Md. Rifat Hossen

Md. Rifat Hossen

Undergraduate AI Researcher

Sitemap

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

Pages

Posts

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)

publications

Facial Expression Recognition: A Machine Learning Approach with SVM, Random Forest, KNN, and Decision Tree Using Grid Search Method

Published in International Workshop on Nonlinear Circuits, Communications and Signal Processing (RISP), Pulau Pinang, Malaysia, 2025

The study aims to investigate the effectiveness of deep learning approaches in recognizing emotions from BC speech while addressing challenges such as degradation and information loss in neural networks.

Recommended citation: Hossen, M. R., Mia, M. U., Islam, R., Hosain, M. S., Hasan, D. M. K., & Shimamura, T. (2025, February 27). Facial Expression Recognition: A Machine Learning Approach with SVM, Random Forest, KNN, and Decision Tree Using Grid Search Method. International Workshop on Nonlinear Circuits, Communications and Signal Processing 2025, Pulau Pinang, Malaysia. https://doi.org/10.5281/zenodo.14937923
Download Paper

Exploring the EmoBone Dataset with Bi-Directional LSTM for Emotion Recognition via Bone Conducted Speech

Published in International Workshop on Nonlinear Circuits, Communications and Signal Processing (RISP), Pulau Pinang, Malaysia, 2025

This study explores the performance of machine learning classifiers—SVM, Random Forest, KNN, and Decision Tree—on the CK+ dataset, a benchmark for FER research.

Recommended citation: Hosain, M. S., Hossen, M. R., Mia, M. U., Sugiura, Y., & Shimamura, T. (2025, February 28). Exploring the EmoBone Dataset with Bi-Directional LSTM for Emotion Recognition via Bone Conducted Speech. International Workshop on Nonlinear Circuits, Communications and Signal Processing 2025 (NCSP'25), Pulau Pinang, Malaysia. https://doi.org/10.5281/zenodo.17384107
Download Paper

Multi-Source Dental X-Ray Dataset Using Image-to-Image Transformation

Published in , 2025

The Teeth View X-ray Image Dataset is a collection of dental X-ray images gathered from different dental clinics. It is designed for machine learning tasks such as object detection. The dataset is organized into one main folder: the object detection dataset.

Recommended citation: Aurnob, Al Rafi; Hossen, Md. Rifat ; Tanim, Sharia Arfin (2025), “Multi-Source Dental X-Ray Dataset Using Image-to-Image Transformation”, Mendeley Data, V1, doi: 10.17632/cgwnxmdp3b.1

Machine learning–assisted optimization of a terahertz photonic metamaterial absorber for blood cancer detection NEW

Published in Plos One, 2025

Several machine learning models were also employed for design prediction, with Gradient Boosting demonstrating excellent performance and enabling up to a 60% reduction in optimization time. The combination of a multi-band, high-absorption design and ML-assisted approach provides a robust, ultrathin, and high-sensitivity platform, offering a promising route toward next-generation terahertz biophotonic sensors for accurate and sensitive blood cancer detection.

Recommended citation: A. Miah, S. Al Zafir, J. Das, J. Al-Faruk, S. I. Zim, R. Ahmad, M. R. Hossen, S. M. A. Haque, A. Wahed, “Machine Learning–Assisted Optimization of a Terahertz Photonic Metamaterial Absorber for Blood Cancer Detection,” PLOS ONE, vol. 21, no. 2, e0340492.
Download Paper

Tversky Loss Mechanisms: A ResUNet Approach to Improving Brain Tumor Segmentation

Published in International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), Rangpur, Bangladesh, 2025

This study introduces the ResUNET segmentation network utilizing a Tversky loss function. It tackles class imbalance,a significant challenge in brain tumor segmentation. We surpassUNET in segmentation outcomes by addressing class imbalanceand accurately segmenting the smaller, critical areas of the tumor.

Recommended citation: M. R. Hossen, E. Hossain, J. Al-Faruk, J. Sultana, M. B. Islam and M. S. Hosain, "Tversky Loss Mechanisms: A ResUNet Approach to Improving Brain Tumor Segmentation," 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), Rangpur, Bangladesh, 2025, pp. 1-6, doi: 10.1109/QPAIN66474.2025.11171708.
Download Paper

Evaluating Targeted Productivity in Bangladesh’s Garment Sector Using Machine Learning and Deep Learning with Explainable AI: A Data-Driven Method for Enhanced Production Planning

Published in In: Proceedings of the 3rd International Conference on Big Data, IoT and Machine Learning (BIM 2025), Taylor & Francis, 2025

This study introduces a data-driven framework utilizing machine learning (ML) and deep learning (DL) methods to accurately predict productivity targets, supplemented by Explainable AI (XAI) tools such as SHAP and LIME.

