Abstract
Human behavior modeling (HBM) is a challenging classification task for researchers seeking to develop sustainable systems that precisely monitor and record human life-logs. In recent years, several models have been proposed; however, HBM remains an inspiring problem that is only partly solved. This paper proposes a novel framework of human behavior modeling based on wearable inertial sensors; the system framework is composed of data acquisition, feature extraction, optimization and classification stages. First, inertial data is filtered via three different filters, i.e., Chebyshev, Elliptic and Bessel filters. Next, six different features from time and frequency domains are extracted to determine the maximum optimal values. Then, the Probability Based Incremental Learning (PBIL) optimizer and the K-Ary tree hashing classifier are applied to model different human activities. The proposed model is evaluated on two benchmark datasets, namely DALIAC and PAMPA2, and one self-annotated dataset, namely, IM-LifeLog, respectively. For evaluation, we used a leave-one-out cross validation scheme. The experimental results show that our model outperformed existing state-of-the-art methods with accuracy rates of 94.23%, 94.07% and 96.40% over DALIAC, PAMPA2 and IM-LifeLog datasets, respectively. The proposed system can be used in healthcare, physical activity detection, surveillance systems and medical fitness fields.
Highlights
Recent developments in human behavior modeling (HBM) help individuals shift their goals from merely counting steps to more comprehensive monitoring and surveillance especially associated with human activities within a controlled environment [1]
Wearable sensors have a wide range of real-world applications that include patient healthcare management, interactive 3D games, security and surveillance, robotics, sports assistance, and tele-immersion technologies
In the features extraction methodology, we proposed a novel combination of features that included Discrete Hartley Transform, Local Mean Decomposition, Spectral Kurtosis, Transient Detection Principles, Envelope Estimation, and Empirical Mode Decomposition
Summary
Recent developments in human behavior modeling (HBM) help individuals shift their goals from merely counting steps to more comprehensive monitoring and surveillance especially associated with human activities within a controlled environment [1]. Standard parameters include heart rate, physical activities through wearable electrocardiogram (ECG), accelerometer and other sensors in wearable devices [5] Nowadays, such sensors are incorporated in body-mounted devices like smart-watches and gloves etc. Wearable sensors have a wide range of real-world applications that include patient healthcare management, interactive 3D games, security and surveillance, robotics, sports assistance, and tele-immersion technologies. Violence detection applications are developed so that immediate action can be initiated against suspicious activities These systems are used by government intelligence agencies to gather relevant information and for the prevention of crime. Robots like the social humanoid “Sophia” and waiter robots have been introduced to socially interact with humans They exercise intelligent abilities using activity recognition technologies. In tele-immersion technologies, systems are used by people in different geographic locations to come together in a common simulated environment
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.
