BSB. M. Ahamed Shafeeq

B. M. Ahamed Shafeeq

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


B. M. Ahamed Shafeeq has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A spatiotemporal deep learning framework for detecting unusual human activity in surveillance videos

    by Manoj Kumar, Mantosh Biswas, Anoop Kumar Patel, Abhay Kumar, Kumar Abhishek, Ahamed Shafeeq B. M.

    With smart gadgets and computers everywhere, real-time video monitoring is now necessary to keep people secure and lower the chance of unexpected human actions. However, current surveillance systems have a lot of trouble effectively spotting unusual actions in real life. Most of the advanced anomaly detection algorithms are trained and tested on synthetic or simulated video datasets. These datasets frequently do not show how complicated and different real-life settings can be. Because of this, their usefulness and capacity to be used in real life are still restricted. We propose a transfer learning-based hybrid deep framework for finding unusual activity in real-world surveillance. We test the model using raw video streams from a subset of the UCF-Crime dataset that shows actual situations of people doing things. First, a pre-trained DenseNet-201, a convolutional neural network, extracts spatial data from video frames that have already been processed. A Bidirectional Long Short-Term Memory (Bi-LSTM) network is used to describe temporal relationships between video sequences in a useful way. The spatial data and the Bi-LSTM’s temporal representations are then integrated to make anomaly identification more precise and dependable. This integrated spatiotemporal architecture identifies abnormal actions of human beings in challenging monitoring situations. The model that was recommended performs better than the state of art methods. It gets 95.04% accuracy on the UCF50 dataset and 62.04% on the untrimmed UCF-Crime dataset. These results suggest that the model performs effective in real-life scenarios.

  • Open Access

    SFQSV Net: State Fusion Quantum Spectral Vision Network for Enhanced Elderly Fall Detection and Preventive Care in Smart Communities

    by Manoj Kumar, Tathagat Banerjee, Prachi Chhabra, Abhay Kumar, Kumar Abhishek, B. M. Ahamed Shafeeq

    A fall occurs when an individual loses balance and strikes the ground or a nearby object. This is a leading cause of accidental death among people aged 65 years and above, making it a universal health issue. Although fall detection systems have shown positive outcomes, detecting falls in varied environments remains challenging. We proposed the State Fusion Quantum Spectral Vision Network (SFQSV Net) to detect falls in diverse scenarios. SFQSV Net integrates quantum-inspired spectral attention with residual and convolutional networks, enhancing spatial and spectral feature extraction. The model incorporates multi-head spectral squeeze attention, residual attention mapping, and a hierarchical quantum-inspired pyramid to enable adaptive multi-scale representation learning. Additionally, spectral-channel coupling, sparse attention, and state-space modeling stabilize the learning process, permit gradient flow, and improve computational efficiency. A fusion-based classification head increases prediction accuracy and interpretability. The model performed well, with an accuracy of 0.9891, macro F1-score of 0.9889, ROC-AUC of 0.9892, Cohen’s kappa of 0.9782, and MCC of 0.9783. These results validate that SFQSV Net outperforms state-of-the-art methods.

  • Open Access

    Multi-level violence recognition via hybrid convolutional-attention and recurrent architectures

    by Manoj Kumar, Birendra Kumar Verma, Sukhendra Singh, Abhay Kumar, Kumar Abhishek, B. M. Ahamed Shafeeq

    Violence recognition is an urgent need for real-time human activity identification in surveillance video streams, which is becoming more important in areas including public safety, law enforcement, and security monitoring. Even while visual understanding has come a long way, finding a balance between accuracy and speed of identification is still a big problem. To address these constraints, we suggest a hybrid deep learning architecture that combines a Time-Distributed Convolutional Neural Network (TD-CNN) with a Long Short-Term Memory (LSTM) network augmented by a spatial attention mechanism. The attention module, which is located between convolutional layers, adaptively highlights important spatial areas, which makes it easier to tell the features apart. The LSTM part of the model looks at how frames are related to each other across time to capture motion dynamics that are important to violent behaviors. The suggested architecture was tested on the Hockey Fight Dataset and got an accuracy of 93%, which is better than many other baselines. Experimental findings indicate that the hierarchical integration of convolutional and recurrent layers with attention significantly improves recognition accuracy while maintaining a computationally lightweight architecture suitable for near-real-time deployment.

