| Annals of Emerging Technologies in Computing (AETiC) |
|
| IAER
| AETiC
| Editorial Board
| Instructions
| Indexing
| Submit Paper
| Special Issues
| Archives
| Contact Us
|
|
 |
|
|
|
|
Ahmed Dhahir Malik, Ansar Jamil, Khaldoon Ammar Omar and Mohd Helmy Abd Wahab Abstract: Through sensor networks, agriculture can be connected to the IoT, which allows us to create connections among agronomists, farmers, and crops regardless of their geographical differences. Faulty sensor detection is critical in IoT. When a sensor becomes faulty, missing data and/or bad data is provided to the control and management systems, which may lead to potential malfunction or even system failures. Because of this, a sensor fault detection mechanism must be implemented in an IoT system to eliminate this potential fault. This paper focuses on the implementation of a faulty sensor detection mechanism using data correlation among multivariate sensor readings, which is called Multivariate Faulty Sensor Detection Mechanism (Multi-FSDM) in a smart agriculture system. The smart agriculture system is attached with multi-variate sensors, which are moisture, temperature, and water sensor. These sensors are connected to Arduino UNO, which is equipped with an ESP8266 Wi-Fi module for internet connectivity. ThingsBoard is selected as the IoT cloud platform. The sensor readings are collected periodically and send to the cloud via the internet. Multi-FSDM calculates the correlation between each sensor reading to determine the health condition of each sensor. When all sensors are in good condition, all sensor readings are correlated with each other. However, when any sensor becomes faulty, sensor readings become uncorrelated. Once uncorrelated sensor readings occur, this means a faulty sensor is detected. Based on the findings, it is proven that Multi-FSDM can detect each sensor state on the smart agriculture system either in a good or faulty condition. When a sensor becomes faulty, Multi-FSDM detects and determines the faulty sensor successfully. Keywords: Faulty sensor detection; smart agriculture; multivariate sensors; IoT. |
Identification of the Exclusivity of Individual’s Typing Style Using Soft Biometric Elements Mohd Noorulfakhri Yaacob, Syed Zulkarnain Syed Idrus, Wan Azani Wan Mustafa, Mohd Aminudin Jamlos and Mohd Helmy Abd Wahab Abstract: Biometric is used as a main security fence in a computer system. The unique characteristics of a person can be distinguished from each other. Human’s biometrics can be categorized into three types: morphological, biological and behavioural. Morphological biometrics uses physical features for recognition. Biological biometrics used to identify user based on biological features. Behavioural biometrics such as gender, culture, height and weight can be used as an additional security measure within a system. These biometric behavioural features are also known as soft biometric. This study uses soft biometric elements (gender, culture, region of birth and educational level) in the keystroke dynamic study to distinguish typing patterns in each of these categories. The Support Vector Machine (SVM) classification method is used to perform this classification for soft biometric identification. The results of this study have shown that soft biometrics in keystroke dynamic can be used to distinguish group of individuals typing. Keywords: Keystroke dynamics; Soft biometrics; Identification; Behavioural biometrics. |
Combination of Thermal and sRGB imaging Techniques for Advanced Surveillance System K. Martin Sagayam, J. Jenkin Winston, Mohd Helmy Abd Wahab, Bharat Bhushan, Radzi Ambar and Hazwaj Mhd Poad Abstract: Surveillance is described as close observation; this term is used mostly when it comes to security observations and recording. Nowadays in our daily life we see the need of security rising up with the constant increase in the world of technology and features. On the other hand, the industries and firms continuously face threats and are pushed to a situation of seeking help for their safety. Also, that there are various blind spots in the regular security cam even the operator is not in a position to identify an emergency or any such need. This work is focused on providing clarity to such issues to the respective personal. It might be an industry, an office workspace, a supermarket or even a house. This concept deals with the enhancement of the surveillance system by infusing two different frames of Thermal and sRGB obtained input and give the output of noise reduced, enhanced and more visible image. Keywords: Surveillance; Thermal imaging; sRGB imaging; Security; image processing; Object detection. |
Brainwave Classification of Task Performed by Stroke Patients using ANN S.K. Narudin, N.H.M. Nasir and N. Fuad Abstract: In this research, 14 stroke patient's brainwave activity with open eyes (OE) and close eyes (CE) sessions are used. This work aims to study and classify 2 activities that validate our data acquisition. The data set of each subject is used to classify the state of the subject during electroencephalogram (EEG) recording. For the classification model, the input signals are alpha, beta, theta, and delta bands. The classification algorithm used in this work is the Artificial Neural Network (ANN). The accuracy value will be obtained from each subject. There are substancial differences between the EEG signals of each patient and hence affecting the accuracy value of the subject. The results obtained from our experiment proved that ANN can be used to classify the state of the subject during data recording. Keywords: EEG; Stroke; Classification; ANN. |
