FedXAI-ISL: Explainable Artificial Intelligence-Based Federated Model in Recognition and Community Decentralized Learning of Indian Sign Language

Indian Sign Language (ISL) is the primary language of communication for the deaf and hard of hearing community in India. It is estimated that over 18 million people in India use ISL. However, there is a lack of technological resources available to help the deaf and hard of hearing community communicate with the hearing community. In this research, we proposed a unique and enhanced model Federated (FL) Explainable Artificial Intelligence (XAI)-based model in Recognition and Community Decentralized Learning of Indian Sign Language (FedXAI-ISL). We have combined the privacy-preserving security and decentralized learning power of federated learning and interpretability, transparency, and improved artificial intelligence predictions of XAI to build a recognition and community decentralized learning model for Indian Sign Language where the users can have a mobile app through which the model works and gets trained through federated learning and XAI. This is proposed to be used to build a community decentralized learning system for Indian Sign Language (ISL) recognition.