paper ID: A012 ELICITING EXPERT KNOWLEDGE IN QUANTIFYING THE HUMAN BEHAVIOUR DURING AN EMERGENCY USING EBBN PROCEDURE Nurulhuda Ramli, Noraida Abdul Ghani, Intan Hashimah Mohd Hashim and Zulkarnain A. Hatta pp. 1 - 9 Paper ID: A018 MINDMAP SHEET: SATU KAEDAH UNTUK MENINGKATKAN PENGUASAAN DAN KEMAHIRAN SUBJEK APLIKASI KOMPUTER MENGGUNAKAN TEKNIK PETA MINDA DI KALANGAN PELAJAR BERMASALAH PEMBELAJARAN DI KOLEJ KOMUNITI BAYAN BARU Noor Sarena Mohd Zahid, Rohani M.M Yusoff, Norhafizah Abdul Rahman and Abda Hamida D Abdul Hameed pp. 10 - 19 Paper ID: A021 PEDICTING PATIENT’S LENGTH OF STAY BY MINING HOSPITAL DATA Saira Seemab and Usman Qamar pp. 20 - 30 Paper ID: A023 DYNAMIC REDEPLOYMENT MANAGEMENT FOR EMERGENCY MEDICAL SYSTEMS WITH TWO TYPES OF SERVERS Huda Zaki Naji and Noraida Abdul Ghani pp. 31 - 37 Paper ID: A026 THE APPLICATION OF ENSEMBLE CLASSIFICATION TECHNIQUES IN SOIL CLASSIFICATION SYSTEM ON THE BASIS OF DMT AND CPT DATA Jarosław Kurek, Michał Kruk, Piotr Bilski, Oguz Akpolat, Simon Rabarijoely and Grzegorz Wieczorek pp. 38 - 45 Paper ID: A027 AGENT BASED TWO BUFFER HIERARCHICAL SCHEDULING ALGORITHM FOR MULTICORE ARCHITECTURE G.Muneeswari and E.M.Malathy pp. 46 - 53 Paper ID: A028 THREE METHODS OF ARTIFICIAL EVOLUTION FOR AUTOMATED & SEMI-AUTOMATED SYNTHESIS OF FREE-FORM 3D PRINTABLE AESTHETIC OBJECTS Jason Teo, Ong Jia Hui, Halimah Manja and Lee Chin Kuan pp. 54 - 66 Paper ID: A030 APPLICATION OF THE RULE-BASED SYSTEM FOR THE CLASSIFICATION OF SOIL LAYERS Piotr Bilski and Simon Rabarijoely pp. 67 - 75


Paper ID: A036 IMPROVED FUZZY-PI CONTROL SCHEME FOR POWER FLOW OF DISTRIBUTED GENERATION Azuki Abdul Salam, Nik Azran Ab Hadi, Fatimah Zaharah Hamidon and Ismail Adam pp. 78 - 85 Paper ID: A039 SYSTEM TO AUTOMATICALLY CALCULATE THE ACCURACY (SACA) Muhammad Awis Jamaluddin Johari, Amru Yusrin Amruddin and Chew Yew Choong pp. 86 - 92 Paper ID: A043 NEURAL NETWORK MODEL USING BACK PROPAGATION ALGORITHM FOR CREDIT RISK EVALUATION Dionicio D. Gante, Bobby D. Gerardo and Bartolome T. Tanguilig III pp. 93 - 104 Paper ID: A048 GENDER CLASSIFICATION USING GLOBAL LEVEL FINGERPRINT FEATURE IN MALAYSIA Siti Fairuz Abdullah,Ahmad Fadzli Nizam Abd Rahman and Zuraida Abal Abas pp. 105 - 112 Paper ID: A049 DISCRETE WAVELET PACKET TRANSFORM FOR ELECTROENCEPHALOGRAM-BASED EMOTION RECOGNITION IN THE VALENCE-AROUSAL SPACE Farzana Kabir Ahmad and Oyenuga Wasiu Olakunle pp. 113 - 121 Paper ID: A053 MAPREDUCE BASED PARTICLE SWARM OPTIMIZATION FOR LARGE SCALE PROBLEMS Saeed Mehrjoo and Saman Dehghanian pp. 122 - 132 Paper ID: A054 PROPOSED CONCEPTUAL FRAMEWORK OF DENGUE ACTIVE SURVEILLANCE SYSTEM IN MALAYSIA Mohd Khalit Othman and Mohd Shahrul Nizam Mohd Danuri pp. 133 - 143 Paper ID: A055 A FRAMEWORK FOR SEMANTIC-BASED ANOMALY DETECTION IN TEXT Mohammed Ahmed Taiye, Siti Sakira Kamaruddin and Farzana Kabir Ahmad pp. 144 - 153 Paper ID: A057 MODIFIED A5/1 STREAM CIPHER FOR SECURED GLOBAL SYSTEM FOR MOBILE (GSM) COMMUNICATION Siti Yohana Akmal Mohd Fauzi, Marinah Othman, Farrah Masyitah Mohd Shuib and Kamaruzzaman Seman pp. 154 - 159


Paper ID: A058 FIRE DETECTION ALGORITHM USING IMAGE PROCESSING TECHNIQUES Kumarguru Poobalan and Siau-Chuin Liew pp. 160 - 168 Paper ID: A059 AN EFFICIENT METHOD TO PREDICT DENGUE OUTBREAKS IN KUALA LUMPUR Duc Nghia Pham, Tarique Aziz, Ali Kohan, Syahrul Nellis, Juraina Abd. Jamil, Jing Jing Khoo, Dickson Lukose, Sazaly Abu Bakar and Abdul Sattar pp. 169 - 178 Paper ID: A065 THE POSSIBILITY OF STUDENTS’ COMMENTS AUTOMATIC INTERPRET USING LEXICON BASED SENTIMENT ANALYSIS TO TEACHER EVALUATION Phuripoj Kaewyong, Anupong Sukprasert, Naomie Salim and Fatin Aliah Phang pp. 179 - 188 Paper ID: A067 UTILIZING PAST EXPERIENCES OF INCIDENT HANDLERS FOR REALIZING A CBR RECOMMENDER IN IT SECURITY INCIDENT RESPONSE Wira Zanoramy A. Zakaria, Kilausuria Abdullah and Faiszatulnasro Mohd Maksom pp. 189 - 194 Paper ID: A068 ADVANCED THRESHOLD SENSITIVE STABLE ELECTION PROTOCOL FOR CLUSTERED HETROGENEOUS WIRELESS SENSOR NETWORKS: ATSEP Priyanka Sharma and Inderjeet Kaur pp. 195 - 201 Paper ID: A070 TSADA-MOBIMINDER: (A LOCATION BASED ALARM MOBILE REMINDER) Marylene S. Eder, Bhombie Ompoc, Arvin Nunez, Jonas Japjap and Krissa Mae Ebdalin pp. 202 - 208 Paper ID: A071 SENTIMENT ANALYSIS OF GOVERNMENT SOCIAL MEDIA TOWARDS AN AUTOMATED CONTENT ANALYSIS USING SEMANTIC ROLE LABELING Siti Salwa Hasbullah and Rita Zaharah Wan-Chik pp. 209 – 218 Paper ID: A072 CROWDALERT: AN ANDROID APPLICATION FOR INCREASING THE AWARENESS AND RESPONSE INITIATIVES OF THE CITIZENS THROUGH CROWDSOURCING John Benedict L. Bernardo*, Kathlyn M. Huavas, GremeirMitz O. Ociones, Ricky A. Pantuan and Jessa Mae P. Vasallo pp. 219 – 228