Management Information Systems and Geographic Information System for Managing Durian Resources Sasalak Tongkaw Abstract: The objective of this research is to develop the data for durian resources with a data collection system via the web-based system and the development of geographic information systems for durian resource management, and the local wisdom of Thai durian gardeners by designing the implement in the same database system, then presenting the durian data in southern Thailand by linking the geographic information system visualization to the map. In this research, the system method is designed using the System Development Life Cycle (SDLC), which includes six steps: requirement gathering and analysis, system design, implementation, integration and testing, development of a system, and maintenance. The results will show the visualization from both systems form and provide the report data with durian gardeners' needs. Keywords: GIS; Durian; MIS; SDLC. |
A Customizable Multilingual Chatbot System for Customer Support Vinothini Kasinathan, Aida Mustapha and Chow Khai Bin Abstract: Implementing third-party services to develop a chatbot is not cost-effective for many small and medium enterprises especially considering that many services only supports one language at a time. To address this gap, this paper proposes a multilingual chatbot system that will allow companies and organizations to customize and deploy their own multilingual chatbot service with two extended features, which are live chat and ticketing system. The chatbot will also be able to understand and reply in English, Malay, and Chinese as well as customizable given the dialogue shell and knowledge base. To achieve this, the development uses TypeScript for frontend web application while Go as the backend development. The development language for mobile application is Dart and the User Interface (UI) library is React. Finally, the database management system used is MongoDB. The developed prototype is then evaluated via a survey questionnaire and the findings suggested that the proposed system would be able to assist small and medium-sized business and organizations to deploy their own chatbot system as an alternative to existing customer services. Keywords: Conversational agents; Chatbots; Multilingual; Customer services. |
Study of B40 Schoolchildren Lifestyles and Academic Performance using Association Rule Mining Puteri NE Nohuddin, Zuraini Zainol and Mohd Hanafi Ahmad Hijazi Abstract: B40 community school children experience many underprivileged lifestyles which impacted their academic performance. Through data trends and patterns, the education top management can observe the progress of academic performance and the lifestyle relationships of students in a school or nearby school. It can also help to identify the causes of progress or deterioration of the performance of B40 community students. Therefore, a data analytics framework is essential to help decision-makers to see and analyze the changing trends and patterns of academic progress in data and related lifestyles of B40 community students more effectively and accurately. The objective of this study is to design and develop association rules analysis to deduce the relevance of academic achievement and lifestyle among schoolchildren from the B40 family. The analysis framework is established in several stages that involve data collection and processing and transformation, then the design, application and evaluate of the association rules algorithms. The framework is expected to benefit students, teachers and Education Ministry. This study foresees whether educational programs and healthy lifestyle awareness can be designed specifically for the B40 children so as to improve their academic achievement as desired by the government. Keywords: Data mining; Association Rules Mining; B40; Academic Performance; Attribute relationships. |
Human Competency Assessment for Software Configuration Management Syahrul Fahmy, Aziz Deraman, Jamaiah Yahaya and Abdul Razak Hamdan Abstract: Late product delivery is a common problem in software projects. Late delivery can be attributed to software change especially in the development and maintenance phases, leading to more work than originally planned, thus increasing project completion time. One approach for managing software change is Software Configuration Management (SCM). SCM was first introduced in the 1970s to ensure the timely delivery of software products. To date, SCM implementation is supported by recognized standards, best practice, and countless commercial and proprietary tools. However, after more than 50 years, the issue of late software product delivery still prevails, questioning the practice of SCM in software organizations. One aspect of SCM that has received little focus in mainstream research is the human aspects. This study aims to identify how the competency of SCM practitioners can be assessed through the identification of SCM competency criteria and the development of a competency assessment framework. The framework was validated through expert reviews and case studies involving practitioners from the public sector, industry, institutes of higher learning and international organizations. Results confirmed the reliability of the SCM competency criteria and the plausibility of the competency assessment framework. Keywords: Software Configuration Management; Software quality; Software engineering; Human competency. |
