MMU Press (Multimedia University)
Not a member yet
714 research outputs found
Sort by
Real Time 3D Internal Building Directory Map
No full textGlobal Positioning System (GPS) is a famous technology around the world in identifying the real time precise location of any object with the assistance of satellites. The most common application of GPS is the use of outdoor maps. GPS offers efficient, scalable and cost-effective location services. However, this technology is not reliable when the position is in an indoor environment. The signal is very weak or totally lost due to signal attenuation and multipath effects. Among the indoor positioning technologies, WLAN is the most convenient and cost effective. In recent research, machine learning algorithms have become popular and utilized in wireless indoor positioning to achieve better performance. In this paper, different machine learning algorithms are employed to classify different positions in the real-world environment (e.g., Ixora Apartment - House and Multimedia University Malacca – FIST building). Received Signal Strength Indication (RSSI) is collected at each reference point. This data is then used to train the model with hyperparameter tuning. Based on the experiment result, Random Forest achieved 82% accuracy in Ixora Apartment and 84% accuracy in one of the buildings in Multimedia University Malacca. These results outperformed the other models, i.e., K-Nearest Neighbors (KNN) and Support Vector Machine (SVM)
HybridEval: An Improved Novel Hybrid Metric for Evaluation of Text Summarization
No full textThe present work re-evaluates the evaluation method for text summarization tasks. Two state-of-the-art assessment measures e.g., Recall-Oriented Understudy for Gisting Evaluation (ROUGE) and Bilingual Evaluation Understudy (BLEU) are discussed along with their limitations before presenting a novel evaluation metric. The evaluation scores are significantly different because of the length and vocabulary of the sentences, this suggests that the primary restriction is its inability to preserve the semantics and meaning of the sentences and consistent weight distribution over the whole sentence. To address this, the present work organizes the phrases into six different groups and to evaluate “text summarization” problems, a new hybrid approach (HybridEval) is proposed. Our approach uses a weighted sum of cosine scores from InferSent’s SentEval algorithms combined with original scores, achieving high accuracy. HybridEval outperforms existing state-of-the-art models by 10-15% in evaluation scores
Towards Analysable Chaos-based Cryptosystems: Constructing Difference Distribution Tables for Chaotic Maps
No full textChaos-based cryptography has yet to achieve practical, real-world applications despite extensive research. A major challenge is the difficulty in analysing the security of these cryptosystems, which often appear ad hoc in design. Unlike conventional cryptography, evaluating the security margins of chaos-based encryption against attacks such as differential cryptanalysis is complex. This paper introduces a straightforward approach of using chaotic maps in cryptographic algorithms in a way that facilitates cryptanalysis. We demonstrate how a chaos-based substitution function can be constructed using fixed-point representation, enabling the application of conventional cryptanalysis tools such as the difference distribution table. As a proof-of-concept, we apply our method to the logistic map, showing that differential properties vary based on the initial state and number of iterations. Our findings demonstrate the feasibility of designing analysable chaos-based cryptographic components with well-understood security margins
Development of Automated Attendance System Using Pretrained Deep Learning Models
No full textAbstract - Smart classroom enables better learning experience to the students and aid towards efficient campus' management. Many studies have shown positive correlation between attendance and student's performance, where the higher the attendance, the better the student's performance. Therefore, many higher learning institutions make class attendance compulsory and students' attendance are recorded. Technological solutions for an advanced attendance system such as face recognition is highly desirable. The authenticity of attendance can be ensured by using such solution. In this work, artificial intelligence based face recognition system is used for attendance recording system. The recognized face is used to confirm the presence of a student to the class. Six pretrained face recognition model are evaluated for the adoption in the system developed. The FaceNet, is adopted in this work with accuracy of more than 95%. The automation system is supported by IoT.
Manuscript received: 25 Nov 2023 | Revised: 11 Jan 2024 | Accepted: 12 March 2024 | Published: 30 Apr 202
The Neutrosophic Economic Order Quantity: Backlogged Shortages and Quality Issues: Neutrosophic EOQ
No full textThis paper investigates an economic order quantity with imperfect qualityitems that are backlogged in the neutrosophic sense.Defuzzification is done by implementingthe signed-distance approach.The objective is to determine the optimal inventory level and optimal backorder quantity that reduces the yearly total cost of the neutrosophic type.Numerical examples are produced to justify the output of the suggested models.
Manuscript received: 14 May 2024 | Revised: 16 June 2024 | Accepted: 12 July 2024 | Published: : 30 Sep 202
Forecasting PM2.5 Concentrations in Chiang Mai using Machine Learning Models
No full textParticulate matter 2.5 poses a significant threat to human life. Over the past decade, there has been a significant increase in the number of articles dedicated to studying and forecasting PM2.5 concentrations. Thailand, particularly Chiang Mai, has elevated levels of dangerous PM2.5 throughout the hot season. The primary objective of this study is to evaluate the efficacy of three widely used machine learning models, namely artificial neural network (ANN), long short-term memory network (LSTM), and convolutional neural network (CNN), in predicting the levels of PM2.5 particles in Chiang Mai. The raw data are obtained from the Pollution Control Department, Ministry of Natural Resources and Environment Thailand between January 2014 and June 2023, a total of 3,468 observations. We split the data into three sets namely, training, validation, and test sets. The criterion to evaluate three machine learning techniques is the median absolute error. The experimental results confirm that all three machine learning models provide similar movements of PM2.5 dust pollution. Moreover, the artificial neural network technique provides better results than the others regarding error measurement.
