Journal of Information Technology and Computing

Efficient Ensemble-based Phishing Website Classification Models using Feature Importance Attribute Selection and Hyper parameter Tuning Approaches

2024-01-10T19:34:21+00:00

The internet is now a common place for different business, scientific and educational activities. However, there are bad elements in the internet space that keep using different attack techniques to perpetrate evils. Among these categories are people who use phishing techniques to launch attacks in the enterprise networks and internet space. The use of machine learning (ML) approaches for phishing attacks classification is an active research area in the field of cyber security. This is because phishing attack detection is a good example of intrusion identification tasks. These machine learning techniques can be categorized as single and ensemble learners. Ensemble learners have been identified to be more promising than the single classifiers. However, some of the ways to achieve an improved ML-based detection models are through feature selection/dimensionality reduction as well as hyper parameter tuning. This study focuses on the classification of phishing websites using ensemble learning algorithms. Random Forest (RF) and Extra Trees ensembles were used for the phishing classification. The models built from the algorithms are optimized by applying a feature importance attribute selection and hyper parameter tuning approaches. The RF-based phishing classification model achieved 99.3% accuracy, 0.996 recall, 0.983 f1-score, 0.996 precision and 1.000 as AUC score. Similarly, Extra Trees-based model attained 99.1% accuracy, 0.990 as recall, F1-score was 0.981, precision of 0.990 while AUC score is 1.000. Thus, the RF-based phishing classification model slightly achieved better classification results when compared with the Extra Trees own. The study concluded that attribute selection and hyper parameter tuning approaches employed are very promising.

Frame-based System for Diagnosing Infertility in Males and Females

2024-01-10T19:34:16+00:00

Diagnosis plays a crucial role in saving the life of a patient. However, due to the challenges faced by medical practitioners such as; few available resources, little amount of time dedicated to diagnose each patient, few numbers of specialists, emergence of new diseases and similarities of symptoms of diseases may hinder achieving accurate diagnosis. Infertility may be caused by a range of medical condition and abnormalities such as diseases, infections and hormonal imbalances in the reproductive system. The prevalence of infertility has negatively affected many couples globally especially in Africa where it is often linked with different traditional superstition in some societies. This led to the need for the development of systems capable of predicting and diagnosing diseases. In this research work, the expert System developed employs the frame-based approach to assess and predict the possible infertility problem that a patient may have based on the symptoms and patient information provided into the system. Outcomes of diagnosis presented to users solely depend on reasoning method implemented in the knowledge base of the system. The system showed an excellent predictive ability of 98% when scoring based on accuracy. It was evaluated on fifty (50) randomly selected infertility cases from the case file of patients. The system was able to effectively predict forty nine (49) infertility cases correctly and one (1) incorrectly. From the study, it is concluded that the frame-based system will assist not only medical practitioners but also individuals affected in achieving timely diagnosis since it can be accessed remotely. Furthermore, the system has the ability to store health records, diagnosis and generate statistical reports of patients.

APPROACHES FOR SOLVING ROUTING AND SECURITY ISSUES IN MOBILE AD-HOC NETWORKS (MANETs): A REVIEW

2024-01-10T19:34:14+00:00

Mobile Ad hoc Networks (MANETs) have been very popular for some years now owing to their ability to allow communication in dynamic and infrastructure-less environments. However, the unique characteristics of MANETs, such as node mobility, limited power resources, and absence of centralized infrastructure, pose challenges in ensuring efficient routing and robust security. This paper presents a review of the existing techniques aimed at improving routing protocols and security in MANETs. Scholarly articles, conference papers, and technical reports published in notable research outlets were sourced. Then, the papers were categorized into two main areas: routing techniques and security mechanisms based on the target of this work. Regarding routing techniques, this review discusses the evolution of traditional routing protocols, including proactive, reactive, and hybrid approaches, and highlights their strengths and limitations. Moreover, the review presents some recent advancement such as location-based, Quality of Service (QoS)-aware, and energy-efficient routing protocols, which address specific challenges in MANETs. In terms of security mechanisms, this review provides an overview of the various threats and attacks that MANETs are susceptible to, including black hole, wormhole, and Sybil attacks. The review then examines the countermeasures proposed in the literature to tackle the security challenges. This article further highlights the emerging trends and research directions in the field of MANETs which include blockchain-based security, machine learning-assisted routing, and Internet of Things (IoT) integration. It is believed that this review can provide further insights to researchers in this domain.

A SURVEY ON PROMISING DATASETS AND RECENT MACHINE LEARNING APPROACHES FOR THE CLASSIFICATION OF ATTACKS IN INTERNET OF THINGS

2024-01-10T19:34:23+00:00

Securing Internet of Things (IoT) against attacks is a very interesting area of research. A cyberattack refers to as any form of malicious activity that targets IT systems, networks and/or people with a view to gaining illegal access to systems and data they contain. Attacks are in various forms as found in computer systems, networks and the cyber space. The immense increment in the amount of internet applications and the appearance of modern networks has created the need for improved security mechanisms. A good example of such modern technology is Internet of Things (IoTs). An IoT is a system that uses the Internet to facilitate communication between sensors and devices. Several approaches have been used to build attacks detection system in the past. The approaches for classifying attacks have been categorised as signature-based and Machine learning based. However, ML techniques have been argued to be more efficient for the identification of attacks or intrusions when compared to signature-based approaches. This study sourced for relevant literature from notable repositories and then surveyed some of the recent datasets that are very promising for ML-based studies in attack classification in IoT environments. The study equally provided a survey of evolving ML-based techniques for the classification of attacks in IoT networks. The study provided clear directions to researchers working in this area of researches by making the necessary information available more easily for the researcher to go about achieving improved ML-based approaches in this area.

Online Customer Reviews and their Effect on the Download of Mobile Applications

2023-12-26T10:00:22+00:00

This research investigated some characteristics of online reviews and their impact on the download of mobile applications. Data was collected from the Google Play store across five of the most popular app categories to provide answers to the research questions and test the hypotheses formulated for this study. A total of 12,169 reviews were provided on different apps under the top five categories, namely: education, business, music & audio, tools, and entertainment, during the study period. The results obtained from the OLS regression indicated that there is a statistically significant relationship between the length of reviews and the download of selected applications; the number of reviews provided for mobile applications and the number of downloads; the number of positive reviews and the number of downloads of the apps chosen; and lastly, the number of negative reviews and the number of downloads of the apps chosen. The overall results of the OLS-regression revealed that the adjusted R-squared value of the model is 0.712. This means that 71.2% of the variability of the dependent variable (app download) is explained by the variables considered in this study, an indication that the model is relevant to the study. Based on these findings, the study recommends that app developers incorporate features into their apps that will prompt users to provide reviews on online app marketplaces, as the number of reviews has a favorable impact on mobile app downloads.