MMU Press (Multimedia University)
Not a member yet
714 research outputs found
Sort by
Face and Facial Expressions Recognition System for Blind People Using ResNet50 Architecture and CNN
No full textMany blind individuals have difficulties in recognizing people’s facial expression which may impact their social interaction. With the recognition, the blind individuals can accurately interpret and respond to the emotions. There is a lack in the existing application with the combination of face and facial expressions recognition. The blind individuals have to rely on multiple applications to accomplish the same task, making it difficult and time-consuming for them to use. The paper aims to recognize faces and facial expressions for blind individuals and provides feedback in real-time. Three face detection algorithms of Haar Cascade Classifier, Dlib, and RetinaFace are compared. Dlib is chosen to process with Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM). It loads the pre-trained model, computes the HOG features, slide the window scanning at different scales, classify the windows using the SVM classifier, generate bounding boxes, and applying non-maximum suppression. ResNet50 architecture is employed to recognize face and Convolutional Neural Networks (CNN) is applied to recognize facial expression. The training accuracy is 70% and validation accuracy is 60%
Kesepakatan Pakar Terhadap Reka Bentuk Aplikasi Mudahalih I-Jawi Menggunakan Kaedah Fuzzy Delphi: (Expert Consensus on The Design of I-Jawi Mobile Application Using Fuzzy Delphi Method)
No full textThe issue of Jawi learning in schools is frequently raised in Malaysia because many students are unable to read and write Jawi effectively. Factors contributing to this problem include a lack of teaching materials, insufficient curriculum, and a lack of practice in the classroom. Students also lack interest in learning Jawi as they perceive it as irrelevant in the modern era. To address this problem, educators are seen as needing to enhance the quality of teaching materials and incorporate more engaging activities into the curriculum. The use of modern technology, such as language learning applications, can also be employed to foster students' interest in learning Jawi. This study aims to identify the appropriate elements in developing Jawi applications and explain the process of developing the i-Jawi application for use in Jawi learning, especially at the preschool level. The Fuzzy Delphi Method (FDM) is utilized to obtain consensus from 13 experts regarding the necessary elements for the application. This study employs a 7-point Likert scale divided into two main sections: Part I - expert demographic information, and Part II - elements found in the i-JAWI APP, including content, text, graphics, audio, and usability. The data obtained is analyzed using Fuzzy Triangular Numbering, while rankings are determined through the Defuzzification Process. The results of the study indicate that the design phase meets FDM criteria, with a threshold value (d) of less than 0.2, expert consensus exceeding 75%, and a fuzzy score (A) exceeding 0.5. Overall, it can be concluded that the development of the i-JAWI APP based on the agreed-upon elements by the experts is highly significant in aiding Jawi learning, particularly at the preschool level.
ABSTRAK
Masalah pembelajaran Jawi di sekolah sering dibangkitkan di Malaysia kerana ramai pelajar tidak dapat membaca dan menulis Jawi dengan baik. Faktor yang menyebabkan masalah ini termasuk kekurangan bahan bantu mengajar, kurikulum yang kurang mencukupi, dan kurangnya latihan dalam kelas. Pelajar juga kurang berminat untuk mempelajari Jawi kerana menganggap bahawa Jawi tidak penting dalam zaman moden. Untuk mengatasi masalah ini, para pendidik dilihat perlu meningkatkan kualiti bahan bantu mengajar dan menambahkan lebih banyak aktiviti menarik dalam kurikulum. Penggunaan teknologi moden seperti aplikasi pembelajaran bahasa juga boleh digunakan untuk menggalakkan minat pelajar dalam mempelajari Jawi. Kajian ini bertujuan unutk mengenal pasti elemen yang sesuai dalam membina aplikasi Jawi dan menjelaskan proses pembinaan aplikasi i-Jawi untuk digunakan dalam pembelajaran Jawi khususnya di peringkat prasekolah. Fuzzy Delphi Method (FDM) digunakan untuk mendapatkan kesepakatan daripada 13 orang pakar mengenai elemen-elemen yang perlu ada dalam aplikasi tersebut. Kajian ini menggunakan skala likert 7 yang terbahagi kepada dua bahagian utama iaitu Bahagian I: maklumat demografi pakar dan Bahagian II: elemen-elemen yang terdapat dalam i-JAWI APP iaitu elemen isi kandungan, teks, grafik, audio dan kemudahan. Data yang diperoleh dianalisis menggunakan Pernomboran Segi Tiga Fuzzy, sementara ranking pula ditetapkan melalui proses Defuzzication. Hasil kajian menunjukkan bahawa fasa reka bentuk ini telah memenuhi syarat-syarat FDM dengan nilai treshold (d) kurang daripada 0.2, peratus kesepakatan pakar melebihi 75% dan nilai skor fuzzy (A) melebihi 0.5. Secara keseluruhannya, dapat disimpulkan bahawa pembinaan aplikasi i-JAWI APP berdasarkan elemen-elemen yang telah dipersetujui pakar ini amat signifikan dalam membantu pembelajaran Jawi khususnya di peringkat prasekolah. Sebagai cadangan, pengkaji-pengkaji pada masa akan datang disarankan untuk mengkaji elemen-elemen lain dan melibatkan pakar-pakar dari pelbagai latar belakang dengan menggunakan metod Fuzzy Delphi ini
