An Efficient Associated Correlated Bit Vector Matrix for Mining Behavioral Patterns from Wireless Sensor Network

摘要

Now a day’s wireless sensor network interesting research area for discovering behavioral patterns WSNs can be used for predicting the source of future events. By knowing the source of future event, we can detect the faulty nodes easily from the network. Behavioral patterns also can identify a set of temporally correlated sensors. This knowledge can be helpful to overcome the undesirable effects (e.g., missed reading) of the unreliable wireless communications. It may be also useful in resource management process by deciding which nodes can be switched safely to a sleep mode without affecting the coverage of the network. Association rule mining is the one of the most useful technique for finding behavioral patterns from wireless sensor network. Data mining techniques have recent years received a great deal of attention to extract interesting behavioral patterns from sensors data stream. One of the techniques for data mining is tree structure for mining behavioral patterns from wireless sensor network. By implementing the tree structure will face the problem of time taking for finding frequent patterns. By overcome that problem we are implementing associated correlated bit vector matrix for finding behavioral patterns of nodes in a wireless sensor network. By implementing this concept we can overcome time complexity and also get most correlated patterns of wireless sensor networks.