UTAR Institutional Repository (Universiti Tunku Abdul Rahman)
Not a member yet
6132 research outputs found
Sort by
An intelligent animal rescue system
Get PDFThe ResQMe Animal Rescue System is a mobile application designed to streamline animal
rescue operations by connecting the public, volunteers, and administrators on a single platform.
Rescue operations sometimes face key challenges, including a lack of animal recognition,
limited educational resources, and inadequate route planning systems. To overcome these
limitations and make rescue operations more effective, ResQMe targets the implementation of
a CNN-based animal recognition system, additional educational resources, and GPS-based
real-time distance calculation and route planning to the nearest rescue clinics. Besides, the
development of extra features, such as OCR-based IC verification, TTS pronunciation, built
in notifications, wildlife rescue reports, user extra description addition, and volunteer
application submissions integration between Firebase and the Android Studio platform, was
successfully implemented among admins and users. By combining core components, ResQMe
meets the requirements in animal rescue operations and promotes public awareness in animal
welfare
Utilising computer vision techniques for automated density and growth estimation in precision aquaculture systems for prawn cultivation
Get PDFPrawn farming, a vital sector of the global aquaculture industry, faces challenges with
traditional monitoring methods that are labor-intensive, error-prone, and lack real-time
capabilities, leading to inefficiencies in feeding and harvest planning, particularly for
small- and medium-scale farmers. This project aims to address these issues by
developing a computer vision-based system for automated density and growth
estimation of Cherax quadricarinatus prawns, enhancing operational efficiency and
sustainability. Utilizing the lightweight YOLO11n neural network, a Raspberry Pi 5,
and a PiCamera (Night Vision), the system automates prawn monitoring, improves
accuracy through machine learning, and ensures affordability at 80 per unit. A
Cron Job feature enables continuous data collection, building a farm-specific dataset to
overcome the lack of standardized prawn data. Deployed in a controlled pond
environment, the system captured 2000 images under varying conditions, achieving
real-time detection at 5 FPS, though initial tests revealed accuracy issues requiring
further data and fine-tuning. By mitigating challenges like environmental variability,
high costs, and technical complexity identified in prior studies, this solution offers a
scalable, user-friendly tool that empowers smaller farms to optimize resource use and
enhance productivity in precision aquaculture
Purchase intention of Gen Z university students over the tiktok shop facilitated by hyper-personalization
Get PDFThis study focuses on investigating the purchase intentions of Generation Z university students in Malaysia towards TikTok Shops, with a focus on the role of hyper-personalization in the Technology Acceptance Model (TAM2). Six variables were investigated, which included social media experience, mobile device specs, internet connectivity, perceived ease of use, perceived usefulness, and hyperpersonalization. Data were gathered using a structured questionnaire posted online, with 210 valid responses analyzed using PLS-SEM. The data show that social media experience and internet connectivity have significant effects on perceived usefulness, but mobile device specifications will not significantly affect. Furthermore, perceived usefulness has a significant effect on purchase intention, whereas perceived ease of use does not. However, when mediated by hyper-personalization, perceived ease of use becomes significant, indicating the importance of hyper-personalization in increasing user engagement and buying behavior. The study adds on TAM2 by incorporating hyper-personalization as a mediating variable, providing theoretical insights into the acceptance of social media e-commerce. In practice, the findings suggest that firms should emphasize increasing internet reliability, develop hyper-personalization tools, and assure user-friendly regulations to increase purchase intentions among Gen Z consumers. This study contributes to the understanding of technology adoption in social media e-commerce and provides practical advice for marketers looking to maximize TikTok Shop's potential. Keywords: TAM 2, Gen Z, Hyper-personalization, Social Media e-commerce, Purchase Intention Subject Area: HF5410-5417.5 Marketing. Distribution of product
The influence of consumption values on Gen Z’s intention to use smart trolleys in Malaysia
Get PDFThis paper aims to examine the degree to which the Theory of Consumption Values (TCV) can explain the intention of Malaysian Generation Z to adopt smart trolleys in the retail environment. As the retail industry undergoes a rapid digital transformation, smart technologies are increasingly incorporated into retail settings to enhance operational efficiency and improve shopping experiences. A significant consumer group, Generation Z, is characterized by its high adaptability, technological abilities, and trend consciousness. Their use and acceptance of smart trolleys are essential to the effective application of such advancements. This quantitative study involved 411 Malaysian Generation Z individuals within the age range of 18 to 30. The survey was administered using two modes, which are an online Google Form and physical distribution. The survey measured five dimensions of consumption values, which were functional value (FV), emotional value (EV), social