A framework for classifying breast cancer via heterogenetic attention mechanism and optimized feature selection AVS Swetha, Manju Bala, Kapil Sharma Intelligent Data Analysis, 2025 Breast cancer poses a significant threat to women’s health, emphasizing the crucial role of timely detection. Traditional pathology reports, though widely used, face challenges prompting the development of automated Deep Learning (DL) tools. DL models, gaining traction in radiology, offer precise diagnoses; however, issues with generalization on varying dataset sizes persist. This paper introduces a computationally efficient DL framework, addressing dataset imbalance through a hybrid model design, ensuring both accuracy and speed in breast cancer image classification. Proposed model novel design excels in accuracy and generalization across medical imaging datasets, providing a robust tool for precise diagnostics. The proposed model integrates features from two classifiers, Inception ResNet V2 and Vision Transformers (ViT), to enhance the classification of breast cancer. This synergistic blend enhances adaptability, ensuring consistent performance across diverse dataset scales. A key contribution is the introduction of an Efficient Attention Mechanism within one of the classifiers, optimizing focus on critical features for improved accuracy and computational efficiency. Further, a Resource-Efficient Optimization model through feature selection is proposed, streamlining computational usage without compromising accuracy. Addressing the inherent heterogeneity within classifiers, our framework integrates high dimensional features comprehensively, leading to more accurate tumor class predictions. This consideration of heterogeneity marks a significant leap forward in precision for breast cancer diagnosis. An extensive analysis on datasets, BreakHis and BACH, that are imbalanced in nature is conducted by evaluating complexity, performance, and resource usage. Comprehensive evaluation using the datasets and standard performance metrics accuracy, precision, Recall, F1-score, MCC reveals the model’s high efficacy, achieving a testing accuracy of 0.9936 and 0.994, with precision, recall, F1-score and MCC scores of 0.9919, 0.987, 0.9898, 0.9852 and 0.989, 1.0, 0.993, 0.988 on the BreakHis and BACH datasets, respectively. Our proposed model outperforms state-of-the-art techniques, demonstrating superior accuracy across different datasets, with improvements ranging from 0.25% to 15% on the BACH dataset and from 0.36% to 15.02% on the BreakHis dataset. Our results position the framework as a promising solution for advancing breast cancer prediction in both clinical and research applications. The collective contributions, from framework and hybrid model design to feature selection and classifier heterogeneity consideration, establish a holistic and state-of-the-art approach, significantly improving accuracy and establishing optimization in breast cancer classification from MRI images. Future research for the DL framework in breast cancer image classification includes enhancing interpretability, integrating multi-modal data, and developing personalized treatments.
Intelligent Nanorobots for Precision Cancer Diagnosis and Treatment using Deep Reinforcement Learning Kapil Sharma, Ravi Ranjan 2025 11th International Conference on Mechatronics and Robotics Engineering Icmre 2025, 2025 Early detection of cancer is essential as it significantly improves treatment outcomes and survival rates by addressing the disease before it spreads to other organs. Many cancers, such as breast, cervical, and colorectal, are highly treatable in their initial stages. With the development of Artificial intelligence, nano technology, the engineers, doctors, and biologist are working on nanorobots for diagnosis and treatment of cancer. It can help detect cancer at an early stage. Early diagnosis often reduces the complexity and cost of treatment, alleviating the physical and financial burdens on patients. Nanorobots are at the forefront of advanced biomedical applications, offering potential breakthroughs in targeted drug delivery and precision diagnostics, particularly for cancer treatment. By integrating artificial intelligence and Deep Reinforcement Learning, these devices can autonomously navigate complex biological environments to detect cancer cells via biomarker gradients. This work explores the deployment of Deep Q-Learning to improve nanorobot decision-making, enabling efficient path optimization and obstacle navigation.
