Poh Soon JosephNg

Traditional fuzzing struggles with efficiency, as maximizing code coverage does not guarantee the discovery of additional vulnerabilities. To solve this, the study introduces topology-aware node evaluation (TANE-Pool), a deep learning model that proactively predicts defects to guide the fuzzing process. The model analyzes the structural properties of a program’s attributed control flow graph (ACFG) via a diffusion attention mechanism. This process identifies fragile code regions and generates a static vulnerability score (SVS) for each basic block. The fuzzer then uses this score to prioritize test cases, concentrating its efforts on the areas most likely to contain flaws. Evaluated on the Juliet test suite and a set of real-world programs, TANE Pool demonstrates superior prediction accuracy. Its integration into a fuzzer significantly enhances the rate of vulnerability discovery, proving that a defect-prediction-guided approach is a more efficient and effective strategy for software security testing.

The integration of artificial intelligence (AI) with big data analytics leads to substantial transformations in the retail sector. This research explores the impact of AI-powered image recognition checkout systems on the retail industry, focusing on operational efficiency, customer experience, and resource waste. Employing a mixed-methods approach, this study combines usability testing and data analytics to assess the viability of this technology in attaining automation and accuracy in retail operations. The study focuses on the creation of robust, resource-efficient systems that foster long-term industrial growth. The findings show that AI-powered solutions not only speed the checkout process but also contribute to sustainable infrastructure by reducing resource consumption and increasing energy efficiency. This report offers significant information, like the impact of AI-powered image recognition checkout systems on operational efficiency, customer experience, and the role of AI in promoting sustainable infrastructure for retailers and governments looking to advance the digitalization of the retail industry.

This study explores the transformative potential of TinyML in unmanned aerial vehicles (UAVs) to address key inefficiencies in traditional search and rescue (SAR) operations, especially in the context of increasingly severe climate-related disasters. By analyzing peer-reviewed studies in major technical databases via the PRISMA guidelines, this work highlights advancements in edge computing, swarm intelligence, and multisensory integration, with a focus on fundamental contributions in embedded AI and autonomous navigation. UAVs supported by TinyML can achieve low-latency and energy-efficient real-time processing, thereby enhancing the efficiency of disaster relief operations in harsh environments. This study emphasizes the need to create synthetic datasets for underrepresented scenarios, conduct robustness tests under extreme conditions, and adopt privacy-focused decentralized learning. It connects technological progress with ethical issues such as monitoring risks and equitable access to disaster technologies. Future research directions can overcome current limitations, including insufficient validation in practical applications, fragmented policies, and high costs in resource-poor regions, through interdisciplinary collaboration, transforming theoretical advancements into scalable and socially responsible TinyML-UAV system solutions.

Dual band antenna design for 4G/5G application and prediction of gain using machine learning approaches

Big data is profoundly changing education under inclusive education. Classroom interaction, a vital component in education, is gaining increased emphasis, driving research into learning environments that better meet interaction needs. Therefore, exploring the construction of a big data-assisted eco-learning environment for classroom interaction is a prospective study. This research focuses on constructing a big data-assisted ecological learning environment based on affordance theory. It examines the relationship among learning environment, classroom interaction, and learning outcomes, using SmartPLS for validation. Through controlled experiments, surveys, teacher-student interaction analysis, and interviews, the study explores learner behavior data. Findings show the big data-assisted eco-learning environment enhances English classroom interaction, thereby further improving learning outcomes, across dimensions like learning space, resource accessibility, technical support, and emotional support. Integrating big data with ecological theory offers insights into educational digitization, supporting flexible classroom interaction, and promoting education equity, inclusivity, and sustainable education through data-driven resource management.