Paper ID: A073 MYABISO: A MOBILE APPLICATION FOR STUDENT ORGANIZATION EVENT MANAGEMENT AND INFORMATION DISSEMINATION Landicho, Junar A.*, Baculio , Ryan Dyl B. , Gabales , Rhyan Jay B. , Geñoso,Earl Hans P. , Martinez and Mark Lester B. pp. 229 - 240 Paper ID: A074 WEB - BASED INTERACTIVE CAMPUS MAP Marylene S. Eder, Catherine Jean L. Nocete, Gemelyn L. Rances, Ethyl M. Tarrosa and Jenilyn N. Yanson pp. 241 Paper ID: A075 FUSION OF MULTIPLE ECHOCARDIOGRAPHY SEQUENCES THROUGH A HYBRID METHOD Samaneh Mazaheri, Rahmita Wirza, Puteri Suhaiza Sulaiman, Mohd Zamrin Dimon, Fatimah Khalid and Rohollah Moosavi Tayebi pp. 242 – 251 Paper ID: A076 E-ATTENDANCE SYSTEM (EAS) USING BLUETOOTH Muhammad Faiz Mokhtar, Che Wan Shamsul Bahri C.W.Ahmad and Khirulnizam Abd Rahman pp. 252 – 260 Paper ID: A077 ONTOLOGY BASED FUZZY INFORMATION RETRIEVAL WITH AN EYE ON FUZZINESS Srabani Sarkar pp. 261 - 272


Paper ID: A012

ELICITING EXPERT KNOWLEDGE IN QUANTIFYING THE HUMAN BEHAVIOUR DURING AN EMERGENCY USING EBBN PROCEDURE

Nurulhuda Ramli, Noraida Abdul Ghani,

Intan Hashimah Mohd Hashim and Zulkarnain A. Hatta Universiti Sains Malaysia, 11800 Penang, Malaysia

[email protected]

ABSTRACT

Elicitation of expert knowledge is a structured approach to consult experts on uncertain subject and where there is insufficient knowledge. Expert elicitation is most often used in identifying, developing and quantifying the unknown parameters in a causal model. In modelling human behavior during an emergency one has to deal with uncertainties with often limited or incomplete knowledge database. This paper is an extension of an earlier work that identified factors affecting human behavior during an emergency. The factors, stressful conditions, individual’s ability in assessing a danger and information regarding the threats were captured in a graphical representation called the Bayesian Network (BN). This study focuses on the quantification phase of the model by conducting an expert elicitation exercise which aims to extract the expert’s knowledge on the inter-dependencies of the factors involved. The experience builds on the semi-structured interviews with the expert who participated in the analysis to give their beliefs by quantifying the relationship of variables using a probability scale. In order to cope with eliciting a large number of probability values from the experts, an elicitation using the Bayesian Belief Network (EBBN) procedure has been carried out. The EBBN requires only a limited amount of elicited probabilities from the experts and uses piecewise linear interpolation to determine the conditional probability of the target variables. The generated probabilities obtained are then used to make inference on the model by inserting and propagating the appropriate evidences throughout the network. Result of the analysis shows that an individual would make a decision to evacuate from a dangerous situation when there is a medium level of stressful conditions experienced, which is dependent on having enough information about the threats received and a high ability in assessing the danger. The finding suggests that formal expert elicitation can support human behavior research when there is limited available knowledge. This research generated many useful insights from the experts involved in the elicitation exercise. The feedback and recommendations for enhancing future procedures with multiple experts are highlighted based on the lessons learnt. Future work of the study should test the validity and sensitivity of the network. Keywords: Bayesian Network, EBBN, Evacuation, Expert Judgement, Human Behaviour.


Paper ID: A018

MINDMAP SHEET: SATU KAEDAH UNTUK MENINGKATKAN PENGUASAAN DAN KEMAHIRAN SUBJEK APLIKASI KOMPUTER MENGGUNAKAN TEKNIK

PETA MINDA DI KALANGAN PELAJAR BERMASALAH PEMBELAJARAN DI KOLEJ KOMUNITI BAYAN BARU

Noor Sarena Mohd Zahid, Rohani M.M Yusoff, Norhafizah Abdul Rahman,

Abda Hamida D Abdul Hameed Kolej Komuniti Bayan Baru

Kementerian Pengajian Tinggi Malaysia [email protected], [email protected],

[email protected], [email protected]

ABSTRAK

Peta minda merupakan salah satu teknik untuk meringkaskan nota pembelajaran kepada sesuatu yang lebih interaktif dalam memudahkan pemahaman pembelajaran. Objektif utama kajian ini ialah untuk meningkatkan kefahaman dan kemahiran pelajar dalam mengenalpasti jenis perkakasan, fungsi dan kegunaan asas setiap perkakasan komputer dengan betul. Fokus kajian adalah untuk meningkatkan penguasaan dan kemahiran asas perkakasan untuk subjek Aplikasi Komputer menggunakan konsep peta minda. Kumpulan sasaran kajian adalah pelajar bermasalah pembelajaran di Kolej Komuniti Bayan Baru yang melibatkan seramai 11 orang pelajar Sesi Nov 2013. Kajian dimulakan dengan tinjauan masalah oleh pensyarah kepada para pelajar sesi Julai 2013 dan melakukan ujian pemahaman (Pra). Kemudian pensyarah menjalankan sesi pengajaran dn pembelajaran menggunakan MindMap Sheet kepada pelajar dan menjalankan ujian pemahaman (Pasca). Hasil dapatan menunjukkan markah purata ujian (pasca) meningkat 10% berbanding markah purata Ujian (Pra). Kesimpulannya, kajian ini menunjukkan hasil peningkatan yang positif dalam meningkatkan penguasaan dan kemahiran subjek Aplikasi Komputer menggunakan konsep peta minda. Beberapa persoalan juga telah dijawab berdasarkan penerimaan hasil dapatan kajian ini.

