Md. Rashed

Mr. Md. Rashed

Information and Communication Engineering, Pabna University of Science and Technology, Pābna, Rājshāhi, Bangladesh
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 March 2025 in Cureus Journal of Computer Science
Verified
Journal Article
Open access
PDF file
Md. RashedMd. Rashed
Md. Rashed
MHMd. Imran Hossain
Md. Imran Hossain
AMAkif Mahdi
Akif Mahdi
GMGulam Mustofa
Gulam Mustofa
Type 2 diabetes mellitus (T2DM) is a major global health issue that significantly reduces life expectancy and impairs overall quality of life. Early diagnosis of T2DM is critical, as it can help prevent or delay the development of associated complications. This study aims to assess the effectiveness of a stacked ensemble machine learning model, incorporating a meta-model approach, for the early detection of T2DM. In the first stage of modeling (Level 1), two base models - random forest (RF) and support vector machines (SVM) - are trained using distinct feature selection, tuning, and optimization strategies. In the second stage, ensemble methods, such as voting and stacking classifiers, are employed to combine the predictions from these base models. The final prediction is made by a meta-model, specifically a gradient boosting classifier (GBC), which classifies individuals as either positive or negative for T2DM. Further classification of positive instances is based on low-, moderate-, or high-risk levels. The system is designed for deployment to enable real-time assessment of diabetes risk. The Meta-Model (GBC), with an accuracy of 99.13%, a precision of 100%, specificity of 100%, and an F1 score of 99.25%, consistently outperforms the base models (SVM and RF) and ensemble models (voting and stacking classifiers), proving highly effective in the early detection of T2DM. This significant accuracy highlights the enormous promise of machine learning methods for assisting in the early identification of T2DM. The findings of this study will significantly enhance precision medicine screening for T2DM, empowering healthcare professionals to diagnose the condition early and ultimately improve patient outcomes.

20 December 2024
Verified
Conference Paper
Closed access
Md. RashedMd. Rashed
Md. Rashed
IHImran Hossain
Imran Hossain
AHAnwar Hossain
Anwar Hossain
Type 2 Diabetes Mellitus (T2DM) is a pressing global health challenge that significantly reduces life expectancy and diminishes quality of life. Early and accurate diagnosis is critical for avoiding the onset of serious complications. In this study, we proposed an Integrated Ensemble Framework (IEF) that utilizes a Stacking Classifier and a Fusion Model (FM) approach to enhance the accuracy of (T2DM) prediction. Initially, the outputs of two base models, the Support Vector Machine (SVM) and Gradient Boosting Classifier (GBC), are combined using the Stacking Classifier. The combined predictions are then processed through the final decision-making stage, where the Integrated Ensemble Framework is acted based on the Random Forest (RF) algorithm. The results demonstrate that IEF achieves exceptional performance, with an accuracy of 99.09%, precision of 100%, sensitivity of 98.53%, F1 score of 99.26%, and Matthews Correlation Coefficient (MCC) of 98.23%. These findings indicate that the IEF, which integrates outputs from base models, improves overall diagnostic accuracy. This IEF approach leverages the strengths of multiple algorithms, yielding more reliable predictions for T2DM diagnosis. The significant improvement in accuracy validates the potential of hybrid machine learning models in supporting early-stage diagnosis and personalized treatment planning, offering a promising solution for enhancing healthcare outcomes in T2DM patients.