value (SV), epistemic value (EP), and conditional value (CV). Statistical Package for Social Science (SPSS) software was used to conduct statistical analysis, such as Pearson correlation and multiple regression analysis. The results revealed that all value dimensions showed a significant positive correlation with the intention to use smart trolleys. These findings indicate that if situational attributes, novelty, social influence, and emotional satisfaction are provided, Gen Z consumers are particularly willing to adopt smart trolleys. Besides, this study was added to the context of the literature by using TCV for the adoption of smart retail technology and provides useful recommendations for retailers and technology developers on how to increase Gen Z consumers’ acceptance of smart trolleys in Malaysia. Keywords: Consumption Values, Theory of Consumption Values (TCV), Smart Trolley Adoption, Consumer Intention, Generation Z, Malaysia. Subject Area: HF5410-5417.5- Marketing. Distribution of products
Factors for the adoption of digital technologies in the machinery and metal manufacturing sector in Klang Valley Malaysia
Get PDFThe advancement of Industry 4.0 has accelerated the adoption of digital technologies in the machinery and metal manufacturing sector to improve efficiency, competitiveness, and sustainability. This study explores the key factors influencing digital technology adoption and its impact on manufacturing performance—specifically, time, cost, and quality improvements. Guided by the Technology-Organisation-Environment (TOE) framework, a structured questionnaire was distributed via email and social media, yielding 55 valid
responses from small, medium, and large firms. Descriptive statistics and Principal Component Analysis (PCA) were used for analysis.
Findings show that perceived usefulness, top management support, compatibility, market demand, and competitive pressure are the most influential adoption factors. PCA identified three core dimensions: Perceived Technological Fit, Institutional and Organisational Readiness, and External
Business Environment. Performance-wise, digital technologies notably improve time efficiency, quality control, and cost management.
The study concludes that successful digital transformation depends on aligning technological capabilities with organisational readiness and environmental drivers. Key recommendations include enhancing leadership support, upskilling the workforce, and expanding digital infrastructure— particularly for SMEs. These insights provide practical guidance for industry stakeholders and policymakers aiming to promote sustainable industrial digitalisation
Molecular cloning of a construct for targeted RecA gene disruption via homologous recombination in Agrobacterium tumefaciens
Get PDFAgrobacterium tumefaciens is a cornerstone of plant genetic engineering and serves as the primary vector for delivering transgenes into a wide variety of plant species. However, the efficiency of this process is compromised by the bacterium's native homologous recombination system, which is mediated by the RecA protein. Functional RecA promotes unintended rearrangements and deletions of the transferred DNA (T-DNA) within the bacterial cell, leading to integrated transgenes that are fragmented, rearranged, or incomplete. This reduces the precision and effectiveness of Agrobacterium-mediated transformation (AMT) and necessitates screening of excessive numbers of transformants to recover a few with the correct construct, making the process inefficient and costly. This study aimed to address this limitation by constructing a targeted gene disruption vector to create a stable recA-deficient strain of A. tumefaciens. The strategy involved engineering a plasmid that upon introduction into Agrobacterium would insertionally disrupt the function chromosomal recA gene with a (cat)-repA cassette via a double-crossover homologous recombination event. To achieve this, the N-terminal and C-terminal regions of recA were amplified by polymerase chain reaction (PCR) using A. tumefaciens genomic DNA as a template. These fragments were then sequentially cloned into the pASK-KO suicide vector flanking the chloramphenicol resistance (cat)-repA cassette. The resulting construct, pASK-NrecA-cat-repA-CrecA, was assembled and propagated in Escherichia coli TOP10 cells. Putative recombinant clones were selected on kanamycin-containing media and validated using a combination of colony PCR, restriction enzyme digestion, and Sanger sequencing, which confirmed 100% identity with the expected plasmid sequence. The successful construction of this vector is a critical first step. Its subsequent introduction into A. tumefaciens is expected to generate a mutant strain with a disrupted recA locus. This engineered strain should exhibit significantly enhanced T-DNA plasmid stability, thereby minimizing rearrangements and ultimately increasing AMT fidelity and efficiency. The development of such specialized strains has significant potential to streamline plant biotechnology workflows, reducing the time and resources required to generate transgenic plants with intact functional genes
VISIONASSIST: Traffic light status detection for the visually impaired
