BTBelayneh Matebie Taye

Belayneh Matebie Taye

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Belayneh Matebie Taye has a total of 44 co-authors. Here are the top co-authors by number of shared publications:

  • Rania M. Ghoniem

    Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia

    7 shared publications
  • Salil Bharany

    Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, India

    6 shared publications
  • Salil Bharany

    Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, India

    6 shared publications
  • Sheifali Gupta

    Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, India

    6 shared publications
  • Ateeq Ur Rehman

    School of Computing, Gachon University, Seongnam-si, Republic of Korea

    5 shared publications
  • Ateeq Ur Rehman

    Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, Tamil Nadu, India

    4 shared publications

Latest Publications

  • Open Access

    Multi-level attention DeepLab V3+ with EfficientNetB0 for GI tract organ segmentation in MRI scans

    by Neha Sharma, Sheifali Gupta, Fuad Ali Mohammed Al-Yarimi, Upinder Kaur, Salil Bharany, Ateeq Ur Rehman, Belayneh Matebie Taye

    Gastrointestinal (GI) cancer is a fatal malignancy that affects the organs of the GI tract. The rising prevalence of GI cancer has recently influenced the health of millions of people. To treat GI cancer, radiation oncologists must carefully focus X-rays on tumors while avoiding other unaffected organs in the GI tract. This research proposes a novel approach to segment healthy organs within the GI tract from magnetic resonance imaging (MRI) scans using a multi-level attention DeepLab V3 + model. The proposed model aims to enhance segmentation performance by incorporating state-of-the-art approaches, such as atrous convolutions and EfficientNet B0 as an encoder, by leveraging hierarchical information present in the data. Here, the attention mechanism is applied at multiple levels of features, i.e., low, medium, and high, to capture and leverage hierarchical information present in the data. At the same time, EfficientNet B0 extracts deep and meaningful features from input images, providing a robust representation of GI tract structures. Hierarchical feature fusion combines local and global contextual information, resulting in more accurate segmentation with fine-grained details. The model is implemented using the UW-Madison dataset, comprising MRI scans from 85 patients with gastrointestinal cancer. To optimize the model, it has been simulated with different parameters, including optimizers, the number of epochs, and cross-validation folds. The model has achieved performance metrics such as a model loss of 0.0044, a dice coefficient of 0.9378, and an Intersection over Union (IoU) of 0.921.


  • Open Access

    A transfer learning–based approach for automated bone fracture classification in X-ray imaging

    by Ruchika Bhuria, Sheifali Gupta, Rania M. Ghoniem, Jaibir Singh, Suman Rani, Belayneh Matebie Taye, Salil Bharany

    Background: Bone fractures present a significant diagnostic challenge in medical imaging, necessitating accurate and automated classification methods. Recent advancements in deep learning have greatly enhanced the diagnostic precision while reducing human error. Objectives: This study proposes an ensemble deep learning model, EnsembleAttenBoneNet, that integrates fine-tuned ResNet50 and EfficientNetB3 models augmented with a Squeeze-and-Excitation (SE) attention mechanism, for robust classification of bone fractures in X-ray images. Design: The dataset consists of ten distinct fracture categories, such as avulsion, comminuted, greenstick, and pathological fractures. Methods: Preprocessing techniques, including resizing, normalization, and augmentation, have been applied to improve generalization. Features extracted from both networks were concatenated and refined using the SE attention module to enhance feature representation. Results: The proposed model achieved a classification accuracy of 99.48%, outperforming the individual models (EfficientNetB3: 98.56%, ResNet50: 97.86%). Conclusion: Experimental results affirm that integrating deep learning models with attention mechanisms significantly improve diagnostic accuracy, rendering the model a valuable tool for clinical fracture detection. Future research will investigate dataset extension and conduct real-world validation to enhance its usability in medical imaging.


  • Open Access

    Enhancing Cyber‐Physical System Security Through Privacy‐Preserving Darknet Traffic Classification With XGBoost

    by Ankita Kumari, Upinder Kaur, Sheifali Gupta, Jaibir Singh, Ajay Kumar, Suman Rani, Belayneh Matebie Taye, Nitin Kumar, Vivek John, Kaushal Kumar, et al.

