Wearable sensor-based human activity recognition (HAR) utilizes artificial intelligence models to analyze real-time data like accelerometer data to recognize daily human activities. While it greatly benefits the life of senior citizens and postoperative patients, it conventionally requires the collected data to be uploaded to a central server to train AI models, raising critical security and privacy concerns. Though Federated learning (FL) emerges as a viable way to cope with these problems, it is confronted by the data heterogeneity problem, where the varying activity patterns of different individuals result in non-identically distributed local data. Some FL models have been proposed to solve the data heterogeneity problem by leveraging the similarity between individuals to create a personalized global model for each individual. However, they are still limited by increased computation or unreliable relationships in the similarity computation. This study proposes a novel profile similarity-based personalized federated learning for wearable sensor-based HAR where the similarity between individuals can be reflected in their profile, such as age, gender, height, and weight. When personalizing a model for an individual, we compute the weighted sum of all clients’ local models, where the weight is determined by the similarity value computed from the profile. In this way, the local models from individuals who have higher similarity values will contribute more towards personalizing a model for a targeted individual than those who are less similar. Experiment results demonstrate that the proposed model outperformed the baseline FL and centralized learning on both RealWorld and SisFall datasets. We also discuss the tradeoff between privacy and personalization and FL's advantages over centralized learning.

基于可穿戴传感器的人类活动识别 (HAR) 利用人工智能模型来分析加速度计数据等实时数据，以识别日常人类活动。虽然它极大地有益于老年人和术后患者的生活，但通常需要将收集的数据上传到中央服务器来训练人工智能模型，这引发了严重的安全和隐私问题。尽管联邦学习（FL）成为解决这些问题的可行方法，但它面临着数据异质性问题，即不同个体的不同活动模式导致本地数据分布不一致。一些FL模型被提出来解决数据异质性问题，利用个体之间的相似性为每个个体创建个性化的全局模型。然而，它们仍然受到相似性计算中计算量增加或关系不可靠的限制。本研究提出了一种新颖的基于个人资料相似性的个性化联合学习，用于基于可穿戴传感器的 HAR，其中个体之间的相似性可以反映在他们的个人资料中，例如年龄、性别、身高和体重。当为个人个性化模型时，我们计算所有客户本地模型的加权和，其中权重由根据个人资料计算的相似度值确定。这样，来自具有较高相似性值的个体的本地模型将比那些不太相似的个体对为目标个体个性化模型做出更多贡献。实验结果表明，所提出的模型在 RealWorld 和 SisFall 数据集上均优于基线 FL 和集中学习。我们还讨论了隐私和个性化之间的权衡以及 FL 相对于集中学习的优势。