Introduction

Hello! I’m Jianlin, a software engineer with a strong foundation in electrical engineering, currently enriching my knowledge as a first-year graduate student at the University of Cyprus. My passion lies at the intersection of Computer Vision, Self-Supervised Learning, and Natural Language Processing.

Education

MSc Artificial Intelligence

University of Cyprus (2023 - Current)

BEng (Hons) in Electrical and Electronic Engineering

University of Central Lancashire (2019 - 2023)

Work Experience

KIOS Research and Innovation Centre of Excellence (KIOS CoE) @ Software Engineer (Computer Vision) (Janurary 2024 - Current)

Participate in cutting-edge research and development of novel technologies and applications in Computer Vision and Machine Learning
Participate in the dissemination of research results in conferences and journals
Responsible for the implementation and testing of new solutions on mobile platforms (drones)
Responsible for the optimization of existing solutions in terms of R&D and industrial applications
Responsible for data collection, annotation, and preparation of datasets for release
Work closely with other researchers and engineers within a team to develop solutions for various cases
Prepare manuals and guidelines

Windsor Brokers @ Service Desk Officer (Feberary 2023 - September 2023)

Ensure proper function of user’s computer, software and any peripherals.
System administration of Systems related withusers.
Computer hardware maintenance.
Assist with other IT professionals for design configuration and change requests.
Computers build up and OS installation.
Troubleshoot computer problems.
Procurement of computer equipment.

FP-MARKETS @ Backoffice Administrator (June 2021 - November 2022)

Providing technical support to the client Ensure and maintain full client access to Trading Platform service.

Projects and Contributions

A CNN-based Real-time Forest Fire Detection System for Low-power Embedded Devices

Publication

This paper proposes a system architecture that uses deep learning image processing techniques to automatically identify forest fires in real-time using neural network models for small UAV applications. Considering the strict power and payload constraints of small UAVs, the proposed model runs on a compact, lightweight Raspberry Pi4B (RPi4B) and its performance is comparable to the state-of-the-art metrics (accuracy and real-time response) while achieving significant reduction in CPU usage and power consumption. The proposed YOLOv5 optimization approach used in this paper includes: 1) Replacing the backbone network to ShuffleNetV2, 2) Pruning the Head and Neck network following the backbone baseline, 3) Sparse training to implement the model-pruning method, 4) Fine-tuning of the pruned network to recover the detection accuracy and 5) Hardware acceleration by overclocking the RPi4B to improve the inference speed of the algorithm. Experimental results of the proposed forest fire detection system show that the proposed algorithm compared to the state-of-the-art that run on RPi single board computer, achieves 50% higher inference speed (9 FPS), reduction in CPU usage and temperature by 35% and 25% respectively and 10% reduced power consumption while the accuracy (92.5%) is only compromised by 2%. Finally, it is worth noting that the accuracy of the proposed algorithm is not affected by deviations in the bird-eye view angle.

EEG Band Discovery

Indoor 3D Positioning System

Contributed to an open-source project using Multiple Stereo Cameras for indoor 3D positioning. Implemented Deep Learning algorithms to enhance system accuracy and reliability.

Community Engagement

Creator of AI-related content on YouTube and Medium, focusing on Machine Learning and Computer Vision.

Talks & Lectures

“A CNN-based Real-time Forest Fire Detection System for Low-power Embedded Devices” - Talk on the 31st Mediterranean Conference on Control and Automation (MED) , Fall 2023.

Publications

Ye, J., Ioannou, S., Nikolaou, P. and Raspopoulos, M., 2023, June. CNN based Real-time Forest Fire Detection System for Low-power Embedded Devices. In 2023 31st Mediterranean Conference on Control and Automation (MED) (pp. 137-143). IEEE.

Independent Research: