Mobile activity recognition and fall detection system for elderly people using Ameva algorithm

Abstract

a b s t r a c tCurrently, the lifestyle of elderly people is regularly monitored in order to establish guidelines for rehabilitation processes or ensure the welfare of this segment of the population. In this sense, activity recognition is essential to detect an objective set of behaviors throughout the day. This paper describes an accurate, comfortable and efficient system, which monitors the physical activity carried out by the user. An extension to an awarded activity recognition system that participated in the EvAAL 2012 and EvAAL 2013 competitions is presented. This approach uses data retrieved from accelerometer sensors to generate discrete variables and it is tested in a non-controlled environment. In order to achieve the goal, the core of the algorithm Ameva is used to develop an innovative selection, discretization and classification technique for activity recognition. Moreover, with the purpose of reducing the cost and increasing user acceptance and usability, the entire system uses only a smartphone to recover all the information required.

Wearables for independent living in older adults: Gait and falls

“…Up to 99% for new method compared to 93% New method facilitated data reduction of over 70% yielding good energy efficiency Concepcion et al [151] Iterative work by the authors using an optimised version of a previous algorithm (Ameva). Data gathered on large cohort with smartphone but only 1 case study presented.…”

RPL-Based Routing Protocols in IoT Applications: A Review

“…Falls are among the main causes of death in elderly people, the detection of such an accident and the timely reporting to the appropriate entity is a key factor in saving the patients life and preventing further developments. Accelerometers are usually used to detect falls, [23], [24], [25] sometimes accompanied by cameras and image sensors to increase the reliability of fall detection [26], [27], [28]. When a fall is detected and confirmed by image sensors, the computer makes a phone call to the emergency department or the health establishment, RSSI can also be used to give an estimated location inside the building.…”

Toward improving indoor magnetic field–based positioning system using pedestrian motion models

“…Shen et al 40 use fuzzy Petri net to analysis and develop the identification of human actions, including normal action, exercising, and falling down. La Concepcion et al 41 leverage data retrieved from accelerometer sensors to generate discrete variables, then the core of the algorithm Ameva is used to develop the selection, discretization, and classification technique for activity recognition. Hakim et al 42 propose a threshold-based fall detection algorithm using a supervised machine learning algorithm to classify activities of daily living (ADL).…”