Toward sensor-based context aware systems.

Yoshitaka Sakurai,Paolo Ceravolo,Kouhei Takada,Ernesto Damiani,Valerio Bellandi,Setsuo Tsuruta,Marco Anisetti

doi:10.3390/s120100632

Yoshitaka Sakurai, Paolo Ceravolo + Show 5 more

Open Access

https://doi.org/10.3390/s120100632

Copy DOI

Abstract

This paper proposes a methodology for sensor data interpretation that can combine sensor outputs with contexts represented as sets of annotated business rules. Sensor readings are interpreted to generate events labeled with the appropriate type and level of uncertainty. Then, the appropriate context is selected. Reconciliation of different uncertainty types is achieved by a simple technique that moves uncertainty from events to business rules by generating combs of standard Boolean predicates. Finally, context rules are evaluated together with the events to take a decision. The feasibility of our idea is demonstrated via a case study where a context-reasoning engine has been connected to simulated heartbeat sensors using prerecorded experimental data. We use sensor outputs to identify the proper context of operation of a system and trigger decision-making based on context information.

Highlights

Context-aware systems have the ability of adapting their behavior to their current operational context
We developed a parser that receives context representations from our Semantics of Business Vocabulary and Business Rules (SBVR) editor and compiles FNL rules into a flat XML encoding of First-Order-Logics (FOL) that can be used for reasoning
We have described a novel approach to context modeling based on an expressive context definition language based on SBVR, showing how it can be interfaced with sensors by generating events from the interpretation of sensor readings

Summary

Introduction

Context-aware systems have the ability of adapting their behavior to their current operational context. Context changes are often triggered by events generated by sensors, like changes in location, Sensors 2012, 12 time and communication involving people other than the user. Integration between sensors and context-based systems is being fostered by rapid evolution of technology; terminal devices like smart phones are equipped with multiple sensors, such as video cameras or audio/video equipment, capable of collecting information from the environment. The behavior of a software system may depend on where the user is located when a certain event takes place, where is she headed, or even whether is she sitting at her desk alone or walking accompanied by others. A major problem in context-based systems is making sure that computers interpret sensor data correctly. Uncertainty in interpretation cannot be tackled by increasing sensor accuracy

Objectives

Methods

Findings

Conclusion