    The growing use of anonymous communication networks, such as the Darknet, creates significant difficulties in identifying malicious operations hiding in encrypted data communications. Traditional machine‐learning models often struggle to accurately classify such traffic due to feature redundancy, class imbalance and the complexity of traffic patterns. This study provides a framework for classifying Darknet traffic using the CIC‐Darknet2020 dataset with a boosted eXtreme Gradient Boosting (XGBoost) algorithm. The proposed method represents network traffic characteristics by incorporating a structured feature‐selection mechanism, dimensionless feature weighting and synthetic minority over‐sampling technique (SMOTE)‐based class balancing to refine them. Additionally, hyperparameter optimisation is performed to improve the model's performance and efficiency. Compared with conventional classifiers such as Support Vector Machines (SVM), Decision Tree (DT) and Random Forest (RF), the proposed approach has achieved better performance, with an accuracy of 96.25%, a precision of 94.3%, a recall of 90.8% and an F1 score of 92.85%. The results show that the model not only improves classification accuracy but also provides better generalisation and robustness in detecting complex Darknet traffic patterns. Furthermore, the framework ensures privacy because it uses only flow‐level features and therefore does not need to inspect packet payloads. These results highlight the effectiveness of the proposed approach for real‐world cybersecurity applications involving encrypted network environments.

  • Open Access

    Attention‐Driven Real‐Time Fusion for Robust Intrusion Detection in Control Networks

    by Ateeq Ur Rehman, Sunawar Khan, Muhammad Adnan Khan, Ayman Altameem, Salil Bharany, Belayneh Matebie Taye, Ahmad Almogren

    The increasing prevalence of cyber threats targeting industrial control systems (ICSs) has made robust and reliable intrusion detection systems (IDSs) essential for securing critical infrastructure. This study proposes an explainable, attention‐driven feature fusion framework for real‐time intrusion detection in Distributed Network Protocol 3 (DNP3) networks. To improve model performance, the proposed research hypothesizes three hybrid deep learning models: CNN + XGBoost (XGB), CNN + bidirectional long short‐term memory (BiLSTM), and CNN + BiGRU, each incorporating a custom attention layer to emphasize significant features for enhanced classification accuracy. The proposed framework preprocesses 81 numerical features using StandardScaler and reshapes the resulting data to fit the CNN architecture. Experiments are conducted on a balanced 11‐class, DNP3 dataset comprising 5126 training samples and 2200 test samples. Among the evaluated models, CNN + XGBoost model outperformed others, achieving an accuracy of 96.50% and macro precision, recall, and F1‐scores of 0.965. It outperforms CNN + BiGRU, which achieves 96.23% accuracy and a macro F1‐score of 0.962, and CNN + BiLSTM, which achieves 91.59% accuracy and a macro F1‐score of 0.915. To enhance model transparency and facilitate security analysis, multiple explainability techniques are employed, including gradient‐weighted class activation mapping (Grad‐CAM) for per‐filter feature visualization, SHapley Additive exPlanations (SHAP) based on 50 representative samples, and local interpretable model‐agnostic explanation (LIME) for individual prediction‐level explanations. Model performance is further evaluated using confusion matrices and receiver operating characteristic (ROC) and precision–recall (PR) curves. In addition, the low inference latency demonstrated by the proposed models highlights their potential suitability for real‐time ICS environments. This scalable and interpretable approach offers significant improvements to ICS security and holds potential for application to other network protocols.

  • Open Access

    Internet of Medical Things‐Driven Deep Learning Approach for Automated Heart Sound Classification

    by Muhammad Sajid, Ghulam Gilanie, Syeda Naila Batool, Salil Bharany, Rania M. Ghoniem, Amna Ikram, Shefali Gupta, Belayneh Matebie Taye

