Research And Design Of Indoor Localization Algorithm For Wireless Sensor Networks Based On Elman Neural Network And RSSI Optimization

With the rapid development of information and computer technology, the focus of people's attention is gradually transferred from the virtual computer network to the ‘real network'. As an important part of the new generation of information technology, however, the Internet of things still can not meet all the needs. Thus a distributed, composed of dozens, hundreds, or even thousands of tiny nodes of the sensor network, people use it to real-time monitoring and check in a region of the actual situation, and in order to control and issued a directive, which is wireless sensor network.Wireless sensor networks merge multiple fields of cutting-edge technologies, including embedded, network systems, sensors, and micro control, etc..With the rapid development of the technology, wireless sensor networks have been widely used in the fields of transportation, military, environmental monitoring, health and family life.Due to the wide application of wireless sensor networks, the physical information and state information which is transmitted through the wireless sensor networks are also very important. However, no matter what kind of system, the most worthy of attention should be physical information and state information in where, from where. Therefore, the positioning system based on wireless sensor network is more worth to study, especially in the complex environment of the room, but also need to be quickly grasp the location of the occurrence of things. With the development and application of neural network algorithm, the wireless sensor network positioning system based on neural network will become the core technology and key technology.This paper from the theory of related technology of wireless sensor network, neural network theory and Zig Bee, using the Zig Bee experimental platform. For data collection and Research on the positioning algorithm. Analysis the difference between indoor and outdoor positioning, then proposed algorithm for Elman neural network model is applied to indoor positioning, and the Elman neural network positioning model and simulation. At the same time, in the research of Elman neural network and indoor positioning, it is found that RSSI is worth collecting and optimizing is the key to realize the location. Therefore, in order to achieve a more accurate and effective positioning as the goal, this paper proposes to optimize and modify the data of the collected positioning information before positioning. The indoor location algorithm can be widely used in the system of information collection and monitoring.