{"title":"学习预测跨维运动的自监督人类活动识别","authors":"Setareh Rahimi Taghanaki, M. Rainbow, A. Etemad","doi":"10.1145/3460421.3480417","DOIUrl":null,"url":null,"abstract":"We propose the use of self-supervised learning for human activity recognition with smartphone accelerometer data. Our proposed solution consists of two steps. First, the representations of unlabeled input signals are learned by training a deep convolutional neural network to predict a segment of accelerometer values. Our model exploits a novel scheme to leverage past and present motion in x and y dimensions, as well as past values of the z axis to predict values in the z dimension. This cross-dimensional prediction approach results in effective pretext training with which our model learns to extract strong representations. Next, we freeze the convolution blocks and transfer the weights to our downstream network aimed at human activity recognition. For this task, we add a number of fully connected layers to the end of the frozen network and train the added layers with labeled accelerometer signals to learn to classify human activities. We evaluate the performance of our method on three publicly available human activity datasets: UCI HAR, MotionSense, and HAPT. The results show that our approach outperforms the existing methods and sets new state-of-the-art results.","PeriodicalId":395295,"journal":{"name":"Proceedings of the 2021 ACM International Symposium on Wearable Computers","volume":"77 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Self-supervised Human Activity Recognition by Learning to Predict Cross-Dimensional Motion\",\"authors\":\"Setareh Rahimi Taghanaki, M. Rainbow, A. Etemad\",\"doi\":\"10.1145/3460421.3480417\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose the use of self-supervised learning for human activity recognition with smartphone accelerometer data. Our proposed solution consists of two steps. First, the representations of unlabeled input signals are learned by training a deep convolutional neural network to predict a segment of accelerometer values. Our model exploits a novel scheme to leverage past and present motion in x and y dimensions, as well as past values of the z axis to predict values in the z dimension. This cross-dimensional prediction approach results in effective pretext training with which our model learns to extract strong representations. Next, we freeze the convolution blocks and transfer the weights to our downstream network aimed at human activity recognition. For this task, we add a number of fully connected layers to the end of the frozen network and train the added layers with labeled accelerometer signals to learn to classify human activities. We evaluate the performance of our method on three publicly available human activity datasets: UCI HAR, MotionSense, and HAPT. The results show that our approach outperforms the existing methods and sets new state-of-the-art results.\",\"PeriodicalId\":395295,\"journal\":{\"name\":\"Proceedings of the 2021 ACM International Symposium on Wearable Computers\",\"volume\":\"77 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-10-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2021 ACM International Symposium on Wearable Computers\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3460421.3480417\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2021 ACM International Symposium on Wearable Computers","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3460421.3480417","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
摘要
我们建议使用自监督学习对智能手机加速度计数据进行人类活动识别。我们提出的解决方案包括两个步骤。首先,通过训练深度卷积神经网络来预测一段加速度计值来学习未标记输入信号的表示。我们的模型利用了一种新的方案来利用过去和现在在x和y维度上的运动,以及过去的z轴值来预测z维度上的值。这种跨维预测方法导致有效的借口训练,我们的模型学习提取强表征。接下来,我们冻结卷积块并将权重转移到下游网络,旨在识别人类活动。对于这项任务,我们在冻结网络的末端添加了许多完全连接的层,并使用标记的加速度计信号训练添加的层来学习对人类活动进行分类。我们在三个公开可用的人类活动数据集上评估了我们的方法的性能:UCI HAR, MotionSense和HAPT。结果表明,我们的方法优于现有的方法,并设定了新的最先进的结果。
Self-supervised Human Activity Recognition by Learning to Predict Cross-Dimensional Motion
We propose the use of self-supervised learning for human activity recognition with smartphone accelerometer data. Our proposed solution consists of two steps. First, the representations of unlabeled input signals are learned by training a deep convolutional neural network to predict a segment of accelerometer values. Our model exploits a novel scheme to leverage past and present motion in x and y dimensions, as well as past values of the z axis to predict values in the z dimension. This cross-dimensional prediction approach results in effective pretext training with which our model learns to extract strong representations. Next, we freeze the convolution blocks and transfer the weights to our downstream network aimed at human activity recognition. For this task, we add a number of fully connected layers to the end of the frozen network and train the added layers with labeled accelerometer signals to learn to classify human activities. We evaluate the performance of our method on three publicly available human activity datasets: UCI HAR, MotionSense, and HAPT. The results show that our approach outperforms the existing methods and sets new state-of-the-art results.