Majid Ahmad Kundroo

About Me

Hello, my name is Majid Ahmad Kundroo, and I am a Postdoctoral researcher at NCLAB. I am deeply involved in the field of artificial intelligence. My undivided attention is drawn to the interesting field of federated learning. With an insatiable curiosity and an uncompromising passion for innovation, I am dedicated to developing vital solutions for more efficient, secure, and decentralized approaches to machine learning. I’m on a quest to shape the future of AI, armed with an extensive understanding of complex algorithms and a solid foundation in statistical analysis. My research focuses on the enormous potential of federated learning, a decentralized technique that allows collaborative model training across numerous devices or companies while maintaining data privacy. I hope to create rapid, secure, and privacy-preserving solutions that enable enterprises to leverage the collective intelligence of their dispersed data by developing distinctive approaches and algorithms.

Research Interests

• Federated Learning: Hyper-Parameter Optimization, Convergence, Communication Efficency
• Machine Learning: Social Media Analysis, Topic Modelling, Deep Learning

News

• [Jan. 2026] Paper titled “FedMeanStd: Federated Aggregation With Outliers Filtering” accepted in IEEE Access, Jan. 2026. [IF 3.6, JCR Top 35.2%]
• [Nov. 2025] Paper titled “FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks” published in Expert Systems with Applications (Elsevier), Nov. 2025. [IF 7.5, JCR Top 6.1%]
• [Oct. 2025] Paper titled “FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning” published in Future Generation Computer Systems (Elsevier), Oct. 2025. [IF 6.1, JCR Top 10%]
• [Sept. 2025] Paper titled “Autoencoder-based Decentralized Federated Learning for Efficient Communication” published in Computer Networks (Elsevier), Sept. 2025. [IF 4.6, JCR Top 17.5%]
• [Sept. 2025] Paper titled “Enhancing Traffic Management in Smart Cities: A Federated Learning Approach for Traffic Light Violation Detection” published in HCIS, Sept. 2025. [IF 3.0, JCR Top 45.5%]
• [August. 2025] Paper titled “FedEasy : Federated learning with ease” published in SoftwareX (Elsevier), Aug. 2025. [IF 2.4, JCR Top 40%]
• [July. 2025] Paper titled “Impact of Network Topologies on Decentralized Federated Learning” accepted in Cluster Computing (Springer), July. 2025. [IF 4.1, JCR Top 21%]
• [May. 2025] Paper titled “ Reinforcement learning-based laser cutting machine parameter optimization” accepted in Journal of Intelligent Manufacturing, May. 2025. [IF 5.9, JCR Top 20%]
• [Feb. 2025] Paper titled “FLDQN: Cooperative Multi-Agent Federated Reinforcement Learning for Solving Travel Time Minimization Problems in Dynamic Environments Using SUMO Simulation” accepted in Sensors, Feb. 2025. [IF 3.4]
• [Jan. 2025] FedEasy a federated learning framework released as an open-Source project. More details can be found at https://fedeasy.readthedocs.io/
• [August. 2024] Paper titled “Demystifying Impact of Key Hyper-Parameters in Federated Learning: A Case Study on CIFAR-10 and FashionMNIST” accepted in IEEE Access, August 2024. [IF 3.4, JCR Top 34.5%]
• [April. 2024] Paper titled “WSN-Driven Advances in Soil Moisture Estimation: A Machine Learning Approach” accepted in MDPI-Electronics, April 2024. [IF 2.6, JCR Top 44.5%]
• [Dec. 2023] Recieved Outstanding Graduate Researcher Award from Chungbuk National University.
• [August. 2023] Paper titled “Federated Learning with Hyper-Parameter Optimzation” accepted in Journal of King Saud University – Computer and Information Sciences, August 2023. [IF 6.9, JCR Top 15%]
• [July. 2023] Recieved best paper award by Korea Digital Contents Society.
• [June. 2023] A paper titled “Effects of Model Hyper-parameters in Federated Learning: A Short Analysis” is accepted in Korea Digital Content Society Conference.
• [May. 2023] One paper related to Federated Learning is accepted to ICDCS 2023.
• [Mar. 2023] Our paper related to analysis of federated learning is published in IEEE Access.
• [Dec. 2022] Our paper about pod autoscaling in Kube-Edge is published in IEEE Access.
• [Aug. 2022] Our paper about disease detection and classifcation of apples is accepted in QAS (I.F 4.0)

Publications

Services

Conference Reviewers

• International Conference on Agriculture-Centric Computation (ICA) 2023

Journal Reviewers

• IEEE Transactions on Network Science and Engineering
• IEEE Internet of Things Journal

Powered by Jekyll and Minimal Light theme.