On the Challenges and Potential of Using Barometric Sensors to Track Human Activity

Abstract

Barometers are among the oldest engineered sensors. Historically, they have been primarily used either as environmental sensors to measure the atmospheric pressure for weather forecasts or as altimeters for aircrafts. With the advent of microelectromechanical system (MEMS)-based barometers and their systematic embedding in smartphones and wearable devices, a vast breadth of new applications for the use of barometers has emerged. For instance, it is now possible to use barometers in conjunction with other sensors to track and identify a wide range of human activity classes. However, the effectiveness of barometers in the growing field of human activity recognition critically hinges on our understanding of the numerous factors affecting the atmospheric pressure, as well as on the properties of the sensor itself—sensitivity, accuracy, variability, etc. This review article thoroughly details all these factors and presents a comprehensive report of the numerous studies dealing with one or more of these factors in the particular framework of human activity tracking and recognition. In addition, we specifically collected some experimental data to illustrate the effects of these factors, which we observed to be in good agreement with the findings in the literature. We conclude this review with some suggestions on some possible future uses of barometric sensors for the specific purpose of tracking human activities.

Human Action Recognition: A Paradigm of Best Deep Learning Features Selection and Serial Based Extended Fusion

“…Several researchers of computer vision developed techniques using machine learning [ 28 ] for HAR. Most of these researches focused on deep learning due to its better performance and few of them used barometric sensors for activity recognition [ 29 ]. Rasel et al [ 30 ] extracted the spatial features using acidometer sensors and classified using multiclass SVM for final activity recognition.…”

On the Feasibility of Localising Smart Devices using Air Pressure

“…Barometers have been used to track a variety of human activity including augmenting GPS accuracy with altitude information, determining changes of floor within buildings and even detecting sudden altitude changes associated with falls [1]. While we have not seen information on localising humans with barometer measurements, people have proposed using pressure measurements to localise vehicles moving on roads, where the elevation changes of the roads have been mapped in advance [2], [3].…”

“…Each hour contains 258,681 data points at varying latitudes and longitudes. Data was extracted using ecCodes GRIB tools 1 .…”

“…At this scale, we can see the individual points are visible, including points on islands. There are small discrepancies between the major 1 Available from https://confluence.ecmwf.int/display/ECC/ecCodes+Home. 2 Available from https://data.gov.ie/dataset/census-2011-boundary-files.…”

“…For example, the iPhone 6 and 7 are rumoured to use a custom Bosch BMP280 sensor. The data sheet for this sensor reports that it can measure pressure ranges from 3,000-11,000Pa, with a relative accuracy of 12Pa and an absolute accuracy of 100Pa [12], however, this seems quite pessimistic compared with some reports [1]. The RMS noise is given as 1.3Pa and the resolution 0.16Pa in the data sheet.…”