Manuscript received: 14 June 2024 | Revised: 2 Aug 2024 | Accepted: 28 Aug 2024 | Published: : 30 Sep 202
Review and Analysis of Mechanical Cutting Tools for Rubber Stamping
No full textRubber industry is one of the major industries in Malaysia. Rubber stamping machine is a machine that cuts rubber sheets into desired shapes and dimensions, facing challenges due to the elastic properties of rubber sheets. These challenges include long process time and non-identical dimension. This review paper focuses on the design of the rubber-stamping machine to address the challenges by reducing process time and producing identical dimensions products. The rubber-stamping machine was fabricated, and analysis was performed to verify its efficiency. The core of the designs is to ensure the user safety, friendliness, and increase productivity and product consistency. Based on the findings from existing studies, the review highlights significant improvements in machine design and operational efficiency. The paper also discusses the impact of these innovations on the competitiveness of rubber stamping operations and provides insights into future directions for research in mechanical design and automation systems. This review can be a crucial resource for developers and manufacturers looking to enhance the efficiency and product quality of rubber-stamping machines, contributing to the advancement of manufacturing practices in the rubber industry.
Manuscript received: 6 May 2024 | Revised: 15 July 2024 | Accepted: 13 Aug 2024 | Published: : 30 Sep 202
Collaborative Learning Management System with Analytical Insights: A Preliminary Study: DOI: https://doi.org/10.33093/ijomfa.2024.5.1.6
No full textThe mode of teaching and learning had been drastically changed over the decades. Therefore, one approach might not fit into all scenarios. Collaborative learning promotes collaboration between the students in completing given tasks with common goals. In this paper, problem statements were formed: (i) the collaboration between students and their teachers in the virtual learning environment has been at the bare minimum, (ii) the learning management system implemented has not been fully utilised with the data and information collected academically. Moreover, systematic literature review (SLR) is practised to investigate insights about collaborative learning, learning management system (LMS) and analytical approaches for student profiling. The aim of this paper is to address three research questions formed in the SLR: (i) What is the most commonly practised methodology for collaborative learning? (ii) What are the typical practised analytical methods and models for student profiling? and (iii) What factors influence students to use the learning management system? Besides, collaborative learning enables the students to conduct group discussions and assignments, promoting mutual interactions and creating knowledge amongst them. Additionally, the third-party LMS lacks synchronous chat feature. A student's profile grants educators valuable insights into the student's academic performance and learning progress. This information contributes to predicting the student’s performance with the assistance of analytical approaches applied. The applied analytical approaches provide useful information about the student’s learning behaviour, allowing the teachers to take adequate action. As a result, a conceptual framework is constructed with hypotheses formulated, reflecting the relations between each construct. Besides, a dedicated collaborative learning management system with machine learning capabilities is an ideal solution, tackling students’ collaboration among peers and between teachers with their academic performance and behaviour taken into account
Impact of Work From Home Factors on Employee Work Engagement: DOI: https://doi.org/10.33093/ijomfa.2024.5.2.2
No full textThe aim of the study is to examine the various work from home related factors which help in bringing about improved employee work engagement based on the work assigned to them. The study employed a quantitative research approach, positivism research philosophy, and case study research design. The study made use of 201 participants, with data collected through questionnaire and online survey tool (Google Form). Participants for the study were sampled from AmIT Global Solutions, AppCable Sdn Bhd, IWG 3.2, Regus Management Malaysia Sdn Bhd, Deventure Sdn Bhd, and Texas Instruments. Thethree hypotheses proposed in the study were examined using multiple regression analysis. The results show that work from home autonomy, safety, and convenience increase employee engagement levels. The findings implied that work from home when adopted and implemented in an effective manner, increases employee work engagement. The results also aligned with the assumption of Herzberg Two Factor theory which holds on to the impact of work from home autonomy, which is a motivational factor and the impact of work from home safety and convenience, which are hygiene factors. In the absence of both factors, employees are less engaged (disengaged). The study has a limitation of small sample size with quantitative research approach
The Impact of Social Media Advertising on Online Shopping Preferences in Nilai City, Malaysia: https://doi.org/10.33093/ijomfa.2024.5.2.4
No full textSocial media advertisements can influence consumers' purchasing preferences by impacting their awareness, attitude, trust, and intention towards the advertised products, services, or brands. This study aims to achieve two objectives: firstly, to determine the correlation between independent variables (security, privacy, product features, social influence, and promotion) and secondly, to examine the relationship between independent variables and dependent variables (online shopping purchasing preference among shoppers in Nilai). Convenience sampling was used to collect survey data, with questionnaires distributed through various online platforms to respondents residing in Nilai. A total of 272 responses were collected. The study utilized a Pearson correlation model and multiple linear regression to achieve the objectives. The R-squared value of 0.564 indicates that the model can explain almost half of the variability in the dependent variables. The results reveal no negative correlations among the independent variables. The weakest correlation observed is between promotion and product features at 0.392. Conversely, the strongest correlation is between security and privacy, with a coefficient of 0.703, indicating a significant influence of security on privacy. In the multiple linear regression model, four independent variables—security, product features, social influence, and promotion—significantly impact the dependent variable