Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Maximizing Element Frequency in an Array: LeetCode 1838 Explained

4 minute read

Published:

In this tutorial, we dive into a fascinating array manipulation challenge: LeetCode problem “1838. Frequency of the Most Frequent Element”. This problem tests our ability to optimize the frequency of elements in an array with a limited number of operations.

Solving LeetCode Problem 2785: “Sort Vowels in a String” — A Comprehensive Guide

3 minute read

Published:

LeetCode’s problem 2785, “Sort Vowels in a String,” poses a unique challenge in string manipulation. The task is to reorder vowels in a given string based on their ASCII values while keeping consonants in their original positions. This article delves into the theory and logic behind solving this problem, using Python as the language of choice.

portfolio

publications

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

Published in 31st Mediterranean Conference on Control and Automation (MED), 2023

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.

Recommended citation: 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. https://clok.uclan.ac.uk/48125/1/MED2023ConferenceV2.pdf

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.