Domain-Robust Pre-Training Method for the Sensor-Based Human Activity Recognition
Domain-Robust Pre-Training Method for the Sensor-Based Human Activity Recognition
复制标题
基于传感器的人体活动识别的域鲁棒预训练方法
DOI：
10.1109/icmlc56445.2022.9941291
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Hasegawa Tatsuhito
中科院分区：
文献类型：
--
作者：
Zhao Zhong-Kai;Hasegawa Tatsuhito
迁移学习通过将学习到的知识从源域迁移到目标域来提高问题解决的效率。在迁移学习中，使用大量数据进行预训练有利于提高模型的鲁棒性。当基于传感器的人类活动识别（HAR）中的域改变时，数据显著不同。目前，HAR中的数据使用相对独立，缺乏海量数据和丰富标签的源域。本文提出了一种新的预训练方法，使用多个领域的数据集来构建一个领域鲁棒的预训练模型。通过考虑活动分类的差异，我们将预训练数据集分为基本活动场景和复杂活动场景。我们基于构成的数据集并使用深度卷积网络来评估最有利于基于传感器的HAR的分类场景。我们表明，我们的方法验证了在基于传感器的HAR的迁移学习的源域的影响。通过构造一个相当大的相关源域，我们的方法可以提高网络模型的泛化能力。本文还证明了大规模和基本的活动分类数据集可以更好地用作预训练模型来参与HAR分类任务。
Transfer learning improves problem-solving efficiency by transferring the learned knowledge from the source domain to the target domain. In transfer learning, using a large amount of data for pre-training is beneficial to improve the robustness of the model. Data differ significantly when the domain changes in Sensor-Based human activity recognition (HAR). Currently, in HAR, data usage is relatively independent, lacking source domains with massive data and rich labels. This paper proposes a new pre-training method using multiple domain datasets to construct a domain-robust pre-training model. We divide the pre-training dataset into basic and complex activities scenarios by considering the difference in activity classification. We evaluate the classification scenarios that are most beneficial for sensor-based HAR based on the constituted dataset and using deep convolutional networks. We show that our method verified the influence of the source domain on transfer learning in sensor-based HAR. By constructing a sizeable correlated source domain, our method can enhance the generalization ability of the network model. This paper also demonstrated that large-scale and basic activity classification datasets can be better used as pre-training models to participate in HAR classification tasks.
影响因子：
1.6
作者：
Kunze, Kai;Lukowicz, Paul
通讯作者：
Lukowicz, Paul
DOI：
10.1145/2971763.2971764
发表时间：
2016-09
期刊：
Proceedings of the 2016 ACM International Symposium on Wearable Computers
影响因子：
--
作者：
Francisco Javier Ordonez;D. Roggen
通讯作者：
Francisco Javier Ordonez;D. Roggen