Complex Events are sequences of sensor measurements indicating interesting or unusual activity in the monitored process. Such events are ubiquitous in a wide range of Wireless Sensor Network (WSN) applications, yet there does not exist a common mechanism that addresses both the considerable constraints of WSNs and the specific properties of Complex Events. We argue that Complex Events cannot be described using standard threshold-based or composite logic approaches and attempting to represent them as such can lead to unpredictable execution cost while detection accuracy suffers from erroneous recording of observations which are common in WSNs. To address this, we develop a family of Complex Event Detection (CED) algorithms based on online symbolic conversion of sensor readings. With fixed execution cost and modest resource requirements, the CED algorithms cater for exact, approximate, non-parametric, multiple and probabilistic detection that is neither application nor data dependent. Overall, full implementation and simulations provide experimental evidence of the advantages of the proposed approach. We find that the proposed algorithms minimise configuration, promote