Transfer Learning Approach for 6G-IoT Applications

Artificial Intelligence (AI) and Machine Learning (ML) have shown a significant role in attaining higher accuracy and precision for real-time Internet of Things (IoT) applications. On the other hand, to obtain a higher throughput in IoT domains viz., Vehicular Communication (VC), Unmanned-Aerial Vehicles (UAV), and Healthcare-IoT (HIoT), it is required to train the AI/ML models with an ample amount of data. Due to security reasons, it is becoming difficult to connect the devices over different networks. Also, the unavailability of data sharing due to company policies has restricted the data usage over other networks. This paper describes the emergence of transfer learning techniques for future 6G-IoT applications which reduce the time taken for retraining these models.