AHAnindya Halder

Anindya Halder

*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


Anindya Halder has a total of 32 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Semi-supervised ensemble learning with interval type-2 fuzzy-rough sets for Parkinson’s disease prediction from multi-omics

    by Ambika Hazarika, Ansuman Kumar, Anindya Halder

    Parkinson’s disease (PD) is a disorder involving progressive degeneration of the nervous system. Its clinical signs typically become noticeable only after substantial impairment has occurred in the substantia nigra, a brain region involved in motor control. Therefore, early and accurate prediction of PD based on molecular alterations is essential for proper diagnosis and improved patient outcomes. In this context, feature-level multi-omics integration has become a useful strategy because it combines molecular information from multiple biological levels and may support a broader understanding of disease progression. This study proposes a novel technique called Semi-supervised Ensemble Learning with Interval Type-2 Fuzzy-Rough Sets (SSEnIT2FRS) for PD prediction from multi-omics data, which leverages interval type-2 fuzzy-rough sets to achieve early and accurate prediction. The type-2 fuzzy-rough set enhances the handling of uncertainty and vagueness present in real-world biological datasets, while the ensemble approach improves predictive robustness by combining the decisions of multiple base classifiers. Furthermore, the inclusion of semi-supervised learning addresses the scarcity of labeled samples. The experimental findings indicate that the proposed method outperforms nine existing methods across all evaluation metrics, achieving the highest accuracy of 98.49%, with precision 0.9820, recall 0.9865, macro \(F_{1}\)-score 0.9836, micro \(F_{1}\)-score 0.9842, kappa 0.9672, specificity 0.9953, and AUC of 0.9969 on the multi-omics dataset. Boxplots, paired t-test results, confidence interval analysis, and SHAP-based explanations further justify the superior performance, robustness, statistical significance, and interpretability of the proposed method. Therefore, the proposed method could be an effective computational technique for identifying PD at an early stage from multi-omics data.

  • AHDSN: an attention-enabled hybrid deep sequential network for cancer survivability prediction from multi-omics data

    by Ambika Hazarika, Ansuman Kumar, Anindya Halder

    Cancer is the leading threat to human health and lifespan. Every day, the number of deaths caused by cancer continues to rise. Therefore, accurately predicting survivability from cancer has become an important area in cancer research. In predicting survivability, multi-omics data is advantageous as it provides information from different molecular levels of human biological processes, encompassing different omics such as genomics, epigenomics, transcriptomics, proteomics, and metabolomics. In this article we introduce a novel method called Attention-Enabled Hybrid Deep Sequential Network (AHDSN) which utilizes Long Short-Term Memory, Bidirectional Gated Recurrent Unit, and the attention mechanism to extract latent features from multi-omics data and Dense layers with softmax activation function for classification. Unlike conventional approaches that predict survival at a fixed time point (e.g., 5-year survival), the proposed AHDSN method predicts overall survival across the complete follow-up period using each patient’s survival time and censoring status. We evaluated the proposed AHDSN method against several state-of-the-art approaches to assess their relative performance in survivability prediction from multi-omics data. To address class imbalance, both Random Oversampling (ROS) and Synthetic Minority Oversampling Technique (SMOTE) are applied during preprocessing to ensure a more balanced distribution of samples across classes. The experimental results show that the proposed AHDSN method surpassed other state-of-the-art methods in terms of accuracy, precision, recall, and \(F_1\)-score across five multi-omics cancer datasets, Glioblastoma, Colon, Breast, Kidney, and Lung, achieving accuracies of 98.33%, 96.00%, 97.14%, 88.24%, and 80.00% when using ROS, and 97.12%, 96.00%, 96.22%, 85.18%, and 80.00% when using SMOTE respectively. Confidence Interval test also demonstrates the superiority of the proposed AHDSN method compared to other existing methods in producing the lowest error rate and the smallest error bound for all five multi-omics datasets. Additionally, SHapley Additive exPlanations analysis and heatmaps are employed to explain feature importance and illustrate how individual omics features contribute to model classification. Furthermore, the ablation study confirms the synergistic benefit of the proposed hybrid architecture and validates the importance of each component.