Anomaly Detection for Sensor Manipulation in Matter Enabled-IoT Devices with Faulty Data Injection Jahnvi Patel, Kapil Sharma 2025 International Conference on Pervasive Computational Technologies Icpct 2025, 2025 The security of Internet of Things (IoT) devices in Matter-enabled networks is crucial, as attacks such as sensor spoofing and data injection can lead to significant disruptions. Sensor manipulation attacks where the attackers manipulate the sensor inputs to create erroneous behavior in devices are issues of serious concern for anomaly detections. Faulty sensor data can cause devices to operate in unsafe or inefficient conditions across various applications, compromising system reliability and performance. The Isolation Forest algorithm is employed to isolate faulty data injections as outliers in sensor readings, offering a robust method for anomaly detection. The approach, therefore, focuses on the possibility of enhancing detection with greater reliability in IoT networks. The lightweight and extensible approach also assembles a process of strengthening Matter-based networks against vulnerabilities emanating from wrong control feedback.
Enhanced Security In Matter-Enabled Iot Networks Through Anomaly Detection Manjit Kumar, Kapil Sharma 2025 International Conference on Pervasive Computational Technologies Icpct 2025, 2025 The adoption of Matter-enabled Internet of Things (IoT) networks has significantly improved interoperability and security in smart environments. However, despite these advancements, mesh networks within the Matter protocol remain vulnerable to security threats, particularly packet flooding attacks. These attacks generate excessive network traffic, causing packet loss, delays, and overall performance degradation. While Matter includes robust security features such as end-to-end encryption, authentication, and replay protection, these measures are insufficient for detecting flooding attacks in real time.This research proposes an intelligent anomaly detection framework that utilizes telemetry data to identify devices contributing to harmful traffic. By employing the Isolation Forest algorithm, the framework accurately distinguishes abnormal network behaviors—such as increased retry attempts and prolonged message delivery times—from normal operations. Experimental results demonstrate its ability to detect malicious activity with high accuracy and minimal false positives.The study underscores the importance of real-time anomaly detection in protecting Matter IoT networks from flooding attacks. The proposed solution is both scalable and resource-efficient, making it well-suited for deployment in resource-constrained IoT environments.
Swarm Intelligence in Robotics: Optimizing PSO Parameters for Target Search in Single and Multiple Scenarios Vikas Sharma, Rahul Gupta, Kapil Sharma 2025 11th International Conference on Mechatronics and Robotics Engineering Icmre 2025, 2025 Target-tracing applications have attracted much interest in unmanned vehicles and mobile robots, especially where human access is limited or dangerous. Several computational techniques such as genetic algorithms, evolutionary computations, and neural networks have been explored to improve the entire system's control mechanism and efficiency. This paper addresses PSO as a high-performance method for enabling collaborative robotic search operations. It has many critical parameters influencing its performance, which are finely optimized using another PSO process to make the best use of this optimization technique. Experimentations set forth show that this indeed does much improve the efficiency and accuracy of searches carried out by robots. These validation experiments work on single-target and multi-target cases to present vivid effectiveness. The results emphasize the ability of PSO to contribute toward autonomous search and rescue operations and all other applications.
FOGSAFE: IoT enabled V2V communication system for enhanced visibility and safety in low visibility conditions Ishita, Izna, Kapil Sharma Applications of Artificial Intelligence in 5g and Internet of Things Proceedings of the 1st International Conference on Applications of AI in 5g and Iot Icaai5gi 2024, 2025 The development of the Internet of Things (IoT) idea in the form of Internet of Vehicles (IoV) has provided a solution to all of the challenges associated with operating a vehicle. The full potential of IoV creates a distributed network of automobiles that cooperate with diverse vehicular systems, addressing numerous issues related to traffic monitoring and road safety measures. Due to their high latency and responsiveness delays, current technologies such as Vehicular Cloud Computing, Vehicle Ad hoc Networks (VANET), and Mobile Cloud Computing are not optimal. Vehicle Fog Computing (VFC), a potential paradigm that combines fog computing and vehicle networks, offers VANETSs an efficient but different approach. Particle swarm optimization (PSO) algorithm is used to route the path optimization which leads to the most efficient routing paths being the best ones in the VANET. VFC boasts several advantages including very high throughput, consuming very little energy, and maintaining energy efficiency, with this hybrid model of Ada Boost and Random Forest Algorithm we get an impressive accuracy of 99.928%.
