MMU Press (Multimedia University)
Not a member yet
714 research outputs found
Sort by
Smart Local Energy Exchange Systems Leveraging The Internet of Things for Decentralized Energy Management
No full textDuring the Industrial Revolution, human society depended on natural energy flows, animal power, and biomass for heat and mechanical energy, with limited energy consumption per capita. However, between 1850 and 2005, global energy production and consumption surged as industrialized societies shifted from traditional energy sources such as wood, crop waste, and biomass to commercial energy forms like natural gas, oil, and electricity. While biomass still accounts for about 10% of global energy use, its primary contribution remains in developing regions. Over the past 200 years, energy consumption patterns have evolved in four key stages: (1) the rise of coal-powered steam engines in the late 19th century, (2) the widespread adoption of internal combustion engines and electric power generation in the first half of the 20th century, (3) the shift towards cleaner energy sources, particularly for electricity generation, and (4) the growing emphasis on reducing pollution and enhancing energy efficiency, especially in smart homes and cities. Despite advancements, the large-scale implementation of energy-efficient technologies is limited by the need for low-cost, easily deployable solutions. Additionally, the vast amount of data generated by smart energy systems presents significant challenges in data storage, organization, and analysis. This paper examines the historical evolution of energy consumption, its impact on economic development, and the ongoing shift toward sustainable energy practices
User Behaviour Prediction in E-Commerce Using Logistic Regression
No full textFrom a psychological perspective, human behaviour reflects underlying thoughts and decision-making patterns, for example, consumer behaviour may correlate with the purchase decisions. In the fast-evolving e-commerce industry, predicting user behaviour is essential for enhancing marketing strategies, improving customer experiences, and increasing sales. However, traditional heuristic (e.g. market basket analysis) approaches to analyse buyer behaviour are often rigid and fail to adapt to complex consumer interactions. This research work develops a predictive model that analyses user behaviour based on data such as historical purchasing patterns and demographic attributes. Based on a review of previous studies, Logistic Regression (LR) is utilized as the primary machine learning algorithm to estimate the likelihood of user performing specific actions including churning and conversion rate. The dataset undergoes preprocessing steps, including data cleaning, feature selection, and normalization, to enhance model accuracy. Evaluation metrics, including accuracy, confusion matrix, precision, recall and F1-Score are used to ensure the model’s performance is reliable and effective. Unlike traditional heuristic approaches, this data-driven method offers a scalable and adaptable solution for behaviour prediction. The findings of this research have the potential to revolutionize e-commerce by providing businesses with actionable insights into consumer behaviour. By leveraging predictive analytics, companies can implement targeted marketing campaigns, personalize recommendations, and improve customer retention strategies. Additionally, this study highlights the significance of behavioural modelling in detecting early signs of customer churn, allowing businesses to take proactive measures. Ultimately, this research contributes to the growing field of data-driven decision-making, offering a scalable and adaptable solution for understanding and predicting user behaviour in online shopping environments
The Application of Hybrid Renewable Energy Systems
No full textHybrid Renewable Energy Systems (HRES) integrate solar, wind, and other renewable energy to deliver more sustainable, dependable, and affordable energy for rural, urban, and industrial areas. Based on 20 articles/journal from 2020–2025 that were taken from Google Scholar, IEEE Xplore, and Scopus, this paper evaluates HRES applications, technologies, barriers, and future development. Storage will increase to 204.47 GW, when solar and wind power dominate with capacities increased by 937% and 118% throughout 2014 to 2020. Optimization tools like HOMER Pro and Particle Swarm Optimization (PSO) can reach up to 1.10% error in energy predictions. HRES can reduce costs and emissions by 86% (solar) and 61% (wind) by prioritizing renewable energies usage. Regulatory loopholes, intermittency, and high initial costs are some of the challenges in the application of HRES. MATLAB visualizations show capacity trends and cost reductions, which supports economic viability. Examples that demonstrate sustainability and highlight reliability include mining activities in Iran and microgrids in Makkovik, Canada. This paper identifies HRES based on the literature, AI, IoT, and policy incentives. Future advancements must go beyond technical constrains and standardize regulations to scale HRES for global energy transformations, smart cities, mining industries, and resilient communities.
