arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.04367cs.LG
收藏

自然时间序列移动活动识别中行为和时间变化下的领域自适应

Domain Adaptation Under Behavioral and Temporal Shifts for Natural Time Series Mobile Activity Recognition

Washington State University(华盛顿州立大学)

Garrett Wilson, Janardhan Rao Doppa, Diane J. Cook

摘要:

越来越多的人的行为被捕获在移动设备上,导致对自动人类活动识别的兴趣增加。然而,现有的数据集通常由脚本运动组成。我们的长期目标是在自然环境中进行移动活动识别。我们收集了一个数据集来支持这一目标,其中包括与下游任务(如健康监测和干预)相关的活动类别。由于人类行为存在很大的差异,我们从两个不同年龄组的许多参与者那里收集数据。由于人类行为可能会随着时间的推移而变化,我们还收集了参与者一个月内的数据,以捕捉时间漂移。我们假设移动活动识别可以受益于无监督的领域自适应算法。为了解决这一需求和测试这一假设,我们分析了跨人和跨时间的领域自适应的性能。然后,我们增强无监督的领域自适应与对比学习和弱监督时,标签比例。该数据集可在https://github.com/WSU-CASAS/smartwatch-data上获得

英文摘要:

Increasingly, human behavior is captured on mobile devices, leading to an increased interest in automated human activity recognition. However, existing datasets typically consist of scripted movements. Our long-term goal is to perform mobile activity recognition in natural settings. We collect a dataset to support this goal with activity categories that are relevant for downstream tasks such as health monitoring and intervention. Because of the large variations present in human behavior, we collect data from many participants across two different age groups. Because human behavior can change over time, we also collect data from participants over a month's time to capture the temporal drift. We hypothesize that mobile activity recognition can benefit from unsupervised domain adaptation algorithms. To address this need and test this hypothesis, we analyze the performance of domain adaptation across people and across time. We then enhance unsupervised domain adaptation with contrastive learning and with weak supervision when label proportions are available. The dataset is available at https://github.com/WSU-CASAS/smartwatch-data

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。

↑