No abstract

No abstract

Wireless body sensor networks (WBSNs) enable a broad range of applications for continuous and real‐time health monitoring and medical assistance. Programming WBSN applications is a complex task especially due to the limitation of resources of typical hardware platforms and to the lack of suitable software abstractions. In this paper, SPINE (signal processing in‐node environment), a domain‐specific framework for rapid prototyping of WBSN applications, which is lightweight and flexible enough to be easily customized to fit particular application‐specific needs, is presented. The architecture of SPINE has two main components: one implemented on the node coordinating the WBSN and one on the nodes with sensors. The former is based on a Java application, which allows to configure and manage the network and implements the classification functions that are too heavy to be implemented on the sensor nodes. The latter supports sensing, computing and data transmission operations through a set of libraries, protocols and utility functions that are currently implemented for TinyOS platforms. SPINE allows evaluating different architectural choices and deciding how to distribute signal processing and classification functions over the nodes of the network. Finally, this paper describes an activity monitoring application and presents the benefits of using the SPINE framework. Copyright © 2010 John Wiley & Sons, Ltd.

Heterogeneous wireless sensor networks are a source of large amount of different information representing environmental aspects such as light, temperature, and humidity. A very important research problem related to the analysis of the sensor data is the detection of relevant anomalies. In this work, we focus on the detection of unexpected sensor data resulting either from the sensor system itself or from the environment under scrutiny. We propose a novel approach for automatic anomaly detection in heterogeneous sensor networks based on coupling edge data analysis with cloud data analysis. The former exploits a fully unsupervised artificial neural network algorithm, whereas cloud data analysis exploits the multi-parameterized edit distance algorithm. The experimental

No abstract