Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item Deep learning-based automated mitosis detection in histopathology images for breast cancer grading(John Wiley and Sons Inc, 2022) Mathew, T.; Ajith, B.; Kini, J.; Rajan, J.Cancer grade is an indicator of the aggressiveness of cancer. It is used for prognosis and treatment decisions. Conventionally cancer grading is performed manually by experienced pathologists via microscopic examination of pathology slides. Among the three factors involved in breast cancer grading (mitosis count, nuclear atypia, and tubule formation), mitotic cell counting is the most challenging task for pathologists. It is possible to automate this task by applying computational algorithms on pathology slides images. Lack of sufficiently large datasets and class imbalance between mitotic and non-mitotic cells in slide images are the two major challenges in developing effective deep learning-based methods for mitosis detection. In this paper, we propose a new approach and a method based on that to address these challenges. The high training data requirement of the advanced deep neural network is met by combining two datasets from different sources after a color-normalization process. Class imbalance is addressed by the augmentation of the mitotic samples in a context-preserving manner. Finally, a customized convolutional neural network classifier is used to classify the candidate cells into the target classes. We have used the publicly available datasets MITOS-ATYPIA and MITOS for the experiments. Our method outperforms most of the recent methods that are based on independent datasets and at the same time offers adaptability to the combination of datasets from different sources. © 2022 Wiley Periodicals LLC.Item A Dual Phase Approach for Addressing Class Imbalance in Land-Use and Land-Cover Mapping From Remotely Sensed Images(Institute of Electrical and Electronics Engineers Inc., 2024) Putty, A.; Annappa, B.; Prajwal, R.; Pariserum Perumal, S.P.Semantic segmentation of remotely sensed images for land-use and land-cover classes plays a significant role in various ecosystem management applications. State-of-the-art results in assigning land-use and land-cover classes are primarily achieved using fully convolutional encoder-decoder architectures. However, the uneven distribution of the land-use and land-cover classes becomes a major hurdle leading to performance skewness towards majority classes over minority classes. This paper proposes a novel dual-phase training, with the first phase proposing a new undersampling technique using minority class focused class normalization and the second phase that uses this learnt knowledge for ensembling to prevent overfitting and compensate for the loss of information due to undersampling. The proposed method achieved an overall performance gain of up to 2% in MIoU, Kappa, and F1 Score metrics and up to 3% in class-wise F1-score when compared to the baseline models on Wuhan Dense Labeling, Vaihingen and Potsdam datasets. © 2013 IEEE.Item BENN: Balanced Ensemble Neural Network for Handling Class Imbalance in Big Data(John Wiley and Sons Inc, 2025) Sneha, S.H.; Annappa, B.; Pariserum Perumal, S.P.Class imbalance is a critical challenge in big data analytics, often leading to biased predictive models. This imbalance can lead to biased models that perform well on the majority class but poorly on the minority class. Many machine learning models tend to be biased towards the majority class because they aim to minimise overall error, often leading to poor performance on the minority class. This paper presents the balanced ensemble neural network, a novel solution to effectively address class imbalance in big data. Balanced ensemble neural network combines the robust capabilities of neural networks with the power of ensemble learning, incorporating class balancing strategies to ensure fair representation of minority classes. The methodology involves integrating multiple neural networks, each trained on balanced subsets of data using techniques like Synthetic Minority Over-sampling Technique and Random Undersampling. This integration aims to leverage the strengths of individual networks while reducing their inherent biases. Our extensive experiments across various datasets reveal that BENN achieves an AUC-ROC score of 0.94, surpassing other models such as random forest (0.88), support vector (0.84) and single neural net (0.80). It was also observed that BENN's performance is better compared to traditional neural network models and standard ensemble methods in key metrics like accuracy, precision, recall, F1-score and AUC-ROC. The results specifically highlight BENN's effectiveness in accurately classifying instances of minority classes, a notable challenge in many existing models. These findings underscore BENN's potential as a substantial advancement in handling class imbalance within big data environments, offering a promising direction for future research and application in machine learning. © 2024 John Wiley & Sons Ltd.Item Class-Balanced Protein Interaction Site Prediction Using Global and Local Features with XGBoost and Deep Learning(Springer, 2025) Kulkarni, B.C.; Sai, B.S.; Kolagad, V.; Patil, N.; Bhat, P.Inter-protein interactions are critical in biological pathways. Determining the protein–protein interaction (PPI) sites is vital for comprehending protein behavior and designing medications. Traditional experimental protocols for pinpointing these sites are prolonged and costly, making computational approaches an efficient alternative. However, many computational methods fail to resolve the problem of class imbalance in PPI datasets and focus predominantly on local contextual features, ignoring global sequence information. In this work, we address class imbalance in PPI site prediction by applying a series of balancing techniques: selective thinning of the majority class, Tomek