Multi-sensor human activity recognition using CNN and GRU

被引:0
作者
Ohoud Nafea
Wadood Abdul
Ghulam Muhammad
机构
[1] King Saud University,Department of Computer Engineering, College of Computer and Information Sciences
来源
International Journal of Multimedia Information Retrieval | 2022年 / 11卷
关键词
Human activity recognition; Convolutional neural networks (CNN); Gated recurrent uni (GRU);
D O I
暂无
中图分类号
学科分类号
摘要
In the current era of rapid technological innovation, human activity recognition (HAR) has emerged as a principal research area in the field of multimedia information retrieval. The capacity to monitor people remotely is a main determinant of HAR’s central role. Multiple gyroscope and accelerometer sensors can be used to aggregate data which can be used to recognise human activities—one of the key research objectives of this study. Optimal results are attained through the use of deep learning models to carry out HAR in the collected data. We propose the use of a hierarchical multi-resolution convolutional neural networks in combination with gated recurrent uni. We conducted an experiment on the mHealth and UCI data sets, the results of which demonstrate the efficiency of the proposed model, as it achieved acceptable accuracies: 99.35% in the mHealth data set and 94.50% in the UCI data set.
引用
收藏
页码:135 / 147
页数:12
相关论文
共 72 条
[1]  
Kankanhalli MS(2008)Application potential of multimedia information retrieval Proc IEEE 96 712-720
[2]  
Rui Y(2021)A survey of human activity recognition in smart homes based on IoT sensors algorithms: taxonomies, challenges, and opportunities with deep learning Sensors 21 6037-40
[3]  
Bouchabou D(2021)Deep learning for sensor-based human activity recognition: overview, challenges, and opportunities ACM Comput Surv (CSUR) 54 1-18
[4]  
Nguyen SM(2021)Multi-input CNN-GRU based human activity recognition using wearable sensors Computing 66 1-3234
[5]  
Lohr C(2022)Smart devices based multisensory approach for complex human activity recognition Comput Mater Contin 70 3221-23
[6]  
LeDuc B(2021)Joint transferable dictionary learning and view adaptation for multi-view human action recognition ACM Trans Knowl Discov Data 15 1-177
[7]  
Kanellos I(2017)Hierarchical classification method based on selective learning of slacked hierarchy for activity recognition systems Expert Syst Appl 88 165-2436
[8]  
Chen K(2021)Ordered physical human activity recognition based on ordinal classification Turk J Electr Eng Comput Sci 29 2416-260
[9]  
Zhang D(2021)HARTIV: human activity recognition using temporal information in videos Comput Mater Contin 363 246-10988
[10]  
Yao L(2019)Multi-head CNN-RNN for multi-time series anomaly detection: an industrial case study Neurocomputing 21 10978-56866