Husain Hashim, Shamila Mohamed Shuhidan and Norizan Anwar Abstract: Digital, information, and networked technologies have largely affected the academic libraries and their users in support of 21st education. This development places demands on them to endure seriously the assessment challenges in the aspect of users’ utilization of Web-based Information Services, not merely to rely on the implicit value of usage statistics, but also to look into the explicit difference that the specific usage of web-based information services has on users’ experience in the form of their perceived scholarly outcomes. In establishing this paper, scoping approach was used as the methodology for preliminary assessment in exploring and analyzing the published research articles from local and international sources. Based on the literature review, this paper aims to propose a conceptual research framework for Malaysian academic libraries comprising three independent variables, namely, library technology, academic library roles, and library learning environment. Besides, information literacy skill is introduced to gain understanding, to what extent, it has a moderating relationship between the independent variables and the university students’ utilization of WBIS, the predicted dependent variable that constitutes implicit and explicit values. This framework will be measured by conducting a research involving six public universities in the Klang Valley of Malaysia. In the long run, it is expected to propose a research method and instruments to support the academic libraries in collecting and analyzing data about utilization of web-based information services among university students. Keywords: Web-based information services; Academic library; Library technology; Academic library roles; Information literacy skills; Utilization. |
Virtual Learning for Human Respiratory System Via Non-Immersive VR (V-HURESYS): An Evaluation Nurul Hidayah Mat Zain, Ismassabah Ismail, Nor Azida Mohamed Noh, Anita Mohd Yasin, Zainab Othman and Siti Nuur Atikah Che Yahaya Abstract: The science includes a lot of concepts and abstract that cannot be seen by the naked eye. Students have a problem remembering and visualize information contained in the science subject. Hence, the idea of the development of effective visualization learning materials using Virtual Reality is expected. By using VR, the user can visualize the structure and interact with the components inside. The purpose of the present study was to evaluate the effectiveness of application in learning the Human Respiratory System through virtual reality (VR). The evaluation conducted among secondary school students by using the Kirkpatrick Model evaluation model. The data collected from 35 Form 3 students that take a science subject. The overall percentage average of the evaluation is 72%, which considered V-HURESYS application was effective in learning the Human Respiratory System through the VR technique. Keenly, the results of the study will emphasize the student’s performance in their science subject, especially in learning Human Respiratory System topics. Keywords: Human Respiratory, Kirkpatrick Model, Science Subject, Virtual Reality. |
Sinkhole Attack Detection and Avoidance Mechanism for RPL in Wireless Sensor Networks Ansar Jamil, Mohammed Qassim Ali and Muhammed E. Abd Alkhalec Abstract: The security issue is one of the main problems in Wireless Sensor Network (WSN) and Internet of Things (IoTs). RPL (Routing protocol for low power and lossy networks) is a standard routing protocol for WSN, is not to be missed from being attacks. The performance of RPL is reduced significantly after being attacked. Sinkhole attack is one of the most common attacks to WSN and RPL, threatening the network capability by discarding packets and disrupting routing paths. Therefore, this paper proposes a new Secured-RPL routing protocol to detect and avoid sinkhole attacks in the network, which is called Cross Layers Secured RPL (CLS-RPL). This routing protocol is enhanced of the existing RPL routing protocol. CLS-RPL is a cross-layer routing protocol that uses information from the data link layer in its security mechanism. CLS-RPL uses a new technique and concept in detecting a sinkhole attack that is based on eave-listening (overhearing) that allows a child node to eave-listening its parent transmission. If the child node does not hear any transmission from its parent node after sending several packets, this means its parent node is a sinkhole attacker. Otherwise, if the node hears transmission from its parent node, this means that its parent node is legitimate and continues to send more packets. CLS-RPL implements a simple security mechanism that provides a high packet delivery ratio. The finding shows that CLS-RPL provides 52% improvement in terms of packet delivery ratio when compared to RPL protocol. Keywords: Cross-layer; RPL; Security; Sinkhole attack; Wireless Sensor Network. |