Katakunci: Pelajar Bermasalah Pembelajaran, Peta Minda, Aplikasi Komputer, Perkakasan Komputer.






Paper ID: A021

PEDICTING PATIENT’S LENGTH OF STAY BY MINING HOSPITAL DATA

Saira Seemab1, and Dr.Usman Qamar 2

1National University of Sciences and Technology, Pakistan

[email protected]

2National University of Sciences and Technology, Pakistan [email protected]

ABSTRACT

Optimal management of health care resources has been one of the recognized areas of interest since the past few years. Emphasis is on providing competitive healthcare in pruned resources. Economical allocation of assets is desired as hospitals operate under rigid budgetary margins. The impetus for this research is essentially established on the reality that huge amounts of possibly valuable data about hospital management are saved in hospital databases. These data can potentially be scrutinized for making decisions like whether to perform further treatment of patient or drop them off. In our proposed topic, first we will explore whether patient drop off can actually be predicted. This is done by discovering temporal patterns in data, on the basis of which a model is proposed to minimize the uncertainty level regarding future patient drop off in hospitals. Several forecasting models will be applied on the dataset obtained from hospitals for prediction purpose and then will assess model’s performance with respect to its accuracy. This measure helps us in gauging our confidence for future forecast, thereby enhancing the planning and management of hospital resources. Keywords: : Patient’s length of stay (LOS), Health Heritage Prize (HHP), ensemble, predictive models, and unnecessary hospitalization.


Paper ID: A023

DYNAMIC REDEPLOYMENT MANAGEMENT FOR EMERGENCY MEDICAL SYSTEMS WITH TWO TYPES OF SERVERS

Huda Zaki Naji1 and Noraida Abdul Ghani2

School of Distance Education, University Sains Malaysia, 11800 Penang, Malaysia [email protected]

[email protected]

ABSTRACT

Emergencies have become a crucial part in our daily lives, principally in urban areas where incidents occur at a high rate due to high population density. As such, the design of emergency medical services systems (EMS) are an important issue in order to prevent premature death, to reduce pain and prevent disability. It is known that the demand for ambulances fluctuates spatially and temporally throughout the day of the week and the time of day. Therefore, EMS managers can improve system performance by using the redeployment strategies in response to fluctuating demand patterns. This shift of staff, although it provides coverage for the region with fluctuating demand, can cause fatigue among members of the ambulance crew. In this paper, we extend the Dynamic Redeployment Coverage Location (DRCL) model to minimize the number of redeployments for two types of services, i.e., the Advance Life Support (ALS) and Basic Life Support (BLS), that are operating through a certain shift. We propose a mathematical model that minimizes the number of redeployments for two types of services while meeting a predetermined level of coverage required. Keywords: Emergency medical system, Dynamic redeployment, Ambulance relocation, Coverage location problem.


Paper ID: A026

THE APPLICATION OF ENSEMBLE CLASSIFICATION TECHNIQUES IN SOIL CLASSIFICATION SYSTEM ON THE BASIS OF DMT AND CPT DATA

Jarosław Kurek1, Michał Kruk2, Piotr Bilski3, Oguz Akpolat4, Simon Rabarijoely5 and Grzegorz Wieczorek6

1Faculty of Applied Informatics and Mathematics, Warsaw University of Life Sciences – SGGW, ul. Nowoursynowska 159, 02-767, Warsaw, Poland

[email protected]

2Faculty of Applied Informatics and Mathematics, Warsaw University of Life Sciences – SGGW, ul.

Nowoursynowska 159, 02-767, Warsaw, Poland [email protected]



4Chemistry Department, Faculty of Science, Mugla University - Kotekli Campus, 48000 Mugla, Turkey

[email protected] 5Faculty of Engineering and Environmental Sciences, Warsaw University of Life Sciences – SGGW, ul.




ABSTRACT

The paper presents the application of some of novel ensemble classification techniques to classify data derived from soil probes. The ensemble learning methods can be applied as an effective classification technique for any common issue. In an ensemble classification system many base classifiers are merged to obtain a classifier with higher performance. The authors take up issue to apply common used and effective ensemble techniques to classification of soil data to one of the soil profile layers. So the goal is to propose some stable method classification based on which we can create soil profile in chosen place. Then we compare the soil profile created automatically from these in-situ tests. It will help geotechnical experts to create such soil profile automatically. Proposed ensemble classification methods will be compared to other applied methods such us SVM, KNN. The results of research will be discussed at the end of article.

Keywords: soil profiles, soil classification, ensemble techniques classification, SVM, KNN Paper ID: A027







AGENT BASED TWO BUFFER HIERARCHICAL SCHEDULING ALGORITHM FOR MULTICORE ARCHITECTURE

G.Muneeswari1 and E.M.Malathy2

1Associate Professor, SSN College of Engineering

[email protected]

2Assistant Professor, SSN College of Engineering [email protected]

ABSTRACT

In the current era, we have moved from multiprocessor system to multicore system. The main travel towards multicore system is the tremendous performance achievement over processor execution. Although there are many hardware challenges imposed on this architecture, the software design also brought into the attention of designing efficient operating system, building intelligent compiler etc., Though many processor scheduling algorithms are developed, keeping all the cores in the active state is a major challenge which conventional algorithms do not implement. In this paper we propose a new agent based two buffer hierarchical scheduling algorithm that enhances the performance of the processor by 20% compared with the traditional algorithms. There are two levels in the overall design wherein in the first level all the tasks are assigned with equal priority and a buffering method is implemented. Whereas in the second level, we consider the real time task and affinity based scheduling is incorporated. For the evaluation results modified linux 2.6.21 kernel along with the FLAME tool is used. Ultimately, the overall results proves that this agent based algorithm outperforms in cpu performance and reduces average waiting time of the process by 4.5% compared with the conventional scheduling algorithms.

Keywords: agent, buffer, hierarchical scheduling, multicore, affinity


Paper ID: A028

THREE METHODS OF ARTIFICIAL EVOLUTION FOR AUTOMATED & SEMI-AUTOMATED SYNTHESIS OF FREE-FORM 3D PRINTABLE AESTHETIC OBJECTS

Jason Teo, Ong Jia Hui, Halimah Manja and Lee Chin Kuan Faculty of Computing & Informatics

Kota Kinabalu Campus Universiti Malaysia Sabah

Jalan UMS, 88400 Kota Kinabalu, Sabah.