Get PDFWith the advancement of public transport in Malaysia, walking has become a vital component for individuals to navigate to public transport stations, work, school or any desired destination as an alternative to avoid traffic congestion. These walking individuals are known as pedestrians, where pedestrian traffic lights have been an important commander in guiding them to cross the road intersection safely by indicating the colour of red or green. However, these pedestrian lights have been found to provide minimal functionality in terms of accessibility for individuals with visual impairments, who have difficulty in interpreting traffic signal indications. Motivated by the need to enhance intersection safety and mobility for this population, this project aims to develop a mobile application that serves as a real-time pedestrian traffic light detector —effectively acting as the “eyes” for visually impaired users. The application introduces a novel solution that integrates traffic light recognition with accessibility-focused output mechanisms, such as auditory alerts and customizable haptic feedback. Using a YOLOv8-based object detection model and the smartphone’s rear camera, the application identifies and classifies pedestrian traffic light signals (red or green), immediately providing users with intuitive audio and haptic cues based on their personalised settings. In order to have a clear picture of the functionalities and limitations of existing assistive technologies in terms of software applications, existing applications such as Seeing AI, Be My Eyes and Lazarillo have been reviewed and presented in the report. Finally, the expected outcome of this project is a fully functional and accessible mobile application that empowers visually impaired individual to cross intersections safely and independently, thereby improving their mobility and confidence in navigating public environment
Companion for elderly: Chatbot and mini-games for Alzheimer’s prediction
Get PDFIn recent years, many elderly people who are living alone have faced lots of difficulties, such as a lack of companionship, difficulty managing daily tasks, and unawareness of health issues like Alzheimer's disease. Although there are a few mobile applications available to help solve these issues, they often lack a comprehensive, all-in-one solution tailored specifically for the elderly. This project aims to study the development of a mobile application designed to help elderly people by combining multiple features into a single platform. The proposed application addresses limitations found in existing mobile applications such as CogniFit, Replika, and MyTheraphy which they do not contain the features cognitive assessment, companionship feature, and tools to assist in daily lives in a single platform. Thus, the proposed application will provide an integrated solution to assist the elderly in their daily lives. It includes a chatbot that serves as a virtual companion to engage users in meaningful conversations and a minigame-based cognitive assessment tool which reference from Mini-Mental State Examination (MMSE) test to help monitor cognitive health. The polynomial regression model with average MAE score of 0.639, average RMSE score of 0.915, and average R² score of 0.595 is integrated as predictive model for Alzheimer’s disease. The application is developed using Android Studio, Unity Game Engine with C#, and Android SDK with Kotlin and JavaScript, and is designed to be compatible with Android smartphones. Besides, users can use the utility tools built in the application such as the contact and the reminder to support in their daily activities
Development of a hand gesture recognition using mediapipe landmarks for windows control system
Get PDFThis project presents the development of a real-time hand gesture recognition system aimed at enable for a intuitive and touchless human-computer interaction. This study explores 2 approaches: a hybrid method combining Mediapipe for hand landmark extraction with Convolutional Neural Network (CNN) classification, and an image-based approach using YOLOv8 for gesture classification. A dataset of nine predefined gestures was prepared with augmentation techniques such as flipping, rotation, scaling and noise addition to improve model generalization. The CNN-Mediapipe approach achieved a high validation accuracy and demonstrated superior performance in real-time execution, along with using PyAutoGUI for control commands, including scrolling, arrow navigation and mouse interaction. Meanwhile, YOLOv8 classifier achieved a good accuracy during training but exhibited lower stability in real-time testing, particularly with specific gestures. The findings suggest that landmark-based models provide a lightweight and efficient solution for gesture recognition into control systems to enhance user experience and lays the foundation for future work on expanding gesture vocabulary, improving its reliability under diverse conditions
Virtual try-on platform
Get PDFThe project focuses on developing a comprehensive Virtual Try-On (VTO) application that integrates Deep learning (DL) technologies. The aim is to provide users with an immersive experience to visualize and customize their full-body look, including clothing, makeup. This solution addresses the limitations of existing virtual try-on systems, which are often constrained to specific categories and reliant on in-store systems. The proposed VTO app is designed to offer a complete styling experience, allowing users to experiment with their entire look within one platform. The use of DL enhances effectiveness and realism of the Virtual Try-On (VTO) system. The app also tackles challenges related to hygiene and time consumption by eliminating the need for physical try-ons in stores, making it a timely solution in the post-pandemic digital shopping era. The project employs Android as the development platform to ensure accessibility across a wide range of devices, particularly in emerging markets. By leveraging advanced technologies, the app promises a more convenient, and engaging shopping and styling experience