This study investigates the impact and implications of implementing cybersecurity identity verification on the popular instant messaging platform, WhatsApp. Specifically, it focuses on the effects of such a measure on resilient infrastructure, user perceptions of the platform's branding and trustworthiness, and the cost-effectiveness of this approach in preventing scams, phishing, fraud, and cybercrime. Empirical data collected from a diverse group of WhatsApp users highlight that the introduction of identity verification could potentially enhance transaction efficiency, foster trust, and boost user satisfaction, particularly regarding the platform's security. However, the cost and complexity of implementation pose significant challenges. Despite these hurdles, most users perceive the potential benefits to outweigh the associated costs, pointing to a broad acceptance of such security measures. The study provides practical and theoretical contributions, offering valuable insights for managers and decision-makers at WhatsApp, as well as contributing to academic discussions on digital platform management and security. The research also underscores the societal implications of such a measure, suggesting an increase in trust in digital communication platforms and supporting safer financial transactions on social media. The integration of identity verification on WhatsApp being a responsive institution emerges as a valuable but complex endeavor, demanding careful planning to ensure maximum value creation for all stakeholders.

This study focuses on examining the user perceptions of a cybersecurity certificate transparency (CT) monitoring tool in the context of artificial intelligence (AI) powered phishing attacks on the Facebook platform. Implementing CT monitoring tools is one strategy for preventing these attacks. It reveals a significant level of concern among respondents regarding the potential risks associated with phishing attacks, indicating a growing awareness of the severity of such threats for future resilient infrastructure development. Users' knowledge and understanding of AI-driven phishing threats were found to vary, emphasizing the need for awareness campaigns towards sustainable development education. The study also highlights varying levels of confidence among users in effectively identifying and thwarting phishing efforts, suggesting the importance of user empowerment through improved training, tools, and technologies as responsive institutions. These findings underscore the significance of addressing user concerns, enhancing security awareness, and providing users with the necessary resources to protect themselves against sophisticated phishing attacks. The research contributes to the understanding of user perceptions and lays the groundwork for further improvements in security measures and user education in the fight against phishing threats on Facebook's inclusive growth.

This research explores the impact of Large Language Models like GPT on the healthcare industry, focusing on operational efficiency, patient experience, and cost structures to promote greater inclusive innovation. Employing a mixed-methods approach, this study integrates quantitative data from structured surveys with qualitative insights from interviews. Grounded in empirical evidence from 66 valid surveys conducted among healthcare professionals and patients in China, this study employs SmartPLS for robust statistical analysis. The findings suggest a significant potential of LLMs in enhancing healthcare delivery, marked by improvements in operational efficiency and patient experience. While LLMs are perceived to potentially lower costs, the study reveals that cost reduction alone does not significantly influence the acceptance of LLM-integrated healthcare solutions in the Chinese context. The high level of trust and acceptance in using LLMs for diagnosis and treatment planning among respondents underscores a shift towards prioritizing quality and effectiveness in healthcare over mere cost savings. This study contributes to the discourse on AI adoption in healthcare, challenging existing assumptions and indicating a future where quality and outcome improvements may be more significant factors for technology acceptance. The research advocates for a balanced approach to LLM integration, emphasizing the importance of both economic and qualitative benefits in enhancing healthcare practices.

Energy limitation is one of the essential parameters in the design of a Wireless body area networks (WBANs) as it is important to improve the lifetime of the network. WBAN routing is an effective approach for establishing energy efficiency sets and assign time slots for the network. Many algorithms that deal with interference model treats the whole WBAN as a minimum interference unit and increase their lifetime cycle. In this research, we report an effective low-energy adaptive clustering hierarchy (LEACH) routing protocol using MATLAB simulation and related C++ simulation codes to enhance the overall performance of the network by improving the energy efficiency and network lifetime cycles. Furthermore, the study sheds light up on the comparison of the protocol and proposes a modified protocol for WBAN. Based on the results obtained from conducting different configurations in the proposed design, the base station should be situated near the network to insure high network performance.

This research investigates the effective implementation of AES encryption techniques, combined with Generative AI, to ensure secure communication on personal social media platforms. The research aims to propose strategies for improving encryption implementation, enhancing usability for easy adoption, and exploring the potential for increased profitability while maintaining security. The research methodology includes a mixed mode to collect data on encryption practices, challenges, and perceptions in social media platforms. The research concludes that the findings will offer valuable insights into the effectiveness, usability, and potential impact of AES encryption techniques, powered by Generative AI, on secure communication while assessing the potential economic benefits and growth of enhanced encryption implementation. The results of this research will contribute to developing robust encryption strategies, user-centred design principles, and cost-effective encryption solutions, ultimately strengthening the security of user communications on personal social media platforms to mitigate cybercrime.