Distributed behavior identification method based on wireless sensor network

Abstract

The invention discloses a distributed behavior identification method based on a wireless sensor network. The method comprises the following steps of firstly, collecting sampling data of sensors, computing the sampling data of the sensors through an active prediction and energy consumption balancing routing algorithm and transmitting the computed sampling data to a centralized control system; secondly performing train excavation on the computed sampling data through the centralized control system to excavate frequent behavior track modes and further generating a frequent behavior track set and a frequent behavior state set; thirdly, further excavating the generated frequent behavior set to obtain associated frequent behavior identification knowledge sets which can be stored in every sensor in a distributed mode; fourthly, storing the frequent behavior identification knowledge sets, and when a user has behaviors, completing a behavior computing process through completed identification information in a multicast message and the knowledge set stored by the corresponding sensor to perform frequent behavior identification and further to identify the behaviors of the user.

Description

technical field [0001] The invention relates to the field of intelligent control, in particular to a distributed behavior recognition method based on a wireless sensor network. Background technique [0002] There are many deficiencies in the research and implementation of behavior recognition in traditional intelligent environments, mainly including the following two points: [0003] 1. Use video monitoring data and RFID data carrying tags to identify residents or pedestrians. [0004] The technology based on video surveillance collects data through video equipment, and uses image processing technology to analyze the data to identify user activities. Because in order to achieve more detailed activity recognition, it is necessary to arrange a large number of dense information collection equipment, and due to the high cost of video surveillance equipment, it is difficult to meet this requirement due to the defects of small coverage areas, and problems such as house structure ...

AI Technical Summary

Problems solved by technology

Because in order to achieve more detailed activity recognition, it is necessary to arrange a large number of dense information collection equipment, and due to the high cost of video surveillance equipment, it is difficult to meet this requirement due to the defects of small coverage areas, and problems such as house structure and indoor light in real scenes It will affect the effectiveness of the recognition results. In addition, the research method using visual monitoring equipment is an intrusive method. Directly taking pictures of the user's life leads to insufficient privacy protection for the user. In the home environment, people do not accept video for a long time. monitoring, so user acceptance of such methods is not high

In addition, actual participants are not willing to carry special gloves that can trigger sensors or other special devices that carry tags, so the RFID sensor method based on tags is not conducive to large-scale promotion

In addition, the application of intelligent environment in life assistance requires more accurate activity recognition. However, the traditional intelligent environment based on tags and video surveillance has relatively rough recognition of activities and cannot meet the required requirements. These methods are difficult to implement. Applying scale to real-world environments

[0005] 2. The current activity detection algorithms based on wireless sensor networks are mostly centralized algorithms, using a centralized data processing method, which requires each sensor to transmit the detected data back to the central node (usually a computer). The central node performs analysis and reasoning, but the real-time performance of this centralized algorithm is not strong, it cannot solve the detection errors that may be caused by network delays, and it does not utilize the computing and storage capabilities of the sensor nodes themselves.

Images