Journal of ICT, Design, Engineering and Technological Science

Evaluating Machine Learning Models for Real-Time IoT Intrusion Detection: A Comparative Study with RTSS Analysis

2025-05-07T02:42:38-05:00

With the ever-increasing sophistication and volume of cyber-attacks, there is a critical need for effective intrusion Detection Systems (IDS) to protect computer networks. Machine Learning (ML) offers powerful tools for IDS by automatically identifying patterns of malicious behavior. This research proposal aims to evaluate and compare the performance of several supervised ML algorithms for network threat detection using the CICIDS 2023 dataset. This paper focuses on widely-used classifiers—logistic regression, Support Vector Machine (SVM), Random Forest, eXtreme Gradient Boosting (XGBoost), and k-Nearest Neighbors (KNN) – applied to both binary (benign vs. attack) and multi-class (multiple attack types) classification tasks. This paper outlines a methodology for data preprocessing, model training, and performance evaluation using metrics like accuracy, precision, recall, and F1-score. By leveraging the comprehensive CICIDS 2023 intrusion dataset, which includes 33 modern attack scenarios across seven categories, this paper expects to gain insights into the relative strengths of each ML approach in detecting diverse cyber threats. The anticipated outcome is an identification of which algorithms (or combination thereof) are most promising for intrusion detection in contemporary network environments, guiding future developments of intelligent IDS. This proposal details the problem motivation, related work, planned methodology, and expected results, establishing a foundation for a thorough experimental study.

Exploring the AI-powered Adoption in Higher Education: A Comprehensive Study Using UTAUT4 Model to Understand User Acceptance and Usage

2025-05-07T02:42:41-05:00

AI-powered learning is an innovative, student-centered educational paradigm integrating formal, informal, and social learning modalities. This study examines the acceptance of AI-powered learning in higher education institutions in Pakistan, concentrating on student acceptance and usage. Contextual awareness, self-directed learning, Personal innovativeness, and performance expectancy Factors were examined using the Smart-PLS approach to evaluate structural relationships and test hypotheses based on the expanded Unified Theory of Acceptance and Use of Technology (UTAUT4). The Results indicate substantial positive correlations between the proposed variables and students' acceptance of AI-powered learning methods. The findings offer significant insights into the structures that may influence the utilization and subsequent outcomes of AI-powered learning acceptance & usage in HEI, including Pakistan, and the UTAUT4 model offers a useful guide for decision-makers and educational institutions working on m-learning adoption at universities.

Intelligent Vehicle Number Plate Recognition System Using Yolo For Enhanced Security In Smart Buildings

2025-05-05T05:28:29-05:00

The demand for advanced security solutions has increased with the continuous growth of urban infrastructure; hence, automated surveillance systems are vital across universities, hospitals, and commercial spaces. This project proposes an end-to-end Automatic Number Plate Recognition (ANPR) system to identify vehicle license plates by capturing high-speed images under optimal lighting conditions, isolating and analyzing plate characters, and translating the visual data into machine-readable text. By deploying these models on embedded systems, the system uses Convolutional Neural Networks (CNNs) and YOLO (You Only Look Once) for real-time object detection and recognition. The solution leverages the power of edge computing to achieve high performance and low latency for effective vehicle monitoring, data logging, and enhancing overall security infrastructure in buildings.

The Analysis of the UI/UX of Mobile Devices on the LAZNAS AL IRSYAD Website Using the User-Centered Design Method

2025-05-14T01:35:26-05:00

The research aims to analyze the User Interface (UI) and User Experience (UX) aspects of the LAZNAS (National Amil Zakat Institution) AL IRSYAD website, specifically when accessed via mobile devices. Employing a User-Centered Design (UCD) approach, the study places users at the core of the design process to identify their needs and the primary issues they encounter. The evaluation was carried out using the System Usability Scale (SUS) method to measure usability and user satisfaction. The findings revealed several shortcomings in the website's initial design, such as non-functional menu buttons, inconsistent icons, and poorly structured page layouts. The initial SUS score was 73.49, categorized as "good," but interviews revealed that several usability issues remained unresolved. Following the analysis, a redesign was conducted based on the findings, resulting in a new prototype created using Figma with a screen size 360x800. The prototype was re-evaluated, yielding an improved SUS score of 83.62, categorized as "excellent." This study is expected to provide design recommendations that address technical issues and enhance the overall user experience. Furthermore, the findings can serve as a reference for LAZNAS AL IRSYAD to optimize their website services.

Enhancing Residential Safety and Comfort Through Smart Home Security and Automation Technologies

2025-05-15T01:38:46-05:00

In the digital era, technology is changing rapidly, and humans are trying to make lives easier, but it brings a new challenge: security. Computer programs or developed hardware can be compromised if not appropriately designed or because of the simple mistakes of an authorized person. The project aims to secure a home using face recognition to unlock the doors and alarm in an emergency. The home security automation technology uses a wireless network to support the alarm and deactivation requirements. The face detection unit uses an internet
connection via an ESP32 CAM; the primary controlled systems are utilized with Wi-Fi technologies. ESP32 manages home electronic appliances and camera devices, featuring a cost-effective structure, easy-to-use interface, and simple deployment. In this project, the system primarily fulfills home security demands using face-detection gadgets, utilizing a controller with a camera. The device can manage a high-power scoring load using security locks.