Mitigating Catastrophic Forgetting in Deep Transfer Learning for Fingerprinting Indoor Positioning

This letter proposes a deep-learning-based fingerprinting indoor positioning method, aiming to mitigate catastrophic forgetting in the process of depth transfer learning. Recently indoor positioning methods based on fingerprint have made great development. The deep transfer learning technique has been applied to transfer the positioning network among different scenarios. But catastrophic forgetting is a big challenge during the supervised transfer learning, which results in poor performance of fine-tuned network in source scenario. In order to solve this issue, the proposed method improves the fine-tuning learning procedure according to the importance of network parameters. It can adaptively control the ratio of network parameters by adding regularization factor to loss function. Simulation results show that the proposed method can effectively improve the positioning accuracy in source scenario without reducing the positioning accuracy in target scenario, especially for the transfer learning in multiple scenarios.