Juniadul Islam

Juniadul Islam

Auto-generated profile, based on publicly available information

Juniadul Islam

Department of Computer Science and Engineering, American International UniversityBangladesh, Dhaka, Bangladesh

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
19 May 2025 in IEEE Access
Verified
Journal Article
Open access
MRMd. Eshmam Rayed
Md. Eshmam Rayed
JJJamin Rahman Jim
Jamin Rahman Jim
JIJuniadul Islam
Juniadul Islam
MMM. F. Mridha
M. F. Mridha
Md Mohsin KabirMd Mohsin Kabir
Md Mohsin Kabir
JHJakir Hossen
Jakir Hossen
Addressing the global challenge of ensuring a consistent and abundant supply of fresh fruit, particularly in the context of fruit crops, is hindered by the prevalence of plant diseases. These diseases directly impact the quality of fruits, leading to a decline in overall agricultural production. Mango leaf diseases pose significant threats to global mango production, necessitating accurate and efficient classification techniques for timely disease management. Our study focuses on introducing MangoLeafXNet, a customized Convolutional Neural Network (CNN) architecture specifically tailored for the classification of mango leaf diseases, along with a healthy class. Our proposed model comprises six layers optimized to capture intricate disease patterns, demonstrating superior performance compared with prevalent pre-trained models. The model is trained and evaluated on three publicly available datasets: MangoLeafBD (4000 images across 8 classes), MangoPest (16 pest classes including healthy leaves), and MLDID (3000 high-resolution images across 5 classes). Our model demonstrated exceptional classification performance, attaining 99.8% accuracy, 99.62% recall, 99.5% precision, and an F1-score of 99.56%. Further validation on the MangoPest dataset and the Mango Leaf Disease Identification Dataset (MLDID) resulted in accuracies of 96.31% and 96.33%, respectively, confirming the robustness and adaptability of MangoLeafXNet across different datasets. Additionally, we incorporate Explainable AI techniques, including GRAD-CAM, Saliency Map, and LIME to enhance the interpretability of our model. We deployed Gradio web interface to create an interactive interface that allows users to upload images of mango leaves and get real-time classification and validation results along with confidence scores. This contribution not only advances the state-of-the-art in mango leaf disease classification but also offers promising prospects for real-time disease diagnosis and precision agriculture applications, contributing to enhanced crop health monitoring and sustainable mango cultivation practices.

17 May 2025 in Malaysian Journal of Science and Advanced Technology
Verified
Journal Article
Open access
PDF file
JIJuniadul Islam
Juniadul Islam
SKSyeda Aynul Karim
Syeda Aynul Karim
TRTaslimur Rahman
Taslimur Rahman
Restrictive Cardiomyopathy (RCM) is a rare but severe heart disease that is often diagnosed in advanced stages, leading to significant clinical consequences. Detecting RCM at an early stage is essential to slowing disease progression and improving patient outcomes. This study introduces a novel approach that leverages multimodal non-invasive data, including electronic health records (EHRs), medical imaging, and genetic information, to enhance early detection and prognosis. The model underwent rigorous training and validation using the ACDC, MIMIC-IV, ClinVar datasets, employing deep learning techniques for feature extraction and classification. The system demonstrated high accuracy (93%), precision (0.90), and recall (0.91%), surpassing conventional diagnostic methods. By analyzing longitudinal patient data, the proposed method identifies subtle biomarkers and predictive patterns indicative of RCM onset. Additionally, it provides personalized prognostic insights, such as assessing the likelihood of heart failure or arrhythmias, all while seamlessly integrating into existing clinical workflows without requiring additional hardware. This research contributes to the advancement of cardiology by incorporating AI-driven methodologies that improve diagnostic accuracy and enhance patient-centered care.

1 January 2024 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
SKSyeda Aynul Karim
Syeda Aynul Karim
JIJuniadul Islam
Juniadul Islam
This paper proposes a flower recognition system using transfer learning with the ResNet-50 architecture. By utilizing pre-trained weights from ResNet-50, the system classifies ten species of flowers, drawing on an extended dataset with over 8,000 labeled images. The study addresses challenges in deep convolutional neural networks, such as overfitting and local optimality, by fine-tuning the ResNet-50 model. Initially, only the final layers of the model are retrained on the flower dataset, while the pre-trained layers remain frozen. After achieving initial convergence, all layers are unfrozen for full model fine-tuning. The dataset is divided into training, validation, and test sets to evaluate the model’s performance, which is measured using accuracy, and F1-score. The experimental results demonstrate that the transfer learning approach significantly improves classification accuracy and generalization, outperforming traditional methods. This approach proves especially effective in handling visually similar flower species and diverse environmental conditions. The study highlights the potential of transfer learning in enhancing the efficiency and robustness of flower recognition systems, contributing to broader applications in image classification tasks.