22 August 2022 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
The advancement of medical research in the field of cancer prognosis and diagnosis using various modalities has put oncologists under tremendous stress. The complexity and heterogeneity involved in multiple modalities and their significantly varied clinical outcomes make it difficult to analyze the disease and provide the correct treatment. Breast cancer is the major concern among all cancers worldwide, specifically for females. To help oncologists and cancer patients, research for breast cancer survival estimation has been proposed. It ranges from complex deep neural networks to simple and interpretable architectures. We propose a utility kernel for a support vector machine (SVM) in this study. It is a simple yet powerful function, which performs better than other popular machine learning algorithms and deep neural networks in the task of breast cancer survival prediction using the TCGA-BRCA dataset. This study validates the proposed utility kernel using four different modalities (gene expression, copy number variation, clinical, and histopathological tissue images) and their multi-modal combinations. The SVM based on our utility kernel empirically proves its efficacy by achieving the highest value on various performance measures, whereas advanced deep neural networks fail to train on small and highly imbalanced breast cancer data.
28 January 2024 in Journal of Molecular Liquids
30 May 2025 in IEEE Access
Accurate classification of breast cancer into distinct molecular subtypes is crucial for personalized treatment and improved patient outcomes. Despite advancements in machine learning, predicting these subtypes remains challenging due to tumor heterogeneity and complex data characteristics. This study introduces the Polyvariant kernel, a novel SVM kernel that leverages the Vision Transformer (ViT) for multimodal data integration from the TCGA dataset of 1,081 breast cancer patients. The ViT extracts features from Whole Slide Imaging (WSI), which are fused with gene expression profiles through an Optimization-Based Search mechanism. These fused features are then classified using the Polyvariant kernel. The proposed approach significantly enhances breast cancer subtype classification, outperforming classical RBF, Polynomial, and Utility kernels, achieving 87% accuracy and 87% recall. The Polyvariant kernel is designed with distinct hyperparameters, enabling effective integration of diverse data sources such as gene expression profiles and WSI. We theoretically validated the proposed Polyvariant kernel by proving the Mercer conditions and establishing it as both a universal approximator and a universal kernel. Furthermore, we empirically demonstrated its superiority by benchmarking it against deep learning models (ResNet-50, VGG16, GoogLeNet) and classical ML datasets. Statistical significance tests confirmed its robustness, reinforcing its effectiveness for complex biomedical data integration. The proposed research demonstrates the efficacy of multimodal data fusion in improving breast cancer subtype classification and establishes the Polyvariant kernel as a powerful tool for complex biomedical data analysis.
21 July 2021 in The European Physical Journal Special Topics
ATAbhijit Jeremiel Theophilus
Abhijit Jeremiel Theophilus
4 October 2024 in IEEE Transactions on Intelligent Transportation Systems
Delivery of items from the producer to the consumer has experienced significant growth over the past decade and has been greatly fueled by the recent pandemic. Amazon Fresh, GrubHub, UberEats, Postmates, InstaCart, and DoorDash are rapidly growing and are sharing the same business model of consumer items or food delivery. Existing food delivery methods are sub-optimal because each delivery is individually optimized to go directly from the producer to the consumer via the shortest time path. We observe a significant scope for reducing the costs associated with completing deliveries under the current model. For this, we model our food delivery problem as a multi-objective optimization, where consumer satisfaction and delivery costs, both, need to be optimized. Taking inspiration from the success of ride-sharing in the taxi industry, we propose DeliverAI -a reinforcement learning-based path-sharing algorithm. Unlike previous attempts for path-sharing, DeliverAI can provide real-time, time-efficient decision-making using a Reinforcement learning-enabled agent system. Our novel agent interaction scheme leverages path-sharing among deliveries to reduce the total distance traveled while keeping the delivery completion time under check. We generate and test our methodology vigorously on a simulation setup using real data from the city of Chicago. Our results show that DeliverAI can reduce the delivery fleet size by 15%, the distance traveled by 16%, and 50% higher fleet utilization w.r.t point-to-point delivery systems.
24 August 2024 in SN Computer Science