Wearable Computing

3Signal Processing In‐Node Environment

3.1 Introduction

The analysis of the state‐of‐the‐art on the BSN domain has highlighted that the development of BSN applications is to date a complex task also due to the lack of programming frameworks with dedicated support to the distinctive requirements of BSN systems.

To support the programming of optimized BSN applications while minimizing the development time and effort, we have designed and realized SPINE (Signal Processing In‐Node Environment) [1–3], an open‐source domain‐specific programming framework for BSNs.

SPINE aims at boosting the prototyping of BSN applications. SPINE enables efficient implementations of signal‐processing algorithms for analysis and classification of sensor data through libraries of processing functionalities. It is organized into two interacting macro‐components, which are, respectively, implemented on commercially available programmable sensor devices and on the personal coordinator (Android smartphones and tablets, or a personal computer). Communication among these devices is wireless, using Bluetooth or IEEE 802.15.4 standards. The high‐level SPINE API (at the coordinator level) allows for dynamic and flexible configuration of sensing and processing functionalities available at the sensor node level. Many biophysical sensors and signal‐processing tasks are natively implemented and available to application developers. In addition, the SPINE framework has been carefully designed to allow for very easy integration ...