Claim Missing Document
Check
Articles

Found 19 Documents
Search

The Rise of Deep Learning in Cyber Security: Bibliometric Analysis of Deep Learning and Malware Kamarudin, Nur Khairani; Firdaus, Ahmad; Osman, Mohd Zamri; Alanda, Alde; Erianda, Aldo; Kasim, Shahreen; Ab Razak, Mohd Faizal
JOIV : International Journal on Informatics Visualization Vol 8, No 3 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.3.1535

Abstract

Deep learning is a machine learning technology that allows computational models to learn via experience, mimicking human cognitive processes. This method is critical in the development of identifying certain objects, and provides the computational intelligence required to identify multiple objects and distinguish it between object A or Object B. On the other hand, malware is defined as malicious software that seeks to harm or disrupt computers and systems. Its main categories include viruses, worms, Trojan horses, spyware, adware, and ransomware. Hence, many deep learning researchers apply deep learning in their malware studies. However, few articles still investigate deep learning and malware in a bibliometric approach (productivity, research area, institutions, authors, impact journals, and keyword analysis). Hence, this paper reports bibliometric analysis used to discover current and future trends and gain new insights into the relationship between deep learning and malware. This paper’s discoveries include: Deployment of deep learning to detect domain generation algorithm (DGA) attacks; Deployment of deep learning to detect malware in Internet of Things (IoT); The rise of adversarial learning and adversarial attack using deep learning; The emergence of Android malware in deep learning; The deployment of transfer learning in malware research; and active authors on deep learning and malware research, including Soman KP, Vinayakumar R, and Zhang Y.
Comparative Analysis of Imputation Methods for Enhancing Predictive Accuracy in Data Models Zamri, Nurul Aqilah; Jaya, M. Izham; Irawati, Indrarini Dyah; Rassem, Taha H.; Rasyidah, -; Kasim, Shahreen
JOIV : International Journal on Informatics Visualization Vol 8, No 3 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.3.1666

Abstract

The presence of missing values within datasets can introduce a detrimental bias, significantly impeding the predictive algorithm's ability to discern patterns and accurately execute prediction. This paper aims to elucidate the intricacies of data imputation methods, providing a more profound understanding of prevalent imputation methods, including list-wise deletion (IGN), mean imputation (AVG), K-Nearest Neighbors (KNN), MissForest (MF), and Predictive Mean Matching (PMM). The dataset employed in this study consists of financial data about S&P 500 companies in the Compustat North America database. The training and validation dataset encompasses 1973 instances, consisting of data during the fourth quarter of 2009, the first quarter of 2010, and the third quarter of 2014. Within this set, 457 missing values were identified and imputed. The test dataset comprises 197 randomly selected instances from the fourth quarter of 2014, equivalent to ten percent of the total instances in the training dataset. The evaluation findings prominently position the dataset derived from MF imputation as the leading performer among all the imputed datasets. The insights derived from this study are intended to assist practitioners in making informed choices when selecting the most suitable data imputation method, particularly in the context of predictive modeling tasks.
Vista Angkasa Apartment Management System Thevaraju, Devi Priya; Zakaria, Zalmiyah; Mohamad Sukri, Khairul Amin; Kasim, Shahreen
International Journal of Advanced Science Computing and Engineering Vol. 1 No. 2 (2019)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1110.338 KB) | DOI: 10.62527/ijasce.1.2.4

