Abstract
The detection of activities of daily living (ADL) and the detection of falls is of utmost importance for addressing the issue of serious injuries and death as a consequence of elderly people falling. Wearable sensors can provide a viable solution for monitoring people in danger of falls with minimal external involvement from health or care home workers. In this work, we recorded accelerometer data from 35 healthy individuals performing various ADLs, as well as falls. Spatial and frequency domain features were extracted and used for the training of machine learning models with the aim of distinguishing between fall and no fall events, as well as between falls and other ADLs. Supervised classification experiments demonstrated the efficiency of the proposed approach, achieving an F1-score of 98.41% for distinguishing between fall and no fall events, and an F1-score of 88.11% for distinguishing between various ADLs, including falls. Furthermore, the created dataset, named “ShimFall&ADL” will be publicly released to facilitate further research on the field.
Highlights
The automated recognition of human activity using various types of sensors is an interesting research area that can have multiple practical applications [1], e.g., in healthcare [2], surveillance [3], entertainment [4], security [5], building management [6], and others
Features were extracted from the accelerometer data using Principal Component Analysis (PCA) and an Support Vector Machine (SVM) classifier was used for the detection of fall events based on the computed features
In this work we proposed and evaluated an activities of daily living and fall detection methodology based on a triaxial wearable accelerometer and machine learning
Summary
The automated recognition of human activity using various types of sensors is an interesting research area that can have multiple practical applications [1], e.g., in healthcare [2], surveillance [3], entertainment [4], security [5], building management [6], and others. Or unexpected activities, such as walking, sitting, running, cycling, standing, falling, fighting, crowd assembling, etc., can be detected using non pervasive sensors that are either remotely positioned, e.g., a camera, or carried by humans, e.g., smart phones, smart watches, smart wristbands [7]. This was made possible by the advancement in microelectronics, wearable sensors, and imaging sensors during the past decade that allowed the widespread manufacturing of small devices with enhanced computational power. Huynh et al [25] combined gyroscope and accelerometer data acquired from sensors placed on the chest and was able to detect various ADL and fall events using a thresholding approach on peak acceleration and peak angular velocity
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.