User Acceptance of QR Code based Mobile Application in Interactive E-Commerce Yuhanis Yusof, Lee Cheng Hooi and Azizi Abas Abstract: Advertisement on products or services can be found in many forms; video, banners, pamphlets, etc. However, these advertisements only function as a one-way communication as consumers are only presented with the product information and the seller. Further action on purchasing the product is absent or is to be made separately. Such an approach may not guarantee a sale for the seller as the customer may only retrieve the information of the product but purchase it elsewhere. Hence, this study demonstrates the use of QR code technology not only in marketing but also in e-commerce. The technology is realized in "On the GoShop" mobile application that has two types of users: seller and buyer. Sellers are people who wanted to promote their product and/or services while buyers are the ones who have a desire to purchase. An evaluation study on the acceptance of the mobile application was then performed on a total of 50 respondents and it is learned that the proposed e-commerce application is well accepted. Ninety percent of the respondents agree with the usefulness of the application and are looking forward to using the application in daily routines. The use of QR code technology not only facilitates consumer in purchasing their desired product but also contribute to cost-effective marketing. Keywords: QR code; digital marketing; e-commerce; digital advertising. |
Development of Intelligent System for Alert Notification in Indoor Planting Khairulnur Najiha Abd Karim, Mohd Hudzari Haji Razali, S.M. Shamsi and Mohamad Noorman Masrek Abstract: The past decade has seen significant advancement in the field of agriculture industry. Various smart appliances such as cellular phones, moisture sensors, humidity sensor and smart irrigation are set to realize the concept of a new smart farming with the help of latest technology. In Malaysia, farmers experience crop damage and decrease in plant quantity and quality because they unable to monitor the crop all day. The development of a monitoring system that can helps farmer grow crops is enticing demand for busy individuals with physical limitations. Global System for Mobile Communication (GSM) technology, which has emerged in the late 1970s, is an ideal solution for this problem. In this paper, a development of intelligent system for alert notification in indoor planting is presented. This paper describes an application of GSM technology for monitoring light system in indoor planting with the use of hardware component like Arduino board, GSM SIM900A, LDR and LED strip. The major role of this system is to enable farmers to get notified when the light system for their plants is down through GSM SIM900A. Each time the light system is light on and light off, the farmers will receive an SMS to notify them. System functional testing was carried to evaluate the performance of implementing GSM SIM900A whether the prototype is free from error or there are a few errors occurs. The results shown that, the system is well functioning for alert notification in indoor planting monitoring. In conclusion, the development of intelligent systems for alert notification in indoor planting was developed using Arduino and GSM SIM900A to able farmers notified about their indoor planting when to be monitored. Keywords: Arduino; GSM Technology; Intelligent System; Monitoring Indoor Planting. |
Valerie Ross and Abid Amir Abstract: The COVID-19 pandemic has caused adverse social, economic, physical and psychological repercussions to mankind. Global healthcare systems are pushed to breaking points. Lockdowns and movement control orders imposed by the Malaysian government and many other nations on its citizens have necessitated home-based solutions to manage rising stress and anxiety due to personal, professional, financial and work-related uncertainties. Frontline healthcare workers bear the brunt of the crisis. This study responds to mental issues caused by the virulent pandemic and recognizes the increasing need for psychosocial rehabilitation among healthcare workers. It aims to create an effective, on-demand, mobile and pleasurable tool based on original music and progressive relaxation techniques that empower users to foster mental health and wellness. A combination of practice-based and user-centred design methodologies was adopted in this interdisciplinary study. Spectral analysis using Raven-Pro sound analysis offers insights into the sonic content of the tool. The result of the study is a prototype model of an innovative digital tool crafted and narrated in the English Language and Malay Language using Bespoke Music and Narration to promote mental health among COVID-19 frontline healthcare workers. Keywords: Bespoke Music and Narration; COVID-19 pandemic; mental health; progressive muscle relaxation. |
Ahmad Affandi Supli, Heng Yu Ping, Norma Liyana Binti Omar and Wong Yun Yi Abstract: Human anatomy is a biology field that studies human body which consists of intricate and complex piece of engineering in which every assembly has an important role. This subject is considered to be very complex and thus need an advanced technology to help users learning this course more effectively. In this study, we propose and report our research strategy and progress to build a constructive play on human anatomy system based on finger motion gesture of Leap Motion controller (LMC). This LMC device can detect hand gestures and fingers’ motion and translate it into interaction input. Then, we utilize holographic display to portray our 3D human anatomy as its output. In detail, the research strategy of this paper consists of research plan, general framework and general architecture of the developed system. Then, we also present our current development of constructive anatomy learning system. In this future, we will discuss in more detail about the development stage. Keywords: Human anatomy learning system; construction play; Leap Motion controller; holographic display. |