Links to remove noisy samples near the class boundary, and random augmentation of the minority class. We then further balance the data using Synthetic Minority Over-sampling Technique (SMOTE) and Generative Adversarial Networks (GANs), with GANs showing a slight edge in improving data quality and reducing noise. Our approach incorporates four key features: secondary structure, raw protein sequence, Position-Specific Scoring Matrix (PSSM), and Relative Solvent Accessibility (RSA). We use both nearby contextual and holistic sequence features for training two models: XGBoost and a Deep Neural Network (DNN). The performance of the models was assessed using accuracy, Matthews correlation coefficient (MCC), precision, recall, and F-score. We correlate the impact of using balanced versus unbalanced datasets and measure the share of global features in enhancing model performance. The findings demonstrate that class balancing significantly upgrades prediction performance. The XGBoost model realized an accuracy of 0.831 and precision of 0.417, outperforming the DNN in these metrics. The DNN model attained a higher recall of 0.723 and an F-score of 0.485, exemplifying its effectiveness in accurately detecting true PPI sites. Both models showcased a good MCC of 0.30, corroborating the effectiveness of the introduced balancing strategies and the assimilation of global features in robust PPI site prediction. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.Item Enhancing Money Laundering Detection in Bank Transactions using GAGAN: A Graph-Adapted Generative Adversarial Network Approach(Springer Science and Business Media Deutschland GmbH, 2025) Kadamathikuttiyil Karthikeyan, G.; Bhowmik, B.The past decade has witnessed profound transformations in the financial sector, driven by the integration of cutting-edge technologies into its core operations. Consequently, banks are increasingly utilizing technologies such as artificial intelligence (AI), blockchain, and big data analytics to offer personalized services, streamline transactions, and improve risk management, enabling the development of new financial products and services that cater to the diverse and evolving needs of customers. Despite these benefits, the banking landscape has also brought about complex challenges, particularly in the fight against money laundering. Money laundering remains a significant threat to the integrity of financial systems, as criminals exploit digital advancements to conceal illicit activities. The growing complexity of digital transactions and the increasing volume of financial data have made detecting and preventing money laundering more challenging than ever. Existing AI-based solutions, while effective to some extent, often grapple with class imbalance issues. This paper addresses the challenge by introducing a novel model named GAGAN (Graph Attention Generative Adversarial Network) and enhances the detection of money laundering activities in bank transactions. The proposed model further addresses the issue of class imbalance, by incorporating Conditional Generative Adversarial Network (cGAN) and Graph Attention Networks (GAT). The GAT classifier is then employed to accurately classify transactions, leveraging attention mechanisms to focus on the most relevant parts of the graph. Empirical results reveal that the proposed model achieves impressive performance metrics, with an accuracy of 98.62%, precision of 98.10%, recall of 98.92%, F1 score of 98.49%, AUC-ROC of 0.99, and a MCC score of 0.991. These results underscore the efficacy of the model in accurately identifying money laundering transactions, showcasing its potential as a robust tool for financial crime detection. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.Item Intelligent money laundering detection approaches in banking and E-wallets: a comprehensive survey(Springer, 2025) Kadamathikuttiyil Karthikeyan, G.; Bhowmik, B.The rapid evolution of financial technologies (FinTech) has propelled the world into a more dynamic and sophisticated digital financial landscape. This transformation has significantly expanded financial inclusion, offering new opportunities to individuals who were previously excluded from or had limited access to traditional banking services. Financial inclusion is crucial as it provides access to a broad spectrum of financial services, including bank accounts, credit and debit facilities, and e-wallets. While the rise in digital transactions has been driven by cost efficiency, convenience, and enhanced security measures, it has also led to an increase in economic crimes, particularly money laundering, resulting in substantial global economic losses. Consequently, the need for effective strategies to combat money laundering has never been more pressing. This study thoroughly investigates the state-of-the-art techniques in money laundering detection harnessing the capabilities of artificial intelligence (AI) technologies. First, we provide an overview of economic crimes and classify their various types, setting the stage for a focused discussion on money laundering. The paper then explores the money laundering landscape, including its impact and recent trends, followed by a discussion on different prevention and detection strategies. The paper also delves into AI-driven detection strategies, particularly those targeting money laundering, including the detection of laundering activities through e-wallets. Additionally, we address the research challenges associated with money laundering detection, such as the issue of class imbalance in financial datasets, and propose solutions to overcome it. Finally, the paper provides insights into future directions for research, aiming to equip the research community with the tools necessary to formulate proactive strategies for preventing and mitigating money laundering and related economic crimes. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.