Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Motion recognition method based on keyboard input perception

A technology for keyboard input and activity recognition, applied in the field of activity recognition, can solve problems such as poor practicability, and achieve the effect of good practicability and good generalization ability

Active Publication Date: 2017-06-20
NORTHWESTERN POLYTECHNICAL UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortcomings of poor practicability of the existing activity recognition methods, the present invention provides an activity recognition method based on keyboard input perception

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Motion recognition method based on keyboard input perception
  • Motion recognition method based on keyboard input perception
  • Motion recognition method based on keyboard input perception

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] refer to figure 1 . The specific steps of the activity recognition method based on keyboard input perception of the present invention are as follows:

[0032] Step 1. Keep the keyboard and the mobile phone at a relatively unchanged position, then turn on the microphone of the mobile phone, record the audio of keystrokes on the keyboard, and record the corresponding real value s(t).

[0033] Step 2: Wiener filter processing is performed on the collected audio signal to reduce the interference of noise to subsequent algorithms. The audio signal s(t) collected in step 1 is filtered by Wiener filter g(t), then the filtered audio signal is x(t)=g(t)*(s(t)+n( t)).

[0034] Step 3. Based on the filtered audio signal, the audio signal x(t) is first divided into a single key signal by using a double-threshold endpoint detection algorithm, and then the single key signal is subjected to frequency domain conversion, and the obtained 0-8KHz range spectrum sequence is normalized ...

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

PUM

No PUM Login to View More

Abstract

The invention discloses a motion recognition method based on keyboard input perception, and the method is used for solving a technical problem that a conventional motion recognition method is poor in practicality. According to the technical scheme of the invention, the method comprises the steps: sampling an audio signal generated during keyboard input, and then carrying out the filtering of the collected audio signal and segmenting a single-key signal through employing a double-threshold end point detection algorithm; recovering an input sequence text of a user from the audio signal based on the frequency domain features of the single-key signal through employing an SVM algorithm; combining the text sequence and the audio signal, respectively extracting the features of the audio signal and the semantic related features, segmenting the text sequence into pieces through a sliding window based on the characteristic difference, taking the pieces as the units through employing an AdaBoost algorithm based on C4.5, and recognizing the different man-machine behavior activities of a user. The method employs the sliding window for the segmentation of the text sequence into pieces, is combined with the AdaBoost algorithm based on C4.5 for activity recognition, is strong in generalization ability, and is good in practicality.

Description

technical field [0001] The invention relates to an activity recognition method, in particular to an activity recognition method based on keyboard input perception. Background technique [0002] The document "Ward J A, Lukowicz P, Troster G, et al.Activity recognition of assembly tasks using body-worn microphones and accelerators[J].IEEE transactions on pattern analysis and machine intelligence, 2006,28(10):1553-1567" gives A user activity recognition method based on microphone and wearable accelerometer device is proposed. The application scenario of this method lies in the classification of manual task activities engaged in maintenance and assembly in the workshop, in which the movement characteristics of the hands and the characteristics of the audio signals generated during the movement of the hands are mainly used. First, two Analysis of different audio signals detected by microphones to segment potentially active segments from continuous data streams. Then, the linear...

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

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/04G10L15/06G10L25/87
Inventor 於志文肖栋郭斌王柱
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com