User behavior and action detection and recognition method

A technology of motion detection and recognition methods, applied in character and pattern recognition, input/output of user/computer interaction, instruments, etc., can solve problems such as less consideration of practicality and popularization of applications, and achieve reduction of computational complexity and classification The effect of high accuracy and reduction of equipment cost
CN106095099AActive Publication Date: 2016-11-09NANJING UNIV OF POSTS & TELECOMM
6 Cites 34 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
NANJING UNIV OF POSTS & TELECOMM
Publication Date
2016-11-09

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a user behavior and action detection and recognition method. Data acquisition of three-dimensional accelerated speeds is achieved through a three-axis acceleration sensor, original data is filtered with a wavelet transformation filtering algorithm, and reliability is improved. On the basis, a data set is effectively optimized with the principle component analysis, four different pattern recognition classification algorithms and three kinds of classification model optimizing algorithm are compared at the same time, and an optimal parameter optimization algorithm and an optimal classifier are finally obtained, so that user behaviors and actions are detected and effectively recognized, and alarming is carried out on abnormal behaviors; besides, experiment results show that the method has the advantages of being high in accuracy, low in relative calculation complexity, high in real-time performance and the like.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a user behavior detection and recognition method, which belongs to the technical field of Wireless Body Area Networks (WBAN). Background technique

[0002] The use of wearable devices to identify human activities is a current research hotspot. One or more wearable devices are used to monitor human body parts. The recognized behaviors mainly include daily activity recognition (basic actions such as standing up, walking, running or sitting down) Sports, fall monitoring in the elderly or medical conditions in infants and young children, etc. Wearable wireless sensor equipment is a new concept system based on mobile computing, which probably originated in the 1960s. Since the 1990s, with the development of science and technology, integrated circuits have developed rapidly on a large scale, which also indicates that the research on wearable devices has entered a new era. Wearable devices have a wide range of applications, and it c...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More