Discrete techniques applied to low-energy mobile human activity recognition. A new approach

Abstract

Human activity recognition systems are currently implemented by hundreds of applications and, in recent years, several technology manufacturers have introduced new wearable devices for this purpose. Battery consumption constitutes a critical point in these systems since most are provided with a rechargeable battery. In this paper, by using discrete techniques based on the Ameva algorithm, an innovative approach for human activity recognition systems on mobile devices is presented. Furthermore, unlike other systems in current use, this proposal enables recognition of high granularity activities by using accelerometer sensors. Hence, the accuracy of activity recognition systems can be increased without sacrificing efficiency. A comparative is carried out between the proposed approach and an approach based on the well-known neural networks.

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

“…However, the majority of existing solutions detect only a few activities. A major step forward would be the possibility for the system to recognize additional activities after the initial training [33,34].…”

Physical Activity Recognition From Smartphone Accelerometer Data for User Context Awareness Sensing

“…Physical activity recognition can be done in a number of ways which usually consists of a battery powered wireless sensor node, measuring accelerometer data [5]. This paper focuses on obtaining accelerometer from a smartphone, other current research has shown interest in this and it has shown promising results and successful implementation [1]- [3], [5], [6].…”

“…This paper focuses on obtaining accelerometer from a smartphone, other current research has shown interest in this and it has shown promising results and successful implementation [1]- [3], [5], [6]. Activity recognition is not a new concept and has been implemented for some time.…”

“…Most features are derived or calculated based on statistical models, therefore include values such as mean, median, max, min, standard deviation, correlation coefficients, etc. [2], [5]. Features such as correlation are very useful for differentiating activities that involve translation in only one direction from those in multiple directions [16].…”

Activity recognition with weighted frequent patterns mining in smart environments

“…Activity recognition (de la Concepción et al, 2014;Fernández-Caballero et al, 2012) has aroused a great interest in the past decade and has been addressed by many research groups using different kinds of physical devices and reasoning techniques. The great interest in activity recognition can be explained in many ways.…”