    The Internet of Medical Things (IoMT) has emerged as a transformative force in healthcare, enabling the development of innovative and noninvasive diagnostic tools that leverage connected technologies. This research focuses on the application of IoMT in conjunction with deep learning techniques to detect and classify heart diseases through the analysis of heart sounds, a method that promises to enhance the accuracy and accessibility of diagnostics. We proposed frameworks that utilize advanced signal processing algorithms to capture and analyze heart sound data, that is, phonocardiograms (PCGs) collected from District Headquarters Hospital, Bahawalnagar, Pakistan. Deep learning models, specifically convolutional neural networks (CNN) and long short‐term memory (LSTM), and a combination of these are employed to identify patterns associated with various cardiac conditions. This study involves a comprehensive dataset comprising annotated heart sounds from diverse demographics, ensuring the robustness and generalizability of the proposed models. The proposed methodology involves using three models: one‐dimensional CNN (1D‐CNN), LSTM, and a combination of 1D‐CNN + LSTM to classify heart sounds into normal, murmur, extra‐systole, and artifact categories. Results demonstrate high accuracy in the classification of common heart diseases, including normal, murmur, extra‐systole, and artifact, surpassing traditional diagnostic methods. The model achieved the highest accuracy for normal cases as of 95%, for murmur cases as of 94%, for extra‐systole cases as of 95%, and for artifact cases as of 96%. This approach holds significant potential for improving patient outcomes through timely and accurate diagnostics, thus exemplifying the power of digital health innovations in modern medicine.


  • Open Access

    SAASU‐UNet++: A Hybrid Swin Transformer–Based Deep Learning Model for Robust Breast Tumour Segmentation in Ultrasound Images

    by Rahul Singh, Sheifali Gupta, Ahmad Almogren, Salil Bharany, Ateeq Ur Rehman, Belayneh Matebie Taye, Ayman Altameem

    Breast cancer is one of the most prevalent and life‐threatening diseases affecting women worldwide, where early detection is crucial for improving survival rates. Ultrasound imaging is widely used due to its non‐invasive, cost‐effective nature and suitability for dense breast tissues. This study introduces Swin‐attention‐enhanced atrous spatial pyramid pooling (ASPP)‐attention‐squeeze‐and‐excitation (SE) uncertainty‐aware U‐Net++ (SAASU‐UNet++), a novel hybrid segmentation framework designed for precise breast tumour segmentation in ultrasound images. The model incorporates a Swin Transformer encoder to capture global context, an attention‐enhanced ASPP module for multi‐scale feature extraction, and a hybrid U‐Net++ decoder embedded with SE blocks for channel recalibration. To improve robustness and uncertainty awareness, Monte Carlo dropout is applied. Training was performed with the Adam optimiser (batch size 32, 100 epochs) on the BUSI dataset containing 780 annotated images (normal, benign, and malignant). Images were resized to 224 × 224, normalised, and augmented with flipping, rotation, and zooming. The proposed model achieved a Dice Coefficient of 96.25% and a Jaccard Index of 92.34%, outperforming state‐of‐the‐art approaches. Ablation studies highlighted the effectiveness of each component, and visual results confirmed close alignment with ground truth, even in challenging cases. SAASU‐UNet++ demonstrates strong potential for real‐world clinical integration in automated breast cancer diagnosis.


  • Open Access

    Retinal vessel segmentation using multi scale feature attention with MobileNetV2 encoder

    by Tanishq Soni, Sheifali Gupta, Salil Bharany, Ateeq Ur Rehman, Rania M. Ghoniem, Belayneh Matebie Taye

    This work introduces the MSFAUMobileNet model, a complex U-Net structure tailored for retinal blood vessel segmentation, which is a critical process for detecting and monitoring retinal diseases such as diabetic retinopathy, glaucoma, and age-related macular degeneration (AMD). The model uses Multi-Scale Feature Aggregation (MSFA), Residual Connections, and Attention Mechanisms to enhance its segmentation accuracy. Utilizing MobileNetV2 as the encoder, the model is capable of effectively generating 13 bottleneck layers' worth of hierarchical features. Although residual connections and attention mechanisms are useful in improving the segmentation process and guaranteeing the precise outlining of intricate vascular networks, MSFA extracts spatial information at various resolutions. The model was tested on the DRIVE dataset and produced exceptionally high scores with accuracy at 99.99%, Dice coefficient at 99.95%, and Intersection over Union (IoU) at 99.94%. These scores show how efficiently the model separates the complex retinal network, enabling early treatment and detection of retinal disease. MSFAUMobileNet is a good medical image analysis software for real clinical practice owing to its computational speed and precision, particularly in the management of retinal disease.