  • Open Access

    Multi-approach technique implementation for segmentation of left ventricular myocardial infarction and quantification

    by Sunanda Hosapalya Gangadharaiah, Kavitha K. S., B. M. Ahamed Shafeeq, Shyam Karanth

    Accurate segmentation and optimal diagnosis are required for myocardial infarction (MI) because it is a life-threatening cardiovascular condition. Therefore, its quantification is necessary to facilitate accurate diagnosis and make beneficial decisions to prevent a heart attack. Advanced cutting-edge techniques, such as deep learning, promise more precise MI segmentation and potentially provide an automated segmentation of annotated cardiac MRI (CMRI) datasets. However, segmentation accuracy is strongly affected by domain shift, low contrast of infarcted tissue, and scarcity of annotated datasets. This study introduces an innovative framework as a hybrid deep-learning framework combining Cycle-Consistent Generative Adversarial Networks (CycleGAN), Discrete Wavelet Transform (DWT), and U-Net to achieve robust MI segmentation. CycleGAN is employed to generate synthetic infarcted images from healthy MRI scans, addressing data scarcity and domain variability. DWT is integrated into the segmentation pipeline to preserve high-frequency spatial details and enhance edge localization, which are crucial for accurate infarct boundary detection. Finally, a U-Net model is trained on a hybrid dataset comprising synthetic and real images with wavelet-based feature fusion. Experiments dataset demonstrate that the proposed method significantly outperforms baseline U-Net models, achieving Dice improvements of 4–8% for infarct segmentation and 2–4% for myocardium segmentation. The results highlight the effectiveness of combining CycleGAN-based data augmentation with multi-resolution wavelet features for improved cardiac tissue delineation.

  • Open Access

    Hypergraph-based contrastive embedding and attention fusion for detection of skin cancer

    by Tathagat Banerjee, Prachi Chhabra, Manoj Kumar, Abhay Kumar, Kumar Abhishek, B. M. Ahamed Shafeeq

    Skin diseases involve a spectrum of problems including infections, and malignancies. Melanoma, the deadliest kind of skin cancer, starts in melanocytes, which make melanin. Early detection is really important, but it’s hard since the visual indications are often quite little and there is a big class imbalance in diagnostic datasets. The proposed C2G-HFMTA framework consists of three hierarchical levels: (a) an overall contrastive learning (CL) framework, (b)two major feature learning branches, namely the Graph Contrastive Embedding Framework (GCEF) and the High-dimensional Feature with Multimodal Transformer Attention (HFMTA), and (c) attention and fusion sub-modules including Hypergraph Bi-Convolutional Attention and Multiscale Transformer Attention, which operate within these branches to enhance discriminative representation learning. The proposed method demonstrates strong performance on benchmark dermoscopic datasets and has the potential to support computer-aided diagnosis systems, subject to further may support future computer-aided diagnosis systems validation and real-world testing. We have used Clustered Class-Based Segmentation (CCBS) for changing the training distributions. Our Class-Based Contrastive Loss (CBCL) works directly on original dermoscopic pictures, that preserves the semantic integrity of the images while making it easier to tell the difference between classes. Our framework outperforms several recent CNN- and transformer-based baselines in controlled experimental settings. It gets 93.2% accuracy and a 92.9% F1-score, and it does well on minority classes. Experiments were conducted on the HAM10000 dataset containing 10,015 dermoscopic images across seven diagnostic categories, using a stratified train–validation–test split of 70%–10%–20%. Performance was evaluated using accuracy, precision, recall, and F1-score, using five-fold stratified cross-validation to ensure robust performance estimation. Ablation experiments show that grouping, cross-branch fusion, and semantic-guided attention are important.


