Tanima Dutta

Rahul Mishra, Hari Prabhat Gupta, Tanima Dutta et al.

Smart sensing provides an easier and convenient data-driven mechanism for monitoring and control in the built environment. Data generated in the built environment are privacy sensitive and limited. Federated learning is an emerging paradigm that provides privacy-preserving collaboration among multiple participants for model training without sharing private and limited data. The noisy labels in the datasets of the participants degrade the performance and increase the number of communication rounds for convergence of federated learning. Such large communication rounds require more time and energy to train the model. In this paper, we propose a federated learning approach to suppress the unequal distribution of the noisy labels in the dataset of each participant. The approach first estimates the noise ratio of the dataset for each participant and normalizes the noise ratio using the server dataset. The proposed approach can handle bias in the server dataset and minimizes its impact on the participants' dataset. Next, we calculate the optimal weighted contributions of the participants using the normalized noise ratio and influence of each participant. We further derive the expression to estimate the number of communication rounds required for the convergence of the proposed approach. Finally, experimental results demonstrate the effectiveness of the proposed approach over existing techniques in terms of the communication rounds and achieved performance in the built environment.

Rahul Mishra, Hari Prabhat Gupta, Tanima Dutta

Deep Neural Network (DNN) has gained unprecedented performance due to its automated feature extraction capability. This high order performance leads to significant incorporation of DNN models in different Internet of Things (IoT) applications in the past decade. However, the colossal requirement of computation, energy, and storage of DNN models make their deployment prohibitive on resource constraint IoT devices. Therefore, several compression techniques were proposed in recent years for reducing the storage and computation requirements of the DNN model. These techniques on DNN compression have utilized a different perspective for compressing DNN with minimal accuracy compromise. It encourages us to make a comprehensive overview of the DNN compression techniques. In this paper, we present a comprehensive review of existing literature on compressing DNN model that reduces both storage and computation requirements. We divide the existing approaches into five broad categories, i.e., network pruning, sparse representation, bits precision, knowledge distillation, and miscellaneous, based upon the mechanism incorporated for compressing the DNN model. The paper also discussed the challenges associated with each category of DNN compression techniques. Finally, we provide a quick summary of existing work under each category with the future direction in DNN compression.