https://ir.kdu.ac.lk/handle/345/8243 2026-04-06T12:56:35Z https://ir.kdu.ac.lk/handle/345/8307 A Comprehensive Review of Advanced Driver Assistance Systems (ADAS) and Their Role in Enhancing Human and Road Safety Laknath, RMS; Katriarachchi, RPS; Wedasinghe, N Advanced Driver Assistance Systems (ADAS) play a crucial role in enhancing road safety by leveraging technological advancements to minimize the risk of accidents. This review highlights the importance of ADAS in mitigating risks, even when human reflexes fall short, by enabling drivers to adapt quickly to changing situations. Key technologies such as Adaptive Cruise Control, Emergency Brake Assistance, and Lane Departure Warning rely on sensor fusion involving radar, LiDAR, and camera imaging, which enhance vehicle responsiveness and provide timely warnings to drivers. The findings emphasize the significance of Vehicle-to-Vehicle (V2V) and Vehicle-to Infrastructure (V2I) communication in facilitating real-time data exchange. This not only improves traffic safety but also accelerates the transition toward fully autonomous driving systems. However, challenges remain, such as ensuring sensor accuracy in adverse weather conditions and addressing security concerns related to data sharing. Further research is necessary to resolve these issues and fully realize the potential of ADAS technologies. The literature review was conducted using highly cited research papers from sources such as ResearchGate, Elsevier, ScienceDirect, and Google Scholar, following the PRISMA workflow to ensure quality and relevance. Results indicate that ADAS contributes significantly to road safety while laying a foundation for adaptive automated driving systems. For instance, emergency braking systems automatically respond to detected faults, and computer vision technology helps identify environmental hazards and driver blind spots, reducing the likelihood of accidents. In conclusion, ADAS not only enhances safety for all road users but also contributes to the development of flexible and safe automated driving systems. By addressing existing challenges, ADAS can further revolutionize road safety, offering society a reliable means of travel with minimal risk, ultimately shaping the future of transportation. 2025-02-06T00:00:00Z https://ir.kdu.ac.lk/handle/345/8306 Real-Time V2V Communication for Traffic Optimization and Collision Prevention Using Machine Learning. Prasanna, MEJ; Wijayarathna, WMSRB; Pradeep, RMM Vehicle-to-vehicle(V2V) communication represent a critical of next generation trans portation systems. This paper explores how to improve V2V systems through the integration of V2X, using machine learning models, and blockchain-based security tech niques, bringing greater road safety and traffic management optimization. Leveraging cellular Vehicle-to-Everything (C-V2X) technology, the proposed system offers enhanced capability in range, scalability, and low-latency communication, making it highly suitable for high-speed mobility scenarios. Furthermore, the study provides insights into the works of power transfer, providing discussions on how electric vehicles would be able to share power and data in real time. The paper also examines the role of machine learning algorithms, particularly Deep Reinforcement Learning (DRL) and transformer based models, in enhancing the efficiency, safety, and data security of V2V systems. Special emphasis is placed on the implications of these technologies for autonomous vehicle systems. By addressing key challenges and proposing innovative solutions, this research contributes to the advancement of intelligent and secure transportation networks. 2025-02-06T00:00:00Z https://ir.kdu.ac.lk/handle/345/8305 Structural Health Monitoring System for Large Structures Using Wireless Sensor Networks: A Machine-Learning Enabled Edge Computing Approach Dissanayake, GASSA; Goonatilleke, MAST; Maduranga, MWP Structural Health Monitoring (SHM) is critical for the safety, durability, and longevity of critical infrastructures ranging from buildings to very big structures such as wind turbines, and bridges. In traditional cloud-based SHM systems, high latency, energy consumption, and low scalability are the challenges. By integrating Machine Learning (ML) with edge computing via Wireless Sensor Networks (WSNs) leveraging device learning, we propose a new approach to address these issues. Deep Neural Networks (DNNs) are directly deployed on edge devices for real-time data analysis and anomaly detection at sensor nodes using the framework. Thus, it reduces the need for continuous data transmission to the centralized servers, reduces energy consumption, and improves system efficiency. Real-time data are collected from key sensors, such as accelerometers and strain gauges, and processed locally by DNNs. Adaptive retraining is enabled by drift detection algorithms, which allow response to changing structural conditions. The findings show that DNNs on the device provide both latency and scalability benefits and are unable to accurately classify clean as well as noisy sensor data. On-device learning in combination with adaptive retraining to keep the system accurate and reactive to changing structural conditions. This proposed system also finds a quantized model using TensorflowLite, for optimizing DNN deployment on resource-constrained devices, to reduce computational overhead and memory footprint, while maintaining acceptable inference accuracy for real-time processing and data transmission. This research also provides a scalable, adaptive solution for real-time infrastructure monitoring, as well as new avenues for adaptive re-training, predictive maintenance, and energy harvesting for Structural Health Monitoring. 2025-02-06T00:00:00Z https://ir.kdu.ac.lk/handle/345/8304 Comprehensive Review on Design of Low-Cost Portable Ventilator for Emergency Use in Resource-Limited Settings Wijesingha, WPNJ; Goonatilleke, MAST Mechanical ventilation serves as a lifesaver in the rapidly evolving field of respiratory disease treatment. However, limitations of existing ventilators, such as high cost and limited portability, affect the accessibility and affordability of respiratory support in resource-limited emergency settings. The aim of this paper is to design a low-cost and portable ventilator machine that overcomes the limitations of ICU ventilators and other portable ventilators. This proposed solution focuses on affordability, portability, and versatility, making it suitable to provide lifesaving respiratory support in various settings. Prior to the design phase, a background study was conducted using the shadow approach, alongside a literature review to collect relevant data and insights. The proposed design consists of an ATmega2560 Arduino microcontroller as the main control board, along with a Honeywell AWM720P1 flow meter, Bosch BMP280 pressure sensor, SST OXY-LC oxygen sensor, and Max30100 pulse oximetry sensor. This system offers Assist Control (AC), Synchronized Intermittent Mandatory Ventilation (SIMV), and Cardiopulmonary Resuscitation (CPR) ventilator modes, as well as adjustable tidal volume, respiratory rate, positive end-expiratory pressure value, and a pressure control system with a user-friendly interface. This design includes a standalone feature, allowing the ventilator to operate in the absence of an external oxygen supply. It also has an alarm system to alert operators or caretakers about potential issues such as high pressure, insufficient oxygen levels, low pulse oximetry, power shortages, or abnormal heart rates. 2025-02-06T00:00:00Z