  • Top Cited Papers
    Open Access

    Ensemble learning for air quality index prediction: integrating gradient boosting, XGBoost, and stacking with SHAP-based interpretability

    by Sukhendra Singh, Manoj Kumar, Vishal Sengar, Abhay Kumar, Kumar Abhishek, B. M. Ahamed Shafeeq

    The increasing challenge of air pollution in cities requires smart methods to make proper predictions and manage the problem. Although machine learning and deep learning models have contributed greatly to weather and pollution forecasting, the main issue is the real-time flexibility, and scalability in the varying atmospheric conditions. This paper introduces a weighted Voting ensemble model that combines Gradient Boosting ( $$\times$$ 4), CatBoost ( $$\times$$ 3), XGBoost ( $$\times$$ 2) and LightGBM ( $$\times$$ 1) to improve the accuracy of Air Quality Index (AQI) forecasting. The full preprocessing (complete-case deletion, which retains extremes) and optimization of hyperparameters (GridSearchCV/Optuna, 5-fold CV) were used to enhance the robustness and generalizability of the model. The Taiwan Air Quality Dataset (2016–2024, $$n=4.6M$$ hourly records from 74 stations), 6 major pollutants (PM2.5, PM10, $$\hbox {NO}_2$$ , $$\hbox {O}_3$$ , $$\hbox {SO}_2$$ , CO), meteorological parameters (wind speed/direction), and 8-h averages) is used to model the data (spatial/temporal IDs are excluded, to allow deployment to a single station). Experimental validation of 60/16/24 splits (random + temporal validation) shows that the ensemble has validation MSE 0.6553 ( $$\hbox {R}^2$$ 0.9969 ), which beats 15 baselines including the deep learning (LSTM MSE 45.4), but has temporal robustness ( $$\Delta$$ $$\hbox {R}^2$$ = − 0.0037). Moreover, SHAP is implemented to offer explainability, as it gives more insights into the contribution of features in predicting AQI. The results indicate the promise of interpretable ensemble learning systems to underpin sustainable urban living, reinforce community health programs, and allow interventions in managing air quality in time.


  • Open Access

    A unified framework with U-Net + + and CNN-RNN-BiGRU architectures for automated weed detection in precision agriculture using AI

    by Vijesh Kumar Patel, Kumar Abhishek, B. M. Ahamed Shafeeq

    The automated weed identification is necessary to enhance crop yield and the sustainable precision agriculture. The use of manual labour and chemical herbicides in traditional practices makes them very expensive, harmful to the environment, and causes more herbicide resistance. To overcome, this paper presents an AI-driven model AgroWeedX-Ensemble, which combines enhanced preprocessing, state-of-the-art segmentation, multi-scale feature extraction, feature selection, and efficient weed detection. An enhanced WeedNet-Adaptive Pre-Processing Optimizer (WN-APO) improves the quality of data by dynamically changing bilateral filtering, augmentation, and normalization to accommodate lighting changes and shadows. The proposed Attention-ASPP Enhanced Hybrid Dilated Network (AA-HDN) is based on the U-Net + + , attention, ASPP, and hybrid dilated convolutions to precisely differentiate between overlapping weed-crop areas. Multi-Scale Residual Spatial Feature Extractor (MS-RSFE) uses HOG, Gabor filters, and ResNet-50 with Feature Pyramid Networks to identify a variety of morphologies of weeds. The Parrot-Wheel Feature Selector (PWFS) is used to reduce feature redundancy by combining Parrot Optimizer and Binary Waterwheel Plant Optimization. Lastly, WeedAttnX-Net is a CNN-based model that adds RNN, Bi-GRU, attention layers, and the Bi-GRU-Attention to lower the false positives and enhance the reliability of the detection. The experimental findings show that AgroWeedX-Ensemble is highly accurate (0.99), precise (0.98), and robust in different field conditions with a lower false positives (0.02) and false negatives (0.009). The suggested system provides a scalable and useful solution to automated weed detection in precision agriculture.


