Wednesday, November 30, 2022

Journal of Information and Communication Technology (JICT) Vol.18, No.4, October 2019

Priya Chaliyath Venugopal & Kamalan Saroja Angel Viji
Nurul Atikah Mohd Sharif, Norazura Ahmad, Nazihah Ahmad, Wan Laailatul Hanim Mat Desa, Khaled Mohamed Helmy,  Wei Chern Ang & Ida Zaliza Zainol Abidin
Idheba Mohamad Ali Omer Swes & Azuraliza Abu Bakar
Zamira Hasanah Zamzuri, Akmalia Shabadin & Siti Zaharah Ishak
Badamasi Imam Ya’u, Norsaremah Salleh, Azlin Nordin, Ali Amer Alwan, Norbik Bashah Idris & Hafiza Abas
Nursuriati Jamil, Izzad Ramli & Norizah Ardi

1Priya Chaliyath Venugopal & 2Kamalan Saroja Angel Viji
1Department of Computer Science & Engineering, Noorul Islam Centre for Higher Education, India
2Department of Computer Science & Engineering, College of Engineering, India;
Through the application of a password-based authentication technique, users are granted permission to access a secure system when the username and password matches with that logged in database of the system. Furthermore, anyone who provides the correct username and password of a valid user will be able to log in to the secure network. In current circumstances, impostors can hack the system to obtain a user’s password, while it has also been easy to find out a person’s private password. Thus, the existing structure is exceptionally flawed. One way to strengthen the password-based authentication technique, is by keystroke dynamics. In the proposed keystroke dynamics based authentication system, despite the password match, the similarity between the typing pattern of the typed password and password samples in the training database are verified. The timing features of the user’s keystroke dynamics are collected to calculate the threshold values. In this paper, a novel algorithm is proposed to authenticate the legal users based on the empirical threshold values. The first step involves the extraction of timing features from the typed password samples. The password training database for each user is constructed using the extracted features. Moreover, the empirical threshold limits are calculated from the timing features in the database. The second step involves user authentication by applying these threshold values. The experimental analyses are carried out in MATLAB simulation, and the results indicate a significant reduction in false rejection rate and false acceptance rate. The proposed methodology yields very low equal error rate of 0.5% and the authentication accuracy of 99.5%, which are considered suitable and efficient for real-time implementation. The proposed method can be a useful resource for identifying illegal invasion and is valuable in securing the system as a correlative or substitute form of client validation.

Keywords: Authentication, computer security, empirical threshold, feature extraction, keystroke dynamics.

btn fulltext

1Nurul Atikah Mohd Sharif, 1Norazura Ahmad, 1Nazihah Ahmad, 1Wan Laailatul Hanim Mat Desa, 2Khaled Mohamed Helmy, 3Wei Chern Ang & 4Ida Zaliza Zainol Abidin
1School of Quantitative Sciences, Universiti Utara Malaysia, Malaysia.
2Faculty of Medicine, AIMST University, Malaysia.
3Clinical Research Centre, Hospital Tuanku Fauziah, Malaysia.
4Emergency and Trauma Department, Hospital Tuanku Fauziah, Malaysia.;;;;;;
The emergency department (ED) of a hospital is an important unit that deals with time-sensitive and life-threatening medical cases. Rapid treatment and accuracy in diagnosis are considered the main characteristics of excellent operational processes in ED. However, in reality, long waiting time and uncertainty in the diagnosis has affected the quality of ED services. Nonetheless, these problems can be improved by utilising computing technologies that assist medical professionals to make fast and accurate decisions. This paper investigates the issues of under-treatment and uncertainty condition of acute asthma cases in ED. A novel approach, known as the fuzzy logic principle is employed to determine the severity of acute asthma. The fuzzy set theory, known as Fuzzy Rule-based Expert System for Asthma Severity (FRESAS) determination is embedded into the expert system (ES) to assess the severity of asthma among patients in ED. The proposed fuzzy methodology effectively manages the fuzziness of the patient’s information data, and determines the subjective judgment of medical practitioners’ level on eight criteria assessed in severity determination. Knowledge acquisition and representation, fuzzification, fuzzy inference engine, and defuzzification are the processes tested by the FRESAS development that incorporates expert advice. The system evaluation is performed by using datasets that were extracted from the ED clerking notes from one of the hospitals in Northern Peninsular Malaysia. System evaluation demonstrates that the proposed system performs efficiently in determining the severity of acute asthma. Furthermore, the proposed system offers opportunities for further research on other types of diseases in ED, and improves other hybridisation approaches.

Keywords: Emergency department, acute asthma, fuzzy rule-based.

btn fulltext

 1Idheba Mohamad Ali Omer Swesi & 2Azuraliza Abu Bakar 
1Faculty of Accounting, University of Al-Jabar Al-Gharbi, Libya
2Faculty of Information Science and Technology, University Kebangsaan Malaysia, Malaysia;
Feature construction (FC) refers to a process that uses the original features to construct new features with better discrimination ability. Particle Swarm Optimisation (PSO) is an effective search technique that has been successfully utilised in FC. However, the application of PSO for feature construction using high dimensional data has been a challenge due to its large search space and high computational cost. Moreover, unnecessary features that were irrelevant, redundant and contained noise were constructed when PSO was applied to the whole feature. Therefore, the main purpose of this paper is to select the most informative features and construct new features from the selected features for a better classification performance. The feature clustering methods were used to aggregate similar features into clusters, whereby the dimensionality of the data was lowered by choosing representative features from every cluster to form the final feature subset. The clustering of each features are proven to be accurate in feature selection (FS), however, only one study investigated its application in FC for classification. The study identified some limitations, such as the implementation of only two binary classes and the decreasing accuracy of the data. This paper proposes a cluster based PSO feature construction approach called ClusPSOFC. The Redundancy-Based Feature Clustering (RFC) algorithm was applied to choose the most informative  features from the original data, while PSO was used to construct new features from those selected by RFC. Experimental results were obtained by using six UCI data sets and six high-dimensional data to demonstrate the efficiency of the proposed method when compared to the original full features, other PSO based FC methods, and standard genetic programming based feature construction (GPFC). Hence, the ClusPSOFC method is effective for feature construction in the classification of high dimensional data.

