MMU Press (Multimedia University)
Not a member yet
714 research outputs found
Sort by
Generative AI-based Meal Recommender System
No full textMaintaining a balanced diet is essential for overall well-being, yet many individuals face challenges in meal planning due to time constraints, limited nutritional knowledge, and difficulty aligning meals with personal dietary needs. Traditional meal recommender systems often rely on predefined plans or collaborative filtering techniques, limiting their adaptability and personalization. This study presents a generative AI-based Meal Recommender System utilizing Variational Autoencoders (VAEs) to generate personalized and nutritionally balanced meal plans. The system processes user inputs, such as dietary preferences, nutritional goals, and ingredient availability, to provide tailored recommendations. VAEs effectively uncover hidden dietary patterns and nutritional relationships within complex data, facilitating relevant and personalized meal suggestions. The system is trained and evaluated using two integrated datasets: one containing detailed nutritional information for complete meal plans, including attributes such as calories, protein, fats, carbohydrates, and sodium, and another listing individual dishes along with their names and user ratings. The meal plan dataset connects multiple dishes into structured daily meal schedules, while the dish dataset provides popularity and quality insights through user feedback. Together, these datasets enable the generation of personalized and nutritionally optimized meal recommendations. Experimental evaluation indicates strong ranking performance with a Normalized Discounted Cumulative Gain (NDCG) score of 0.963. However, Root Mean Square Error (RMSE), Mean Squared Error (MSE), and Mean Absolute Error (MAE) scores of 47.77, 2282.32, and 36.28, respectively, highlight potential areas for improving nutritional accuracy. A practical comparison with existing meal recommendation applications demonstrates the VAE model’s advantages in terms of personalization, nutritional fine-tuning, and recommendation diversity. The research contributes to AI-driven nutrition planning, healthcare, and fitness, offering a scalable and intelligent solution for personalized dietary recommendations
Identifying the Barriers to Digital Financial Inclusion in The Most Financially Excluded Country Using Machine Learning Algorithm
No full textDespite the call of digital financial services (DFS) to improve inclusive growth and reduce poverty, the adoption of DFS remains low in Nigeria. The objective of this study is to examine the barriers of ability, access and usage of DFS in Nigeria. This study uses secondary data Global Findex year 2017 and year 2021 to predict the socioeconomic factors on the target variables of DFS (ability, access and usage). Using a machine learning (ML) algorithm, namely the J48 decision tree in the Waikato Environment for Knowledge Analysis (WEKA) software, this study analyses the predictive strength of variables such as gender, education, income quintile, employment status, and urbanicity in determining ability, access to and usage of DFS. The main findings from the results show that the J48 decision tree demonstrates improvement in correctly classifying instances for year 2017 data to the year 2021 data. The root nodes for all sets of data show that education is the main predictor for DFS. The first-level split is gender for DFS when the target variables are ability and usage but is age when the target variable is access. Results show that education is the main barrier of DFS whereas gender and age are the secondary impediments to the adoption of DFS. Policymakers can benefit from the findings of this study to design targeted interventions—such as increasing their education level and organizing more digital financial literacy programs to accelerate DFS adoption among marginalized groups. The novelty of this study is to utilize a ML algorithm to identify the barriers of DFS and its accuracy rate has increased from the results of using the year 2017 data to the year 2021 data. By exploring key determinants through ML, this study contributes to the broader agenda of financial inclusion and promotes the accomplishment of sustainable development goals
The Role of Electroencephalography in Advancing Sleep Research
No full textElectroencephalography (EEG) is fundamental in sleep research, providing critical insights into cerebral activity and significantly contributing to the diagnosis of sleep disorders. This study examines recent progress in EEG-based sleep research, emphasizing cutting-edge methods for sleep staging and disease identification. The amalgamation of machine learning and deep learning methodologies, encompassing hybrid models such as CNN-LSTM, has markedly improved the precision of sleep stage categorization and automated analysis. Enhancements in signal quality and dependability, especially by improvements in artifact removal methods like wavelet-enhanced independent component analysis (ICA), have further advanced these developments. The implementation of multimodal strategies, wearable EEG technology, and AI-enhanced systems has broadened the sphere of sleep monitoring beyond clinical environments, rendering it more accessible and individualized. This article examines the use of EEG in detecting sleep disorders, including insomnia, obstructive sleep apnea, and narcolepsy, by identifying biomarkers and abnormalities in sleep architecture. Emerging research underlines the promise of clinical EEG, marking it as a transformational tool for both study and therapy. Nonetheless, obstacles persist in domains such as noise reduction, biomarker standardization, and scalability. Future directions include merging EEG with imaging modalities like fMRI, developing wearable technology, and employing advanced AI for individualized sleep health management. In particular, EEG is highlighted as a transformational and promising tool for promoting sleep medicine through novel, accessible, and effective solutions.
