Abstract
Human activity recognition (HAR) has gained lots of attention in recent years due to its high demand in different domains. In this paper, a novel HAR system based on a cascade ensemble learning (CELearning) model is proposed. Each layer of the proposed model is comprised of Extremely Gradient Boosting Trees (XGBoost), Random Forest, Extremely Randomized Trees (ExtraTrees) and Softmax Regression, and the model goes deeper layer by layer. The initial input vectors sampled from smartphone accelerometer and gyroscope sensor are trained separately by four different classifiers in the first layer, and the probability vectors representing different classes to which each sample belongs are obtained. Both the initial input data and the probability vectors are concatenated together and considered as input to the next layer’s classifiers, and eventually the final prediction is obtained according to the classifiers of the last layer. This system achieved satisfying classification accuracy on two public datasets of HAR based on smartphone accelerometer and gyroscope sensor. The experimental results show that the proposed approach has gained better classification accuracy for HAR compared to existing state-of-the-art methods, and the training process of the model is simple and efficient.
Highlights
Human activity recognition (HAR) refers to the process of computer detection, analysis and understanding of various human activities and behaviors through different machine learning algorithms
This study mainly conducted related experiments on the HAR dataset, which was completed by 30 volunteers aged 19–48 assisted by smartphone accelerometer and gyroscope, including six human activities, and its extension dataset
The dataset was initially obtained from accelerometer and gyroscope on a smartphone fixed to the tester’s waist, including three-axis linear acceleration and three-axis angular velocity captured at a constant rate of 50 Hz
Summary
HAR refers to the process of computer detection, analysis and understanding of various human activities and behaviors through different machine learning algorithms. It has wide application prospects in the fields of virtual education and entertainment, sport injury detection, elderly care and rehabilitation, and smart home environment monitoring. HAR technology usually utilizes different multi-modal data generated from various hardware devices to detect human posture, physical activity status and behavioral actions [1]. As mobile phones and other wearable device sensors have evolved, inertial sensor data have been acquired using mobile or wearable embedded sensors placed on different body parts to infer details of human activity and postural transition. Some people have recently suggested the social networking method [3], which is founded on the appropriate human profiles
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.
