MD Roman Sarkar

MD Roman Sarkar

PhD Fellow

Harbin Institute of Technology

Profile ID RP-004-0382 Joined 2026-05-21 3 articles
0Connections
4
Total Views
3
Total Publications
92
Publication Views

About me

Dr. MD Roman Sarkar is a Bangladeshi entrepreneur, researcher, and technology innovator currently pursuing his PhD fellowship at Harbin Institute of Technology. He is widely recognized for his contributions to the fields of software technology, digital innovation, and AI-driven healthcare research. Roman is the Founder of Geniusplug Technology and Bangladesh Todays, and also serves as Co-Founder of Genius IT Institute. Through his visionary leadership and entrepreneurial expertise, he has successfully expanded business operations across multiple international markets, including the Netherlands, Denmark, Switzerland, Canada, the United Kingdom, the United States, and several Middle Eastern countries. Roman began his entrepreneurial journey shortly after completing his Diploma in Engineering from SPI in 2018. Since then, he has established himself as a dynamic leader with a strong focus on technological advancement, software development, and digital transformation. His professional interests particularly emphasize artificial intelligence, machine learning, medical image analysis, and intelligent healthcare systems for clinical decision support. In addition to his achievements in technology and business, Roman is also an accomplished author. His notable publications, The Scammer’s Dark Ledger and Digital Marketing Trends, have received recognition for their insightful exploration of cyber fraud, digital ecosystems, and emerging business technologies. Through his ongoing research, innovation, and literary contributions, Dr. Roman continues to inspire young entrepreneurs, researchers, and technology enthusiasts both in Bangladesh and internationally.

Articles(3)

Authors: Md Roman Sarkar, Md Rased Hasan, Md Shohel Rana, Md Ariful Islam, Md Mushfiqur Rahman Neidhe

DOI: 10.1109/qpain66474.2025.11172261

Volume1
Issue1
Pages1-6
Abstract

The unfolding global trajectory of COVID-19 has made it abundantly clear that scalable, accurate diagnostic solutions, especially in resource-limited healthcare settings, are urgently required. The present study therefore proposes a novel, transfer learning-based framework for COVID-19 detection employing chest X-ray imagery, repurposing the Google Derm Foundation neural network, a model originally trained for dermatological classification. By integrating domain-specific feature extraction with a custom neural network classifier optimized for binary COVID-versus-non-COVID inference, it constitutes a hybrid architecture that transcends conventional approaches. The pipeline incorporates rigorous preprocessing techniques, stratified cross-validation, and exhaustive ablation studies to guarantee robustness and reliability. Key contributions include the validation of the Google Derm Foundation model's adaptability to pulmonary diagnostics and the systematic performance comparison of multiple network architectures. Empirical results reveal notable superiority: the Google derm-foundation achieved an accuracy of 94.39%, precision of 95.72%, and F1-score of 94.31%, outperforming traditional classifiers and pretrained convolutional networks such as VGG19 and ResNet50. Full visualization of the models, including their use of confusion matrices and accuracy curves, allows for additional insights into the model's behavior to be gleaned. The close inspection of erroneous negatives highlights the clinical consequences of making a mistaken diagnosis. This research advances AI-driven medical imaging by presenting a scalable, interpretable, and highperforming solution for COVID-19 detection. The next steps consist of data augmentation, class-imbalance mitigation, and domain-adaptation approaches aimed at making the technologies clinically even more useful.

Authors: Md. Roman Sarkar, Md. Arman Hossain, S. M. Sojib Ahamed

DOI: 10.46827/ejsss.v9i6.1690

Volume9
Issue6
Pages69-74
Abstract

Traffic jams are the biggest problem of this magnitude in the world’s densely populated cities. A lot of research is being done all over the world, and it is important. I visit some of the most populous cities in the world, like Dhaka, Delhi, Jakarta, etc. I have researched some of the possible issues that seem relevant to me and have discussed them in detail in this research paper. Here, I have mentioned what causes traffic jams. Ways to reduce traffic jams. Powerful traffic law and traffic software system. Real-life solutions, etc. The methods I mentioned are for future research. It can solve traffic jams. In this research, I have mentioned the factors that cause traffic jams in Dhaka and how they can be solved. I have discussed special software that can develop the traffic system and free a densely populated city like Dhaka from traffic jams. It will help the economies of Dhaka and Bangladesh develop more. </p><p> </p><p><strong> Article visualizations:</strong></p><p><img src="/-counters-/lit/0757/a.php" alt="Hit counter" /></p>