Application of Gradient-based Edge Detection on Defined Surface Feature Boundary Ainaa Farhanah Mohd Razali and Mohd Fauzi Ismail Abstract: In surface topography, the detection of edges or surface feature boundary should be made prior to the characterization process to ensure precise measurement of the surface feature. However, problem arises when the existing edge detection from the image processing area is being directly adopted on the surface without firstly defining the exact location of edges. Thus, an approach has been carried out with the aim of developing the definition of edges to identify its exact location. The process of developing the definition of edges is conducted based on theoretical understanding and demonstration on the simulated surface topography data with the help of MATLAB software. Gradient-based edge detection operators are applied to see their performance on the defined surface feature boundary. Overall findings of this study showed that there are slight discrepancies of the edge position signified by the gradient-based operators to manually-defined edges. Despite of such outcome, it is then recommended to use either the Sobel operator or the Prewitt operator as a tool to signify the edge before proceeding with characterization process in future study due to their stability and clarity in producing the surface gradient function. Keywords: Edge detection; Feature boundary; Structured surface; Surface topography. |
Q-CAM: Queue Monitoring System using Camera Farah Nadiah Mohammad Ramlee, Radzi Ambar, Mohd Helmy Abd Wahab, Chew Chang Choon and Muhammad Mahadi Abd Jamil Abstract: Development and design of mobile queue counter monitoring system is an alternative way for people who visit service premises to monitor queue number through phone without having to be at the place to wait for their turn. A long waiting line and waiting time are the reasons why this project had been developed. Many related systems had been introduced by different companies but due the high cost of installation and maintenance, some service companies had difficulties to implement the system. However, the proposed mobile queue counter monitoring system called Q-CAM is an add-on device which will be installed with the existing system and uses only ESP32 camera and FTDI Programmer as hardware development. A smartphone application is developed by using MIT App Inventor to ease the customer to monitor queue number on the app. In this work, the hardware designs of the propose device is described. Furthermore, the steps to develop the smartphone app is demonstrated. Preliminary experimental results show that the average time required to display a captured queue number image on the app were 5 seconds (during strong Wi-Fi signal) and 10.8 seconds (during weak Wi-Fi signal). Keywords: Queue monitoring system; ESP32 camera; smartphone application; Wi-Fi; QMS. |
Reading Speed Performance based on Interface Design Elements for Web Interfaces Zuriana Abu Bakar and Tan Zhiang Abstract: The development of technology and internet has contributed to more people viewing on-screen content and an increase the amount of material that can be read directly from a Web-based platform. The transformation from paper-based materials to digital materials on the Web, more or less has affected the readability of the materials in which information presented on the printed and web-based documents is dissimilar. However, only few studies have been carried out on the presentation of information specifically, the readability of the text in web-based platform. Meanwhile, readability is one of the crucial aspect of Web usability and could affect the success of a website. The speed of reading is regarded as a good measure of readability. Therefore, this study aims to measure the readers reading speed for web interfaces. This study followed a quantitative analysis method that used experiments to collect data and involved university students as the test subjects. A Web-based Reading Speed Test System (RSTS) was developed for data collection and analysis purpose. The findings of this study found that the web interface with the combination of blue font color, yellow background color and Arial font type have the highest reading speed. In contrary, web interface that consists of combination black font color, white background color and Arial font type have the lowest reading speed. In addition, the reading speed of male participants was slightly higher than the female participants. To conclude, the results of this study signify that the interface design had a significant impact on the students reading speed for web pages. Keywords: Design elements; Interface design; Reading speed performance; Web interface. |