ABSTRACT

Designing a 3D object is a very laborious process that usually involves significant expertise and time investment through the use of various 3D computer-aided design software. Numerous researchers have proposed mathematical formulas to automatically design aesthetic shapes in 2D space and this has led to recent efforts being done on studies which use mathematical formulas to create objects in 3D space. In this paper, we report on the use of the Gielis Superformula to automatically generate 3D object shapes through an artificial evolutionary optimization process. Free-form 3D shapes are synthesized through three different methods: (1) a fully automated single-objective approach, (2) a fully automated multi-objective approach, and (3) an interactive, semi-automated multi-objective approach. Various novel fitness functions were designed to evaluate the shapes generated by the Superformula in order to discriminate between aesthetic versus non-aesthetic shapes. Post-evolution shapes were then fabricated using 3D printing for human evaluation. The results demonstrate that the proposed approaches are indeed feasible in terms automating part of or even the entire design process for synthesizing free-form 3D printable that are aesthetically pleasing.

Keywords: Evolutionary 3D Art, Evolutionary Optimization, Automatic 3D Shape Generation, Gielis Superformula, Computational Aesthetics.


Paper ID: A030

APPLICATION OF THE RULE-BASED SYSTEM FOR THE CLASSIFICATION OF SOIL LAYERS

Piotr Bilski1,2 and Simon Rabarijoely3

1Institute of Radioelectronics, Warsaw University of Technology ul. Nowowiejska 15/19, 00-665, Warsaw, Poland

[email protected]

2Department of Applied Informatics, Warsaw University of Life Sciences – SGGW ul. Nowoursynowska 159, 02-776, Warsaw, Poland

[email protected] 3Faculty of Engineering and Environmental Sciences, Warsaw University of Life Sciences – SGGW, ul.


ABSTRACT

The paper presents the application of the rules-based system to the classification of soil layers based on the information obtained from the in-situ testing using geotechnical probes. The idea of the automated soil identification is presented. The rules induction algorithm is presented in detail as the useful tool of the knowledge extraction from the available measurements taken at the particular locations. The application of the rules-based system to identify the soil categories in other locations based on extracted knowledge is described. Experimental results show the advantages and drawbacks of the proposed method. The paper is concluded with future prospects of the approach.

Keywords: Rules induction, Classification, In-Situ testing, geotechnical profile generation


Paper ID: A036

IMPROVED FUZZY-PI CONTROL SCHEME FOR POWER FLOW OF DISTRIBUTED GENERATION

Azuki Abdul Salam1, Nik Azran Ab Hadi2, Fatimah Zaharah Hamidon3 and Ismail Adam4

1Universiti Kuala Lumpur-British Malaysian Institute

[email protected]

2Universiti Teknikal Malaysia Melaka, [email protected]

3Universiti Kuala Lumpur-British Malaysian Institute

[email protected]

4Universiti Kuala Lumpur-British Malaysian Institute [email protected]

ABSTRACT

This paper presents the mathematical model of the Proton Exchange Membrane Fuel Cell (PEMFC) and analyzes the structure of a grid connected PEMFC generation system. In order to get better waveforms of grid current, a Fuzzy-PI controller is introduced into the grid connected PEMFC generation system. The current control scheme for grid connected PEMFC generation system is a PI controller scheme, which would lead to large transient response due to the load increases. Thus, a Fuzzy-PI control scheme is proposed in order to improve the power flow control. The PI controller parameters automatically, according to changes of system parameters. When the proposed grid connected PEMFC generation system using the Fuzzy-PI controller is simulated in Matlab/Simulink, the results show that the proposed control scheme works effectively for the power flow grid.

Keywords: PEMFC, Fuzzy-PI, Matlab/Simulink


Paper ID: A039

SYSTEM TO AUTOMATICALLY CALCULATE THE ACCURACY (SACA)

Muhammad Awis Jamaluddin Johari1, Amru Yusrin Amruddin2 and Dr. Chew Yew Choong3

Software Development Lab, ICT Department, MIMOS Berhad, Malaysia [email protected]

[email protected] [email protected]

ABSTRACT

Sentiment analysis is an analysis process which is related to the opinions, feedbacks, and emotions towards entities. There are many existing tools for sentiment analysis including commercial tools like Alchemy, Repustate, and Semantria, and open source tools such as Natural Language Toolkit, and PHPInsight. When one adopted the open source tool, he has to spend more time to manually calculate the accuracy of the sentiment analysis tools. Due to this scenario, this research states two objectives that are; (1) improving the performance and accuracy of PHPInsight by involving its database and algorithm and (2) proposed a tool called SACA to automatically analysis the sentiment and calculate the accuracy of the analysis. Sentiment analysis engine is a system to automatically analyze the user’s emotion of an article. PHPInsight is an open source tool and developed by applying Hypertext Preprocessor (PHP). PHPInsight is implemented with a simple algorithm that consists of three processes that are filtering, scoring, and classifying. Based on the experiment done, we found that PHPInsight is able analyze the sentiment quickly compared to other tools such as TextBlob, Natural Language Tool Kit (NLTK), and Repustate. The contribution of this research is we develop System to Automatically Calculate the Accuracy (SACA) in order to easily calculate, record, and compare the accuracy of the sentiment analysis engine. SACA is implemented by applying PHP language. This system consists of uploading page, displaying sentiment analysis result, calculating and displaying the accuracy of the sentiment analysis, and presenting the detail scoring of positive, negative, and neutral words for each article. In order to evaluate the effectiveness and efficiency of the proposed work, the research applies 100 news article resources which are written formally and clearly. There are 10 categories of the news article that are world, business, technology, entertainment, sports, science, health, lifestyle, travel, and politics. In creating a benchmark, three respondents are involved in manually analyzing the 100 of news article. During improvement of PHPInsight, SACA is very useful in calculating, comparing, and displaying the accuracy of the PHPInsight easily and efficiently.

Keywords: Sentiment Analysis, Accuracy System, System Automatically


Paper ID: A043

NEURAL NETWORK MODEL USING BACK PROPAGATION ALGORITHM FOR CREDIT RISK EVALUATION

Dionicio D. Gante1, Bobby D. Gerardo2 and Bartolome T. Tanguilig III3

1Technological Institute of the Philippines, Quezon City, Philippines [email protected]

2West Visayas State University, Iloilo City, Philippines

[email protected]

3Technological Institute of the Philippines, Quezon City, Philippines [email protected]

ABSTRACT

The utilization of neural network as a data mining technique which is used for classification, pattern recognition and time-series forecasting plays an important role in financial applications. Neural network attempt to build machine that will imitate brain activities and be able to learn through examples. A neural network supplied with enough examples can perform classification and even discover new trends and patterns that would be beneficial for humankind. This paper present the results of an experiment made with the aid of KangarooBPNN, a graphical user interface software that uses back propagation algorithm in order to find the Mean Squared Error (MSE) of a supervised neural network model. The German credit dataset was used for training and testing the twelve neural network models for credit risk evaluation. The results were recorded in a tabular form, compared and analyzed carefully to determine which among the twelve neural network models developed with different network parameters and stopping criteria is good for a credit risk evaluation system. Moreover, after the thorough examination of gathered results, it was found out that NN-1B model with 20 input neurons, 10 hidden neurons and 1 output neuron is a good neural network model to be used for credit risk evaluation system at 0.3 learning rate, 0.4 value of accuracy and at 10,000 epochs.

