Using fuzzy logic for robust event detection in wireless sensor networks

Event detection is a central component in numerous wireless sensor network (WSN) applications. Nevertheless, the area of event description has not received enough attention. The majority of current event description and detection approaches rely on using precise values to specify event thresholds. However, we believe that crisp values cannot adequately handle the often imprecise sensor readings. In this paper we demonstrate that using fuzzy values instead of crisp ones significantly improves the accuracy of event detection. We also show that our fuzzy logic approach provides higher event detection accuracy than two well-established classification algorithms. A disadvantage of using fuzzy logic is the exponentially growing size of the fuzzy logic rule-base. As sensor nodes have limited memory, storing large rule-bases could be a challenge. To address this issue, we have developed a number of techniques that help reduce the size of the rule-base by more than 70%, while preserving the event detection accuracy.