.png){kind=icon}
返回
DWOSC: Dynamic Weight Optimization and Smoothness Constraint for Sensor-Based Human Activity Recognition
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2024.3366277.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The sensor-based human activity recognition (SHAR) task aims to detect and analyze signals captured by various sensors embedded in intelligent devices to assist people's daily lives, which inherently have variations, spatial inconsistency, and noise characteristics. Inspired by the success of deep learning, many researchers have designed various neural network architectures to improve the SHAR model's performance. Albeit effective, these manners are not optimal due to ignoring the imbalance and difficulty of interclass and intraclass of sensor inherently characteristic, which proposes the challenge for resource-constrained devices. To address this challenge, we present a simple and effective optimization strategy for sensor signal processing, including dynamic weight optimization (DWO) and smoothness constraint (SC) strategies, termed DWOSC, which provide a framework to optimize loss function and enhance activity recognition performance. The DWO aims to address the class imbalance and hard-to-recognize samples. The SC seeks to maintain the smoothness of decision boundaries for complex samples. This way, the proposed approach can achieve a more stable convergence of the model and further improve the SHAR task's performance without raising complexity. Extensive experiments conducted on three benchmark SHAR datasets, e.g., OPPORTUNITY, University of Southern California Human Activity Dataset (USC-HAD), and UniMib, demonstrate the superiority of our method over the deep learning baselines and existing SHAR works.
Keyword:
Deep learning
Optimization
Sensors
Task analysis
Human activity recognition
Training
Data models
dynamic weight optimization (DWO)
optimization strategy
sensor-based human activity recognition (SHAR)
smoothness constraint (SC)
期刊
IF:
5.9
论文数:
2.0W
被引数:
5.8W
机构
引用论文
A systematic study of the class imbalance problem in convolutional neural networks卷积神经网络中类不平衡问题的系统研究.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏AHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge DevicesAHAR: 自适应CNN，用于低功耗边缘设备中的节能人体活动识别
OAAI
OAAI分享收藏Arsenic removal from aqueous solutions by adsorption using novel MIL-53(Fe) as a highly efficient adsorbent使用新型MIL-53(Fe) 作为高效吸附剂通过吸附从水溶液中去除砷RSC Advances
RSC AdvancesIF0
PREAI
分享收藏Development of a Multi-Dimensional Parametric Model With Non-Pharmacological Policies for Predicting the COVID-19 Pandemic CasualtiesIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Pharmacological characteristics of facilitation of hippocampal population spikes by cholinomimeticsNeuroscience
NeuroscienceIF0
PREAI
分享收藏
查看更多内容