Universal Collaboration Strategies for Signal Detection: A Sparse Learning Approach

In a conventional signal detection problem, the goal is to design a system for detecting a specific signal of interest [1]. The performance of such systems degrades if the signal evolves over time or for other known signals. Due to the advent of Big Data applications, modern detection systems are expected to perform signal detection tasks for different signal models. Hence, it is desirable to build a universal system which is flexible enough to generalize to several signal models. This paper considers a Wireless Sensor Network (WSN) consisting of a number of sensors and a FC. WSNs often operate with severe resource limitations. Consequently, minimizing the system complexity in terms of communication is critical [2]. For example, resources can be conserved if the nodes do not transmit irrelevant or redundant data. Such transmissions can be avoided through dimensionality reduction [3].