Integrated LLM for Effective Messaging Sony Rajput, Jeebananda Panda, Kapil Sharma Proceedings 2025 7th International Conference on Artificial Intelligence and Speech Technology Aist 2025, 2025
AI and Digital Twins Transforming Healthcare IoT Vikas Sharma, Kapil Sharma, Akshi Kumar Proceedings of the 14th International Conference on Cloud Computing Data Science and Engineering Confluence 2024, 2024
Melanoma Skin Cancer Detection Using InvolutionNet Shubham Chaudhary, Vishal Gupta, Kunal Deo, Kapil Sharma 2024 Control Instrumentation System Conference Guiding Tomorrow Emerging Trends in Control Instrumentation and Systems Engineering Ciscon 2024, 2024
EvilSpot: Detection and Mitigation in Multi Channel Sushant A.A., Tanmay Arora, Vishesh Abrol, Kapil Sharma IEEE International Conference on Advances in Electronics Communication Computing and Intelligent Information Systems Icaecis 2023 Proceedings, 2023
Analysis of Histopathological images: An Overview Ravi Sharma, Kapil Sharma, Manju Bala Proceedings of International Conference on Computing Communication Security and Intelligent Systems Ic3sis 2022, 2022
Supervision Software using Artificial Intelligence Shantanu Shishodia, Tanmay Garg, Shubhanshu Chaudhary, Kapil Sharma 2022 2nd International Conference on Computer Science Engineering and Applications Iccsea 2022, 2022
Penetration Testing of Wireless EncryptionProtocols Sandesh Jain, Sarthak Pruthi, Vivek Yadav, Kapil Sharma Proceedings 6th International Conference on Computing Methodologies and Communication Iccmc 2022, 2022
Taxonomy of Routing Protocols Kapil Sharma, Himanshu Anand, Himanshu Nandanwar, Anamika Chauhan 2022 International Conference for Advancement in Technology Iconat 2022, 2022
Real-Time Object Size Dimensioning in Raspberry Pi Sahil Khadane, Sahil Saini, Samarth Mittal, Kapil Sharma 7th International Conference on Communication and Electronics Systems Icces 2022 Proceedings, 2022
Retinal Vessel Detection Using Residual Y-net Anindita Roy, Kapil Sharma 2021 International Conference on Smart Generation Computing Communication and Networking Smart Gencon 2021, 2021
Comparative study of ranking algorithms Sandeep Suri, Arushi Gupta, Kapil Sharma Proceedings 2019 International Conference on Computing Electronics and Communications Engineering Iccece 2019, 2019
Indian smart city ranking model Delhi Technological University, Delhi, India., Kapil Sharma, Sandeep Tayal, Delhi Technological University, Delhi, India. International Journal of Recent Technology and Engineering, 2019
A Survey on Malware Analysis Techniques for Android Using Permissions 12th Indiacom 5th International Conference on Computing for Sustainable Global Development Indiacom 2018, 2018
5G millimeter wave propagation with intelligent grid selection for obstacle avoidance International Journal of Computer Information Systems and Industrial Management Applications, 2018
A REVIEW ON CHALLENGES AND SCOPE OF SPATIAL DATA MINING 11th Indiacom 4th International Conference on Computing for Sustainable Global Development Indiacom 2017, 2017
Quality issues with big data analytics Proceedings of the 10th Indiacom 2016 3rd International Conference on Computing for Sustainable Global Development Indiacom 2016, 2016
Tuning of software cost drivers using BAT algorithm Proceedings of the 10th Indiacom 2016 3rd International Conference on Computing for Sustainable Global Development Indiacom 2016, 2016
5G millimeter wave (mmWave) communications Proceedings of the 10th Indiacom 2016 3rd International Conference on Computing for Sustainable Global Development Indiacom 2016, 2016
Optimization of revenue generated by hydro power plant by Bat Algorithm(BA) Proceedings of the 10th Indiacom 2016 3rd International Conference on Computing for Sustainable Global Development Indiacom 2016, 2016
Software bug localization using Pachinko Allocation Model Proceedings of the 10th Indiacom 2016 3rd International Conference on Computing for Sustainable Global Development Indiacom 2016, 2016
Clustering based feature selection methods from fMRI data for classification of cognitive states of the human brain Proceedings of the 10th Indiacom 2016 3rd International Conference on Computing for Sustainable Global Development Indiacom 2016, 2016
A new chaotic-primitive and its application in customizing AES for lightweight multimedia encryption Proceedings of the 10th Indiacom 2016 3rd International Conference on Computing for Sustainable Global Development Indiacom 2016, 2016
Ranking of software reliability growth models using bacterial foraging optimization algorithm 2015 International Conference on Computing for Sustainable Global Development Indiacom 2015, 2015
A statistical view of software reliability and modeling 2015 International Conference on Computing for Sustainable Global Development Indiacom 2015, 2015
Improving software quality based on relationship among the change proneness and object oriented metrics 2015 International Conference on Computing for Sustainable Global Development Indiacom 2015, 2015
Optimizing intermediate COCOMO Model using BAT algorithm 2015 International Conference on Computing for Sustainable Global Development Indiacom 2015, 2015
Analysis and ranking of software Engineering metrics 2015 International Conference on Computing for Sustainable Global Development Indiacom 2015, 2015
Applications of artificial Bee Colony Optimization technique: Survey 2015 International Conference on Computing for Sustainable Global Development Indiacom 2015, 2015
5Unified software development process based classification of software reliability models 2015 International Conference on Computing for Sustainable Global Development Indiacom 2015, 2015
A comparative study of various text mining techniques 2015 International Conference on Computing for Sustainable Global Development Indiacom 2015, 2015
Development and Evaluation of a Weather-based Forewarning Model for Managing Maydis Leaf Blight in Maize Using Novel Fungicides JK Sharma, VK Meena, Lekha, HVS Shekhawat, K Choudhary, K Sharma, ... Journal of Crop Health 78 (2), 38 , 2026 2026
Linking soil enzymes and microbial community dynamics with organic carbon fluctuations for sustaining the soil health M Negi, P Kumar, A Chauhan, S Sharma, HD Sharma, K Sharma Scientific Reports , 2026 2026
Comparison Of Nasal Intermittent Positive Pressure Ventilation and Nasal Continuous Positive Airway Pressure in Preterm Infants with Respiratory Distress Syndrome: A Randomized … P Verma, M Ishtiyaq, KD Sharma International Journal of Medical and Pharmaceutical Research 7, 3173-3177 , 2026 2026 Citations: 1
Quantum Computing-Based Hyperparameter Optimization of Neural P Chowdhury, K Sharma Proceedings of International Conference on Data Science and Artificial … , 2026 2026
Optimizing Irrigation and Fertigation for Phenological, Yield and Quality Traits in Apple ( Malus × domestica Borkh.) cv. ‘Super Chief’ in North-Western Himalayas K Sharma, JC Sharma, R Sharma, S Sharma, M Negi, S Ananthakrishnan, ... Applied Fruit Science 67 (6), 433 , 2025 2025
Design of an Integrated and Automated System for Ground Handling NI Motiwala, K Sharma, RS Pant, NP Gulhane Lighter Than Air Systems: Select Proceedings of DELTAs 2024, 135 , 2025 2025
Introduction to NLP in finance: Sentiment analysis and risk management R Ranjan, K Sharma, A Kumar Transformative Natural Language Processing: Bridging Ambiguity in Healthcare … , 2025 2025 Citations: 6
HDSF: A Healthcare Decision Support Framework to Provide A Seamless and Adaptable Patient Experience R Sharma, KD Sharma, A Bijalwan Biomedical Informatics and Smart Healthcare 1 (1), 1-8 , 2025 2025 Citations: 1
Mulching and irrigation strategies for climate resilient apple cultivation in high-density orchards S Ananthakrishnan, JC Sharma, N Sharma, S Kumar, SV Shankar, ... Scientific Reports 15 (1), 17125 , 2025 2025 Citations: 6
CXMArena: Unified Dataset to benchmark performance in realistic CXM Scenarios R Garg, K Sharma, K Gupta arXiv preprint arXiv:2505.09436 , 2025 2025
Comparative Analysis of Latency and Throughput in Matter-Enabled and Non-matter IoT Devices Over Varying Network Conditions A Kumar, A Mittal, K Sharma International Conference on Data Science and Artificial Intelligence, 171-181 , 2025 2025
Quantum Computing-Based Hyperparameter Optimization of Neural Networks P Chowdhury, K Sharma International Conference on Data Science and Artificial Intelligence, 303-314 , 2025 2025
Flavopiridol: a promising cyclin-dependent kinase inhibitor in cancer treatment US Baghel, P Kriplani, NM Patel, M Kaur, K Sharma, M Meghani, ... Naunyn-Schmiedeberg's Archives of Pharmacology 398 (4), 3489-3511 , 2025 2025 Citations: 13
COMPARISON OF SOCIODEMOGRAPHIC, CLINICAL AND SPIROMETRIC VARIABLES OF COPD AND COPD WITH BRONCHIECTASIS SUBJECTS. K Sharma, J Prabha, V Goyal, N Gaur, V Tanwar, N Adlakha, N Goel International Journal of Medicine and Public Health 15 (2), 705-711 , 2025 2025
Thresholds Derivation of Software Code Metrics for God Class Detection Using Metaheuristic Approaches K Sharma, JK Chhabra 2025
Next-generation healthcare: Digital twin technology and Monkeypox Skin Lesion Detector network enhancing monkeypox detection-Comparison with pre-trained models V Sharma, A Kumar, K Sharma Engineering Applications of Artificial Intelligence 145, 110257 , 2025 2025 Citations: 9
Hybrid Anomaly Detection Framework for Matter-Enabled IoT Devices V Krishan, S Dhar, K Sharma 2025 IEEE 14th International Conference on Communication Systems and Network … , 2025 2025
Breaking Barriers in Satellite Image Segmentation: A U-Net Ensemble Approach. V Sharma, A Kumar, K Sharma Journal of Engineering Science & Technology Review 18 (2) , 2025 2025
Digital twin: securing IoT networks using integrated ECC with blockchain for healthcare ecosystem V Sharma, A Kumar, K Sharma Knowledge and Information Systems 67 (3), 2395-2426 , 2025 2025 Citations: 20
A framework for classifying breast cancer via heterogenetic attention mechanism and optimized feature selection AVS Swetha, M Bala, K Sharma Intelligent Data Analysis 29 (2), 459-489 , 2025 2025
MOST CITED SCHOLAR PUBLICATIONS
Selection of optimal software reliability growth models using a distance based approach K Sharma, R Garg, CK Nagpal, RK Garg IEEE Transactions on Reliability 59 (2), 266-276 , 2010 2010 Citations: 216
Demand side management through load shifting in IoT based HEMS: Overview, challenges and opportunities S Sharda, M Singh, K Sharma Sustainable Cities and Society 65, 102517 , 2021 2021 Citations: 192
A novel clustering method using enhanced grey wolf optimizer and mapreduce AK Tripathi, K Sharma, M Bala Big data research 14, 93-100 , 2018 2018 Citations: 167
Hierarchical deep neural network for mental stress state detection using IoT based biomarkers A Kumar, K Sharma, A Sharma Pattern Recognition Letters 145, 81-87 , 2021 2021 Citations: 122
RSAM: Robust self-attention based multi-horizon model for solar irradiance forecasting S Sharda, M Singh, K Sharma IEEE Transactions on Sustainable Energy 12 (2), 1394-1405 , 2020 2020 Citations: 121
Antioxidant activity of Potentilla fulgens: An alpine plant of western Himalaya V Jaitak, K Sharma, K Kalia, N Kumar, HP Singh, VK Kaul, B Singh Journal of Food Composition and Analysis 23 (2), 142-147 , 2010 2010 Citations: 116
A parallel military-dog-based algorithm for clustering big data in cognitive industrial internet of things AK Tripathi, K Sharma, M Bala, A Kumar, VG Menon, AK Bashir IEEE Transactions on Industrial Informatics 17 (3), 2134-2142 , 2020 2020 Citations: 104
Root‐specific expression of chickpea cytokinin oxidase/dehydrogenase 6 leads to enhanced root growth, drought tolerance and yield without compromising nodulation H Khandal, SK Gupta, V Dwivedi, D Mandal, NK Sharma, ... Plant biotechnology journal 18 (11), 2225-2240 , 2020 2020 Citations: 96
Cryptanalysis of image encryption scheme based on a new 1D chaotic system S Dhall, SK Pal, K Sharma Signal processing 146, 22-32 , 2018 2018 Citations: 88
Real-time emotional health detection using fine-tuned transfer networks with multimodal fusion A Sharma, K Sharma, A Kumar Neural computing and applications 35 (31), 22935-22948 , 2023 2023 Citations: 81
Flexible, thin composite film to enhance the electromagnetic compatibility of biomedical electronic devices V Rathi, V Panwar, G Anoop, M Chaturvedi, K Sharma, B Prasad IEEE Transactions on Electromagnetic Compatibility 61 (4), 1033-1041 , 2018 2018 Citations: 80
5G millimeter wave (mmWave) communications SK Agrawal, K Sharma 2016 3rd international conference on computing for sustainable global … , 2016 2016 Citations: 76
MEmoR: A multimodal emotion recognition using affective biomarkers for smart prediction of emotional health for people analytics in smart industries A Kumar, K Sharma, A Sharma Image and Vision Computing 123, 104483 , 2022 2022 Citations: 72
Recent trends in multicue based visual tracking: A review A Kumar, GS Walia, K Sharma Expert Systems with Applications 162, 113711 , 2020 2020 Citations: 69
Consensus algorithms in blockchain technology: A survey K Sharma, D Jain 2019 10th International Conference on Computing, Communication and … , 2019 2019 Citations: 69
Biotransformation of tea catechins into theaflavins with immobilized polyphenol oxidase K Sharma, SS Bari, HP Singh Journal of Molecular Catalysis B: Enzymatic 56 (4), 253-258 , 2009 2009 Citations: 69
A chaos-based probabilistic block cipher for image encryption S Dhall, SK Pal, K Sharma Journal of King Saud University-Computer and Information Sciences 34 (1 … , 2022 2022 Citations: 60
Genetically optimized Fuzzy C-means data clustering of IoMT-based biomarkers for fast affective state recognition in intelligent edge analytics A Kumar, K Sharma, A Sharma Applied Soft Computing 109, 107525 , 2021 2021 Citations: 58
Parallel bat algorithm-based clustering using mapreduce T Ashish, S Kapil, B Manju Networking Communication and Data Knowledge Engineering: Volume 2, 73-82 , 2017 2017 Citations: 55
Dynamic frequency based parallel k-bat algorithm for massive data clustering (DFBPKBA) AK Tripathi, K Sharma, M Bala International Journal of System Assurance Engineering and Management 9 (4 … , 2018 2018 Citations: 51