FedDHr: Improved Adaptive Learning Strategy Using Federated Learning for Image Processing
Anuhya Velagapudi, B. Jhansi, M. Hemalikha, P. Vijayalakshmi · 2023
FL (Federated learning) has grown in popularity as a field of research that allows for the training of an algorithm over many decentralised servers that are having local data samples without requiring data exchange. Numerous application domains (like medical image analysis diagnosis made by doctors) lack a significant amount of properly labeled and full data that can be found in one place. Due to the prevalence of artificial intelligence in new application sectors, there are few rising issues on privacy of data and user. New algorithms of various research works are analysed in this study and it introduces a new technique that address the data heterogeneity and adaptive learning rate of the model to perform Image processing, Deep Learning.