Wireless sensor networks (WSNs) are composed of large number of small, inexpensive devices, called sensor nodes, which are equipped with sensing, processing, and communication capabilities. While traditional applications of wireless sensor networks focused on periodic monitoring, the focus of more recent applications is on fast and reliable identification of out-of-ordinary situations and events. This new functionality of wireless sensor networks is known as event detection. Due to the fact that collecting all sensor data centrally to perform event detection is inefficient in many occasions, the new trend in event detection in wireless sensor networks is to perform detection in the network. Design of in-network event detection methods for wireless sensor networks is by no means straightforward, as it needs to efficiently cope with various challenges and concerns including unreliability, heterogeneity, adaptability, and resource constraints. In this thesis, we tackle this problem by proposing fast, accurate, innetwork, and intelligent event detection methods using artificial intelligence (AI) and machine learning (ML) approaches. To this end, the main objective of this thesis is to analyze, investigate applicability, and optimize artificial intelligence (AI) and machine learning (ML) methods for efficient, distributed, local and in-network event detection in wireless sensor networks (WSNs). The main contributions of the thesis can be summarized as: Feature extraction and reduction in three datasets for event detection in WSNs. We choose three datasets containing sensory data from real V Acknowledgment Give light, and the darkness will disappear of itself. Desiderius Erasmus (1466-1536) known as Erasmus of Rotterdam, Dutch Renaissance humanist, Catholic priest, social critic, teacher, and theologian.