Nazatul Aini Abd Majid

Malay songket motifs are a vital component of Malaysia’s intangible cultural heritage, characterized by intricate visual designs and deep cultural symbolism. However, the practical digital preservation and retrieval of these motifs present challenges, particularly due to the rotational variations typical in textile imagery. This study introduces a novel Content-Based Image Retrieval (CBIR) model that integrates Principal Component Analysis (PCA) for feature extraction and Quadratic Geometric Distance (QGD) for measuring similarity. To evaluate the model’s performance, a curated dataset comprising 413 original images and 4956 synthetically rotated songket motif images was utilized. The retrieval system featured metadata-driven preprocessing, dimensionality reduction, and multi-angle similarity assessment to address the issue of rotational invariance comprehensively. Quantitative evaluations using precision, recall, and F-measure metrics demonstrated that the proposed PCAQGD + Rotation technique achieved a mean F-measure of 59.72%, surpassing four benchmark retrieval methods. These findings confirm the model’s capability to accurately retrieve relevant motifs across varying orientations, thus supporting cultural heritage preservation efforts. The integration of PCA and QGD techniques effectively narrows the semantic gap between machine perception and human interpretation of motif designs. Future research should focus on expanding motif datasets and incorporating deep learning approaches to enhance retrieval precision, scalability, and applicability within larger national heritage repositories.

Augmented Reality (AR) offers potential benefits in assembly training, yet there is a scarcity of research on knowledge retention when utilizing 3D model and animation overlays through Mobile Augmented Reality (MAR). This study investigates the influence of MAR applications, leveraging the signaling principle through 3D animated models, on knowledge gain and retention in a complex Internet of Things (IoT) assembly task. In this regard, this study developed a MAR framework and application to facilitate IoT assembly training. A comparative study was conducted with 40 participants, equally distributed between the MAR and paper manual groups based on prior knowledge and AR familiarity. The evaluation consisted of three phases: a pre‐test, an immediate post‐test, and a delayed post‐test. Data collection involved knowledge tests, task completion time, error rates, usability and subjective feedback. Results showed significant knowledge gain in both groups, with the MAR group achieving a 21% increase and the paper group 15%. In terms of knowledge retention, both approaches were equally effective in helping users retain knowledge and improve task completion performance by reducing task completion time. Notably, the MAR group (0.5 error rate) made fewer errors than the paper group (1.35 error rate). Additionally, MAR demonstrated higher effectiveness based on Perceived Usefulness, Ease of Use, and the NASA Task Load Index. These findings suggest that while both methods support knowledge retention, MAR with better accuracy and usability, making it a valuable tool for IoT assembly training.

A collaborative augmented reality (CAR) system allows multiple users to communicate with each other in a shared 3D environment. Technology Acceptance Model (TAM) is a well-known method for predicting user acceptance of new technology, it also has the two strongest dimensions of acceptance: perceived usefulness and perceived ease of use. However, it can be further developed with external dimensions to investigate acceptance more comprehensively for the CAR system, with its 3D characteristics and collaborative ability, requires additional dimensions for measurement. This study aims to analyze and identify a suitable external dimension to be incorporated in TAM for CAR. We acquired the previous using the Web of Science database, which included keywords such as 'augmented reality,' 'virtual reality,' and 'technology acceptance model.' We analyzed eighteen high quality papers from a pool of ninety-seven papers, including journals and conferences. Resultantly, thirty-two external dimensions have been identified from previous TAM studies. After thorough analysis, a foundation TAM for the CAR system is proposed, along with suggestions for external dimensions for different CAR domain applications. The developed TAM includes perceived enjoyment, aesthetic quality, system quality, social presence, satisfaction, information quality, interactivity, collaboration quality and embodiment quality in the CAR context. Other factors, such as social norms, mobility, and others, are applicable to different CAR domain applications. The identified acceptance factors will assist researchers in enhancing their collaborative experience and conducting further analysis in the field of CAR.