Keywords: Neural Network, Back Propagation Algorithm, Credit Risk Evaluation, Credit Scoring.


Paper ID: A048

GENDER CLASSIFICATION USING GLOBAL LEVEL FINGERPRINT FEATURE IN MALAYSIA

Siti Fairuz Abdullah,Ahmad Fadzli Nizam Abd Rahman, Zuraida Abal Abas

Faculty of Information and Communication Technology Universiti Teknikal Malaysia Melaka

Hang Tuah Jaya 76100 Durian Tunggal, Melaka

[email protected]; {fadzli, zuraidaa}@utem.edu.my

ABSTRACT

Biometric have been accepted and plays a very crucial role in identification, verification, and authenticity of a person. This biometrics actually refers to the metrics related to human characteristics and has been used in computer science to identify and verify the person for authentication purpose. Some examples of biometrics are DNA, fingerprints, eye retinas and irises, voice patterns, facial patterns, hand measurements and so on. In this paper, the fingerprints will be our focused and used to classify the gender of a person in Malaysia. Even though the studies of gender classification using the fingerprint have been studied before but in Malaysia this is the first ever study within our knowledge. The main objective of this study is to find the mean of ridges density of male and female in Malaysia and to find the best classifier among the existing techniques that can classify the gender more accurately.

Keywords: Fingerprint, Gender classification, ridge density.


Paper ID: A049

DISCRETE WAVELET PACKET TRANSFORM FOR ELECTROENCEPHALOGRAM-BASED EMOTION RECOGNITION IN THE VALENCE-AROUSAL SPACE

Farzana Kabir Ahmad*, Oyenuga Wasiu Olakunle

Computational Intelligence Research Cluster, School of Computing, College of Arts and Sciences

Universiti Utara Malaysia, 06010 UUM Sintok, Kedah, Malaysia *[email protected]

ABSTRACT

Human emotion recognition is the key step toward innovative human-computer interactions. The advanced in computational algorithms and techniques has recently offered the promising results in recognizing human emotion. Recently, Electroencephalogram (EEG) has been shown as an effective way in identifying human emotion since it records the brain activity of human and can hardly be deceived by voluntary control. However, due to the non-linearity, non-stationary, and chaotic nature of the EEG signals, it is difficult to be examined and has been an extensive research area in the present years. Moreover, the high dimensional of the feature vectors has make the analysis task more challenging. In this research, two emotion recognition experiments were performed in order to classify human emotional states into high/low valence or high/low arousal. The first experiment was aimed to evaluate the performance of Discrete Wavelet Packet Transform (DWPT) in extracting relevant features, while the second experiment was conducted to identify the combination of electrode channels that optimally recognize emotions based on the valence-arousal model. Additionally, in this study, a leave-one-out cross validation was performed using Radial Basis Function-Support Vector Machines (RBF-SVM) as the classifier on a publically available dataset. The experimental results have shown that an average accuracy of 68.83% with average F1-score of 0.666 for valence and average accuracy of 68.83% with F1-score of 0.633 for arousal were achieved for 32 subjects. Furthermore, four frontal channels which include Fp1, Fp2, F3, and, F4 were identified significant in providing relevant information compare to the remaining 6 channels namely T7, T8, P3, P4, O1, and O2 for EEG-based emotion recognition in the valence-arousal space.

Keywords: Discrete Wavelet Packet Transform; Electroencephalogram; emotion recognition; valence-arousal model.


Paper ID: A053

MAPREDUCE BASED PARTICLE SWARM OPTIMIZATION FOR LARGE SCALE PROBLEMS

Saeed Mehrjoo1 and Saman Dehghanian2

1 Department of Computer Engineering, College of Engineering, Dariun Branch, Islamic Azad University, Dariun, Iran

[email protected]

2Department of Computer engineering, Payame Noor University, Iran [email protected]

ABSTRACT

Recently, the MapReduce data parallel programming model has become very powerful and widespread system. Solving complex and difficult optimization problems are very challenging. PSO has been used increasingly as an effective technique for solving such problems, over the previous few years. Although PSO has many advantages, it has a considerable drawback; long time to find solutions for large scale problems. In this paper, we present a novel method to run PSO on MapReduce in parallel. With a good optimization performance, MapReduce based PSO can enlarge the swarm population and problem dimension sizes, speed up its running greatly and provide users with a feasible solution for complex optimizing problems in reasonable time.

Keywords: MapReduce, Particle Swarm Optimization, speedup.



Paper ID: A054

PROPOSED CONCEPTUAL FRAMEWORK OF DENGUE ACTIVE SURVEILLANCE SYSTEM IN MALAYSIA

Mohd Khalit Othman1 and Mohd Shahrul Nizam Mohd Danuri2

Department of Information Systems, Faculty of Computer Science and Information Technology University of Malaya, 50603 Lembah Pantai, Kuala Lumpur, MALAYSIA

[email protected], [email protected]

ABSTRACT

This paper introduces Dengue Active Surveillance System (DASS) framework for an early warning system of the outbreak. Dengue and dengue hemorrhagic fever are emerging as major public health problems in most Asian countries such as Malaysia. Effective prevention and control programs will depend on improved surveillance. A new approach to active surveillance is outlined with emphasis on the inter-epidemic period. The objective is to develop an early warning surveillance system (framework) than can predict epidemic dengue to improve current passive surveillance system available in Malaysia. Basically, the framework introduced data harvesting process from multiple sources as input, data pre-processing using data aggregator and filtering engine, storing large data in repository, analytic engine for analysis and processing the large data, and presentation of the information to the users. The data harvested from 3 major sources such weather or flood information, build development information and social media or search engine trend information. The data aggregator will aggregate the data to 3 different type of data such structured, semi-structured and unstructured data. The data parse to the filtering engine for filtering and cleaning the data sources using suitable keywords prior to store it in the large data repository. After that, the large data will be processed and analyzed using algorithm or mathematical calculation to determine the expected dengue cases. Then, the processed information will be presented to the users in a form of web or mobile application and other method such short message service (SMS). Finally, the system will be evaluated based on the comparison study with the traditional passive system.

Keywords: Dengue Active Surveillance System, System Requirement, Dengue Data, Big Data, Machine Learning.


