Melissa Jia Ying Chong

Ms. Melissa Jia Ying Chong

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 October 2022
Verified
Conference Paper
Closed access
AHAu Yang Her
Au Yang Her
Weng Kean YewWeng Kean Yew
Weng Kean Yew
PYPang Jia Yew
Pang Jia Yew
MCMelissa Jia Ying Chong
Melissa Jia Ying Chong
Commonly in Malaysia, the road surfaces deteriorate over time which results to potholes. With the increasing number of potholes on the road, it has become a road hazard, potentially harming the safety of the Malaysian citizens. Potholes generally will cause drivers to skew away from their original direction which may result in vehicle damages and/or road accidents. Computer vision has improved significantly in the past decade to improve the technologies that require image processing, such as pothole detection. However, it has several limitations in pothole detection as potholes have inconsistent shapes, making it difficult to obtain an accurate prediction. Another limitation is the speed of the detection algorithm is not able to predict the pothole in real time. In this paper, the use of computer vision technology on vehicles is presented as a form of solution to detect the potholes in real time. A deep learning model based on Convolutional Neural Networks, YOLOv5 is found to improve the accuracy of the prediction as compared to past results. The findings on the trained YOLOv5 model have a mAP@0.5 of 80.8 %, 82.2 % and 82.5 % on the YOLOv5m6, YOLOv5s6 and YOLOv5n6 respectively. The trained YOLOv5n6 model was chosen to be the main image processing model for its robust performance to size ratio. The results were able to demonstrate the actual deployment of the trained YOLOv5n6 model on the road in real time with distance estimation.

15 August 2025 in Sensors
Verified
Journal Article
Open access
PDF file
JKJinghuey Khor
Jinghuey Khor
MSMichail Sidorov
Michail Sidorov
MCMelissa Jia Ying Chong
Melissa Jia Ying Chong
Unmanned Aerial Vehicles (UAVs) face collision risks due to Beyond Visual Line of Sight operations. Therefore, UAV Traffic Management (UTM) systems are used to manage and monitor UAV flight paths. However, centralized UTM systems are susceptible to various security attacks and are inefficient in managing flight data from different service providers. It further fails to provide low-latency communication required for UAV real-time operations. Thus, this paper proposes to integrate Drone-to-Drone (D2D) communication protocol into a secure public blockchain-based UTM system to enable direct communication between UAVs for efficient collision avoidance. The D2D protocol is designed using SHA256 hash function and bitwise XOR operations. A proof of concept has been built to verify that the UTM system is secure by enabling authorized service providers to view sensitive flight data only using legitimate secret keys. The security of the protocol has been analyzed and has been proven to be secure from key disclosure, adversary-in-the-middle, replay, and tracking attacks. Its performance has been evaluated and is proven to outperform existing studies by having the lowest computation cost of 0.01 ms and storage costs of 544–800 bits.

17 October 2022
Verified
Conference Paper
Closed access
MCMelissa Jia Ying Chong
Melissa Jia Ying Chong
Weng Kean YewWeng Kean Yew
Weng Kean Yew
PYPang Jia Yew
Pang Jia Yew
AHAu Yang Her
Au Yang Her
With the increase of road vehicles, road accidents are an increasingly severe threat with incredible economic and social impacts. There has been a rising trend of fatalities and non-fatal casualties caused by road accidents in recent years. One of the main factors contributing to this is the slow dispatch of authorities during an accident as there is currently a lack of an automated accident reporting system. Thus, in this paper, the design of a real-time road accident reporting system was developed and presented. Computer vision was used in accident detection through the employment of a trained model via deep learning. The system then uses location detection and Global System for Mobile Communications (GSM) to accurately report accidents to the relevant authorities. Cloud-based data analytics is also used to store collected data in a designated cloud location for future reference. A working prototype was developed with on-the-road testing demonstrating successful hazard detection and distance measurement as well as location detection. The reporting system and cloud analytics system was able to show instantaneous dispatch and storage of data to the respective targets. Overall, a working prototype was successfully designed, developed, and tested with both simulated inputs and live on-the-road footage.

9 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
SLShoon Kit Lim
Shoon Kit Lim
MCMelissa Jia Ying Chong
Melissa Jia Ying Chong
JKJinghuey Khor
Jinghuey Khor
TLTing Yang Ling
Ting Yang Ling
Recent advances in agentic and physical artificial intelligence (AI) have largely focused on ground-based platforms such as humanoid and wheeled robots, leaving aerial robots relatively underexplored. Meanwhile, state-of-the-art unmanned aerial vehicle (UAV) multimodal vision-language systems typically rely on closed-source models accessible only to well-resourced organizations. To democratize natural language control of autonomous drones, we present an open-source agentic framework that integrates PX4-based flight control, Robot Operating System 2 (ROS 2) middleware, and locally hosted models using Ollama. We evaluate performance both in simulation and on a custom quadcopter platform, benchmarking four large language model (LLM) families for command generation and three vision-language model (VLM) families for scene understanding.