Algorithm for carrying out feature extraction, classification and identification on burial area invasion vibration signals

A vibration signal and feature extraction technology, which is applied in character and pattern recognition, calculation, computer parts and other directions, can solve the problems that the recognition effect cannot meet the requirements and cannot be recognized, and achieve denoising and fine processing, and solve the modal The effect of aliasing problems

Active Publication Date: 2016-11-16
YANGTZE UNIVERSITY
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the above two methods, the recognition effect of the existing technology cannot meet the requirements, and even cannot recognize

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
  • Algorithm for carrying out feature extraction, classification and identification on burial area invasion vibration signals
  • Algorithm for carrying out feature extraction, classification and identification on burial area invasion vibration signals
  • Algorithm for carrying out feature extraction, classification and identification on burial area invasion vibration signals

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in conjunction with the accompanying drawings and embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form.

[0028] Due to the variability of mechanical properties and topography, the blasting vibration wave has random and non-repeatable characteristics that change complexly with time; through the on-site blasting waveform and related frequency spectrum measured in different environments, it is reflected that: under different conditions, the vibration waveform generated by blasting There are obvious differences: not only the vibration amplitude changes complicatedly, but also the frequency and duration of the wave show obvious differences with the characteristics of the explosion source, the center distance of the explosion, the scale of the explosion and the medium; it is a typical non-stationary signal The...

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 an algorithm for carrying out feature extraction, classification and identification on burial area invasion vibration signals. The algorithm is suitable for multi-grating sensing and detection systems, and comprises the following steps of: acquiring vibration signals through a multi-grating sensor network; carrying out decomposition by utilizing an EEMD algorithm so as to obtain an IMF component; calculating an EEMD energy entropy; eliminating interferences of un-artificial signals; carrying out feature extraction; and finally carrying out classification, identification and early warning on invasion signals by adopting a support vector machine which is optimized through a particle swarm algorithm. According to the algorithm disclosed by the invention, the alarm correctness is improved, the false alarm rate is reduced and a practical value is provided.

Description

technical field [0001] The invention relates to the fields of signal processing and pattern recognition, in particular to a feature extraction and classification recognition algorithm for mausoleum intrusion vibration signals suitable for a multi-grating sensor detection system. Background technique [0002] In recent years, driven by commercial interests, tomb robbers have committed many crimes in the ancient tomb area, resulting in the destruction of a large number of underground precious cultural relics. Tomb robbers’ equipment and methods are becoming more and more advanced. After ancient tombs are excavated, precious cultural relics will not only be lost to other places, but also the cultural and scientific value of ancient tombs will be destroyed. The losses are immeasurable. The security methods commonly used at home and abroad include infrared rays, cameras, ultrasonic waves, microwaves, etc. These methods have their inherent scope of use and thus have certain limita...

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): G06K9/00
CPCG06F2218/08G06F2218/12
Inventor 张健
Owner YANGTZE UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap