Journal of Advanced Research in Computing and Applications

Handwritten Character Recognition using Enhanced Artificial Neural Network

Muhammad Arif Mohamad — 2024-09-18

This study addresses the concerns regarding the performance of Handwritten Character Recognition (HCR) systems, focusing on the classification stage. It is widely acknowledged that the development of the classification model significantly impacts the overall performance of HCR. The problems identified specifically pertain to the classification model, particularly in the context of the Artificial Neural Network (ANN) learning problem, leading to low accuracy in recognizing handwritten characters. The objective of this study is to improve and refine the ANN classification model to achieve better HCR. To achieve this goal, this study proposed a hybrid Flower Pollination Algorithm with Artificial Neural Network (FPA-ANN) classification model for HCR. The FPA is one of the metaheuristic approaches is utilized as an optimization technique to enhance the performance of ANN, particularly by optimizing the network training process of ANN. The experimentation phase involves using the National Institute of Standards and Technology (NIST) handwritten character database. Finally, the proposed FPA-ANN classification model is analyzed based on generated confusion matrix and evaluated performance of the classification model in terms of precision, sensitivity, specificity, F-score and accuracy.

Legibility Environment Factor for Shoulder-Surfing Resistant Authentication Scheme using Visual Perception of Graphical-based Authentication

Juliana Mohamed — 2024-09-17

Shoulder surfer is among the factors that make authentication unsecure. The physical transaction processes at automated teller machines (ATM) are the most likely to be vulnerable to shoulder surfer attacks. In addition, using an app through smartphone gives insecure situation to the user during any authentication activities. Legibility environment factors are one of the factors that affect legibility from the shoulder-surfer’s viewing angle. The research focuses on Shoulder-Surfing Resistant Authentication Scheme using Visual Perception of Graphical-based authentication. The research is carried out by developing the algorithm of the authentication process. The research allows for auto-hiding or auto-glaring techniques to the algorithm and experiment so that a shoulder-surfer cannot be seen during authentication activities. The outcome satisfies the objective and is in accordance with the legibility impact factor. Based on the results, the research concludes that the strategy successfully reduces shoulder surfers' legibility outside of the safe zone to a crucial level.

LifeGuardian; A Smart Bracelet for Visually Impaired Elderly

Mohamad Adrian Mohd Fuaad — 2024-09-17

This study investigates the utilization of Internet of Things (IoT) as a promising technology to monitor and enhance individuals' well-being. The study aims to achieve a comprehensive understanding of the main objectives, namely, to assess the effectiveness of health bracelets in tracking vital signs and physical activity especially in the case of visually impaired people, to evaluate their impact on health outcomes, and to identify potential limitations and challenges. The study employs an agile-method approach, combining data analysis from a diverse sample of participants and qualitative research regarding health, into creating a unique Arduino device that utilises IoT and various sensors to track wearer’s vitals. Results indicate that LifeGuardian accurately measures heart rate, temperature, and valuable insights into individuals' overall health status. Moreover, wearing the LifeGuardian for an extended period has been associated with improved health activity levels and enhanced awareness of personal health. The discussion highlights the need for further research to address these limitations, as well as the importance of customization and personalization features in future bracelet designs. Overall, this study contributes to the growing body of knowledge on LifeGuardian and offers insights for researchers, practitioners, and developers to enhance the effectiveness and user experience of these wearable devices.

Design and Development of iAQSA as an Innovative Web Application to Support Qualitative Research

Amnah Salah Majzob AbdelMaged — 2024-09-18

This paper presents a design and development of a web-based application called iAQSA that can assist and guide novice researchers to embark on a qualitative research method through fundamental stages. The web application serves as a platform in guiding the researchers from the beginning of the proposal to the reporting stage of the research findings. Additionally, it facilitates effective communication and collaboration between researchers and their supervisors. Supervisor can provide feedback, and approve submitted research proposals directly within the platform, enhancing the mentoring process and ensuring the quality of research outputs. iAQSA also provides a functionality to search for Islamic resources (from Al-Quran, Hadiths, and Islamic scholars) to support the research findings. The methodology used for the design and development of iAQSA was Agile Scrum, allowing for continuous feedback and improvements based on user input. Overall, iAQSA aims to streamline the qualitative research process, making it more efficient and manageable for postgraduate students. By providing a structured platform, it helps reduce the complexity and challenges associated with qualitative research process.

Optimising Text Steganography with Alpha-Based Representative Binary: Analysing Contain Letter Used and Capacity Ratio

Roshidi Din — 2024-09-18

Text steganography has become essential for secure communication in the digital age, offering a method to hide messages within seemingly ordinary text. This paper introduces the Alpha-based Representative Binary technique, an advanced feature-based method for text steganography. It utilizes both capital and small letters to represent 2-bit binary values, embedding more information without altering the visual integrity of the text. By assigning different binary values to uppercase and lowercase letters, this technique optimizes the balance between information density and detectability. Embedding 2-bit values strikes an ideal balance, as it allows for a higher capacity of hidden information while maintaining a low profile. This study evaluates the performance of the Alpha-based Representative Binary technique against existing methods like QUAD and One-Flow-2-bit, focusing on two metrics performance: the total character count in the stego text (contain letter used) and the amount of data that can be embedded relative to the cover text size (capacity ratio). The findings underscore the technique's strengths in maintaining secure and undetectable hidden messages within text. This paper highlights the evolution and effectiveness of feature-based methods, emphasizing the need for continued innovation to address detection risks and content modification challenges. By providing a detailed analysis and potential improvements, this paper aims to contribute to the development of more robust and undetectable text steganography systems. The perceptions gained from this paper is expected as valuable for researchers and practitioners in the field of secure communication.

Analytical and Empirical Insights into Wireless Sensor Network Longevity: The Role MAC Protocols and Adaptive Strategies

Sunariya Utama — 2024-09-18

Wireless Sensor Networks (WSNs) have become essential in various fields, such as corporate industries, environmental monitoring, military defense, and healthcare, due to their ability to monitor and transmit data from remote locations. However, the battery-powered nature of WSN nodes necessitates a strong emphasis on energy conservation to extend network lifespan. This paper evaluates the impact of different Medium Access Control (MAC) protocols on WSN performance, focusing on energy efficiency and data transmission reliability. We explore various MAC protocols, including contention-based protocols like Carrier Sense Multiple Access (CSMA), schedule-based protocols like Time Division Multiple Access (TDMA), and hybrid protocols that combine both approaches. The methodology integrates analytical modelling, empirical data collection, and expert interviews to comprehensively assess the performance and longevity of WSNs under different MAC protocols. Analytical models were developed to simulate WSN behavior, considering factors such as node density, traffic load, and energy consumption. Empirical data from real-world deployments and experimental setups were analyzed to validate the models and provide practical insights. Expert interviews further highlighted the challenges and considerations in MAC protocol design and implementation. This paper underscores the importance of context-specific MAC protocol selection and the potential of adaptive strategies, including machine learning, to enhance WSN efficiency and reliability. These insights can guide the development of more sustainable and high-performing WSN applications.

Interval-Valued Fuzzy Bézier Curve Interpolation Model and its Visualization

Nor Ashikin Sahrom — 2024-09-17

Curve interpolation is a crucial aspect in several applications, however, traditional approaches often face difficulties in handling data uncertainty and imprecision. This study presents a new interval-valued fuzzy Bézier curve interpolation model designed to address these difficulties effectively. In this paper, interval-valued fuzzy Bézier curve interpolation is introduced. The interval-valued fuzzy control points is defined as the data points to utilizes Bézier blending algorithms to provide smooth and accurate interpolations. In addition, a visualization method is presented to aid in understanding the interpolated curves, improving the interpretation of the results. The model's practical effectiveness is demonstrated through numerical examples. This study enhances curve interpolation techniques by utilizing an interval-valued fuzzy Bézier curve interpolation model. It provides a strong solution for dealing with uncertainty and imprecision in different fields.