Abstract

Vista Angkasa Apartment is one of the oldest apartments in the Bangsar South area, with a total of 8 blocks and consisting of more than 1000 units of houses. Currently, all the transaction related to the maintenance of each apartment is recorded manually. It is very difficult to manage all the data manually and if some information is required urgently then to obtain it also is very difficult. It will not only take a lot of time, but it also increases the chances of errors. Therefore, to solve the issues faced, an apartment management system that allows management staff to view the apartment’s data and tenant’s data as well as maintenance requests, notices and complaints has been developed. It also increases the efficiency and the effectiveness of Vista Angkasa Apartment Management by eliminating the current manual system. Compilation of data can be done easily with just a click of mouse. The methodology that has been applied to develop the system will be Agile with the PHP programming language. The developed system has successfully tested with the real time data at the Vista Angkasa Apartment. Based on the obtained results, the Vista Angkasa Apartment Management System solved the current issues with the management office and tenants.
University Course Timetabling System For Part-Time Students Ruslaan, Mohd Asyraf; Zakaria, Zalmiyah; Saringat, Mohd Zainuri; Kasim, Shahreen
International Journal of Advanced Science Computing and Engineering Vol. 1 No. 2 (2019)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (297.012 KB) | DOI: 10.62527/ijasce.1.2.5

Abstract

University timetabling system is a part of a timetabling problem that aims to produce course timetable that meets student needs such as the maximum number of subjects that can be offered, the maximum number of elective subjects that can be offered and the number of subject students can take. In every semester, the timetabling process in UTMSPACE is done manually where there are likely to be a small number of students who will have problems because the subject to be taken is not in the subjects offering list. Additionally, the number of subjects offered is also not optimal and this will result in a loss on UTMSPACE because each subject is offered at a cost. Therefore, in order to solve this problem, the Heuristic-based approach is used to overcome the problems mentioned and speed up the process to generate timetable. Heuristic engines have been developed using PHP language programming. This approach has been successfully tested and implemented using real-time scheduling data at UTMSPACE for Software Engineering course. The results show that Heuristics has successfully solved the problem of producing a timetable without affecting students who want to enroll the subject offered.
Feature Extraction and Classification On Single Nucleotide Polymorphism Kamarudin, Nur Fatihah; Ali Shah, Zuraini; Md Fudzee, Mohd Farhan; Kasim, Shahreen
International Journal of Advanced Science Computing and Engineering Vol. 1 No. 2 (2019)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (274.247 KB) | DOI: 10.62527/ijasce.1.2.6

Abstract

Malay in Peninsular Malaysia can be divided into eight sub-ethnics which are Malay Bugis, Malay, Malay Champa, Malay Jawa, Malay Kelantan, Malay Kedah, Malay Minang and Malay Pattani. Ancestry informative marker (AIM) can be used to represent the eight subethnic of Malay population in Peninsular Malaysia. In this research, single nucleotide polymorphism (SNP) datasets of eight sub-ethnics are analyses in order to obtain the AIM for Malays population in Peninsular Malaysia. However, the dataset may have outlier, missing data and redundancy that may impact the accuracy of the result. Pre-processing data is an important step that will remove the entire problem. Iterative pruning principal component analysis (ipPCA) is one of the techniques that usually use in analysis on genome datasets to extract the information. It can be applied on the high structured data and can improve the resolution of the data. It also used for structure a sub-population. Random Forest and Hidden Naïve Bayes is used to classify the SNP that can be used as AIM. Information Gain Ratio will rank the chosen AIM based on the value of each attribute
Diagnosis Specialist System at Palm Oil Hassan, Norhasniza; Zakaria, Zalmiyah; Ali Shah, Zuraini; Abdullah, Noryusliza; Kasim, Shahreen
International Journal of Advanced Science Computing and Engineering Vol. 1 No. 2 (2019)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (764.72 KB) | DOI: 10.62527/ijasce.1.2.13

Abstract

 The project that was developed is a computerize system that will be ableto diagnose problems happened to palm oil tree. Generally, there is twomain problem that always happened to palm oil tree; disease and pest.This system developed to store the knowledge in the related field into aknowledge base to help the newcomer in this field to make a decision tosettle the problem faced. To solve this problem, data driven searchtechnique applied to search for the symptom stored in the knowledgebase. The system developed using expert system concept. Based on thisconcept, a knowledge base was built to store all the knowledge compiled.Inference engine used to search the knowledge in the knowledge base.The knowledge based was stored in MySQL database and the inferenceengine was developed using PHP language.
Diagnostic Imaging Management System in Batu Pahat Hospital Abdullah, Nuraini; Selamat, Norhanim; Kasim, Shahreen
International Journal of Advanced Science Computing and Engineering Vol. 1 No. 2 (2019)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (979.027 KB) | DOI: 10.62527/ijasce.1.2.14

