Characterizing and monitoring patient activities through time series data is critical for identifying lifestyle patterns that may impact health outcomes. Sedentary behavior is a significant concern due to its association with various health risks. This study introduces a lightweight supervised classifier for healthcare applications based on ordinal pattern transformation to detect sedentary behavior in federated learning scenarios. Our hypothesis is grounded on the idea that sedentary behavior exhibits distinct dynamics compared to other activities, and information descriptors derived from the transformation of ordinal patterns effectively capture these differences. Next, we proceed with the federated learning training. We train a neural network-based encoder locally and send the local models to a server. The federated learning process updates the encoder weights based on the encoded representations of the clients’ data, enabling the model to learn from different participants. Finally, we personalize the model for the specific task of classifying sedentary behavior. Our approach utilizes a meta-learning framework, incorporating a Siamese neural network to learn a similarity space. We fine-tune the model in this step by further training the last neural network layer. This fine-tuning allows the model to adapt and specialize in accurately classifying sedentary behavior. We carry out a comprehensive analysis to support our hypothesis. We also extensively validated our proposal by comparing it with other methods over five different datasets. We obtain the best results using a smaller ML model compared with the best approaches in the literature. Specifically, our model has 78.73% times fewer parameters and consumes 48.67% times less energy than the best result in the literature.

中文翻译：

---

一种新颖的联合元学习方法，用于从可穿戴数据中区分久坐行为


通过时间序列数据表征和监测患者活动对于识别可能影响健康结果的生活方式模式至关重要。久坐行为是一个值得关注的问题，因为它与各种健康风险有关。本研究引入了一种基于序数模式转换的用于医疗保健应用的轻量级监督分类器，以检测联邦学习场景中的久坐行为。我们的假设基于以下观点：与其他活动相比，久坐行为表现出独特的动态，并且从序数模式转换中派生的信息描述符有效地捕获了这些差异。接下来，我们进行联邦学习训练。我们在本地训练基于神经网络的编码器并将本地模型发送到服务器。联邦学习过程根据客户端数据的编码表示更新编码器权重，使模型能够向不同的参与者学习。最后，我们针对久坐行为分类的特定任务个性化模型。我们的方法利用元学习框架，结合暹罗神经网络来学习相似性空间。我们通过进一步训练最后一个神经网络层来微调模型。这种微调使模型能够适应并专门准确地对久坐行为进行分类。我们进行了全面的分析来支持我们的假设。我们还通过将其与五个不同数据集的其他方法进行比较来广泛验证我们的建议。与文献中的最佳方法相比，我们使用更小的 ML 模型获得了最佳结果。具体来说，我们的模型参数减少了 78.73%，消耗了 48 个参数。比文献中的最佳结果减少 67% 的能量。