MMU Press (Multimedia University)
Not a member yet
714 research outputs found
Sort by
Cyber Security Threats of Using Generative Artificial Intelligence in Source Code Management
No full textGenerative Artificial Intelligence (Generative AI) models are now broadly used for academic writing and software development for the sake of productivity and efficiency. Concerns on the impact of Artificial Intelligence (AI) tools on academic integrity and cybersecurity grow bigger with time. Generative AI is being used for code generation, editing, and review, raising ethical and security challenges. A big concern is the involuntary introduction of vulnerabilities into codebases. They can reproduce known bugs or malicious code that compromise software integrity because of the way models are trained: on large datasets. The tools may also pose additional security threats often encountered during software development. AI models trained on public data will generate code that resembles copyrighted content, creating ownership and legal grey areas. Use of AI to delegate coding increases potential adversarial attacks and model poisoning. Addressing these challenges would therefore call for a balanced approach towards AI integrating into software development. Secure coding practices, thorough testing, continuous monitoring, and collaboration between developers, security professionals, and AI researchers should be balanced. Strong governance, regular audits, transparency in AI development, and the embedding of ethical standards in AI usage will help in ensuring it is safe and effective. Generative AI should be seen as a tool to enhance, not replace, human expertise in software development. While automation can streamline workflows, developers must remain vigilant to detect and mitigate AI-induced vulnerabilities. A proactive approach that combines human oversight with AI-driven efficiency will be key to securing the future of software development
Enhancing Imbalanced Data Augmentation: A Comparative Study of GANified-SMOTE and Latent Factor Integration
No full textOne such serious problem in machine learning (ML) is imbalanced datasets. Minority class samples are usually sparse but hold significant meaning. The model can become biased toward the majority class due to unbalanced class distribution. This results in fraudulently high accuracy without being able to detect minority cases. This bias is also most perilous in critical applications, where ignoring minority cases can be highly destructive. To overcome this problem, the Synthetic Minority Oversampling Technique (SMOTE) is one of the most widely used. SMOTE creates balanced class distribution by interpolating between existing minority samples. It creates samples that are too close to one another and can lead to overfitting and limit the generalization of the model. Recent advancements in generative modeling, especially Generative Adversarial Networks (GANs), offer a more effective solution to handle class imbalance. GANs utilizes a generative discriminator structure to produce synthetic data highly similar to real data. A hybrid technique called GANified-SMOTE combines the power of SMOTE with the generation power of GANs to produce more diverse and realistic minority class samples. The technique improves the model strength and eliminates the limitations of traditional oversampling. This paper presents the incorporation of latent factors into the architecture of GANified-SMOTE framework. Latent variables reveal hidden structures and relations in the data, leading to a closer synthetic sample and improving classification accuracy. By incorporating latent factors, this research aims to build a better oversampling method for imbalanced classification sets
Cyclone Nature Prediction with the help of a Customized SVM Model
No full textEfficiently predicting the nature of tropical cyclones through machine learning techniques has always posed a challenge in the quest to save human lives. While existing research has proposed various methods to accurately predict cyclone behavior and reduce its impact on humanity, this paper introduces a unique customized Support Vector Machine (SVM) model. Unlike existing models, this machine learning-based custom model enhances evaluation metrics, offering significant improvements in binary classification forecasting. The paper also presents a schematic diagram outlining an architectural design for cyclone nature detection utilizing satellite images. The proposed customized SVM model achieves impressive classification metrics, with accuracy at 95%, precision at 94.78%, recall at 94.5%, and an F1-score of 94.9%. In contrast, other models such as Random Forest (RF), SVM, decision tree (DT), and Logistic Regression (LR) fall short, failing to reach an accuracy exceeding 92%. Furthermore, future work may involve the development of hybrid models.
Manuscript received: 3 May 2025 | Revised: 30 Jun 2025 | Accepted: 13 Jul 2025 | Published: 30 Nov 202
First Zagreb Index and its Characteristics on Neutrosophic Graph
No full textTopological indices mark an irreplaceable place for applications in crisp and fuzzy graphs. These indices are extended to the neutrosophic graphical idea to rectify the imprecise values or information acquired before, since the uncertain cases are organized and allocated as a separate membership called "indeterminacy". We apply and explore the First zagreb index and its properties on the neutrosophic graphical system in the line of Wiener and Forgotten indices. This fills the gap between fuzzy and its graphical extensions on indices discussion, thereby extends the applicable areas. Also, an improvised and unique application is portrayed to observe the importance of First zagreb index in the neutrosophic theme of graphs. This contributes to the real life in a greater way than the fuzzy idea.
