Abstract
Human activity recognition (HAR) has been a vital human–computer interaction service in smart homes. It is still a challenging task due to the diversity and similarity of human actions. In this paper, a novel hierarchical deep learning-based methodology equipped with low-cost sensors is proposed for high-accuracy device-free human activity recognition. ESP8266, as the sensing hardware, was utilized to deploy the WiFi sensor network and collect multi-dimensional received signal strength indicator (RSSI) records. The proposed learning model presents a coarse-to-fine hierarchical classification framework with two-level perception modules. In the coarse-level stage, twelve statistical features of time–frequency domains were extracted from the RSSI measurements filtered by a butterworth low-pass filter, and a support vector machine (SVM) model was employed to quickly recognize the basic human activities by classifying the signal statistical features. In the fine-level stage, the gated recurrent unit (GRU), a representative type of recurrent neural network (RNN), was applied to address issues of the confused recognition of similar activities. The GRU model can realize automatic multi-level feature extraction from the RSSI measurements and accurately discriminate the similar activities. The experimental results show that the proposed approach achieved recognition accuracies of 96.45% and 94.59% for six types of activities in two different environments and performed better compared the traditional pattern-based methods. The proposed hierarchical learning method provides a low-cost sensor-based HAR framework to enhance the recognition accuracy and modeling efficiency.
Highlights
The rapid development of the Internet of Things (IoT) technology and artificial intelligence has promoted the mutual “communication” between people and things and between things, greatly improving the lifestyle and quality of life of human beings
Aiming to produce low-cost, lightweight and high-precision human activity recognition, we proposed a novel hierarchical recognition framework based on WiFi-received signal strength indicator (RSSI) wireless sensing information using ESP8266 as the sensor hardware
The activity recognition model was constructed by combining coarse-level and fine-level recognition models based on the proposed hierarchical classification method, and the recognition performance of the proposed method was evaluated according to four evaluation measures, namely the average accuracy; recall; precision; and f-score
Summary
The rapid development of the Internet of Things (IoT) technology and artificial intelligence has promoted the mutual “communication” between people and things and between things, greatly improving the lifestyle and quality of life of human beings. Huang et al [18] proposed WiDet, a human detection system based on WiFi-RSSI This system used the deep learning method, namely the convolutional neural network (CNN), to automatically learn the features from the sensor sequence data, and combined the original RSSI measurements with the wavelet coefficients as the input of the neural network, which can distinguish the signal change caused by human movement from the random noise interference, and improve the detection accuracy of walking behavior to 95.5%. The proposed hierarchical learning framework combines a pattern-based method with signal statistical features to detect the coarse-level activities, and a deep learning model for the secondary detection to accurately identify the similar activities To accurately recognize similar activities, the GRU model was leveraged to identify similar activities by extracting activity features from the contextual relationship between sensor signal frames, which can greatly enhance the recognition accuracy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