Manuscript received: 5 Jan 2025 | Revised: 10 Feb 2025 | Accepted: 18 Feb 2025 | Published: 31 Mar 202
Chaos Synchronization of the Lu System Using Single-Variable Feedback
No full textThis paper explores a simple yet effective way to synchronize the chaotic Lü system using just one variable from the master system. Rather than relying on full-state observation or advanced nonlinear control, the method uses a straightforward linear feedback approach and takes advantage of the inherent stability in cascade-connected systems to achieve synchronization. One of the main strengths of this approach is its efficiency. By transmitting only a single state variable, it keeps communication demands low—something that’s especially helpful in real-time applications or when resources are limited. Another benefit is that the method doesn’t depend on knowing the bounds of the master system’s trajectories in advance, which makes it more flexible for systems that are unpredictable or constantly changing. The controller itself is also relatively simple to put into practice, avoiding the complexity often seen in other synchronization methods. The approach is backed by solid theoretical analysis, and simulation results using MATLAB show that it works well in practice. Overall, this method offers a lightweight and practical solution for chaos synchronization—ideal for situations where minimal data and easy implementation are key.
Manuscript received:16 Feb 2025 | Revised: 16 Apr 2025 | Accepted: 1 May 2025 | Published: 30 Jul 202
Improved Lyapunov Functional for Stability Analysis in Delay-Differential Systems
No full textThis paper explores the stability of differential systems influenced by time delays, with a specific focus on situations where these delays change over time. Such systems often present analytical challenges due to the unpredictable nature of the delays. To tackle this, we introduce a new form of Lyapunov–Krasovskii functional, which leads to a refined condition for stability that depends directly on the characteristics of the delay. This condition is formulated using Linear Matrix Inequalities (LMIs), which offer a practical way to assess stability while maintaining a solid theoretical foundation. By modeling the effects of time-varying delays more accurately, the method contributes both to a deeper understanding of how such delays affect system behavior and to more reliable tools for analyzing systems where delays are a built-in feature that cannot be ignored.
Manuscript received:23 Feb 2025 | Revised: 16 Apr 2025 | Accepted: 29 Apr 2025 | Published: 30 Jul 202
Exploring the Experiences and Challenges of Online Learning at a Private University in Malaysia: DOI: https://doi.org/10.33093/ijomfa.2025.6.1.10
No full textThis study explores online learning experiences, focusing on their advantages and disadvantages through a qualitative analysis of responses from 30 students at a private institution in Malaysia. The data was collected to gain insight into students' positive impacts and challenges during online learning. The study identified key positive impacts of online learning, including flexibility and accessibility, which allowed students to attend classes from any location and manage their schedules effectively. Students appreciated the opportunity to review recorded lectures and access various online resources. However, the research also highlighted significant negative impacts, such as feelings of isolation, technical issues like unstable internet connections, and challenges with unfamiliar digital platforms. The absence of a structured learning environment negatively impacted student focus and motivation, while inadequate support and instructor communication further diminished engagement and satisfaction. The findings suggest that while online learning offers substantial advantages regarding convenience and resource availability, critical challenges must be addressed. Strategies recommended include improving technical infrastructure, fostering interactive and collaborative online environments, and enhancing support systems for students to mitigate the negative aspects of online learning. This study provides a nuanced understanding of the varied experiences of online learning, offering valuable insights into the strengths and weaknesses of this educational mode. The recommendations presented aim to enhance the overall student experience in online learning environments
A Critical Review of Theory of Planned Behavior in Knowledge Payment: DOI: https://doi.org/10.33093/ijomfa.2025.6.2.4