Recommended citation:
Download Paper

Enhancing DeepFake Classification Performance Using a CNN and XceptionNet-Based Pipeline

Published in IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS 2025), Kushtia, Bangladesh, 2025

To combat this, the study introduces a dual-model deepfake detection system that combines a custom lightweight convolutional neural network (CNN) with a transfer learning-based XceptionNet.

Recommended citation: N. T. Susmi, M. Chandra Chanda, M. S. Hosain, M. Rifat Hossen, M. A. Hossain and A. Fazal Mohammad Zainul Abadin, "Enhancing DeepFake Classification Performance Using a CNN and XceptionNet-Based Pipeline," 2025 IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS), Kushtia, Bangladesh, 2025, pp. 1-6, doi: 10.1109/COMPAS67506.2025.11381636.
Download Paper

Attention-Based Deep Learning for Scalable Speech Emotion Recognition with Synthetic Bone-Conducted Speech

Published in IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS 2025), Kushtia, Bangladesh, 2025

This work contributes a scalable and robust solution for SER, grounded in the benefits of synthetic BC speech modeling that can enhance the reliability of emotion recognition systems in real-world applications.

Recommended citation: M. I. Shihab Shad, S. Khan, M. S. Hosain, A. Mahdi, M. C. Chanda and M. R. Hossain, "Attention-Based Deep Learning for Scalable Speech Emotion Recognition with Synthetic Bone-Conducted Speech," 2025 IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS), Kushtia, Bangladesh, 2025, pp. 1-6, doi: 10.1109/COMPAS67506.2025.11381631.
Download Paper

Brain Tumor Detection in MRI Images with YOLOv12

Published in IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS 2025), Kushtia, Bangladesh, 2025

In this research, we introduce an enhanced approach for brain tumor detection that employs the latest YOLOv12 object detection framework. We assess and contrast the performance of YOLOv12 with several other leading models, illustrating its supe- rior detection accuracy.

Recommended citation: M. U. Mia, M. S. Hosain, M. T. W. Mulk, M. N. Bhuiyan, M. R. Hossen and L. C. Paul, "Brain Tumor Detection in MRI Images with YOLOv12," 2025 IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS), Kushtia, Bangladesh, 2025, pp. 1-6, doi: 10.1109/COMPAS67506.2025.11381885.
Download Paper

Explainable Machine Learning Framework for Detecting Lumpy Skin Disease with Environmental and Climate Factors

Published in IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS 2025), Kushtia, Bangladesh, 2025

This study presents a comprehensive comparative analysis of eleven machine learning algorithms specifically aimed at binary classification within an environmental context.

Recommended citation: M. R. Hossen, M. U. Mia, M. N. Bhuiyan, M. K. Saha, R. Islam and M. S. Hosain, "Explainable Machine Learning Framework for Detecting Lumpy Skin Disease with Environmental and Climate Factors," 2025 IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS), Kushtia, Bangladesh, 2025, pp. 1-6, doi: 10.1109/COMPAS67506.2025.11381718
Download Paper

Enhancing Robustness and Accuracy of Bone-Conducted Speech Emotion Recognition via Transformer Models

Published in 10th International Conference on Electrical Engineering and Informatics (ICEEI2025), Malaysia, 2025

This research presents a high-performance SER model based on the Wav2Vec2.0 transformer framework, fine-tuned with a custom dataset named audio EmoBon, created with bone-conducted (BC) speech from Malaysian speakers.

Recommended citation: M. R. Hossen, K. A. A. Bakar, M. U. Mia, M. N. Hossain and M. S. Hosain, "Enhancing Robustness and Accuracy of Bone-Conducted Speech Emotion Recognition via Transformer Models." 2025 International Conference on Electrical Engineering and Informatics (ICEEI), Kuching, Malaysia, 2025, pp. 1-6, doi: 10.1109/ICEEI68459.2025.11330456.
Download Paper

Speech Emotion Recognition from Bone-Conducted Speech Using Wav2Vec2 Transformer Mode

Published in IEEE 7th International Conference on Sustainable Technologies for Industry 5.0 (STI 2025) Dhaka, Bangladesh, 2025

This paper introduces an end-to-end SER system based on the Wav2Vec2.0 transformer model, fine-tuned with the EmoBone dataset—a comprehensive, multi-national BC speech dataset featuring eight emotion categories collected from 29 speakers in 10 countries.

Recommended citation: M. K. Saha, M. S. Hosain, M. R. Hossen, S. K. Ray, L. C. Paul and M. S. Uddin, "Speech Emotion Recognition from Bone-Conducted Speech Using Wav2Vec2 Transformer Model," 2025 IEEE 7th International Conference on Sustainable Technologies For Industry 5.0 (STI), Dhaka, Bangladesh, 2025, pp. 1-6, doi: 10.1109/STI69347.2025.11367517.
Download Paper

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.