Authors: MD. Roman Sarkar, S M Sojib Ahamed, Md Miftahul Bari, Md Mehedi Hasan, Fuad Hasan Shishir

DOI: 10.55529/jipirs.45.55.62

Volume4
Issue45
Pages55-62
Abstract

The COVID-19 pandemic currently underway has highlighted a need for fast and accurate screening tools to help identify the disease, particularly in resource-poor settings. In this paper, a deep convolutional neural network (CNN) model is proposed for the automatic detection of COVID-19 pneumonia using chest X-ray images that helps in reducing the cost and processing time compared to traditional testing procedures. It uses several deep-structured medical image data types and improvement of the deep learning model architecture to achieve good diagnostic accuracy. Our hybrid CNN architecture integrates VGG-16 for feature extraction and ResNet-50 for pattern complexity assessment in detecting fine changes characteristic of COVID-19 pneumonia. Our dataset for this study is a collection of few thousands labelled chest X-ray images categorized in three classes, which are COVID-19, viral pneumonia and healthy cases. More advanced data preprocessing methods such as normalized, augmentation, and filtered noise has also been carried out which enhances in the model performance. We have high accuracy, recall, and good F1-score in the experimental results proving model robustness are applicable in real-world clinical scenarios. These research results speak to the importance of AI for improving diagnosis workflows, especially in fast-to-deploy large scale scenarios needed during a pandemic to cope with healthcare burdens.

No matching articles

Try another word from the title, author or DOI.

Brief Bio

Dr. MD Roman Sarkar is a Bangladeshi entrepreneur, researcher, and technology innovator currently pursuing his PhD fellowship at Harbin Institute of Technology. He is widely recognized for his contributions to the fields of software technology, digital innovation, and AI-driven healthcare research. Roman is the Founder of Geniusplug Technology and Bangladesh Todays, and also serves as Co-Founder of Genius IT Institute. Through his visionary leadership and entrepreneurial expertise, he has successfully expanded business operations across multiple international markets, including the Netherlands, Denmark, Switzerland, Canada, the United Kingdom, the United States, and several Middle Eastern countries. Roman began his entrepreneurial journey shortly after completing his Diploma in Engineering from SPI in 2018. Since then, he has established himself as a dynamic leader with a strong focus on technological advancement, software development, and digital transformation. His professional interests particularly emphasize artificial intelligence, machine learning, medical image analysis, and intelligent healthcare systems for clinical decision support. In addition to his achievements in technology and business, Roman is also an accomplished author. His notable publications, The Scammer’s Dark Ledger and Digital Marketing Trends, have received recognition for their insightful exploration of cyber fraud, digital ecosystems, and emerging business technologies. Through his ongoing research, innovation, and literary contributions, Dr. Roman continues to inspire young entrepreneurs, researchers, and technology enthusiasts both in Bangladesh and internationally.

Affiliations

Nothing added yet.

Education

Nothing added yet.

Honors & Awards

Nothing added yet.

Society Memberships

Nothing added yet.

Expertise

Nothing added yet.

Specialty

Nothing added yet.

Other Online Pages

Scholars in the same field

HK
Dr Harnoor kaur
0 publications
AS
ankit singh
0 publications
VK
Vinay Kumar
0 publications
VS
Vinny Sharma
0 publications
RM
RAVINDRA MOHAN
0 publications
MN
Mohammad Nasir
0 publications
HP
Himanshu Pandey
0 publications
SR
SHUBHRA RAMCHANDANI
0 publications
AK
Ajay Kumar Singha
0 publications

Following

Nobody here yet.

Followers

Nobody here yet.

3 Publications