Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition.
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition.
复制标题
DOI：
10.3390/s16010115
复制
发表时间：
2016-01-18
期刊：
影响因子：
--
通讯作者：
Roggen D
中科院分区：
文献类型：
--
作者：
Ordóñez FJ;Roggen D
人类活动识别（HAR）的任务，传统上已经解决了使用启发式过程中获得的工程特征。目前的研究表明，深度卷积神经网络适合从原始传感器输入中自动提取特征。然而，人类活动是由复杂的运动序列组成的，捕捉这种时间动态是成功的HAR的基础。基于最近递归神经网络在时间序列领域的成功，我们提出了一个基于卷积和LSTM递归单元的通用深度活动识别框架，该框架：（i）适用于多模态可穿戴传感器;（ii）可以自然地执行传感器融合;（iii）在设计特征时不需要专业知识;（iv）明确地对特征激活的时间动态进行建模。我们在两个数据集上评估了我们的框架，其中一个数据集已用于公共活动识别挑战。我们的研究结果表明，我们的框架在挑战数据集上的表现比竞争性深度非循环网络平均高出4%;比之前报道的一些结果高出9%。我们的研究结果表明，该框架可以应用于同质传感器模态，但也可以融合多模态传感器，以提高性能。我们描述了关键建筑超参数对性能的影响，以提供有关其优化的见解。
Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters’ influence on performance to provide insights about their optimisation.