Paper ID: A055

A FRAMEWORK FOR SEMANTIC-BASED ANOMALY DETECTION IN TEXT

Mohammed Ahmed Taiye1, Siti Sakira Kamaruddin2 and Farzana Kabir Ahmad 3

123School of Computing Universiti Utara Malaysia [email protected], {sakira, farzana58}@uum.edu.my23

ABSTRACT

Anomaly detection is a vital task in text mining. It has a diverse application in domains like Law, Digital Library, Print media and Journal articles. More so, anomalous text information is detected from documents to communicate useful patterns of text data. These text data can be translated into core ideas by revealing its meaning to disturbing events like the misuse of information overload in unstructured text documents, bank fraud detection and socio-political threats to national security. However, detecting core ideas in an unstructured anomalous text data requires more effort and often leads to enormous amount of inconsistency. Moreover, retrieving semantics in text document may yield important knowledge for optimized decision making and enhanced business excellence. A conceptual framework of mining anomalous text data in corpus is introduced in this article. The proposed framework includes text pre-processing and text representation of documents into a normalized canonical text format. Canonical form is a notion stating that related idea should have the same meaning representation. This representation enables the similar meanings of different words to be captured in a single semantic representation through word senses and synonyms to simplify the reasoning task. The framework also employs sequential exception technique to identify anomalous text data from the represented canonical form. This technique belongs to the deviation-based anomaly detection method where it do not depend on statistical analysis or distance measurement to detect anomalous data instead it sequentially identifies anomaly by analysing the primary features of the data in a set. The main idea behind this technique is to investigate the implicit redundancy of data. This method is favourable compared to statistical and distance-based method due to its linear complexity. In our framework, we propose to include all functions of the sequential exception technique namely; dissimilarity function, smoothing factor and cardinality function. The components presented in this framework will be leveraged to improve the efficiency of detecting semantics from different corpora to accuratly identify anomalous text data with consistent and meaningful level of information.

Keywords: Text anomaly, Sequential exception technique, corpus, semantic representation, canonical form



Paper ID: A057

MODIFIED A5/1 STREAM CIPHER FOR SECURED GLOBAL SYSTEM FOR MOBILE (GSM) COMMUNICATION

Siti Yohana Akmal Mohd Fauzi, Marinah Othman, Farrah Masyitah Mohd Shuib and Kamaruzzaman Seman

Faculty of Science & Technology University Sains Islam Malaysia (USIM)

Bandar Baru Nilai, 71800 Nilai Negeri Sembilan

Malaysia [email protected]

ABSTRACT

A5/1 is well-known as the encryption standard for Global System for Mobile (GSM) communication, one of the most largely used cellular system in the world. Despite its wide usage however, it has numerous security vulnerabilities that leaves it susceptible to attacks. In this paper, a modified A5/1 is described. The proposed design looks at the effect of modifying the combinational function to enhance its random features, thus making it more secure overall. The modified algorithm which was simulated using C++, has been found to give the desired results when its randomness was tested using the NIST (National Institute of Standard and Technology) test suite, following which, further analysis was done by varying its parameters, and the results are then compared against other published work.

Keywords: A5/1 stream cipher, NIST test suite, LFSR, GSM communication, information security.


Paper ID: A058

FIRE DETECTION ALGORITHM USING IMAGE PROCESSING TECHNIQUES

Kumarguru Poobalan1 and Siau-Chuin Liew2

Faculty of Computer Science and Software Engineering, University Malaysia Pahang, Lebuhraya Tun Razak, 26300 Gambang, Pahang, Malaysia


ABSTRACT

Lately fire outbreak is common issue happening in Malays and the damage caused by these type of incidents is tremendous toward nature and human interest. Due to this the need for application for fire detection has increases in recent years. In this paper we proposed a fire detection algorithm based on image processing techniques which is compatible in surveillance devices like CCTV, wireless camera to UAVs. The algorithm uses RGB colour model to detect the colour of the fire which is mainly comprehended by the intensity of the component R which is red colour. The growth of fire is detected using sobel edge detection. Finally a colour based segmentation technique was applied based on the results from the first technique and second technique to identify the region of interest (ROI) of the fire. After analysing 50 different fire scenarios images, the final accuracy obtained from testing the algorithm was 93.61% and the efficiency was 80.64%.

Keywords: Fire Detection, Image Processing, Signal Processing.


Paper ID: A059

AN EFFICIENT METHOD TO PREDICT DENGUE OUTBREAKS IN KUALA LUMPUR

Duc Nghia Pham1, Tarique Aziz1, Ali Kohan1, Syahrul Nellis2, Juraina binti Abd. Jamil2, Jing Jing Khoo2, Dickson Lukose1, Sazaly bin Abu Bakar2 and Abdul Sattar3

1 MIMOS Berhad, Malaysia 2 TIDREC, University of Malaya, Malaysia

3 IIIS, Griffith University, Australia

ABSTRACT

In recent years, there has been a surge in dengue outbreaks in Malaysia. A dengue outbreak can cause severe damages to the society. Hence, it is critical to be able to predict a dengue outbreak in advance to minimize the damage and loss. In this paper, we propose a new machine learning approach to predict the number of dengue cases in Kuala Lumpur, in particular the areas surrounding the University of Malaya (UM) Medical Centre. We identified several different factors that can contribute to a surge in the number of dengue cases that occurred near the UM Medical Centre. Apart from the daily mean temperature and daily rainfall factors that have been frequently used in other studies, we also considered the enhanced vegetation index (EVI) as an input factor to our prediction engine. We trained our linear regression model on these three factors against the number of dengue cases from 2001 to 2010. We then tested our model on the 2011 data. The experimental results showed that our approach was able to predict the number of dengue cases 16 days in advance with high accuracy.

Keywords: Dengue Outbreak Prediction, Linear Regression Model.


Paper ID: A065

THE POSSIBILITY OF STUDENTS’ COMMENTS AUTOMATIC INTERPRET USING LEXICON BASED SENTIMENT ANALYSIS TO TEACHER EVALUATION

Phuripoj Kaewyong1, Anupong Sukprasert2, Naomie Salim3 and Fatin Aliah Phang4

1Information Technology Department, Suan Dusit University, Thailand.

[email protected]

2Mahasarakham Business School, Mahasarakham University, Thailand. [email protected]

3 Faculty of Computing, Universiti Teknologi Malaysia, Malaysia.

[email protected]

4 Faculty of Education, Universiti Teknologi Malaysia, Malaysia. [email protected]

ABSTRACT

This paper aims to investigate the possibility of the qualitative analysis of students' freestyle text comments using lexicon based sentiment analysis to predict teacher performance. The students’ feedbacks from RateMyProfessors.com were collected for the experimental. We employ a qualitative measuring using lexicon based sentiment analysis to automatic interpret sentiment word and determine the overall polarity of one document in students' comment into positive and negative classes. A comparison between sentiment score and numerical response ratings of teacher evaluation aspects were analyzed and plotted into graphs in order to compare the relationship between each pair of two variables. Particularly, we investigate and elaborate these visual correlation results through the statistical techniques using Pearson’s correlation and Spearman’s rank. The initial results of the qualitative measuring using sentiment analysis are relative to enhance teacher performance evaluation using quantitative measuring. In order to gain additional insight into more teacher evaluation aspects from students' comments, aspect based sentiment analysis using a large scale dataset is recommended.

