A Novel Feature Set Extraction Based on Accelerometer Sensor Data for Improving the Fall Detection System

Abstract

Because falls are the second leading cause of injury deaths, especially in the elderly according to WHO statistics, there have been a lot of studies on developing a fall detection and warning system. Many approaches based on wearable sensors, cameras, Infrared sensors, radar, etc., have been proposed to detect falls efficiently. However, it still faces many challenges due to noise and no clear definition of fall activities. This paper proposes a new way to extract 44 features based on the time domain, frequency domain, and Hjorth parameters to deal with this. The effect of the proposed feature set has been evaluated on several classification algorithms, such as SVM, k-NN, ANN, J48, and RF. Our method achieves a relative high performance (F1-Score metric) in detecting fall and non-fall activities, i.e., 95.23% (falls), 99.11% (non-falls), and 96.16% (falls), 99.90% (non-falls) for the MobileAct 2.0 and UP-Fall datasets, respectively.

The Application of Machine Learning on the Sensors of Smartphones to Detect Falls in Real-Time

“…Any issue requiring remote monitoring of fall occurrences is covered by the provided approach [3,9,11]. Numerous recordings of interested subjects participating in various activity types are needed for the robust development and testing of fall detection algorithms.…”

Machine Learning Based Approaches for Cough Detection From Acceleration Signal

“…The frequency domain features include statistical features like mean, standard deviation, average absolute deviation, minimum and maximum values, difference between maximum and minimum values, median, median absolute deviation, interquartile range, count of negative values, count of positive values, number of values above mean, number of peaks, skewness, kurtosis, and energy [9]. The set of features estimated from time domain signals include similar features to those from the frequency domain, plus Hjorth features ( Activity, mobility and complexity) as in[10] and Autoregression coefficients with Burg order equal to three[11]. Furthermore, the system extracts the maximum and minimum index and their difference from both the time and frequency domain signals.To enhance the performance of a classifier, it is crucial…”