Abstract

 Management System Development Department of Diagnostic Imagingat Hospital Batu Pahat is an effort to automate the existing manualsystem which includes the application of radiological, patientinformation storage, information storage staff, patient follow-upappointments, patient and personal property items stored equipmentinformation manually. Storage of records in this manual will result induplication of information if the patient came to do the x-ray followup.In addition, all patients who undergoing treatment radiological arerequired to leave their personal belongings outside the treatment room.This is likely the patient will lose personal items is high. The mainpurpose of this system to ensure the Diagnostic Imaging Departmentof Hospital Batu Pahat in upgrading and improving its serviceperformance. Prototype Model development methodology used in thisproject. The system will help facilitate the management of dailyoperations of the Department of Diagnostic Imaging. As a result ofthis project is expected to assist the Department of Diagnostic Imagingtowards more efficient management of the organization, in line withgovernment efforts to provide the best service to the people.
Path Apps for Box of Ramadhan Ling, Teng Mee; Kasim, Shahreen; Saedudin, RD Rohmat
International Journal of Advanced Science Computing and Engineering Vol. 1 No. 2 (2019)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (463.671 KB) | DOI: 10.62527/ijasce.1.2.15

Abstract

 destination of rural area due to unclear addresses. This problem alsofaced by owner and members of the Box of Ramadhan when theyneed to give delivery services to underprivileged people cause lowefficiency of service provided. Thus, this project is conducted todesign and develop an application called Path Apps for Box ofRamadhan for Android device user to solve problems of reachdestination and get related information to reduce overall timespending. Unified Modelling Language diagram used to show therelationship and interaction among all classes. The proposed systemis categories into two different interfaces as admin interface and userinterface. The application consists of few modules such as login andregistration, user list, profile, current location, route, multiplemarkers and address list and chat modules. Time management, routeplanning and inventory will be under control by user according toprogram schedule. This contribute to high efficiency of work.
Print It To Me Development System Dickenn, Haezel Ann; Ramli, Azizul Azhar; Ali Shah, Zuraini; Kasim, Shahreen
International Journal of Advanced Science Computing and Engineering Vol. 1 No. 1 (2019)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (556.326 KB) | DOI: 10.62527/ijasce.1.1.16

Abstract

This paper addresses the project where, by the end of the project, the web-based system is able to provide an online printing service system to any party or individual who are staying in-campus to make money with their personal printer. In-campus student and staff are allowed to register as service provider (SP) and they can view and accept order via this webbased system. The system are able to display and show requests by customers while the service providers can select the requests and provide proper service to them. Furthermore, the system should have limitless availability of access, compared to the current printing request process.
Online Diagnose System for Risk of Kidney Failure Mohd Noh, Noraziah; Zakaria, Zalmiyah; Kasim, Shahreen
International Journal of Advanced Science Computing and Engineering Vol. 1 No. 1 (2019)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1098.026 KB) | DOI: 10.62527/ijasce.1.1.17

Abstract

Renal or kidney failure, only a few citizen alert in this renal failure problem. They have a lot of thing to done, and disregard on their healthy matter, especially on organ healthy that it cannot be see directly on our eyes. On that matter, online Diagnosis Renal Failure system is developed to help society to diagnose their healthy on renal failure view. System is developed online to give an advantage to society to achieve or access the system everywhere. System has two major module, diagnosis module and information module. Diagnosis module is the part where the user can make a diagnose. Information module has two sub modules, information on renal failure and information on dialysis center all around city in peninsular Malaysia. The system development is performed on expert system methodology with prototyping as the model. Production rules technique is used to represent knowledge and for searching process pattern matching technique has been use. The system expectantly can give a benefit to society and performing diagnosis in represent the knowledge of expert in medical field.