Manuscript received: 16 Jun 2025 | Revised: 29 Jul 2025 | Accepted: 10 Aug 2025 | Published: 30 Nov 202
Music Made by AI: How Does Indonesian Copyright Law Address This Issue?
No full textThe development of AI has enabled the creation of musical works without direct human involvement. This phenomenon poses new challenges for copyright law in Indonesia. This research aims to assess the legal arrangements related to copyright, music, and AI in the Indonesian legal system. Furthermore, this research will also formulate the legal protection of AI-produced music. The research method used is normative law with legislation, cases, and comparative studies. The results show that Copyright Law in Indonesia has not explicitly regulated the process of creating musical works by AI but still focuses on creations produced by humans. The absence of regulations creates legal uncertainty for music industry players and AI developers. Therefore, the formulation of progressive and adaptive legal policies is needed to provide legal certainty and copyright protection for musical works that involve AI technology in the creation process
Artificial Intelligence in Blockchain-Based Energy Markets: Regulatory and Technological Perspectives
No full textThe move to phase out fossil fuels has become a global priority, driven by the pressing need to address climate change and promote sustainable development. This shift is transforming energy systems from traditional centralised models into dynamic peer-to-peer (P2P) marketplaces. In these new ecosystems, prosumers emerge as active participants who autonomously trade energy while leveraging distributed energy resources, fundamentally changing how we produce and consume power. At the forefront of this shift is the powerful combination of artificial intelligence (AI) and blockchain technology in P2P energy trading. Together, these innovations are reshaping decentralised energy systems, creating more scalable and resilient energy networks that grow from the ground up. This raises a crucial question: Can AI in blockchain-enabled peer-to-peer energy trading systems bring revolutionary transformation in decarbonising energy landscapes? As we explore this possibility, we uncover the remarkable potential of these technologies to fundamentally alter the energy sector while acknowledging both their promise and their challenges. The rapid progress of AI in this field presents a modern version of the tortoise and hare paradox. While technological innovation races ahead at breakneck speed, regulatory frameworks struggle to keep pace, creating growing gaps between what is technically possible and what is legally permitted. 
A Study of Multimodal Metaphors in the Chinese Environmental Documentary, Behemoth
No full textThis study examines how the environmental documentary Behemoth, directed by Zhao Liang, uses metaphor to represent environmental degradation in China, particularly in regions like Inner Mongolia and Shanxi, where industrialization and coal mining have caused severe pollution. Despite its serious impact on public health, awareness among the population remains limited due to institutional constraints that restrict open communication. The objective of this study is to analyse how the documentary uses multimodal metaphors to communicate environmental issues and raise awareness. Drawing on Forceville’s multimodal metaphor theory and using a textual analysis method with coding adapted from Fan’s multimodal metaphor coding sheet, the study identifies how visual, verbal, and textual metaphors are strategically employed. The findings show that Behemoth uses split images, orientation metaphors (e.g., good vs. evil), and metaphors of life (lambs, sheep, coal miners), hope, and religion to emphasize the severity of ecological destruction and position humans as its root cause. These metaphors play a critical role in helping audiences comprehend the scale and impact of environmental crises, suggesting that metaphorical imagery is a powerful tool for environmental communication
Deconstructing Surah At-Tahrim, Verse 9: Boundaries of Harsh Preaching in the Case of Abuya Mama Ghufron on YouTube