  • Open Access

    SentXFormer: a transformer-enhanced hybrid deep learning framework for cross-domain sentiment analysis of customer reviews

    by Ajeet Kumar, Kumar Abhishek, Ahamed Shafeeq B M

    Cross domain sentiment analysis is still a difficult task because of vocabulary changes, context change and domain specific sentiment. Conventional models are not known to generalize over unknown areas leading to decreased accuracy and unreliable transfer performance. This paper presents a deep learning model named SentXFormer, which is a transformer-based hybrid framework that enhances the sentiment classification in heterogeneous domains. SentXFormer is based on the hybrid SentiConGRU-Net architecture, which consists of CNN and GRU layers, and contextual embeddings of BERT, RoBERTa, and Domain-Adaptive BERT (DABERT). A domain adaptation module based on an adversarial training with a Gradient Reversal Layer (GRL) also encourages domain-invariant representations to be learned. The experiments are done on 23,440 sentiment-labeled reviews across three publicly available datasets including Amazon (7,550 samples), Yelp (8,450 samples), and IMDB (7,440 samples). SentXFormer performed well in in-domain, reaching 98.7% (Amazon), 97.67% (Yelp) and 98.8% (IMDB) accuracies. The model is stable in terms of transferability in cross-domain settings with an accuracy of 91–93% on all train-test combinations. The comparative analysis with LSTM, CNN, GRU, and latest transformer-based adaptation models demonstrates that SentXFormer is always better than the current baselines. The findings indicate that SentXFormer is an efficient, strong and scalable tool to sentiment analysis in heterogeneous and real-life customer review contexts.


  • Open Access

    Multiscale tumor characterization in histopathology via self-distilled transformers and topology-aware visual encoding

    by Tanvir H. Sardar, P. Naresh, Sk Mahmudul Hassan, Praveen Kulkarni, Rajesh T. M, B. M. Ahamed Shafeeq

    The increasing complexity of whole slide images in histopathology requires models that would be accurate across magnifications while being robust to visual, topological, and contextual variations in the setting. Thus far, existing approaches have either failed to generalize across various resolutions, have ignored the inherent structural relationships within tissue architecture, or have not integrated a mechanism to adaptively prioritize samples during training. Aside from this, most approaches do not consider both pixel-level appearance and morphological context, which restricts their diagnostic reliability sets. This research aims to address these limitations by providing a framework for Multiscale Tumor Characterization by synergizing RepVGG-DINO encoders, self-distilled visual transformers, and hierarchical attentions. The Pathology-Adaptive Uncertainty-Aware Consistency (PAUAC) Framework ensures consistency in prediction across 10 and 40 and introduces a dual-branch consistency model with uncertainty-weighted KL divergence regularization. The Structural Attention-Constrained Graph Regularizer (SACGR) which is a topology-aware visual encoding technique focuses on constrains attention in the ViT decoders thereby embedding spatial priors from superpixel-based graphs into them. The Multiscale Pathology Curriculum Scheduler (MPCS) creates a sample prioritization mechanism based on entropy, guiding the training from simpler to more complex tissue patterns. The Transformer-Driven Dual-Modality Morphometry Network integrates H&E image features with Voronoi-based nuclear morphometry using cross-modal self-attention to enhance representational richness for the process. Finally, the Contrastive Cell-Contextual Representation Alignment (CCCRA) module improves embedding consistency across different magnifications by using positional contrastive learning sets. The combination of these modules brings measurable improvements (+2.3% Dice score, +21% faster convergence, +3.7% accuracy for morphologically ambiguous samples, and +12.6% normalized mutual information in embeddings) sets. This work marks a great leap in tumor characterization within histopathology, establishing resolution-aware, topology-constrained, and morphology-fused learning in an interpretable and scalable manner for the process.


  • Open Access

    Online alert system for DDoS attack detection and prevention using machine learning classification algorithms

    by Bindu Madavi K. P., Krishna Sowjanya K., Tanvir Habib Sardar, Ahamed Shafeeq B. M.