No full textThe Theory of Planned Behavior (TPB) is a widely applied theoretical framework for predicting individual intentions and behaviors. However, its application in the knowledge payment domain remains limited. Existing studies primarily focus on TPB’s three core constructs while overlooking emerging factors. Additionally, most studies rely on quantitative methods, particularly cross-sectional surveys, lacking longitudinal and experimental research, which may result in an incomplete understanding of consumer knowledge payment behavior. This study utilizes a Systematic Literature Review (SLR) methodology to thoroughly examine the current research based on the TPB within the domain of knowledge payment. A systematic search method was employed to gather pertinent research from prominent academic databases, accompanied by stringent inclusion and exclusion criteria to guarantee the representativeness and credibility of the chosen literature. Additionally, qualitative content analysis and knowledge mapping techniques were applied to synthesize key findings and identify potential theoretical gaps. The findings suggest that incorporating trust, motivation, and electronic word-of-mouth (e-WOM) can enhance the explanatory power of TPB in knowledge payment research. Moreover, adopting longitudinal studies, experimental designs, and big data analytics can improve the robustness and predictive capabilities of future research. While this study provides a theoretical expansion framework, further empirical validation is required. Future research should integrate interdisciplinary approaches, such as psychology, behavioral economics, and data science, to further enrich TPB's theoretical and practical significance in knowledge payment studies
A study of online grocery shopping behaviour in Malaysia
No full textThe Malaysian e-commerce industry has been growing; however, online grocery shopping is still underpenetrated in Malaysia. This study investigated the factors affecting online grocery shopping behaviour in Malaysia. This study integrated the Technology Acceptance Model (TAM) and Theory of Planned Behaviour (TPB) variables with price as an additional factor. Data were collected through a survey involving 344 Malaysians who were at least 18 years old and had an online grocery shopping experience. SPSS statistical software was used to analyse the data. It was found that attitude, subjective norm, and perceived behavioural control have significant positive relationships with online grocery shopping intention, which further positively influences online grocery shopping behaviour. Perceived usefulness, perceived ease of use, and price have insignificant associations with online grocery shopping intention. The study provides useful information and implications for academics and grocers regarding the factors affecting online grocery shopping behaviour in Malaysia
Key determinants of rental rates for A-grade office space in the Colombo-Central Business District: A tenants’ perspective
No full textProperty investors and tenants face complicated decision-making due to rent variations among purpose-built office buildings in the same market. While rental discrepancies are accepted as normative across economies, recent trends show the Asian office market experiencing notable growth and instability. This trend is also observed in Colombo's Central Business District (CBD), and thus far, a comprehensive analysis of the drivers behind the fluctuations is lacking. This study aims to fill this gap by examining the determinants of rental rates for A-grade office spaces in Colombo from tenants' perspectives through market research. Factors such as building age, occupancy restrictions, maintenance costs, unit size, and additional and green features emerge as significant influencers while building brand and additional and green features play a moderating role. The study’s findings contribute to the growing body of knowledge that can be used to develop and sustain a healthier office market industry
Mesh Convergence Analysis on The Aerodynamic Performance of A Sedan Vehicle
No full textThis article performs a comprehensive mesh convergence analysis on the aerodynamic efficiency of sedan vehicles. Leading CAD and CFD tools, such as CATIA and ANSYS Fluent are used to model the geometry and run the aerodynamic simulations. The simulations are centred on evaluating the drag coefficient (Cd) for four different sedan profiles. A full scale and half scale profile model configuration were used to analyse and assess the simulations’ impact precision and computational efficiency. A thorough mesh sensitivity investigation is conducted to determine the effect and influence of the element sizing on Cd precision and processing time. The finding points to an element size of 0.5 m, as the optimal choice offering a balance between computational resource efficacy and precision on aerodynamic predictions. The full-scale model reduces the computational time significantly without compromising accuracy hence making it the selected choice for the aerodynamic simulations. The findings of this study underscore the importance of selecting an appropriate mesh element size for vehicle aerodynamic model. This study recommends a 0.5 m element size for future aerodynamic evaluations, thereby improving the equilibrium between simulation accuracy and computational cost in sedan aerodynamics.
Manuscript Received: 27 January 2025, Accepted: 3 March 2025, Published: 15 March 2025, ORCiD: 0000-0001-9707-078