Keywords: Sentiment Analysis, Teacher Evaluation, Students’ comment, Correlation Analysis.


Paper ID: A067

UTILIZING PAST EXPERIENCES OF INCIDENT HANDLERS FOR REALIZING A CBR RECOMMENDER IN IT SECURITY INCIDENT RESPONSE

Wira Zanoramy A. Zakaria, Kilausuria Abdullah and Faiszatulnasro Mohd Maksom MyCERT, Cybersecurity Malaysia, Level 7, SAPURA@MINES

Jalan Tasik, The Mines Resort City 43300 Seri Kembangan, Selangor, Malaysia

{wira, suria, fais}@cybersecurity.my

ABSTRACT

Incident response is a very important subject in IT security. Due to significant rise in the number of total reported incidents, there is a need for an intelligent based recommender system to assist the Incident Handlers (IH) in responding to cyber threats. This work explores the application of the Case-based Reasoning (CBR) methodology in order to develop a CBR recommender system for assisting IH in handling and responding to cyber security incidents. The architecture of the proposed system and the work done on case representation describing some sample cyber incident category are discussed in this paper.

Keywords: CBR system, recommender system, case representation, incident response


Paper ID: A068

ADVANCED THRESHOLD SENSITIVE STABLE ELECTION PROTOCOL FOR CLUSTERED HETROGENEOUS WIRELESS SENSOR NETWORKS: ATSEP

Priyanka Sharma

Department of Computer Science Ajay Kumar Garg Engineering College

Ghaziabad, India [email protected]

Inderjeet Kaur

Department of Computer Science Ajay Kumar Garg Engineering College

Ghaziabad, India [email protected]

ABSTRACT

In this paper we proposed a new heterogeneous reactive routing protocol Advanced Threshold Sensitive Stable Election Protocol (ATSEP) which is based on the clustering approach, by making the effective use of ESEP and TEEN protocol. The major benefit of using clustering approach is that Clustering technique minimizes the use of energy and increase the life of network. We increase the heterogeneity of nodes up to level four naming the nodes as normal, advanced, super and super advanced. We perform the simulation of this protocol in MATLAB. Simulation results clearly show that ATSEP protocol perform better than ESEP protocol.

Keywords—clustering; heterogeneity; routing protocols; SEP; ESEP; TEEN; WSN; efficiency



Paper ID: A070

LOCATION BASED ALARM MOBILE REMINDER)

*Marylene S. Eder, Bhombie Ompoc, Arvin Nunez, Jonas Japjap, Krissa Mae Ebdalin

Information Technology Department Mindanao University of Science and Technology

Lapasan Cagayan de Oro City, Philippines *[email protected]

ABSTRACT

Existing location based alarm applications has inability to give information to user’s particular direction to a specified place of destination and doesn’t display a particular scenic spot from its current location going to the destination. With this problem, a location based alarm mobile reminder was developed. The application is implemented on Android based smart phones to provide services like providing routing information, helping find nearby hotels, restaurants and scenic spots and offer many advantages to the mobile users to retrieve the information about their current location and process that data to get more useful information near to their location. It reminds the user about the location when the user enters some predefined location. All the user needs to have is the mobile phone with android platform with version 4.0 and above, and then the user can select the destination and find the destination on the application. The main objective of the project is to develop a location based application that provides tourists with real time information for scenic spots and provides alarm to a specified place of destination. This mobile application service will act as assistance for the frequent travelers to visit new places around the City.

Keywords: Location based alarm, mobile application, mobile reminder, tourist’s spots


Paper ID: A071

SENTIMENT ANALYSIS OF GOVERNMENT SOCIAL MEDIA TOWARDS AN AUTOMATED CONTENT ANALYSIS USING SEMANTIC ROLE LABELING

Siti Salwa Hasbullah1 and Rita Zaharah Wan-Chik2

1Malaysian Institute of Information Technology, Universiti of Kuala Lumpur (UniKL) [email protected]

2Centre for Research and Innovation, Universiti of Kuala Lumpur (UniKL)

[email protected]

ABSTRACT

In this paper, we propose to develop an automated content analysis tool to help the Malaysian government’s cyber and legal advisors, as well as the government leaders, to understand public sentiment via their comments which are posted on the official government leaders' or ministerial social media sites (i.e., Twitter, Facebook, etc.). In this study, we explore and apply the Semantic Role Labeling (SRL) techniques that generate new methods to filter and classify the social media content data set, advancing the state of the art in sentiment detection approaches. This proposed automated content analysis tool would be able to provide a platform to measure the impact of public sentiment over the government leader’s postings, and the public’s comments, on their officials’ social media sites. The results and findings from the impact measurement could then be used as a recommendation in the developing or reviewing the national’s cyber communication policy.

Keywords: Sentiment Analysis, Natural Language Processing, Semantic Role Labeling, Social Media, Automated Content Analysis


Paper ID: A072

CROWDALERT: AN ANDROID APPLICATION FOR INCREASING THE AWARENESS AND RESPONSE INITIATIVES OF THE CITIZENS THROUGH

CROWDSOURCING

John Benedict L. Bernardo*, Kathlyn M. Huavas, GremeirMitz O. Ociones, Ricky A. Pantuan and Jessa Mae P. Vasallo

Department of Information Technology Mindanao University of Science and Technology

C.M. Recto Ave. 9000 Cagayan de Oro City, Philippines [email protected]

ABSTRACT

Crowdsourcing is a way of collecting information provided by the volunteers. This crowd sourced information has the capacity to increase the people’s situational awareness in times of disasters. The research reflected in this paper strives to demonstrate the benefits of crowdsourcing during natural disasters and the ways of utilizing it for disaster response. Shared information regarding natural disasters from social media is often scattered as the inputs from these media are uncategorized. For this reason, the study aims to equip the citizens a medium that is solely intended for sharing and/or obtaining natural disaster-related information. Ergo, an android application was developed to gather and publicize these volunteered information. The capability of crowdsourcing and the effectiveness of the application were evaluated and the result shows overwhelming agreement that this study is indeed efficient in increasing the awareness and response initiatives of the citizens during natural disasters.

Keywords: Crowdsourcing, Natural Disasters, Mobile Application, Social Media, Awareness


Paper ID: A073

MYABISO: A MOBILE APPLICATION FOR STUDENT ORGANIZATION EVENT MANAGEMENT AND INFORMATION DISSEMINATION

Landicho, Junar A.*, Baculio , Ryan Dyl B. , Gabales , Rhyan Jay B. ,

Geñoso,Earl Hans P. , Martinez , Mark Lester B.