A Formal OLAP Algebra for NoSQL based Data Warehouses Shreya Banerjee, Sourabh Bhaskar, Anirban Sarkar and Narayan C. Debnath Abstract: NoSQL solutions are started to be increasingly used in modern days’ Data Warehouses (DW). However, business analysts face challenges when performing On Line Analytical Processing (OLAP) queries on these NoSQL systems. The lack of uniform representation of various OLAP operations over different types of NoSQL based DWs is one of them. In addition, deficiency of precise semantics in OLAP operations create obstacles to effective query interpretation over distinct types DWs. This paper is aiming to deal with aforementioned challenges. Formal and rigorous specification are represented in this paper for different kinds of OLAP operators and operations. These precise specifications are capable to analyse business queries. Further, the proposed formal specifications are implemented in a document-oriented database using a suitable case study. In addition, the proposed approach aids efficient visualization techniques of data cubes over NoSQL based DWs. Keywords: Data Cube; NoSQL Data Warehouses; OLAP query algebra; Ontology. |
A Unified Conceptual Model for Data Warehouses Shreya Banerjee, Sourabh Bhaskar, Anirban Sarkar and Narayan C. Debnath Abstract: These days, NoSQL (Not only SQL) databases are being used as a deployment tool for Data Warehouses (DW) due to its support for dynamic and scalable data modeling capabilities. Yet, decision-makers have faced several challenges to accept it as a major choice for implementation of their DW. The most significant one among those challenges is a lack of common conceptual model and a systematic design methodology for different NoSQL databases. The objective of this paper is to resolve these challenges by proposing an ontology based formal conceptual model for NoSQL based DWs. These proposed concepts are capable of realizing the cube concepts for visualization of multi-dimensional data in NoSQL based DW solutions. In this context, two strategies are specified, implemented and illustrated using a case study for devising of the proposed conceptual model. Keywords: Conceptual Model; MongoDB based Implementation; NoSQL Data Warehouse; Ontology-driven Model. |
Surface Reversal Method Algorithm Development Nor Athirah Roslan and Mohd Fauzi Ismail Abstract: The reversal method introduced by previous research focuses in finding reference datum of topography data of cylinder end surface but somehow ignores the existence of error. This problem leads to the purpose in introducing an understanding of how this method can be improvised. Thus, in this paper, a primitive approach was done by introducing the algorithm of the surface reversal method and simulating the reversal method on a selected surface to test how it works. This paper used MATLAB software for the majority of data processing. It started by preparing two simulated surfaces which were surface A and surface B (180o rotation). Then, it continued with the preparation of surface by converting the surface data into an image file type which made surface A and surface B aligned in the same direction before conducting surface correlation and finally finding the best match point between both surfaces. These basic steps play an important role to ensure the whole procedure for the next future studies is accurate. The peak result at position (540 x 409) from surface correlation was able to ease the next procedure by having a proper position before doing surface subtraction. The algorithm developed through MATLAB has successfully demonstrated the primary steps of surface reversal method. Keywords: Reversal method; Reference datum; Surface topography; Error and uncertainty. |
Application of Support Vector Regression in Krylov Solvers Rehana Thalib, Maharani Abu Bakar and Nur Fadhilah Ibrahim Abstract: Support vector regression (SVR) is well known as a regression or prediction tool under the Machine Learning (ML) which preserves all the key features through the training data. Different from general prediction, here, we proposed SVR to predict the new approximate solutions after we generated some iterates using an iterative method called Lanczos algorithm, one class of Krylov solvers. As we know that all Krylov solvers, including Lanczos methods, for solving the high dimensions of systems of linear equations (SLEs) problems experiences breakdown which causes the sequence of the iterates is incomplete, or the good approximate solution is never reached. By assuming that some iterates exist after the breakdown, then we could predict what they are. It is realized by learning the previous iterates generated by the Lanczos solvers, which is also called the training data. The SVR is then used to predict the next iterate which is expected the sequence now has similar property as the previous one before breaking down. Furthermore, we implemented the hybrid SVR-Lanczos (or SVR-L) in the restarting frame work, then it is called as hybrid restarting-SVR-L. The idea behind the restarting is that one time running hybrid SVR-L cannot obtain a good approximate solution with small residual norm. By taking one iterate which is resulted by the hybrid SVR-L, putting it as the initial guess, will give us the better solution. To test our idea of prediction of SLEs solutions, we also used the regular regression and compared with the SVR. Numerical results are presented and compared between these two predictors. Lastly, we compared our proposed method with existing interpolation and extrapolation methods to predict the approximate solution of SLEs. The results showed that our restarting SVR-L performed better compared with the regular regression. Keywords: SLEs; Machine Learning; SV; Lanczos solvers; hybrid; restarting. |