Students often feel overwhelmed by object-oriented programming courses. They find it difficult and complex to learn, requiring a high cognitive load to use the concepts in coding. These issues lead to demotivation in learning programming. This research aims to identify and verify factors that contribute to learning object-oriented programming from two perspectives: interviews and surveys. A literature review was conducted to identify these factors, followed by interviews with five experts who have been teaching object-oriented programming for over ten years to confirm them. Based on the interview results, a questionnaire was developed and administered to 31 bachelor students and 19 lecturers with master’s or doctorate degrees in computer science. The responses indicated that the identified factors were acceptable, with scores ranging from 3.74 to 4.65. The outcomes of this study are a set of factors that should be considered in a programming environment to improve the teaching and learning of object-oriented programming and make it more accessible and engaging for students.

In many academic fields, predicting student academic success using data mining techniques has long been a major research issue. Monitoring students in higher education institutions (HEIs) and having the ability to predict student performance is important to improve academic quality. The objective of the study is to (1) identify features that form clusters that have holistic characteristics and (2) develop and validate a prediction model for each of the clusters to predict student performance holistically. For this study, both classification and clustering methods will be used using Support Vector Machine (SVM) and K-means clustering. Three clusters were identified using K-means clustering. Based on the learning program outcome feature, there are primarily three types of students: low, average, and high performance. The prediction model with the new labels obtained from the clusters also gained higher accuracy when compared to the student dataset with labels using their semester grade.

The power of mobile devices has been harnessed as a platform for augmented reality (AR) that has embarked on opportunities to combine more inputs called multimodal inputs. There has been little research into the multimodal inputs that combine emotion, speech and markers in a mobile AR learning environment. This study aims to propose a framework for a mobile AR learning system that incorporates the combination of multimodal inputs, namely emotion, image-based marker and speech in order to determine how such a combination can enhance the learning experience. The proposed framework integrates the multimodal inputs based on the decision tree and develops into a four-phase learning system based on Kolb’s experiential learning model. To evaluate this learning system, 38 students were selected and divided into two groups for an experiment on vocabulary at a primary school. Quantitative findings showed better results concerning learning effectiveness, mental load, engagement, competency and challenge when the three multimodal inputs, speech, marker and emotion, were combined. Therefore, the proposed multimodal framework can be used as a guideline to develop a multimodal based AR application for learning environment by integrating multimodal inputs and Kolb’s experiential learning model.

The objective of the research is to develop a model based on Principal Component Analysis and clustering for batch-processing load balancing in the cloud computing environment. The findings show that the model is able to extract the current computing resources of the physical hosts and cluster the hosts based on their similarity features. The computing resources of the virtual machine for a new requested task is then extracted and matched with the hosts clusters to select the most suitable physical hosts based on the computing resources. Conversely, when compared with the simulation results of the Round Robin and First Come First Serve load balancing models, the proposed method shows a decrease failure rate of task deployment events.

Augmented reality is one of the technologies that will impact teaching and learning. When augmented reality is applied in an educational setting, it can provide a superior learning environment because educators can add specific virtual information to enrich the existing learning materials or to create new learning materials that integrate the environment. Therefore, discussions on augmented reality applications for learning can be vastly found in the literature. Each application utilizes the resources available by using approaches appropriate for the learning outcome in question. The key problem with achieving learning outcome in analysing group one elements in a periodic table, is that some students have difficulties in visualizing an atom and what more to relate them with reactivity. The objective of this paper is to design and develop a learning application that supports science, technology, engineering and mathematics (STEM) education based on guided discovery learning to assist the students through questions based on exposure to various evidences via augmented reality. This application incorporates the use of 3D model of atoms and video of real experiments. To achieve the objective, action research is used to solve existing problem in a selected school. The application was evaluated by 25 students aged 16 years in a secondary school in Malaysia and has proven to be effective in improving the students’ marks in tests conducted at the end of the application usage. The students can get many benefits from using the augmented reality based application because it supports Education 4.0 like flexibility in teaching and learning where learning is freed for the limitation of time, place and pace of study.