.png){kind=icon}
返回
A General Multistage Deep Learning Framework for Sensor-Based Human Activity Recognition Under Bounded Computational Budget
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2024.3481549.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, sliding windows have been widely employed for sensor-based human activity recognition (HAR) due to their implementational simplicity. In this article, inspired by the fact that not all time intervals in a window are activity-relevant, we propose a novel multistage HAR framework named MS-HAR by implementing a sequential decision procedure to progressively process a sequence of relatively small intervals, i.e., reduced input, which is automatically cropped from the original window with reinforcement learning. Such a design naturally facilitates dynamic inference at runtime, which may be terminated at an arbitrary time once the network obtains sufficiently high confidence about its current prediction. Compared to most existing works that directly handle the whole window, our method allows for very precisely controlling the computational budget online by setting confidence thresholds, which forces the network to spend more computation on a difficult activity while spending less computation on an easy activity under a finite computational budget. Extensive experiments on four benchmark HAR datasets consisting of WISMD, PAMAP2, USC-HAD, and one weakly labeled dataset demonstrate that our method is considerably more flexible and efficient than the competitive baselines. Particularly, our proposed framework is general since it is compatible with most mainstream backbone networks.
Keyword:
Deep learning
Human activity recognition
Computational efficiency
Accuracy
Proposals
Reinforcement learning
Predictive models
Power demand
Heuristic algorithms
Data models
early exit
human activity recognition (HAR)
reinforcement learning
sensors
sequential decision
期刊
IF:
5.9
论文数:
2.0W
被引数:
5.8W
机构
引用论文
Sino-Angolan agricultural cooperation: still not reaping rewards for the Angolan agricultural sector
OAAI
OAAI分享收藏Efficient dense labelling of human activity sequences from wearables using fully convolutional networks.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏A Tutorial on Human Activity Recognition Using Body-Worn Inertial Sensors使用身体佩戴的惯性传感器进行人体活动识别的教程
PREAI
分享收藏分享收藏
查看更多内容