An active semi-supervised deep learning model for human activity recognition
An active semi-supervised deep learning model for human activity recognition
复制标题
DOI：
10.1007/s12652-022-03768-2
复制
发表时间：
2022-03
影响因子：
--
通讯作者：
Haixia Bi;Miquel Perello-Nieto;Raúl Santos-Rodríguez;Peter A. Flach;I. Craddock
中科院分区：
文献类型：
--
作者：
Haixia Bi;Miquel Perello-Nieto;Raúl Santos-Rodríguez;Peter A. Flach;I. Craddock
人类活动识别（HAR）旨在推断人们的行为模式，是数字健康和环境智能领域的一个基础研究问题。近年来，机器学习方法在 HAR 中的应用得到了大力研究。然而，这项任务仍然面临许多挑战，其中一个重大障碍在于注释的长期短缺。为了解决这个问题，我们建立了一种新的 HAR 范式，它将主动学习和半监督学习集成到一个框架中。主要思想是通过主动选择信息最丰富的样本进行注释以及以半监督的方式利用未标记的实例来降低注释成本。特别是，我们建议通过卷积神经网络（CNN）的时间集成来利用大量未标记数据，通过聚合不同时期的训练网络的输出来产生稳健的共识预测。我们对三个公共基准数据集进行了广泛的实验。所提出的方法在 PAMAP2、USCHAD 和 UCIHAR 数据集上的低注释场景中分别实现了 0.76、0.45 和 0.91 的 Macro F1 值，优于多种最先进的深度模型。消融研究证明了该框架的两个组成部分（即基于主动学习的样本选择和时间集成的半监督模型训练）在缓解标签不足问题方面的有效性。交叉验证和统计显着性实验进一步证明了该方法的鲁棒性和泛化能力。源代码可在 https://github.com/HaixiaBi1982/ActSemiCNNAct 获取。
Human activity recognition (HAR), which aims at inferring the behavioral patterns of people, is a fundamental research problem in digital health and ambient intelligence. The application of machine learning methods in HAR has been investigated vigorously in recent years. However, there are still a number of challenges confronting the task, where one significant barrier lies in the longstanding shortage of annotations. To address this issue, we establish a new paradigm for HAR, which integrates active learning and semi-supervised learning into one framework. The main idea is to reduce the annotation cost by actively selecting the most informative samples for annotation, as well as leveraging the unlabelled instances in a semi-supervised way. In particular, we propose to utilize the massive unlabelled data via temporal ensembling of convolutional neural networks (CNN), which yields robust consensus predictions by aggregating the outputs of the training networks on different epochs. We conducted extensive experiments on three public benchmark datasets. The proposed method achieves Macro F1 values of 0.76, 0.45 and 0.91 in a low annotation scenario on PAMAP2, USCHAD and UCIHAR datasets respectively, outperforming a multitude of state-of-the-art deep models. The ablation study proves the effectiveness of the two components of the framework, i.e., active learning-based sample selection and semi-supervised model training with temporal ensembling, in alleviating the issue of insufficient labels. Cross-validation and statistical significance experiments further demonstrate the robustness and generalization ability of the proposed method. The source codes are available at https://github.com/HaixiaBi1982/ActSemiCNNAct.