arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.12178cs.LGeess.SPstat.ML
收藏

基于领域自适应批量归一化的增量式实时的个性化人体行为识别

Incremental Real-Time Personalization in Human Activity Recognition Using Domain Adaptive Batch Normalization

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Carnegie-Mellon-University(卡内基梅隆大学)

Alan Mazankiewicz, Klemens Böhm, Mario Bergés

摘要:

来自智能手机加速度计等设备的人类活动识别(HAR)是普适计算中的一个基本问题。基于机器学习的识别模型在应用于不是训练数据的一部分的新用户时通常表现不佳。以前的工作已经解决了这一挑战,通过个性化的一般识别模型的新用户在一个静态的批量设置的独特的运动模式。它们要求预先提供目标用户数据。更具挑战性的在线设置受到的关注较少。没有来自目标用户的样本可以提前获得,但它们会按顺序到达。另外,用户的运动模式可随时间改变。因此,适应新的和忘记旧的信息必须权衡。最后,目标用户不应该做任何工作来使用识别系统,比如标记任何活动。我们的工作解决了所有这些挑战,提出了一个无监督的在线领域自适应算法。分类和个性化都是实时的连续和增量发生的。我们的解决方案通过对齐隐藏神经网络层中所有主题的特征分布来工作,无论是源还是目标。为此,我们使用用户特定的均值和方差统计数据对层的输入进行归一化。在训练期间,这些统计信息是在用户特定的批处理上计算的。在联机阶段,对任何新的目标用户进行增量估计。

英文摘要:

Human Activity Recognition (HAR) from devices like smartphone accelerometers is a fundamental problem in ubiquitous computing. Machine learning based recognition models often perform poorly when applied to new users that were not part of the training data. Previous work has addressed this challenge by personalizing general recognition models to the unique motion pattern of a new user in a static batch setting. They require target user data to be available upfront. The more challenging online setting has received less attention. No samples from the target user are available in advance, but they arrive sequentially. Additionally, the motion pattern of users may change over time. Thus, adapting to new and forgetting old information must be traded off. Finally, the target user should not have to do any work to use the recognition system by, say, labeling any activities. Our work addresses all of these challenges by proposing an unsupervised online domain adaptation algorithm. Both classification and personalization happen continuously and incrementally in real time. Our solution works by aligning the feature distributions of all subjects, be they sources or the target, in hidden neural network layers. To this end, we normalize the input of a layer with user-specific mean and variance statistics. During training, these statistics are computed over user-specific batches. In the online phase, they are estimated incrementally for any new target user.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