Sajeeb Kumar Ray

Sajeeb Kumar Ray

Prospective PhD student | Researcher - Computer Vision, Deep Learning, NLP | Specialist @ Codeforces, 4★ @ CodeChef | Student of the Year Awardee

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

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

portfolio

Outstanding Academic Result

Published:

Student of Dept. of Information and Communication Engineering (ICE) at Pabna University of Science and Technology (PUST)

Certifications

Certified in Advanced Learning Algorithms and Supervised Machine Learning from Stanford University’s DeepLearning.AI, along with a Problem Solving (Basic and Intermadiate) Certificate from HackerRank.

Vice President - ICE Association

The ICE Association is an organization in which all students of the Department of ICE are default members. It supports students by providing mental, financial, and extracurricular assistance (Jan 2025 to Sep 2025)

publications

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

Published in Under Review, 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.

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

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

Published in 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, S. K. Ray, M. A. Hossain, M. A. Rashidul Hasan, Alamin and M. B. Al Zabir Shammo, "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, 2024, pp. 1-4, doi: 10.1109/ICRPSET64863.2024.10955913
Download Paper

Embedded Systems-Based AC Device Controller

Published in 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, S. K. Ray, M. A. Hossain, M. A. R. Hasan, N. Islam and M. M. A. Hossain, "Embedded Systems-Based AC Device Controller," 2024 International Conference on Recent Progresses in Science, Engineering and Technology (ICRPSET), Rajshahi, Bangladesh, 2024, pp. 1-6, doi: 10.1109/ICRPSET64863.2024.10955881
Download Paper

Generating Bangla Image Captions with Deep Learning Techniques

Published in 6th International Conference on Sustainable Technologies for Industry 5.0 (STI), Narayanganj, 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: M. A. Hossain, M. A. R. Hasan, S. K. Ray and N. Islam, "Generating Bangla Image Captions with Deep Learning Techniques," 2024 6th International Conference on Sustainable Technologies for Industry 5.0 (STI), Narayanganj, Bangladesh, 2024, pp. 1-6, doi: 10.1109/STI64222.2024.10951094
Download Paper

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: S. K. Ray, A. Islam, M.C. Chanda, N. Islam, M. A. Hossain, M. A. R. Hasan 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, 2024, pp. 1-6
Download Paper

Attn-CapBN: An Attention-based Bangla Image Captioning using the Bangla View Dataset

Published in Intelligent Systems with Applications (Under Review; Elsevier-Q1), 2025

Understanding images through natural language descriptions is a fundamental challenge in artificial intelligence, bridging computer vision and natural language processing. While significant progress has been made in English image captioning, resource-scarce languages such as Bangla remain underexplored. To address this gap, this study introduces BanglaView, a large-scale Bangla image captioning dataset inspired by Flickr30k, consisting of 31,783 images paired with 158,915 professionally verified Bangla captions. Each image is annotated with five diverse and fluent descriptions, ensuring both quality and linguistic richness. Building on this resource, we propose Attn-CapBN, an encoder–decoder framework that employs a custom-designed CNN feature extractor and a visual attention mechanism with a GRU decoder to generate contextually coherent Bangla captions. Rigorous training and evaluation were conducted using both BanglaView and the BAN-Cap dataset. Experimental results demonstrate that Attn-CapBN achieves strong performance, with BLEU-1 to BLEU-4 scores of 0.623, 0.487, 0.394, and 0.333 on BanglaView, and 0.620, 0.485, 0.398, and 0.332 on BAN-Cap, respectively. These results surpass existing baselines, highlighting the effectiveness of the proposed CNN-based feature extractor and attention-guided decoding. The contributions of this work include the release of BanglaView as a benchmark dataset and the introduction of Attn-CapBN as a robust architecture for Bangla image captioning, paving the way for further advancements in regional language captioning and multimodal AI research.

Recommended citation: Md Anwar Hossain, Mirza AFM Rashidul Hasan, Sajeeb Kumar Ray, and Naima Islam, Attn-CapBN: An Attention-based Bangla Image Captioning using the Bangla View Dataset. Available at SSRN: https://ssrn.com/abstract=5708615 or http://dx.doi.org/10.2139/ssrn.5708615
Download Paper

RViT-FusionNet: A Local Cross-Attention Feature Fusion-based Hybrid Framework for Brain Tumor Classification

Published in Neural Computing and Applications (Under Revision; Springer-Q1), 2025

This manuscript presents RViT-FusionNet, a hybrid deep learning architecture that combines convolutional neural networks (CNNs) with a refined Vision Transformer (RViT) for brain tumor classification using MRI scans. The key contribution is in the local cross-attention feature fusion mechanism, designed to capture both local spatial features and global contextual dependencies across multiple MRI modalities. Extensive experiments on benchmark datasets demonstrate that the proposed framework achieves higher accuracy and robustness compared to standard CNN, ViT, and hybrid transformer models.

Recommended citation: N. Islam, S. K. Ray, M. A. Hossain et al., “RViT-FusionNet: A Local Cross-Attention Feature Fusion-based Hybrid Framework for Brain Tumor Classification,” Neural Computing and Applications.

Enhanced Plant Health Monitoring with Dual Head CNN for Leaf Classification and Disease Identification

Published in Journal of Agriculture and Food Research (Elsevier-Q1), 2025

Developed a Dual-Head CNN (DH-CNN) for plant leaf classification and disease detection. Achieved 99.71% accuracy in leaf classification and 99.26% in disease identification using the PlantVillage dataset. Enhanced agricultural automation for improved crop management.

Recommended citation: Sajeeb Kumar Ray, Md. Anwar Hossain, Naima Islam, Mirza A.F.M. Rashidul Hasan, Enhanced plant health monitoring with dual head CNN for leaf classification and disease identification, Journal of Agriculture and Food Research, Volume 21, 2025, 101930
Download Paper | Download Slides

talks

teaching