RARuhul Amin

Ruhul Amin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ruhul Amin has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Data-Driven Prediction of Maternal Health Risk Level Using Machine Learning Algorithms

    by Ruhul Amin, Muhammad Muzammil, Jannatul Mauya, Shamim Reza, Maniruzzaman, Choudhury Mukammel Wahid, Hyoungju Kim, Jungpil Shin

    Identification of maternal health risks is crucial due to the direct impact on the fetus. Pregnancy-related complications can be reduced through quality care and continuous health monitoring for expectant mothers. However, identifying risk levels and providing appropriate treatment remains challenging, particularly in resource-limited settings. A major contributor to maternal and child morbidity and mortality is the failure to identify risk levels at an early stage. To address this issue, we conducted extensive statistical data analysis and applied machine learning techniques to determine maternal risk levels (High or Low). The study utilized data from 1,205 pregnant women collected from Kurigram General Hospital, Bangladesh. Exploratory data analysis (EDA) was performed to uncover hidden patterns in the dataset. Missing values in continuous features were imputed using a skewness- and kurtosis-based method—KDE-MICE—while logistic regression was used to impute missing values in categorical features. Outliers were detected using two methods: Z-score and Inter-quartile Range (IQR), and were treated by replacing them with median values. Following data preprocessing, three feature selection techniques—Mutual Information (MI), correlation analysis, and permutation feature importance (PFI)—were employed to identify key risk factors. Significant predictors for maternal risk level included GD, pre-existing diabetes, BMI, HR, and mental health. Eight ML algorithms—LR, DT, RF, SVM, KNN, NB, GB, and AdaBoost were used for maternal risk prediction. GB based model demonstrated the highest performance: 98.17% accuracy, 98.10% precision, 98.09% recall, and a 98.09% F1-score.


  • Open Access

    Sophisticated Audio Source Separation: A Statistical Exploration of Clarity and Precision With FastICA

    by Razu Ahmed, Jannatul Mauya, Shamim Reza, Ruhul Amin

    This study evaluates audio source separation with Fast Independent Component Analysis (FastICA) in a fully specified, reproducible pipeline and benchmarks it against Principal Component Analysis (PCA) and Nonnegative Matrix Factorization (NMF). Three conversational recordings collected at the Department of Statistics, Pabna University of Science and Technology were canonicalized to 48 kHz WAV 96.63 s each, converted to mono, trimmed at 25 dB, RMS‐normalized, and time‐aligned. Sources were mixed with a fixed 3 × 3 row‐normalized Gaussian matrix. FastICA used parallel updates with a logcosh nonlinearity and unit‐variance whitening; PCA served as a multichannel linear baseline; NMF operated on a mono short‐time Fourier transform with KL divergence and NNDSVDA initialization, followed by soft masking and inverse transform. Performance was computed with BSS Eval after best‐permutation and scale alignment and summarized over 10 runs as mean ± SD. FastICA achieved Signal‐to‐Distortion Ratio (SDR) 53.51 ± 0.07 dB, Signal‐to‐Interference Ratio (SIR) 53.52 ± 0.07 dB, and Signal‐to‐Artifact Ratio (SAR) 79.58 ± 0.00 dB, well above a 20 dB high‐quality SDR threshold. PCA yielded SDR 2.79 ± 0.00 dB, SIR 2.79 ± 0.00 dB, SAR 80.64 ± 0.00 dB; NMF produced SDR −2.26 ± 0.00 dB, SIR 0.41 ± 0.00 dB, SAR 4.80 ± 0.00 dB. Waveform and spectrogram visualizations, together with descriptive, high‐order, and entropy statistics, corroborate these outcomes. The results establish FastICA as an effective classical approach for audio source separation and provide a transparent reference pipeline for comparative studies using SDR, SIR, and SAR.