  • Open Access

    Hybrid AI Model With CNNs and Vision Transformers for Precision Pest Classification in Crops

    by Neha Sharma, Fuad Ali Mohammed Al‐Yarimi, Salil Bharany, Ateeq Ur Rehman, Belayneh Matebie Taye

    Crop pests pose a significant threat to agricultural productivity, making it essential to develop effective pest management techniques. Prompt and accurate identification of pests is necessary for effective pest management and preventing significant damage. This paper proposes HyPest‐Net, a hybrid deep learning architecture that integrates convolutional neural networks (CNNs) for local feature extraction, channel and spatial attention mechanisms for refining salient features, and a vision transformer (ViT‐B/16) module for modeling long‐range dependencies. This integrated hybrid architecture enables accurate pest classification by resolving challenges posed by visually similar species, background clutter, and varied illumination issues that standalone CNNs or ViTs inadequately address. Preprocessing and augmentation have been used to enhance the generalizability of the proposed model over the dataset. The proposed model was evaluated on two benchmark datasets: a rice pest dataset (5 classes) and the dangerous farm insects dataset (15 classes). Experimental results demonstrate that HyPest‐Net achieved an accuracy of 0.95 on the rice pest dataset. The proposed model achieved a precision of 0.95, a sensitivity of 0.95, a specificity of 0.94, and an F1 score of 0.94. The proposed model achieved an accuracy of 0.93 on the dangerous farm insects dataset. The proposed HyPest‐Net model offers a lightweight yet powerful solution for real‐time, explainable pest classification, supporting practical applications in precision agriculture.


  • Open Access

    A Systematic Review of Blockchain, AI, and Cloud Integration for Secure Digital Ecosystems

    by Jaibir Singh, Salil Bharany, Suman Rani, Ateeq Ur Rehman, Belayneh Matebie Taye, Ruby Pant, Upinder Kaur


  • Open Access

    A multi stage deep learning model for accurate segmentation and classification of breast lesions in mammography

    by Sultan Ahmad, Eali Stephen Neal Joshua, Nakka Thirupathi Rao, Rania M. Ghoniem, Belayneh Matebie Taye, Salil Bharany

    Mammography is a routine imaging technique used by radiologists to detect breast lesions, such as tumors and lumps. Precise lesion detection is critical for early treatment and diagnosis planning. Lesion detection and segmentation are still problematic due to inconsistencies in image quality and lesion properties. Hence, this work presents a new Multi-Stage Deep Lesion model (MSDLM) for enhancing the efficacy of breast lesion segmentation and classification. The suggested model is a Three-Unit Two-Parameter Gaussian model with U-Net, EfficientNetV2 B0, and a domain CNN classifier. U-Net is utilized for lesion segmentation, EfficientNetV2 B0 is employed for image deep feature extraction, and a CNN classifier is used for lesion classification. The MSDLM feature cascade is designed to enhance computational efficiency while retaining the most relevant features for breast cancer detection and identifying the minimum number of features most important in the detection and classification of breast lesions in mammograms. The Multi-Stage Deep Learning Model (MSDLM) was validated using two benchmark datasets, CBIS-DDSM and the Wisconsin breast cancer dataset. Segmentation and classification tasks were indicated by accuracy values of 97.6%, indicating reliability in breast lesion detection. Its sensitivity of 91.25% indicates its reliability in detecting positive cases, a basic requirement in medical diagnosis. It also indicated an Area Under the Curve (AUC) of 95.75%, indicating overall diagnostic performance irrespective of thresholds. The Intersection over Union (IoU) of 85.59% verifies its reliability to detect lesion areas in mammograms. MSDLM with a Gaussian distribution provides precise localization and classification of breast lesions. The MSDLM model allows for improved information flow and feature refinement. The algorithm outperforms baseline models in both effectiveness and computational cost. Its performance on two diverse datasets verifies its generalizability and enables radiologists to receive exact automated diagnoses.