Recommender System for Multiple Databases Based on Web Log Mining Wan Hussain Wan Ishak and Nurul Farhana Ismail Abstract: Finding information from a large collection of resources is a tedious and time-consuming process. Due to information overload, searchers often need help and assistance to search and find the information. Recommender system is one of the innovative solutions to the problem related to information searching and retrieval. It helps and assist searchers by recommending the possible solution based on the previous search activities. These activities can be obtained from the web log, which requires a web log mining approach to extract all the keywords. In this study, keywords obtained from the library web log were analysed and the search keyword patterns were obtained. These keyword patterns were from several databases or resources that were subscribed by the library. The finding revealed some of the popular keywords and the most searchable databases among the searchers. This information was used to design and develop the recommender system that can be used to assist other searchers. The usability test of the recommender system showed that it is beneficial and useful to the searchers. These findings will also benefit the management in planning and managing the subscription of online databases at the university’s library. Keywords: Information retrieval; recommender system; web log mining; multiple databases; information overload. |
MyAbility: A Web Portal for Students with Challenge based on Web Content Accessibility Guideline 2.0 Abdul Aziz Hamzah, Zatul Amilah Shaffiei, Nor Hayati Abdul Hamid and Nurulnadwan Aziz Abstract: Statistic of people with challenge in Malaysia has been gradually increased. People with challenge are those who have certain impairments such as physical, visual, hearing, learning, speech, mental and multiple challenges that may hinder their effective interaction and participation in society. This also includes the students with challenge in higher learning institution (i.e. Universiti Teknologi MARA, Malaysia). Based on the interview, it was reported that there is lack of proper platform for students with challenge to interact and access the information particularly related to university, since their requirements on the facilities provided are different with general students. Thus, higher learning institution including Universiti Teknologi MARA, Malaysia has come out with a policy regarding students with challenge based on five (5) principles which are inclusivity, accessibility, equity, flexibility and equivalence to bridge the gap between the students with challenge, facilities and the communities in the university. To fulfil the policy, technology should be used as a medium for students with challenge to get greater opportunity to interact and access the information. Therefore, this project aims to develop a web portal for students with challenge which focus on accessibility principle. Web Development Life Cycle (WDLC) methodology has been utilized to complete the development of web portal, which is based on the standard of Web Content Accessibility Guideline (WCAG) 2.0. User experience testing has been carried out in terms of the functionality provided by the developed web portal to the students with challenge. It was found that the accessibility elements provided in the developed web portal are well function. Hence, this study concludes that a proper design and development of a web portal could bridge the gap between students with challenge, communities as well as facilities provided in university. Keywords: Human computer interaction; Interaction design; Inclusive design; Web content accessibility; People with challenge; User Experience. |
A Machine Learning Approach for Improving the Performance of Network Intrusion Detection Systems Adnan Helmi Azizan, Salama A. Mostafa, Aida Mustapha, Cik Feresa Mohd Foozy, Mohd Helmy Abd Wahab, Mazin Abed Mohammed and Bashar Ahmad Khalaf Abstract: Intrusion detection systems (IDS) are used in analyzing huge data and diagnose anomaly traffic such as DDoS attack; thus, an efficient traffic classification method is necessary for the IDS. The IDS models attempt to decrease false alarm and increase true alarm rates in order to improve the performance accuracy of the system. To resolve this concern, three machine learning algorithms have been tested and evaluated in this research which are decision jungle (DJ), random forest (RF) and support vector machine (SVM). The main objective is to propose a ML-based network intrusion detection system (ML-based NIDS) model that compares the performance of the three algorithms based on their accuracy and precision of anomaly traffics. The knowledge discovery in databases (KDD) methodology and intrusion detection evaluation dataset (CIC-IDS2017) are used in the testing which both are considered as a benchmark in the evaluation of IDS. The average accuracy results of the SVM is 98.18%, RF is 96.76% and DJ is 96.50% in which the highest accuracy is achieved by the SVM. The average precision results of the SVM is 98.74, RF is 97.96 and DJ is 97.82 in which the SVM got a higher average precision compared with the other two algorithms. The average recall results of the SVM is 95.63, RF is 97.62 and DJ is 95.77 in which the RF achieves the highest average of recall than SVM and DJ. In overall, the SVM algorithm is found to be the best algorithm that can be used to detect an intrusion in the system. Keywords: Intrusion detection systems; detection rate; false alarms; CIC-IDS2017; random forest; decision jungle; machine; support vector machine. |
|