31 August 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Muhammad JamilMuhammad Jamil
Muhammad Jamil
AKAdnan Kavak
Adnan Kavak
Hossein FotouhiHossein Fotouhi
Hossein Fotouhi
Md. RashedMd. Rashed
Md. Rashed
EGEmre Gezer
Emre Gezer
Gautam SrivastavaGautam Srivastava
Gautam Srivastava
Background/Objectives: Multidimensional lifestyle interventions that combine healthy diet, physical activity, and psychosocial support are central to effective self-management of type 1 and type 2 diabetes. Although digital health tools can improve lifestyle monitoring, existing AI-based dietary assessment methods often struggle to estimate food quantity accurately because food size and scale are difficult to determine from images. This can lead to inconsistent estimates of food mass and energy content. Methods: In this study we introduce nutrition and exercise modules of our AI-assisted Diabetes Care (AIDCare) mHealth digital platform developed for diabetes patients. For effective diet management, we present the PC2FoodNet model, which uses an EfficientNetV2-S backbone with multi-task regression and food-density priors to jointly estimate food volume, mass, and nutrients. For patient safety, we put nutrition-in-the-loop for making diet plans and rectifications of patients’ daily key nutrient intake according to the requirements of the patients. The exercise module includes professionally designed exercises using Unreal Engine’s MetaHuman plugin. The model was evaluated using 4-fold stratified cross-validation on a dataset of 22,070 images covering 40 Turkish food categories. Results: PC2FoodNet achieved a mean Top-1 classification accuracy of 94.39% ± 0.47% and Top-5 accuracy of 98.90% ± 0.18% across the four folds. The corresponding Macro-F1 and Weighted-F1 scores were 93.14% ± 0.59% and 94.16% ± 0.36%, respectively. The physics-constrained regression framework achieved mean RMSE values of 3.01 mL for food volume, 30.17 g for mass, and 57.55 kcal for energy. The confidence-based referral mechanism identified uncertain cases for clinical review, resulting in a clinical referral rate of 23.81%. Conclusions: AIDCare combines physically consistent AI-based dietary assessment with personalized physical activity and continuous psychosocial support. By keeping nutrition involved when AI predictions are uncertain, the proposed framework reduces the risks associated with fully automated lifestyle recommendations. This approach provides a practical foundation for safer, more personalized, and evidence-based diabetes lifestyle management.

31 July 2025
Verified
Conference Paper
Closed access
HIHabibul Islam
Habibul Islam
Md. RashedMd. Rashed
Md. Rashed
NPNitun Kumar Podder
Nitun Kumar Podder
IHImran Hossain
Imran Hossain
AMAnkur Kumar Mondol
Ankur Kumar Mondol
Chronic Obstructive Pulmonary Disease (COPD) is a progressive respiratory disorder that causes airflow obstruction and breathing difficulties, making early diagnosis essential for effective treatment and management. Traditional diagnostic methods, such as auscultation and pulmonary function tests, rely on expert interpretation, leading to variability and potential delays in detection. To address these challenges, this study introduces a hybrid deep-learning framework that leverages multiple models for accurate respiratory sound classification. We explore several deep learning techniques, including 1D-CNN + LSTM, spectrogram-based CNNs such as VGG19, ResNet101, and EfficientNet, CBAM, DenseNet, and waveform-based models like WaveNet and SoundNet. Among these models, WaveNet demonstrates superior performance, achieving 95% accuracy, 99% precision, 99% recall, 99% F1-score, 75.38% G-mean, $\mathbf{6 6. 5 7 \%}$ MCC, and an RMSE of $\mathbf{1 4. 7 4 \%}$, outperforming traditional and other deep learning-based approaches. Our experimental results highlight the effectiveness of deep learning in respiratory sound analysis, with WaveNet proving to be a highly reliable model for early COPD detection. This framework enhances diagnostic accuracy, providing a promising solution for automated respiratory disease classification and early medical intervention.

