Abstract
With the improvement of people's living standards, the demand for health monitoring and exercise detection is increasing. It is of great significance to study human activity recognition methods that are different from traditional feature extraction methods. This article uses convolutional neural network algorithms in deep learning to automatically extract features of activities related to human life. It uses a stochastic gradient descent algorithm to optimize the parameters of the convolutional neural network. The trained network model is compressed on STM32CubeMX-AI. Finally, this article introduces the use of neural networks on embedded devices to recognize six human activities of daily life, such as sitting, standing, walking, jogging, upstairs and downstairs. The acceleration sensor related to human activity information is used to obtain the relevant characteristics of the activity, thereby solving the human activity recognition (HAR) problem. The network structure of the constructed CNN model is shown in Figure 1, including an input layer, two convolutional layers and two pooling layers. After comparing the average accuracy of each set of experiments and the test set of the best model obtained from it, the best model is then selected.
Highlights
In the past 10 years, the Internet of Things industry has developed rapidly
Experimental results show that increasing the number of sensors can improve the classification accuracy; Wang proposed coupled Hidden Markov model (HMM) to identify multiuser behavior in the smart home environment and developed a multimodal sensing platform to distinguish single-user and multiuser activities; Kwapisz et al proposed the use of smartphones with sensors for human activity recognition (HAR)
The purpose of this article is to be different from traditional feature extraction methods, using convolutional neural network (CNN) to automatically extract the collected human activity acceleration data features, and to train the CNN through the STM32CubeMX-artificial intelligence (AI) tool for four times compression load
Summary
In the past 10 years, the Internet of Things industry has developed rapidly. With the reduction in size, performance, and cost of various sensors and electronic devices, these electronic components have become more widely used in life. Compared with the disadvantages of the expensive cost and poor portability of deploying external devices to identify the human body’s activity status, wearable sensors can collect various behavioral data of the human body through integrated sensors to identify the human body’s activity status. Experimental results show that increasing the number of sensors can improve the classification accuracy; Wang proposed coupled HMM to identify multiuser behavior in the smart home environment and developed a multimodal sensing platform to distinguish single-user and multiuser activities; Kwapisz et al proposed the use of smartphones with sensors for HAR. The classification effect on the activity and the experimental results show that Bayesian decision-making achieves the best classification accuracy with the smallest computational complexity
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