No full textThis study examines the interpretation of Surah At-Tahrim, verse 9 through a deconstructive lens, addressing the growing prevalence of firm preaching in contemporary Islamic discourse, particularly in selected sermons delivered on YouTube. The core issue lies in the perceived dissonance between traditional Islamic principles of preaching, which emphasise wisdom and compassion, and the rise of more rigid, confrontational da'wah styles that may risk shaping public perceptions of Islam negatively. The study critically explores how classical Qur’anic exegesis, particularly that of Ibn Kathir, conceptualises firmness in preaching and contrasts this with rhetorical strategies observed in modern digital sermons. Using Jacques Derrida’s theory of deconstruction and a thematic interpretive method, this research analyses the content, language, and theological implications of these sermons within the framework of Qur’anic hermeneutics. The findings reveal that while classical exegesis affirms the necessity of firmness in defending Islamic values, it also incorporates principles of contextual wisdom and justice. These elements are not always consistently reflected in certain contemporary preaching approaches. This study contributes to the field of Islamic communication by offering a contextual critique of digital religious expression and proposing a balanced ethical framework for da'wah in pluralistic societies
Dynamic Job Recommendation by Profiling Undergraduates Academic Performances
No full textJob-seeking tasks are always challenging. Often, job recommendation systems require human intervention in the job-seeking process. Therefore, the study focuses on recommendation of most relevant job sectors and prioritizing companies based on a student’s profile. The objectives of this study are: (i) to identify important features that optimize job recommendation, (ii) to construct a predictive model that recommends most relevant job sectors, and (iii) to recommend companies by computing the similarity between student and job profiles. In this study, the dataset was collected from Graduate Tracer Study from a university. Additionally, a job dataset was collected to extend the training dataset. As a result, both students and job profiles are used in this study. To enhance the accuracy, several models have been utilized for classifying job sector. This includes both hierarchical and single level classification. In hierarchical classification, Random Forest and Categorical Boosting were utilized; while in single level classification, a total of 9 different machine learning models were utilized. To assess the model’s performance, the metrics such as accuracy, weighted precision, weighted recall, and weighted f1-socre, were utilized. The finding shows that Hierarchical Classification outperforms Single Level Classification, with evaluation metrics ranging from approximately 72% to 76%, whereas Single Level Classification achieved around 58% to 62%. In conclusion, the integration of BorutaShap with Bidirectional Encoder Representation Transformers with 12 transformed layers enhances the performance of Hierarchical Classification, with the highest evaluation metrics around 75%. To recommend companies, a predefined rule is utilized to filter relevant companies, then, the similarity of the companies is measured using Cosine Similarity after transforming both student and company information using Bidirectional Encoder Representation Transformers with 12 transformed layers
Lightweight String Similarity Approaches for Duplicate Detection in Academic Titles
No full textThis study addresses the critical challenge of detecting duplicate final year project (FYP) titles in academic institutions, where minor variations like reordering, synonyms, and paraphrasing often obscure plagiarism. We systematically evaluate four string similarity algorithms - Jaro-Winkler, Levenshtein Edit Distance, TF-IDF with Cosine Similarity, and Jaccard Similarity - using a synthetic dataset of 250 title pairs representing common duplication patterns. Our experiments reveal that character-based methods (Jaro-Winkler and Edit Distance) achieve perfect detection (F1-score=1.0) for literal matches, including typographical variations and phrase reordering. At the same time, TF-IDF demonstrates strong semantic capability (F1-score=0.95), albeit with some false positives. Jaccard Similarity performs poorly (Recall=0.40) due to its inability to handle paraphrased content. The analysis of score distributions show a clear separation between duplicates and non-duplicates for character-based approaches, compared to significant overlap in set-based methods. Based on these findings, we propose a practical two-stage screening framework: initial high-confidence filtering using Jaro-Winkler (threshold>0.9) followed by semantic validation with TF-IDF (threshold>0.8). This hybrid approach offers institutions an effective balance between accuracy and computational efficiency for title screening. This study contributes by demonstrating how existing string similarity techniques can be orchestrated into a lightweight, two-stage screening framework tailored for academic title duplication, balancing accuracy with deployment feasibility in institutional settings. Future work should explore multilingual extensions and validation with real-world title datasets to further enhance the practical applicability of these findings