Keywords: Particle swarm optimisation, feature construction, genetic programming, classification, high- dimensional data

 btn fulltext

1Zamira Hasanah Zamzuri, 2Akmalia Shabadin & 2Siti Zaharah Ishak 
1Faculty of Science and Technology, Universiti Kebangsaan Malaysia, Malaysia.
2Malaysia Institute of Road Safety Research, Selangor, Malaysia.;;
Exploring the cause and effect of hazardous events such as traffic accident is vital to the society. Statistical analyses have been a great help in terms of understanding and making inference on the cause-effect analysis and also predicting the occurrence of the accident in the future. One of the issues that could not be handled by the conventional way of statistical modelling is the interrelationships exist between the variables in the data set. With the advent of technology and the wide application of machine learning algorithm, this goal can be achieved through the Bayesian network analysis, in which it is a directed acyclic probabilistic graphical model. By using Hill Climb (HC) and Tabu algorithms, the structure of the data was learnt and their relationship is estimated through the conditional probability based on the Bayes’ theorem. We found that that weather does impact on the accident occurred through the lighting condition and the traffic system. It is also learnt that fatality accidents have a higher likelihood to occur in head-on, turn over and out of control accidents. The use of Bayesian network allows for the probability queries which is very important estimates needed as we want to know what is the risk that we face given the information that we have in hand.

 KeywordsBayesian network, HC algorithm, Tabu algorithm, traffic accidents.

btn fulltext

 Badamasi Imam Ya’u, Norsaremah Salleh, Azlin Nordin, Ali Amer Alwan, Norbik Bashah Idris & Hafiza Abas
Department of Computer Science, International Islamic Univesity, Malaysia.,;;;;
Mobile applications and devices have played a significant role in boosting global businesses that encompass various domains such as health, education, banking, and transportation. These tools have become indispensable for everyday activities, and its applications have been developing rapidly with diverse features and platforms. However, this has created new problems and security challenges. To ensure the quality and security of these applications, a rigorous and systematic testing using cloud-based environment is required. By employing systematic mapping study (SMS) method, this paper will examine the empirical studies that address the issues on cloud-based mobile application testing. This paper presents a total of 23 primary studies that investigate cloud based mobile application testing and the effect of Testing as a Service (TaaS). The majority of these studies (56.5%) contribute to literature with a number of framework proposals. A large proportion of the studies (60.9%) analyzed Android applications, and usually supported a single type of mobile app testing. Other than that, the majority of the studies (52.2%) have failed to investigate the outcomes of TaaS, despite a plethora of services that offers TaaS. The SMS method conducted in this paper has identified gaps in literature, which are: 1) there is a lack of general and scalable approaches to support the diverse types of mobile app testing for applications using various platforms, and 2) the lack of evaluation methods such as case study to validate the proposed approaches.

Keywords: Cloud-based mobile application testing, systematic mapping, testing-as-a-service.

btn fulltext

 1Nursuriati Jamil, 1Izzad Ramli & 2Norizah Ardi 
1Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Malaysia,
2Academy of Language Studies, Universiti Teknologi MARA, Malaysia,;;
The pronunciation of Malay vowels are taught according to the International Phonetic Association transcription sound chart. The documentation for pronunciations are conducted by describing and distinguishing the vowel’s sound through impressionistic. In the last five years, several studies were carried out to quantify the standard Malay vowels pronunciation using formant frequencies. However, only one work was identified that measures Malay vowels using formant frequencies for the Kedah district. Nonetheless, there were contradiction in some of the findings as the spoken vowels wereextracted from a read speech, that may not be representative of the natural dialect. Therefore, this paper investigated the Malay vowels variations from three districts (Perlis, Kelantan, and Terengganu) using spontaneous speeches acquired in a natural setting. Eight (8) Malay vowels were collected from local males and females residing in Perlis, Kelantan, and Terengganu. Four formant frequencies (F1-F4) were measured from the vowels extracted from the spontaneous speeches of the locals. Further analysis on the first and second formant suggest that the Malay vowels of Terengganu and Kelantan have a broader range of formants that are located in approximately the same position in the mouth. However, the vowels of the Perlis dialects were closely positioned in a narrower region of the mouth. A Malay vowel diagram was  plotted that can be used for future reference in research and as an educational tool for language learning. Furthermore, Kelantan and Terengganu dialects are shown to be similar based on the first and second formants.

Keywords: formant frequencies, Malay dialect, vowel diagram, vowel recognition.

btn fulltext

Universiti Utara Malaysia Press
 Universiti Utara Malaysia, 06010 UUM Sintok
Kedah Darul Aman, MALAYSIA
Phone: +604-928 4816, Fax : +604-928 4792

Creative Commons License

All articles published in Journal of Information and Communication Technology (JICT) are licensed under a Creative Commons Attribution 4.0 International License.