Supervised Expert System for Wearable MEMS Accelerometer-Based Fall Detector

Abstract

Falling is one of the main causes of trauma, disability, and death among older people. Inertial sensors-based devices are able to detect falls in controlled environments. Often this kind of solution presents poor performances in real conditions. The aim of this work is the development of a computationally low-cost algorithm for feature extraction and the implementation of a machinelearning scheme for people fall detection, by using a triaxial MEMS wearable wireless accelerometer. The proposed approach allows to generalize the detection of fall events in several practical conditions. It appears invariant to the age, weight, height of people, and to the relative positioning area (even in the upper part of the waist), overcoming the drawbacks of well-known threshold-based approaches in which several parameters need to be manually estimated according to the specific features of the end user. In order to limit the workload, the specific study on posture analysis has been avoided, and a polynomial kernel function is used while maintaining high performances in terms of specificity and sensitivity. The supervised clustering step is achieved by implementing an one-class support vector machine classifier in a stand-alone PC.

An Event Polarized Paradigm for ADL Detection in AAL Context

“…Of course, as well evidenced by the brief review of the state of the art on currently available approaches for ADL detection presented in the following, mandatory features of such monitoring systems are the reliability and the user acceptability. Different approaches have been proposed to develop systems to assess the human posture [2], [3] and to detect ADL and falls in the Ambient Assisted Living (AAL) context, such as customized devices [4]- [6] and smartphone-based platforms [7]- [14]. An extensive review of fall detection systems, including comparisons among different approaches, is available in [15].…”

An event polarized paradigm for ADL detection in AAL context

“…Falling, which is one of the main causes of trauma among older people, stair negotiation, user posture are just few examples of daily activities and a reliable monitoring of ADL by using poor invasive and easy to use devices would really change the way of achieving awareness on the user status thus reducing times for the implementation of emergency activities. Different approaches have been proposed to develop systems for ADL detection in the Ambient Assisted Living contexts, such as customized devices [1,2], smartphone based platforms [3][4][5][6][7][8][9][10]. Customized solutions, such as systems presented in [1,2], present sounding performances.…”

“…Different approaches have been proposed to develop systems for ADL detection in the Ambient Assisted Living contexts, such as customized devices [1,2], smartphone based platforms [3][4][5][6][7][8][9][10]. Customized solutions, such as systems presented in [1,2], present sounding performances. Anyway the problem with such systems is that they could provoke users diffidence and discomfort due to body positioning and difficult to use thus compromising the possibility to actually improve their life quality.…”

Human movement detection using attitude and heading reference system

“…Many approaches have been proposed [5]- [11]. According to [12] fall detection systems are based in three types of equipment: wearable devices, ambient devices and camera-based devices.…”