Building Cyber Resilience: Key Factors for Enhancing Organizational Cyber Security
No full textThe increasingly pervasive influence of technology on a global scale, coupled with the accelerating pace of organizations operating in cyberspace, has intensified the need for adequate protection against the risks posed by cyber threats. This paper aims to identify cyber resilience management attributes that can enable organizations to sustain and continually adapt in the face of evolving cyber risks and threats. The researcher explores the intersections between cybersecurity and resilience by reviewing existing frameworks, models, studies, and surveys. This study establishes the attributes of resilience with the integration of resilience theory and security theory, along with their position in the cyber domains. By proposing a converged model with fundamental factors for attaining cyber resilience, this study offers a novel contribution to cyber security management
A SWOT Analysis With A Digital Transformation: A Case Study For Hospitals In The Pharmaceutical Supply Chain
No full textThe pharmaceutical business meets all requirements for a complicated and tightly regulated sector, including multi-stakeholder participation. The objective is to study digital transformation strategies in hospitals to improve the safety and convenience of pharmaceutical services when providing healthcare services. In this study, a SWOT analysis is performed to identify strengths, weaknesses, opportunities, and threats with a digital transformation case study for hospitals in the pharmaceutical supply chain in Ho Chi Minh City, Vietnam. Information source for SWOT analysis of published articles and reports in the following aspects: Digital transformation environment of hospitals in the global pharmaceutical supply chain; new technology with reliability, safety, and security; Culture with human resources and customer experience; Laws and policies. The outcomes of the SWOT analysis highlight the opportunities, threats, weaknesses, and opportunities. The SWOT matrix and pertinent strategies should be used by hospitals in the pharmaceutical supply chain to maximize their strengths and opportunities while minimizing risks or managing their weaknesses and issues with the digital transformation. Finally, decision-makers and stakeholders are urged to apply the lessons learned from SWOT analysis and planning to the hospital's role in building a reliable pharmaceutical supply chain. The consequences of this study include integrating potent new technology, revising methods, and redesigning organizational structure in order to alter and modernize a pharmaceutical supply chain operation
RFID and Facemask Detector Attendance Monitoring System
No full textThe article emphasizes the significance of attendance monitoring for safety during the COVID-19 pandemic and proposes an RFID-based solution coupled with face mask detection systems to address attendance challenges. The project aims to create a contactless monitoring system that ensures face mask compliance and provides real-time attendance data for data-driven decision-making. The article also covers various technology-related topics, including the historical usage of face masks, the development of attendance systems using biometric identification and electronic methods, and facial recognition technology's applications in surveillance and finance. It introduces XAMPP, a user-friendly web application development and testing tool, and presents an overview of the IC7408 chip used in digital electronics. The study's key findings show that increasing sample size and optimizing epochs and batch size improve face mask detection accuracy, while RFID scanner distance affects scanning delay and accuracy. The research provides valuable insights into the performance of the proposed attendance monitoring system.
Manuscript received: 23 June 2023 | Revised: 15 July 2023 | Accepted: 10 August 2023 | Published: 30 September 202
Neighbourly Edge Irregularity on Interval-valued Pythagorean Neutrosophic Graph
No full textInterval-Valued Pythagorean Neutrosophic Graph (IVPNG) comprises independent and dependent membership elements of interval entries. This paperdemonstrates some kinds of irregular properties on IVPNG like neighbourly irregular, neighbourly totally irregular, strongly irregular, strongly totally irregular, highly irregular,and highly totally irregular. On certain conditions, neighbourly edge irregular and neighbourly edge totally irregular IVPNG satisfy these irregular properties and vice versa.