  • Open Access

    Improved multiscale attention based deep learning approach for automated sugarcane leaf disease detection using BSRI data

    by Jannatul Mauya, Ruhul Amin, Imam Hossain, Sabba Ruhi, Shamim Reza

    Early and accurate detection of sugarcane leaf diseases is critical for improving crop productivity and reducing economic losses in the agricultural sector. Timely interventions enable sustainable crop management and better resource use. In this study, we propose a deep learning-based approach for sugarcane leaf disease classification that leverages a novel architecture, the Multi-scale Attention-based Dense Residual Network (MADRN). The MADRN model integrates dense residual learning and multi-scale attention mechanisms to effectively capture fine-grained, disease-specific features and address challenges related to domain variability and complex data patterns. Two datasets are used to evaluate the model: a Kaggle dataset and a blended dataset created by combining Kaggle images with those from the Bangladesh Sugarcrop Research Institute (BSRI), simulating real-world conditions. All images undergo preprocessing steps, including resizing, normalization, and data augmentation, before training. Additionally, several baseline models (CNN, VGG16, MobileNetV2, and XceptionNet) are fine-tuned and compared with the MADRN model. Experimental results demonstrate that MADRN consistently outperforms baseline models in accuracy, precision, recall, and F1-score across both datasets, achieving up to 94.78% accuracy on the Kaggle dataset and 92.25% on the blended dataset. These findings highlight MADRN’s superior ability to learn discriminative features and generalize effectively across diverse data sources, making it a promising tool for precision agriculture and disease management. To facilitate practical implementation, a web-based application is developed, enabling real-time and user-friendly disease detection. This research lays a strong foundation for the development of accurate, scalable, and practical disease classification tools that can support sustainable agricultural practices.


  • Open Access

    Grid Search Based Hyperparameter-Tuned Deep Learning Model for Osteoporosis Diagnosis with Bi-Cubic Interpolation of X-Ray Images

    by Ruhul Amin, Md.SHamim Reza, Dewan Ahmed Muhtasim, Jungpil Shin, Maniruzzaman, Md.MAhfujul Hasan

    A non-communicable disease that affects the bones is called osteoporosis (OP). It results in altered bone microstructures, insufficient bone regeneration, and decreased bone mineral density (BMD). Until the disease progresses, individuals often don't realize they have it. Even with the widespread use of deep learning (DL) and machine learning (ML) algorithms, the early diagnosis of osteoporosis patients can still be improved. By automatically extracting hierarchical features from X-ray images through the application of a wide range of competitive ML (Gaussian Process (GP) kernel, SVM, XGBoost, Bagging), and DL models, we provide highly accurate and consistent predictions to accurately and early predict osteoporosis patients. In the proposed approach, we extracted and integrated significant features using three image feature extractors (LBP, CLBP, and HOG) with 95% PCA. Furthermore, we proposed upscaling (2 × &4 ×) employing bicubic interpolation to enhance the image intensity. Subsequently, we applied the interpolated images to the suggested customized convolution neural network (CNN) model to improve the diagnostic performance. The proposed GP model outperformed other GP kernel and traditional ML models, achieving notable results with 67.74% accuracy, 61.97% precision, 92.52% recall, 74.12% F1-score, and a 67.77% AUC. To enhance osteoporosis classification, we developed a hybrid stacked CNN model, which demonstrated excellent performance on interpolated images. The proposed CNN model achieved state-of-the-art results, with 98% accuracy on the training set, and 95% accuracy on both the test and validation sets, significantly surpassing existing models. The numerical comparison shows the CNN model's superiority, with about a 30% increase in accuracy over the GP model. However, this research demonstrates the strong efficacy of the CNN model in handling complicated image data, making it a more sophisticated tool for osteoporosis detection.


  • Open Access

    Unlocking stroke prediction: Harnessing projection-based statistical feature extraction with ML algorithms

    by Saad Sahriar, Sanjida Akther, Jannatul Mauya, Ruhul Amin, Shahajada Mia, Sabba Ruhi, Shamim Reza


  • Open Access

    Improving diabetes disease patients classification using stacking ensemble method with PIMA and local healthcare data

    by Md Shamim Reza, Ruhul Amin, Rubia Yasmin, Woomme Kulsum, Sabba Ruhi


  • Open Access

    Intensive Statistical Exploration to Identify Osteoporosis Predisposing Factors and Optimizing Recognition Performance With Integrated GP Kernels

    by Ruhul Amin, Shamim Reza, Maniruzzaman, Al Mehedi Hasan, Hyoun-Sup Lee, Si-Woong Jang, Jungpil Shin

