Abstract:

Concerning the sensor data based activity recognition problem， deep Convolutional Neural Network （CNN） was used to perform activity recognition on public OPPORTUNITY sensor dataset， and an improved Progressive Neural Architecture Search （PNAS） algorithm was proposed. Firstly， in the process of neural network model design， without manual selection of suitable topology， PNAS algorithm was used to design the optimal topology in order to maximize the F1 score. Secondly， a Sequential Model-Based Optimization （SMBO） strategy was used， in which the structure space was searched in the order of low complexity to high complexity， while a surrogate function was learned to guide the search of the structure space. Finally， the top 20 models with the best performance in the search process were fully trained on OPPORTUNIT dataset， and the best performing model was selected as the optimal architecture searched. The F1 score of the optimal architecture searched in this way reaches 93.08% on OPPORTUNITY dataset， which is increased by 1.34% and 1.73% respectively compared with those of the optimal architecture searched by evolutionary algorithm and DeepConvlSTM， which indicates that the proposed method can improve previously manually-designed architectures and is feasible and effective.

Key words: Human Activity Recognition （HAR）, deep learning, Neural Architecture Search （NAS）, Convolutional Neural Network （CNN）, Sequential Model-Based Optimization （SMBO）

摘要：

为了解决基于传感器数据的运动识别问题，利用深度卷积神经网络（CNN）在公开的OPPORTUNITY传感器数据集上进行运动识别，提出了一种改进的渐进式神经网络架构搜索（PNAS）算法。首先，神经网络模型设计过程中不再依赖于合适拓扑结构的手动选择，而是通过PNAS算法来设计最优拓扑结构以最大化F1分数；其次，使用基于序列模型的优化（SMBO）策略，在该策略中将按照复杂度从低到高的顺序搜索结构空间，同时学习一个代理函数以引导对结构空间的搜索；最后，将搜索过程中表现最好的20个模型在OPPORTUNIT数据集上进行完全训练，并从中选出表现最好的模型作为搜索到的最优架构。通过这种方式搜索到的最优架构在OPPORTUNITY数据集上的F1分数达到了93.08%，与进化算法搜索到的最优架构及DeepConvLSTM相比分别提升了1.34%和1.73%，证明该方法能够改进以前手工设计的模型结构，且是可行有效的。

关键词: 人体运动识别, 深度学习, 神经网络架构搜索, 卷积神经网络, 基于序列模型的优化