Manuscript received: 13 May 2023 | Revised: 28 July 2023 | Accepted: 10 August 2023 | Published: 30 September 202
Mental Health Problems Prediction Using Machine Learning Techniques
No full textMental health problems encompass a range of conditions that can impact an individual's emotions and behaviors. The conventional methods of mental illness prediction often suffer from the issue of either over-detection or under-detection and the time-consuming manual review process of patients' data during screening sessions. Therefore, this research aims to utilize machine learning techniques to predict mental health problems, complementing the traditional clinical screening and diagnosis process. The proposed models in this project: Logistic Regression, K-Nearest Neighbors, and Random Forest leverage relevant factors from the dataset concerning mental health survey published by Open Source Mental Disorders in 2014 to predict mental health problems. Feature selection and hyperparameter fine-tuning are employed to identify the factors contributing to mental health problems and enhance the performance of the models. The evaluation of these models is measured using accuracy, recall, precision, F1 score, and AUROC. Experimental evaluation results indicated that the Random Forest model utilizing hyperparameters derived from the RandomizedSearchCV method outperforms during model selection using cross-validation. When predicting test set data, it exhibits a good generalization with an accuracy of 83.23%, recall of 89.87%, precision of 78.02%, F1 score of 83.53%, and AUROC of 83.57%.
Manuscript received: 13 May 2023 | Revised: 2 August 2023 | Accepted: 17 August 2023 |Published: 30 September 2023
Knowledge Mapping of Board Governance Research: A Visual Analysis Using CiteSpace: DOI: https://doi.org/10.33093/ijomfa.2023.4.2.10
No full textBased on the bibliometric and visualization analysis of relevant board governance research literature from 2003 to 2022, this study summarizes and outlines the knowledge structure, hot topics, and future research directions in the field of board governance. The research findings indicate that the publication volume in the field of board governance has shown an exponential growth trend, which highlights the increasing importance and research demand in this area. Company performance has become a critical topic in the field of board governance research. Furthermore, collaboration and communication among research institutions promote knowledge sharing and enhance the quality of board governance research. Through keyword clustering and burst analysis, corporate governance, ownership, and firm performance are identified as crucial keywords in the field of board governance, highlighting researchers' emphasis on improving corporate governance systems, optimizing ownership structures, and enhancing firm performance. Moreover, gender diversity, boards of directors, and corporate governance are identified as research hotspots, indicating scholars' attention to board structures and institutional designs, as well as the value of female directors' participation in board governance. Finally, sustainable development and green governance are recognized as frontier trends in board governance research, underscoring the importance placed on corporate social responsibility and environmental impact, as well as the role of boards in driving sustainable development. These research findings provide important insights for academia, practitioners, and policymakers, driving the development of board governance theories and continuous improvements in practice to achieve sustainable development goals for companies
Social entrepreneurship for young people with disabilities: A conceptual analysis
No full textEmployment is one of the most basic needs of everyone, including people with disabilities (PWD). However, the numerous obstacles faced by PWD limit their ability to actively participate in the labour market, become economically self-sufficient, and contribute to national economic development. In general, PWD all over the world face a high risk of unemployment. Therefore, this study explored the function of social entrepreneurship in eradicating unemployment among young PWD. This research also emphasised the challenges experienced by PWD in securing employment in Malaysia. Among the issues highlighted are the negative attitudes of employers towards PWD and how employers could adopt the social entrepreneurship perspective. The systematic review method was used to examine the previous literature to accomplish the highlighted purpose and seek answer to the research questions. The literature review revealed problems of unemployment among young PWD. Hence, the improvement of young PWD’s employment have to be focused systematically by taking into account the social entrepreneurship’s perspective. This study is expected to provide a significant contribution to the knowledge on employment of young PWD and would increase the number of their participation in the workplaces
Factors Affecting Customer Satisfaction on Online Shopping: An Empirical Study : DOI: https://doi.org/10.33093/ijomfa.2023.4.2.4
No full textThis paper examines the effect of website layout, privacy and security, customer experience, customer service, and product delivery service on online shopping satisfaction in Malaysia. With swift economic development and advanced digital technology infrastructure, online shopping in Malaysia is undergoing transformation. Businesses are advised to change their business operation towards digitalization. In this study, the survey link containing the questionnaire was sent to 300 respondents randomly via several online social media platforms. As a result, 257 responses were received with 85.67% of the response rate. Based on the findings from the multiple regression analysis, website design, customer experience, and product delivery service all had a significant impact on online shopping satisfaction. Further investigation also revealed that website layout was the most important determinant of satisfaction. Therefore, it is critical for online retailers to better understand their online customers' preferences to create better customer values that lead to customer satisfaction and the development of long-term profitable relationships