    Osteoporosis, a common skeletal disorder, necessitates the identification of its risk factors to develop effective preventive measures. It is crucial to identify the underlying risk factors and their relationships with the response class attribute. Different machine learning (ML) algorithms and feature selection approaches are used to estimate the risk of osteoporosis. However, ML-based algorithms may struggle to detect risk factors as well as grading of osteoporosis due to different measurement scale of data and their probability distributional assumptions. Violation of these assumptions and results interpretation may be improper in the presence of heteroscedasticity, or unequal variance in data. In this study, we seek to overcome distribution assumption constraints and improve the interpretability of our results by using rigorous statistical approaches, ensuring a robust and trustworthy study of osteoporosis risk variables. The study dataset consists of 40 clinical, lifestyle, and genetic attributes, allowing for a comprehensive analysis of potential risk factors associated with osteoporosis. In the analysis, after confirming the normality assumption using Kolmogorov-Smirnov and Shapiro-Wilk tests, independent t-test assess the factor ALT, FBG, HDL-C, LDL-C, FNT, TL, TLT, and URIC has a substantial impact on the risk of developing osteoporosis. The Mann-Whitney U test for the non-normal FN variable likewise showed a p-value of less than 0.05, indicating that this variable has a significant effect on the likelihood of developing osteoporosis. Based on the chi-square test p-values for the categorical factors, gender, calcium, calcitriol, bisphosphonate, calcitonin, COPD, CAD, and drinking have a severe significant risk of osteoporosis. For developing the predictive Gaussian Process (GPs) model, we proposed two customized integrated GP kernels into the analysis to enhance the modeling of complex relationships within the data. The proposed GP kernel model (modified kernel 2) outperforms the other individual kernels in this experiment and has the best accuracy score of 86.64% and AUC score of 86.63% on osteoporosis data. Moreover, a simulation study is also conducted to robustify the proposed model, the results are improved by different evaluation matrices ranging in accuracy from 0.60-11.41% and AUC from 0.50-11.60%.


  • Open Access

    A Fine-Tuned Hybrid Stacked CNN to Improve Bengali Handwritten Digit Recognition

    by Ruhul Amin, Shamim Reza, Yuichi Okuyama, Yoichi Tomioka, Jungpil Shin

    Recognition of Bengali handwritten digits has several unique challenges, including the variation in writing styles, the different shapes and sizes of digits, the varying levels of noise, and the distortion in the images. Despite significant improvements, there is still room for further improvement in the recognition rate. By building datasets and developing models, researchers can advance state-of-the-art support, which can have important implications for various domains. In this paper, we introduce a new dataset of 5440 handwritten Bengali digit images acquired from a Bangladeshi University that is now publicly available. Both conventional machine learning and CNN models were used to evaluate the task. To begin, we scrutinized the results of the ML model used after integrating three image feature descriptors, namely Binary Pattern (LBP), Complete Local Binary Pattern (CLBP), and Histogram of Oriented Gradients (HOG), using principal component analysis (PCA), which explained 95% of the variation in these descriptors. Then, via a fine-tuning approach, we designed three customized CNN models and their stack to recognize Bengali handwritten digits. On handcrafted image features, the XGBoost classifier achieved the best accuracy at 85.29%, an ROC AUC score of 98.67%, and precision, recall, and F1 scores ranging from 85.08% to 85.18%, indicating that there was still room for improvement. On our own data, the proposed customized CNN models and their stack model surpassed all other models, reaching a 99.66% training accuracy and a 97.57% testing accuracy. In addition, to robustify our proposed CNN model, we used another dataset of Bengali handwritten digits obtained from the Kaggle repository. Our stack CNN model provided remarkable performance. It obtained a training accuracy of 99.26% and an almost equally remarkable testing accuracy of 96.14%. Without any rigorous image preprocessing, fewer epochs, and less computation time, our proposed CNN model performed the best and proved the most resilient throughout all of the datasets, which solidified its position at the forefront of the field.