Energy-Efficient Integration of Continuous Context Sensing and Prediction into Smartwatches

Abstract

As the availability and use of wearables increases, they are becoming a promising platform for context sensing and context analysis. Smartwatches are a particularly interesting platform for this purpose, as they offer salient advantages, such as their proximity to the human body. However, they also have limitations associated with their small form factor, such as processing power and battery life, which makes it difficult to simply transfer smartphone-based context sensing and prediction models to smartwatches. In this paper, we introduce an energy-efficient, generic, integrated framework for continuous context sensing and prediction on smartwatches. Our work extends previous approaches for context sensing and prediction on wrist-mounted wearables that perform predictive analytics outside the device. We offer a generic sensing module and a novel energy-efficient, on-device prediction module that is based on a semantic abstraction approach to convert sensor data into meaningful information objects, similar to human perception of a behavior. Through six evaluations, we analyze the energy efficiency of our framework modules, identify the optimal file structure for data access and demonstrate an increase in accuracy of prediction through our semantic abstraction method. The proposed framework is hardware independent and can serve as a reference model for implementing context sensing and prediction on small wearable devices beyond smartwatches, such as body-mounted cameras.

Quantifying Sources and Types of Smartwatch Usage Sessions

“…Our smartwatch dataset was collected in-the-wild with an application available on Google Play Store called Insight 4 Wear 1 , introduced in [28]. The user accepts the provided enduser license agreement to allow the application to store the information locally and periodically (every three hours), check for Wi-Fi connectivity, and upload the logged data to the server.…”

Lesson Learned from Collecting Quantified Self Information via Mobile and Wearable Devices

“…Therefore we have created and used the simple smartwatch app that has been described previously. Findings of this study have been used to create a resource efficient smartwatch framework for contextual data collection [20].…”

“…(iii) There is a lack of multivariate reflection methods to analyze the collected daily life information, e.g., visualizing incoming calls based on the location and time of the day. Privacy issues [18] and battery limitations [19,20] are important but known issues, and thus we do not list them as our novel findings. Nevertheless, we have tackled them from another perspective, which is worth further explanation.…”

A natural language query interface for searching personal information on smartwatches

“…Moreover, all of these works have a translation component from end users' questions to machine languages, such as SQL or SPARQL. However, small devices, such as smartwatches, have limited resources [12]. Therefore, a light resource-efficient customized query module is favored over SQL, SPARQL or any other resource intensive query engines, which is not trivial to implement on small devices.…”