Department of Information Technology College of Industrial and Information Technology Mindanao University of Science and Technology

Cagayan de Oro City, 9000 Philippines *[email protected]

ABSTRACT

Mobile-based Student Notification System is an android type mobile notifying application designed and developed for the thorough dissemination of events to students for the awareness of the compulsory/non-compulsory events and event information which this application sole purpose is to provide more user-centric information services to students. With the use of AngularJS and MongoDB as an Online Database, it has been taken advantage to create custom command functionalities. Accessing, notifying and creating events are among the primary and fundamental features that this study has to offer. The researchers analyzed the results of the test survey and evaluation form and proved that the application is a user friendly, efficient and accurate enough in disseminating events or request of an upcoming event to advisers and has the important features for the students’ necessity of upcoming event information.

Keywords: user-centric, AngularJS, MongoDB, student organization, information dissemination


Paper ID: A074

WEB - BASED INTERACTIVE CAMPUS MAP

Marylene S. Eder, Catherine Jean L. Nocete, Gemelyn L. Rances, Ethyl M. Tarrosa and Jenilyn N. Yanson

College of Industrial and Information Technology Mindanao University of Science and Technology

CM Recto Ave. Lapasan, Cagayan de Oro City, 9000 Philippines

*[email protected]

ABSTRACT

Interactive maps can be a great way of displaying useful information in an engaging and attractive

way by inviting the user to take action. With huge developments in GEO tagging over the last decade,

the advent of Google Maps APIs and the introduction of Fusion tables, more and more websites are

taking advantage of these comprehensive tools to showcase their data. Interactive Web-based

Campus Information System is intended in providing a Campus Information System. Data of various

natures were compiled together and made possible to examine graphical and non-graphical data in a

broad manner. A 3D application was practiced on the Campus Information System and exported to

the Internet environment additionally with rendering many buildings successfully. It is open to

constant updates, user-friendly for both trained and untrained users, and capable of responding to all

needs of users and carrying out analyses. Based on the data gathered through questionnaires,

researchers analyzed the results of the test survey and proved that the system is user friendly, deliver

information to users, and the important features that the students expect.

Keywords: interactive campus map, faculty location, building, web – based,

mailto:*[email protected]


Paper ID: A075

FUSION OF MULTIPLE ECHOCARDIOGRAPHY SEQUENCES THROUGH A HYBRID METHOD

Samaneh Mazaheri1, Rahmita Wirza1, Puteri Suhaiza Sulaiman1, Mohd Zamrin Dimon2, Fatimah Khalid1, Rohollah Moosavi Tayebi1

1Faculty of Computer Science and Information Technology, University Putra Malaysia, Malaysia 2 Cardiothoracic Unit, Surgical Cluster, Faculty of Medicine, UiTM, Malaysia

ABSTRACT

Medical image fusion is the procedure of combining several images from one or multiple imaging modalities. It can employ to enhance the image quality and decrease redundancy and randomness. It leads to increase the clinical application of medical images for assessment of diagnosis and medical problems. This paper presents a compounding method which intends expanding the field of view, enhancing the signal to noise ratio, improving contrast of the echo images and also decrease the impact of noise and artifacts. For validation, a comparison has been done between results of some well-known techniques and the proposed method via numerical evaluation and it has been concluded that the proposed method has the best result for cardiac ultrasounds images compounding.

Keywords: Fusion, Discrete Wavelet Transform, Principal Component Analysis, Echocardiography Sequences.


Paper ID: A076

E-ATTENDANCE SYSTEM (EAS) USING BLUETOOTH

Muhammad Faiz Mokhtar1, Che Wan Shamsul Bahri C.W.Ahmad2 and

Khirulnizam Abd Rahman3

Faculty of Information Science and Technology,

Kolej Universiti Islam Antarabangsa Selangor, MALAYSIA [email protected]


ABSTRACT

Nowadays, several office, company, or organization, whether governmental or non-governmental

organizations are still using manual or traditional methods to record the attendance of their staff.

More than that, they used a punch card machine. In line with technological developments, it can be

said almost all workers have at least one smartphone. Therefore, we develop our projects, E-

Attendance System (EAS) to utilize the existing technology by using smartphone that capable to

record the attendance of staff using their smartphone device with Bluetooth feature. Raspberry Pi

equipment is also used in this project.

Keywords : Attendance system, Bluetooth, Raspberry Pi




Paper ID: A077

ONTOLOGY BASED FUZZY INFORMATION RETRIEVAL WITH AN EYE ON FUZZINESS

Srabani Sarkar

Department of Mathematics, Vivekananda College for Women Kolkata 700008, India

[email protected]

ABSTRACT

Retrieval of relevant document from a huge set of data is a crucial task particularly in an age when world-wide-web literally crisscrosses the world. The task becomes all the more difficult if the process involves recovery of fuzzy data. Then, not only does the text comparison between query and document become sufficient, but at the same time concept matching also assume importance.

In our previous paper, we worked out a data extracting system to handle queries and documents involving fuzzy concepts along with crisp concepts. There we gave emphasis on lowering effect of fuzziness upon relevance between query and document while fuzzy keywords are matched. Throughout our research, we considered an ontology created by using fuzzy linguistic terms as a variable called fuzzy-valued variable. A layered approach has been adopted and emphasis is given on modularity. We take the concerned linguistic variable to sit at the root of a tree with the semantically similar terms situated at the end of the branches of the tree and through the process the meaning of the term is reflected.

The present paper can be considered as an extension of our previous paper. Here we modify our data extracting system to cope up with the fuzziness that creeps in at the time of computing relevance between query and document with the help of method described by us in another previous paper. The modified method is elaborated with an example.

Keywords: Fuzzy set, Fuzzy-valued variable, Data retrieval, Ontology, NLP.



NEXT CONFERENCES

1ST INHAD INTERNATIONAL MUZAKARAH & MU'TAMAR ON HADITH 2015 (IMAM2015)

Conference Dates: 21st & 22nd December 2015 Venue: Melia Hotel, Kuala Lumpur, Malaysia

4TH GLOBAL SUMMIT ON EDUCATION (GSE 2016) Conference Dates: 14-15 March 2016

Venue: Kuala Lumpur, Malaysia

3RD INTERNATIONAL CONFERENCE ON ARABIC AND ISLAMIC STUDIES 2016 (ICASIC 2015)

Conference Dates: 14 -15 March 2016 Venue: Kuala Lumpur, Malaysia

abstract book - worldconferences.networldconferences.net/proceedings/aics2015/abstrac… · ·...

Documents