Sajeeb Kumar Ray

Sajeeb Kumar Ray

Researcher: Computer Vision, Deep Learning, NLP | Specialist @ Codeforces, 4★ @ CodeChef | Top Student & Class Representative @ Dept. of ICE, PUST

Publications

Total Publication: 5

Journal Article: 1 Conference Article: 4
Under Review: 3+

Journal Articles

Enhanced human activity recognition through deep multi-layer perceptron on the UCI-HAR dataset

Published in International Journal of Advances in Applied Sciences (IJAAS), 2024

This paper examines human activity recognition (HAR) using the UCI-HAR dataset, presenting a multi-layer perceptron (MLP) model that achieves 97% accuracy.

Recommended citation: M. A. Hossain, S. K. Ray, N. Islam, A. Alamin, and M. A. F. M. R.Hasan, "Enhanced human activity recognition through deep multi-layer perceptron on the UCI-HAR dataset," International Journal of Advances in Applied Sciences, vol. 13, pp. 429-438, 2024.
Download Paper

Freshness Detection of Fruits and Vegetables Using Multi-Task CNN and ResNet-50 [Under Review]

Published in Under Review in MECS Press Journal, 2024

In this research, developed a deep multi-task learning CNN model (MTL-CNN) for fruit freshness detection and fruit-type classification, achieving 98.63% accuracy by leveraging shared feature extraction and addressing imbalanced datasets.

Recommended citation: SK Ray, MA Hossain, N Islam and Mirza AFMRH; Freshness Detection of Fruits and Vegetables Using Multi-Task CNN and ResNet-50.

Conference Papers

Deep Learning Based Lung Image Segmentation Using XR-U-Net

Published in 27th International Conference on Computer and Information Technology (ICCIT), Cox’s Bazar, Bangladesh., 2024

We propose XR-U-Net, an enhanced deep-learning framework based on U-Net, achieving 95.7% segmentation accuracy for lung X-ray images. This model can aid healthcare professionals by improving diagnostic speed and accuracy in detecting lung-associated pathologies.

Recommended citation: SK Ray, A Islam, MC Chanda, N Islam, MA Hossain, Mirza AFMRH and Alamin, "Deep Learning Based Lung Image Segmentation Using XR-U-Net", 2024 27th International Conference on Computer and Information Technology (ICCIT), Cox’s Bazar, Bangladesh.

Generating Bangla Image Captions with Deep Learning Techniques

Published in 6th International Conference on Sustainable Technologies for Industry 5.0 (STI), Dhaka, Bangladesh, 2024

We introduce a Bangla image captioning model using EfficientNetB4 and ResNet-50 for feature extraction, with EfficientNetB4 achieving a BLEU score of 0.54. This study also presents the BanglaView dataset, fostering advancements in accessibility and Bengali digital communication.

Recommended citation: MA Hossain, Mirza AFMRH, SK Ray and N Islam, "Generating Bangla Image Captions with Deep Learning Techniques", 2024 6th International Conference on Sustainable Technologies for Industry 5.0 (STI), Dhaka, Bangladesh.

Embedded Systems-Based AC Device Controller

Published in 2024 International Conference on Recent Progresses in Science, Engineering and Technology (ICRPSET), Rajshahi, Bangladesh, 2024

The Embedded Systems-based AC Device Controller automates the operation of AC devices using a microcontroller and real-time clock (RTC) for precise, user-defined durations. It enhances energy efficiency, operational safety, and convenience by eliminating manual intervention and preventing unnecessary power usage.

Recommended citation: Alamin, SK Ray, MA Hossain, Mirza AFMRH, N Islam and MM Arman, "Embedded Systems-Based AC Device Controller", 2024 International Conference on Recent Progresses in Science, Engineering and Technology (ICRPSET), Rajshahi, Bangladesh

Vehicle Classification and Detection Using YOLOv8: A Study on Highway Traffic Analysis

Published in 2024 International Conference on Recent Progresses in Science, Engineering and Technology (ICRPSET), Rajshahi, Bangladesh, 2024

This study introduces a vehicle detection and classification framework for Bangladeshi roadways using the YOLOv8n model, optimizing traffic flow and enhancing road safety. Tested on real-time traffic footage, the model effectively handles urban complexities but requires further accuracy improvements in congested settings.

Recommended citation: N Islam, SK Ray, MA Hossain and Mirza AFMRH, "Vehicle Classification and Detection Using YOLOv8: A Study on Highway Traffic Analysis", 2024 International Conference on Recent Progresses in Science, Engineering and Technology (ICRPSET), Rajshahi, Bangladesh