  • RateNet: a deep neural framework for inferring ratings from textual features

    by Kumar Deep Barman, Anindya Halder, Ansuman Kumar, Bhaskar Bordoloi


  • Open Access

    A novel deep sequential learning architecture for drug drug interaction prediction using DDINet

    by Anindya Halder, Biswanath Saha, Moumita Roy, Sukanta Majumder

    Drug drug Interactions (DDI) present considerable challenges in healthcare, often resulting in adverse effects or decreased therapeutic efficacy. This article proposes a novel deep sequential learning architecture called DDINet to predict and classify DDIs between pairs of drugs based on different mechanisms viz., Excretion, Absorption, Metabolism, and Excretion rate (higher serum level) etc. Chemical features such as Hall Smart, Amino Acid count and Carbon types are extracted from each drug (pairs) to apply as an input to the proposed model. Proposed DDINet incorporates attention mechanism and deep sequential learning architectures, such as Long Short-Term Memory and gated recurrent unit. It utilizes the Rcpi toolkit to extract biochemical features of drugs from their chemical composition in Simplified Molecular-Input Line-Entry System format. Experiments are conducted on publicly available DDI datasets from DrugBank and Kaggle. The model’s efficacy in predicting and classifying DDIs is evaluated using various performance measures. The experimental results show that DDINet outperformed eight counterpart techniques achieving \(95.42\%\) overall accuracy which is also statistically confirmed by Confidence Interval tests and paired t-tests. This architecture may act as an effective computational technique for drug drug interaction with respect to mechanism which may act as a complementary tool to reduce costly wet lab experiments for DDI prediction and classification.


  • Rice Leaf Diseases Classification Using Deep Learning Algorithms for Smartphone Application Development: An Empirical Study

    by Albania Suting, Ansuman Kumar, Anindya Halder, Leimapokpam Lousingkhombi Chanu

    Rice is the most widely consumed grain across the world. The rice plants often suffer from diseases. Early detection of such diseases and adopting remedial measures can help the farmers to avoid major losses and can produce best-quality crops in large quantities. However, the conventional rice leaf disease detection techniques are often not accurate, time-consuming and sometimes require laboratory testing. In this context, automatic rice leaf disease detection techniques are presented based on the various deep learning classifiers (namely MobileNetV2, ResNet50, VGG16 and Le-Net5) and an Android application is also developed in order to instantly determine the possible rice diseases from the uploaded rice leaf images captured by the smartphone. The developed models are tested using the publicly available benchmark rice leaf dataset containing three types of rice leaf diseases, namely bacterial leaf blight, leaf smut and brown spot. Experimental results show that MobileNetV2 model performed better compared to other models in terms of classification accuracy, recall and [ ]-score. The results of statistical significance test also confirmed the superiority of the MobileNetV2 model over other compared deep learning models.

  • Detection of Dense Built-Up Area in Low-Resolution Satellite Images Using Deep Learning and DBSCAN Approaches

    by Shambo Chatterjee, Soumya Bhattacharyya, Sourav Saha, Anindya Halder, Priya Ranjan Sinha Mahapatra

    Recent developments in satellite image processing tend to eliminate the need for intensive on-site surveys of urban or rural areas for infrastructure allocation planning. In particular, the detection of buildings in satellite images can significantly aid in rural or urban planning. However, detecting individual buildings in low-resolution satellite images is challenging due to a lack of visual clarity. In order to address this problem, we propose a computer vision-based hybrid framework to detect densely constructed building regions in low resolution satellite images, which can also serve as an assistive framework for automated geo-spatial survey of various sites. Our hybrid framework is comprised of three modules, namely the Mask R-CNN module, an ANN-based refinement module, and a DBSCAN based refinement module. The Mask R-CNN is employed to predict probable clustered building regions in the satellite image, whereas the ANN-based refinement module is applied to remove homogeneous regions (e.g. vegetation area) from the Mask R-CNN-detected clustered building region. Finally, a DBSCAN-based refinement module removes non-congested built-up regions so that densely constructed built-up areas can be identified with better precision. Our experimentation using publicly accessible satellite image datasets (AIRS dataset-Kaggle) establishes the effectiveness of the proposed hybrid framework in identifying densely populated building areas in low-resolution satellite images. The outcomes of the proposed framework demonstrated an approximately 5–10% improvement over various Mask R-CNN and U-Net-based approaches in terms of achieving better precision value of the detection.


  • Computational analysis of gene expression data using bidirectional long short-term memory for disease diagnosis

    by Srirupa Dasgupta, Mou Dutta, Anindya Halder, Abhinandan Khan, Goutam Saha, Rajat Kumar Pal