Gesture recognition plays an important role in smart homes, such as human–computer interaction, identity authentication, etc. Most of the existing WiFi signal-based approaches exploit a large number of channel state information (CSI) datasets to train a gestures classification model; however, these models require a large number of human participants to train, and are not robust to the recognition environment. To address this problem, we propose a WiFi signal-based gesture recognition system with matched averaging federated learning (WiMA). Since there are differences in the distribution of WiFi signal changes caused by the same gesture in different environments, the traditional federated parameter average algorithm seriously affects the recognition accuracy of the model. In WiMA, we exploit the neuron arrangement invariance of neural networks in parameter aggregation, which can improve the robustness of the gesture recognition model with heterogeneous CSI data of different training environments. We carried out experiments with seven participant users in a distributed gesture recognition environment. Experimental results show that the average accuracy of our proposed system is up to $90.4\%$, which is very close to the accuracy of state-of-the-art approaches with centralized training models.

WiFi-based human gesture recognition has a wide range of applications in smart homes. Existing methods train gesture classification models by collecting large amounts of WiFi signal data in a centralized manner. However, centralized training faces challenges, including high communication overhead and the risk of data privacy leakage. Federated learning (FL) provides an opportunity to collaboratively train and share models without compromising data privacy. One of the main challenges FL faces is data that is non-Independent and Identically Distributed (non-IID) across clients. Specifically, in the gesture recognition scenario, since the transmission of WiFi signals is susceptible to cross-environment and cross-person interference, non-IID mainly manifests itself as a cross-domain problem. Cross-domain makes the knowledge learned between client models incompatible. Therefore, in the cross-domain scenario, effectively extracting and combining the knowledge learned by the client is a challenge. To solve this problem, we propose pFedBKD, a novel personalized federated learning scheme via bidirectional distillation. First, the knowledge that is beneficial to the client is extracted from the shared server model through knowledge distillation in the client, which helps train the personalized model of the client. Second, the server adaptively adjusts the aggregation weights according to the deviation between the shared model and the client’s local model so that the server’s shared model can extract more public knowledge. We conduct experiments on multiple open-source datasets. Experimental results show that our method is superior to existing methods and effectively alleviates the problem of reduced model recognition accuracy caused by cross-domain challenges.

Federated learning-based human activity recognition (FL-HAR) has emerged as a significant research topic due to its extensive applications, enabling the collective integration of local client data and knowledge without compromising user privacy. A major challenge within FL-HAR is addressing the heterogeneity of data across distributed clients, which leads to varying feature distributions for the same activity across different clients. To overcome this limitation, we propose a novel algorithm for FL-HAR, termed FedPMP, with Adaptive Model Partitioning and Personalized Model Aggregation. This approach customizes individual models for each client, aligned with their individual data distribution. Specifically, our partitioning strategy categorizes the model into globally shared components and locally personalized components, based on layer-wise feature drift. The global components capture general features across the majority of user groups, while the local components extract user-specific personalized features. Furthermore, our personalized model aggregation approach separately consolidates the shared and personalized components, facilitating collaboration among clients in accordance with feature relevance. Notably, we prove that FedPMP converges under feature drift conditions, providing a solid theoretical foundation for its practical deployment. Extensive experiments on various real-world HAR benchmarks demonstrate that FedPMP can effectively address the issue of feature drift in HAR, boosting recognition accuracy for clients and reducing the variance in accuracy among them. Our method enhances recognition accuracy by an average factor of 5%, proving its efficacy and robustness under feature drift conditions.

WiFi signals based gesture recognition plays an important role in smart homes, such as human-computer interaction, identity authentication and so on. Most of existing approaches need a large number of channel state information dataset for model training to recognized human gestures. However, the robustness of the model to new users will be seriously affected, when the number of users participating in the training dataset is lacking. To address this problem, we propose a gesture recognition system based on matched averaging federated learning framework (WiMA). WiMA exploits parameter matching federated learning to training gesture prediction model, instead of traditional parameter aggregation. Experimental results show that the average accuracy of WiMA can be up to 90.4%, when 7 users participate in model training in 2 different rooms.

Edge computing involves distributed devices operating in dynamic environments with diverse resource constraints and highly heterogeneous data distributions. In these settings, personalized federated learning (PFL) provides a collaborative learning framework that preserves the unique data characteristics of each device. However, PFL models often encounter bidirectional catastrophic forgetting. During consecutive training rounds, the personalized characteristics learned by local models are readily overwritten by updates from the global model, while the global model’s shared representations are degraded by distribution shifts arising from heterogeneous local data. This challenge is further amplified in edge computing settings, where devices must adapt to fast-changing heterogeneous data. To address this issue, we propose FedSSM, a novel framework that leverages state-space models to mitigate forgetting in PFL. By capturing the temporal evolution of local model parameters through hidden states, the framework enhances the retention of critical knowledge throughout training rounds. Extensive experiments on multiple benchmark datasets demonstrate that FedSSM outperforms various state-of-the-art PFL algorithms, particularly with high data heterogeneity.