2 November 2025
Verified
Conference Paper
Closed access
Md. RashedMd. Rashed
Md. Rashed
IHImran Hossain
Imran Hossain
ZIZahidul Islam
Zahidul Islam
FNFeroza Naznin
Feroza Naznin
Real-time detection of safety-critical events such as fires, traffic accidents, and vehicle license plates is a key enabler for intelligent transportation and urban surveillance systems. In high-density CCTV networks, these tasks must be performed under diverse environmental conditions, including low light, motion blur, and compression artifacts, while meeting strict latency requirements. Conventional single-frame object detection methods often suffer from unstable predictions, producing false positives that can overwhelm monitoring operators and automated alert systems. To address these challenges, we propose a temporal-enhanced YOLOv8-based detection framework that explicitly incorporates temporal reasoning into the detection pipeline. Our approach combines histogram equalization for enhanced visual contrast, YOLOv8 for spatial detection, ByteTrack for robust object association, and a 1D Temporal Convolutional Network (1D-TCN) for temporal filtering of event predictions. This integration not only stabilizes detections across frames but also significantly reduces false alarms in continuous video streams. And dual-channel alert system, integrating multimedia notifications and voice calls, ensures a rapid response from stakeholders. Performance was evaluated against state-of-the-art methods, achieving an overall accuracy of 91.60%, surpassing techniques like color analysis with wavelet transform and YOLOv8-EfficientNetB0. With low latency (13.3 ms for fire, 11.4 ms for accidents) and high precision (94.4% for accidents, 95.4% for number plates), it excels in challenging conditions. This system contributes significantly to human well-being by enabling faster emergency response, enhancing public safety, and supporting smarter urban management.

28 September 2026 in Nutrients
Verified
Journal Article
Open access
PDF file
Muhammad JamilMuhammad Jamil
Muhammad Jamil
AKAdnan Kavak
Adnan Kavak
Hossein FotouhiHossein Fotouhi
Hossein Fotouhi
Md. RashedMd. Rashed
Md. Rashed
EGEmre Gezer
Emre Gezer
Gautam SrivastavaGautam Srivastava
Gautam Srivastava
Background/Objectives: Multidimensional lifestyle interventions that combine healthy diet, physical activity, and psychosocial support are central to the effective self-management of type 1 and type 2 diabetes. Although digital health tools can improve lifestyle monitoring, existing AI-based dietary assessment methods often struggle to estimate food quantity accurately because the food size and scale are difficult to determine from images. This can lead to inconsistent estimates of food mass and energy content. This paper aimed to develop and technically evaluate PC2FoodNet, an AI-based framework for food recognition and physics-constrained physical quantity estimation, and to integrate dietary assessment and exercise support within the proposed AI-assisted Diabetes Care (AIDCare) mHealth platform for multidisciplinary lifestyle support. Methods: The AIDCare platform incorporates AI-assisted nutrition and professionally guided exercise modules to support personalized lifestyle management for individuals with diabetes. For dietary assessment, PC2FoodNet uses an EfficientNetV2-S backbone with multi-task regression and food-density priors to jointly model food volume, mass, and energy. A nutrition professional-in-the-loop approach supports the development and review of individualized diet plans and the assessment of patients’ daily key nutrient intake according to individual nutritional requirements. The exercise module includes professionally designed exercises using Unreal Engine’s MetaHuman plugin. The model was evaluated using four-fold stratified cross-validation on a dataset of 22,070 images covering 40 Turkish food categories. For physical quantity modeling, volume, mass, and energy targets were derived from standardized category-level references anchored to a 100 g reference portion rather than from image-specific ground-truth measurements. Results: PC2FoodNet achieved a mean Top-1 classification accuracy of 94.39% ± 0.47% and Top-5 accuracy of 98.90% ± 0.18% across the four folds. The corresponding Macro-F1 and Weighted-F1 scores were 93.14% ± 0.59% and 94.16% ± 0.36%, respectively. For the standardized category-level reference targets, the physics-constrained regression framework achieved mean MAE and RMSE values of 2.14 mL and 3.01 mL for reference volume, 21.65 g and 30.17 g for reference mass, and 41.20 kcal and 57.55 kcal for reference energy across all 22,070 pooled out-of-fold predictions. The confidence-based referral mechanism identified uncertain cases for clinical review, resulting in a clinical referral rate of 23.81%. Conclusions: AIDCare combines physics-constrained AI-based dietary assessment with personalized physical activity and continuous psychosocial support. A nutrition professional remains involved when AI predictions are uncertain, reducing the risks associated with fully automated lifestyle recommendations. The proposed approach provides a practical foundation for safer, more personalized, and evidence-based diabetes lifestyle management.
1