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

Time series classification method based on improved spiking neural network

A pulse neural network and time series technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as difficult access to labeled data, reduce the number of parameters, reduce complexity, and improve global search The effect of superior ability

Active Publication Date: 2019-12-31
HOHAI UNIV CHANGZHOU
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in reality, it is difficult to obtain a large amount of labeled data, and more unlabeled data

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
  • Time series classification method based on improved spiking neural network
  • Time series classification method based on improved spiking neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0099] In order to evaluate the classification effect of the improved spiking neural network on time series, the network performance is verified by using the TwoPatterns dataset in the time series classification archive of UCR (University of California, Riverside). The TwoPatterns dataset contains a total of 1000 training samples and 4000 test samples, and the length of each sample sequence is 128. The TwoPatterns dataset contains four classes of analog waveform sequences.

[0100] When converting the 1×128 time series into a two-dimensional texture image, some values ​​are properly discarded for the convenience of calculation, and a two-dimensional texture image with a size of 120×120 is obtained.

[0101] Set a downsampling layer to average the pixel values ​​of every four points of 2×2 size in the two-dimensional texture image, and convert the two-dimensional texture image with a size of 120×120 into an image with a size of 60×60 .

[0102] Set the number of input neurons...

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 time series classification method based on an improved spiking neural network. The method comprises the following steps of: intercepting a one-dimensional time sequence signal from original time sequence data, converting the one-dimensional time sequence signal into a two-dimensional texture image by using an improved recurrence plot, constructing an overall structure framework of an impulsive neural network, and reasonably zooming the two-dimensional texture image by using a down-sampling layer according to the size of the two-dimensional texture image; inputting thescaled two-dimensional texture image into an input layer of a network, and converting the two-dimensional texture image into a Poisson pulse sequence; determining the initial learning rate of the network and the maximum value and the minimum value of the boundary of the cyclic learning rate by using a cyclic learning rate method; continuously updating connection weights among neurons of the network by using a pre-synaptic and post-synaptic trace learning rule; and after network training is completed, classifying the time series by counting pulse triggering conditions of excitatory neurons.

Description

technical field [0001] The invention belongs to the field of time series signal classification and relates to a time series signal classification method based on an improved impulse neural network. Background technique [0002] Time series data is the most common data type in daily life, and it exists widely in almost every field of human cognition. With the development of intelligent equipment and Internet of Things detection technology, a large amount of time series data is collected in production and life. Time series data has the characteristics of orderliness and timeliness, which contains a large amount of intuitive information and potential knowledge. As an important branch of the time series research field, time series classification has become a hot topic in the current time series research field. It is of great practical significance to use scientific and reasonable methods to realize the rapid and accurate classification of time series. [0003] At present, art...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06F18/241Y02P90/30
Inventor 苗红霞张衡贾澜齐本胜王建鹏
Owner HOHAI UNIV CHANGZHOU
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