19684 research outputs found
Sort by
Deep Learning-Based Malaysian Sign Language (MSL) Recognition:Exploring the Impact of Color Spaces
No full textSign language is one form of communication for this group of people to communicate with each other. Not only for people with hearing problems but sign language is also useful for people who are mute or have problem speaking. The most used sign language is the American Sign Language (ASL) that is widely used in English speaking countries. In Malaysia, Bahasa Isyarat Malaysia (BIM) or Malaysian Sign Language (MSL) is still a new teaching to the community in Malaysia. Hence, in this project, a dataset with 5980 images of the signed alphabet is used to train models to recognize what the signs mean. The problem this project aims to address is the limited research and the availability of datasets in the field of Malaysian Sign Language (MSL) recognition using deep learning and various color spaces. Two deep learning models that are used are Convolutional Neural Network (CNN) and Residual Network 18 (ResNet18). The images are also converted into different color spaces which are RGB, YCbCr, Grayscale and the combination of RGB and YCbCr. The findings reveal that RGB is the most effective color space for CNNs, achieving up to 83.9% accuracy, while YCbCr performed best with ResNet18, achieving 88.3% accuracy. These results demonstrate the importance of color space selection in sign language recognition and contribute to the growing body of research on MSL. Key metrics such as precision, recall, and F1-score further underscore the robustness of the proposed system.</p
Towards the Development of a Novel Smart Work-holding Fixture for Advanced Manufacturing
No full text
Parametric Sound Field Auralization of Small Room Acoustics for Perceptual Research on Room Reflections
No full textA Study of Attitudes of Iranian Students in Malaysia about Learning English and English as a Lingua Franca (ELF)
Get PDF
Exploring how Game Theoretical Models can improve the British Transportation Sector for the benefit of Britons
Get PDFShort packet communication in IoT networks:performance analysis
No full textIn this paper, we investigated the block error rate (BLER) performance of a wireless powered communication network (WPCN) employing short packet communication (SPC). In this system, a source node harvests energy from a dedicated power beacon and utilizes the harvested energy to transmit short packets to a destination equipped with multiple antennas. We adopt a time-switching (TS) protocol for energy harvesting and information transmission. To enhance the reliability of the communication link, selection combining (SC) is employed at the receiver. We derive a closed-form expression for the average BLER, taking into account the impact of key system parameters such as the time-switching ratio, energy harvesting (EH) efficiency, and the number of receive antennas. Our analytical results, validated through Monte Carlo simulations, reveal the interplay between these parameters and their influence on the BLER performance. The findings of this study provide valuable insights into the design and optimization of WPCNs for reliable short packet transmission in various emerging applications, particularly those with stringent energy and latency constraints.</p
Access Repository Dashboard
Do you manage Huddersfield Research Portal? Access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard!