Research
Research
My current research focuses on developing efficient and privacy-preserving Federated Learning (FL) algorithms for cross-device systems. I am working on designing adaptive and scalable FL frameworks that address key challenges such as communication efficiency, statistical heterogeneity, privacy preservation, and resource constraints. My approach involves optimizing aggregation strategies, improving model personalization, and enhancing robustness to varying device availability. To demonstrate real-world applicability, I have designed and evaluated these algorithms for smart city systems, including urban sensing applications such as noise mapping, weather forecasting, and road condition monitoring. By integrating theoretical analysis with practical implementation, my work aims to advance trustworthy and scalable FL solutions for decentralized learning in complex, resource-constrained environments.
A. Kapoor and D. Kumar, “Enhancing Smart Cities with Federated Learning: A Framework for Secure, Scalable, and Intelligent Urban Sensing Systems”, IEEE Internet of Things Magazine, 2025.
A. Kapoor and D. Kumar, “Federated Learning for Urban Sensing Systems: A Comprehensive Survey on Attacks, Defences, Incentive Mechanisms, and Applications,” IEEE Communications Surveys & Tutorials, 2024. (IF 46.7)
A. Kapoor and D. Kumar, “Computation and Communication Efficient Approach for Federated Learning based Urban Sensing Applications against Inference Attacks,” Pervasive and Mobile Computing, 2024. (IF 3.5)
A. Kapoor, and D. Kumar, “Federated Meta Learning for Cross-Domain Personalization with Partial Model Initialization,” in International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 2025. (In Press)
A. Kapoor, P. Gulati, and D. Kumar, “Clustered Federated Learning Framework for Non-IID Ambient Noise Mapping for Urban Sensing,” in International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 2025. (In Press)
A. Kapoor, S.D. Sharma, D. Kumar, and S.N. Sharma, “iProLSTM-FL: A Federated Learning Framework for Promoter Identification using LSTM Networks,” in 7th International Conference on Signal Processing, Computing and Control (ISPCC), Himachal Pradesh, India, 2025.
A. Kapoor, and D. Kumar, “Federated Learning Framework for Adaptive Spatio-Temporal Graph Neural Networks in Weather Forecasting,” in 31st National Conference on Communications (NCC), Delhi, India, 2025.
A. Kapoor, and D. Kumar, “K-HashFed: Communication Efficient Federated Learning through Gradient Clustering and Hashing,” in 50th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hyderabad, India, 2025.
A. Kapoor, and D. Kumar, “Federated Learning-based Real-Time Participatory Road Condition Monitoring System,” in 18th IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), Guwahati, India, 2024.
A. Kapoor, and D. Kumar, “Efficient Drone-Based Mobile Wireless Sensor Network for Spatio-Temporal Environmental Monitoring,” in 18th IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), Guwahati, India, 2024.
A. Kapoor, A. Anand, and D. Kumar, “Visual Techniques for Clustering Tendency Assessment of Networks,” in IEEE International Conference on Electrical, Electronics, Communication and Computers (ELEXCOM), Roorkee, India, 2023.
S. Gupta, A. Kapoor, and D. Kumar, “Optimization of User Resources in Federated Learning for Urban Sensing Applications,” in Proceedings of International Workshop on Federated Learning for Distributed Data Mining, KDD, California, USA, 2023.
S. Gupta, A. Kapoor, and D. Kumar, “A Resource Adaptive Secure Aggregation Protocol for Federated Learning based Urban Sensing Systems,” in Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD), pp. 135–135, Mumbai, India, 2023.
D. Kumar and A. Kapoor, “An end-to-end privacy preserving framework for user privacy, model reliability, and fair incentivization for federated learning based urban sensing system,” Indian Institute of Technology Roorkee, India. copyright granted by the Copyright Office, Government of India, Diary no. 11608/2024-CO/SW. Registration no. SW-18890/2024, June 2024.