This paper presents the development of a real-time weather classification system using a hybrid Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) architecture. The system integrates visual data from surveillance cameras and time-series weather sensor data to classify weather conditions into sunny, cloudy, and rainy categories. Two data alignment strategies were explored to...
In 2019, alongside the sudden emergency by COVID-19 outbreak, an "infodemic" of misinformation emerged, causing public confusion and leading to mistrust in health authorities. In this paper, we propose a method to mitigate misinformation by enhancing query rewriting in retrieval-augmented generation (RAG) using Large Language Models (LLMs). LLMs such as ChatGPT and Llama have shown remarkable...
This dissertation is about creating a non- redundant, effective and low- complexity denoising method. Denoising an image is involves removing noise from an image to keep the original elements of the image and remove the unwanted additions. Transform- based denoising depends on the transform used in the denoising method. Recent works focus more oin improving the performance of the denoising,...
Tracking of medical device usage is essential for timely maintenance and reducing unexpected breakdowns. This study investigates the use of a 3-axis magnetometer to monitor the operational states of syringe pump by analysing magnetic flux changes. The magnetometer is embedded within an Ultra-Wide Band tag, which also enables real-time localization of the device. Magnetic flux data were...
This study investigates the efficacy of the X7f202 Ultra-Wideband (UWB) radar for detecting respiratory activity across various resting body positions. Under controlled conditions, radar signals were recorded in supine, lateral, and prone positions, with subjects alternating between normal breathing and breath-holding. Data from 20 subjects reveal consistent differences in signal frequency and...
The integration of artificial intelligence (AI) into medical devices is revolutionizing modern healthcare by improving diagnostic accuracy, enabling real-time monitoring, and aiding clinical decision-making. As healthcare systems worldwide grapple with challenges such as rising costs, aging populations, workforce shortages, and environmental issues, there is a pressing need for sustainable,...
Rapid diagnostic test (RDT) kits are widely used for point-of-care detection of infectious diseases. However, interpreting their results can be challenging, especially for visually impaired individuals or when the test lines are faint or ambiguous. This paper proposes a multi-stage YOLO-based deep learning framework to automate and improve the accuracy of RDT result interpretation. The system...
Abstract—This review paper focuses on improving AI-based traffic analytics applications in smart cities by integrating emergency response vehicle (ERV) datasets through transfer learning. The research addresses challenges such as the lack of specialized datasets representing ERVs under diverse conditions and the limitations of conventional traffic management systems in prioritizing emergency...
