Energy-aware activity classification using wearable sensor networks

Abstract

This paper presents implementation details, system characterization, and the performance of a wearable sensor network that was designed for human activity analysis. Specific machine learning mechanisms are implemented for recognizing a target set of activities with both out-of-body and on-body processing arrangements. Impacts of energy consumption by the on-body sensors are analyzed in terms of activity detection accuracy for out-of-body processing. Impacts of limited processing abilities for the on-body scenario are also characterized in terms of detection accuracy, by varying the background processing load in the sensor units. Impacts of varying number of sensors in terms of activity classification accuracy are also evaluated. Through a rigorous systems study, it is shown that an efficient human activity analytics system can be designed and operated even under energy and processing constraints of tiny on-body wearable sensors.

Comparing metabolic energy expenditure estimation using wearable multi-sensor network and single accelerometer

“…In our previous work [3][15], mean and entropy have been proved to be efficient in activity recognition, since they capture both the direction and moving intensity of the limb the sensor is attached to. Using those features, we are able to different fourteen different activities namely, bicep curls, riding a bike briskly and slowly, jogging, jumping jacks, walking briskly and slowly, sweeping, squats, climbing stairs, lying down, sitting reclined, sitting straight and standing.…”

“…In our previous work [3][15], it was shown that the wearable sensor network is able to detect the 14 activities with up to 96.95% accuracy, and it was proved that more sensors can deliver higher detection accuracy. When similar mechanism is applied on ActiGraph GT3X+ sensor, the accuracy drops to 80.71%, and it showed some difficulties in differentiating between jumping jacks and walking fast, climbing stairs and riding a bike briskly, and sitting straight and standing.…”

Human Movement Monitoring and Analysis for Prehabilitation Process Management

“…In preliminary testing, 3D accelerometers were attached to the right and left wrist and ankle of two participants during walking and stationary cycling activities. These four locations were chosen as they have been used in healthy populations to detect walking and cycling activities with good accuracy [29]. This initial testing was designed to determine the effectiveness of accelerometers in each location (wrist and ankle) to differentiate walking and cycling activities at light, moderate, and vigorous intensities.…”

Metabolic energy expenditure estimation using a position-agnostic wearable sensor system

“…For example, in many previous work, sensors are placed on the hip [8][11] [12], however, it may not be convenient for women wearing some types of clothes while wearing a sensor on the hip. Similarly, sensors on the wrist [15] are not suitable for formal occasions for both men and women. In this paper, we present a sensor position-agnostic energy expenditure estimation scheme, in which a sensor can be attached in any of a number of predefined locations on the body.…”