Manuscript received:8 Apr 2025 | Revised: 31 May 2025 | Accepted: 19 Jun 2025 | Published: 30 Jul 202
The impact of AI chatbot adoption on customer experience in e-retailing
No full textDue to the outbreak of the COVID-19 pandemic, the changes in shopping norms from offline to online and rapid development in the field of artificial intelligence (AI) have redefined customer experience. This change has brought lucrative opportunities for organisations to provide better customer service by interacting with customers using chatbots. Thus, this research was conducted to examine the attributes of AI chatbots that affect online customer experience in the e-retailing market. This paper applied the Technology Acceptance Model (TAM) to design a research model to investigate the relationship between chatbot usability, responsiveness, and online customer experience. A quantitative method was employed to test the research model, and data were collected from an online survey. A total of 101 usable responses were received and examined using SPSS software. The results show a positive relationship between chatbot usability and online customer experience, while no significant relationship is observed between chatbot responsiveness and online customer experience. The findings of this study offer insights for academics, industry practitioners, and policymakers aiming to utilise the potential of AI chatbots to enhance online customer experience and elevate overall customer satisfaction in the e-retail sector
Virtual reality application for tourism in Saudi Arabia
No full textTourism significantly contributes to global economies and societal development. Virtual tourism has emerged as a crucial alternative during crises like the COVID-19 pandemic, sustaining the tourism sector. This paper explores virtual tourism's potential for Saudi destinations, focusing on its impact and acceptance among 600 participants from Jeddah, Riyadh, Dammam, and Abha. Using a descriptive-analytical approach and an applied experiment with virtual reality tours of Jeddah's historical sites, the results show a positive attitude towards virtual tourism, highlighting its economic viability and support for activation. SEM analysis confirmed that perceived presence significantly influences user satisfaction and engagement, which in turn impact the intention to visit real destinations. These findings underscore virtual tourism's potential as a marketing, tourism promotion, and cultural preservation tool, contributing to the sustainable development of Saudi Arabia's tourism sector amidst global challenges
Developing MSMEs' competitive advantage through enterprise risk management and dynamic capabilities in Surabaya and Lampung
No full textMicro, Small, and Medium Enterprises (MSMEs) in Indonesia play a vital role in the economy, accounting for almost 99% of business units and contributing significantly to Gross Domestic Product (GDP) and employment. Amidst rapid market dynamics, especially after the COVID-19 pandemic, MSMEs face the challenge of managing risks and increasing dynamic capabilities to maintain competitive advantage. This study examines the effect of implementing Enterprise Risk Management (ERM) to increase the dynamic capabilities and competitive advantage of MSMEs in Surabaya and Lampung, Indonesia. The research methodology used a qualitative approach with in-depth interviews with the MSME owners. Data were analyzed using a three-level coding model to understand how ERM implementation affects MSME business strategies and decisions facing market threats and opportunities. The results of this study indicate that ERM implementation positively affects MSMEs' dynamic capabilities
Evaluating The Impacts of Speed Bumps on Pavement Condition
No full textSpeed bumps are a common traffic calming measure used to reduce vehicle speeds and improve safety. However, installing speed bumps without adherence to recommended standards can lead to additional problems, such as increased wear and tear on both vehicles and the road surface. This study investigates the impacts of speed bumps on Pavement Condition Index (PCI), focusing on surface roughness, cracking, and rutting. For this purpose, five asphalt-paved roads in Benue State were selected, including Makurdi–Aliede, Gboko-Ugbema, Makurdi-Gboko, Vandeikya-Tsar, and SRS–JOSTUM Southcore. Each site was divided into sections, and PCI values were calculated based on various distress types such as longitudinal cracking, block cracking, and rutting. The results indicated significant pavement deterioration near the speed bumps, with PCI values dropping to 18 on the Makurdi–Aliede road and to 10 on the Gboko-Ugbema road in sections directly after the bumps. Rutting was found to be the dominant distress type, particularly in the sections closest to the bumps. However, the effect of speed bumps on PCI values was minimal on the SRS–JOSTUM Southcore road, where traffic is lighter and dominated by smaller vehicles. These findings suggest that careful consideration should be given to the design and installation of speed bumps, especially on roads with high traffic volumes, to prevent accelerated pavement deterioration
Challenges and Advances in Boundary Layer Control on Aerodynamic Flow
No full textBoundary layer control (BLC) is essential for enhancing an aircraft's overall performance, stability, and efficiency. It contributes to increased lift generation, decreased drag, and improved flying stability when controlled appropriately. The review outlines the challenges and recent advances in BLC techniques within the context of aerodynamic flow. This is to provide a clear understanding of advantages and limitations associated with different BLC strategies. The traditional BLC techniques, including suction, blowing, and vortex generators, have limitations and drawbacks that can cause major repercussions. The review compares the modern developments in BLC while high-lighted key challenges such as energy cost, durability and scalability. Suggestions for future improvement include hybrid control systems that combine passive and active elements, model predictive control (MPC), artificial intelligence (AI), and real-time monitoring via the Internet of Things (IoT) to overcome these constraints. From this comparative and forward-looking approach, a better airplane performance and sustainability flying can be resulted through increasingly intelligent and effective BLC systems
An Economic Analysis of the Effectiveness of Relevant Market Delineation Methods in Abuse of Dominant Position Cases in India
No full textIn antitrust legislation, determining the relevant market is fundamental and a major determinant of how abuse of dominant position cases are decided. In the Indian context, the Competition Act lists factors to determine the relevant market. However, the relevant market delineation involves a lot of subjectivity, resulting in arbitrary decision-making and several case laws being testaments to the same. Further, the increasing variety in online marketplaces, the emergence of new e-commerce business models, and contemporary determinants of the relevant market (such as network effects) have made the issue even more complex and subjective. The paper argues that the mechanism adopted to delineate the relevant market is highly subjective and aims to highlight the issues associated with delineating abuse of dominant position cases in India. The approaches to determining the relevant market used in the contemporary Competition Commission of India order illustrate the challenges associated with these tests. It aims to propose an alternative to the current approaches, to reduce the arbitrariness and disparity in the adjudication of similar matters. The paper seeks to address whether the current method(s) of identifying the relevant market in abuse of dominant position cases are effective