Sensory substance classification method based on olfaction brain waves and PSO-SVM (particle swarm optimization support vector machine)

A PSO-SVM and classification method technology, applied in the field of sensory substance classification based on olfactory brain waves and PSO-SVM, can solve problems such as poor repeatability, doping with subjective factors, and inability to fully reflect the real feeling of the human body, and achieve sensory evaluation process Conciseness, rigor and scientificity, and the effect of reducing costs

Inactive Publication Date: 2018-08-21
NORTHEAST DIANLI UNIVERSITY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the development of science and technology, more and more precision instruments for analyzing flavor substances have emerged as the times require, but relying on instrumental analysis alone cannot fully reflect the real feeling of the human body, so the sensory evaluation of the human body still occupies an important position
In the process of sensory evaluation, personnel are required to personally participate in the use of sensory organs such as vision, smell, and taste. They are easily disturbed by daily habits and eating conditions. The sensory evaluation results given are mixed with personal Subjective factors, so it has a certain degree of subjectivity and poor repeatability

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
  • Sensory substance classification method based on olfaction brain waves and PSO-SVM (particle swarm optimization support vector machine)
  • Sensory substance classification method based on olfaction brain waves and PSO-SVM (particle swarm optimization support vector machine)
  • Sensory substance classification method based on olfaction brain waves and PSO-SVM (particle swarm optimization support vector machine)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0021] Materials and methods: 3 different brands of beer (Tsingtao, Cordon Bleu, Harbin) were selected, and their alcohol concentrations and raw materials are shown in Table 1 below:

[0022] Table 1 Samples of 3 different brands of beer

[0023]

[0024] In terms of olfactory EEG signal analysis, the EEG signals used are self-collected data in the laboratory. After the original EEG signals are collected, EEG preprocessing is performed first (including deleting bad areas, filtering out 50Hz power frequency interference, and superimposing data. average, wavelet transform, etc.); then perform linear analysis and nonlinear analysis on it, and use the peak value, mean value, standard deviation, center value, center frequency, power sum, and spectral entropy obtained by sub-frequency bands as eigenvalues; considering the collected The electrode contains different regions, so the electrode screening is carried out; finally, the selected feature value is sent to the corresponding ...

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 sensory substance classification method based on olfaction brain waves and a PSO-SVM (particle swarm optimization support vector machine). The method comprises the followingsteps: S1, obtaining electroencephalogram information of an examinee by using a brain-computer interface system, namely an electroencephalograph; S2, pre-processing the acquired electroencephalogram data; S3, extracting characteristics of the pre-processed electroencephalogram data based on linear characteristic and nonlinear characteristic analysis, wherein the characteristics comprise 76-dimensional data such as peak, mean, standard deviation, central value, center frequency, power and spectral entropy of alpha, beta and theta bands, as electroencephalogram characteristics in electroencephalogram research; S4, performing pattern recognition by using a PSO-SVM method. The sensory substance classification method disclosed by the invention is suitable for sensory evaluation of substances, and the sensory evaluation process is more concise, and more standardized, rigorous and scientific.

Description

technical field [0001] The invention relates to the technical field of sensory substance classification, in particular to a sensory substance classification method based on olfactory brain waves and PSO-SVM. Background technique [0002] Sensory evaluation is an interdisciplinary subject that is gradually developed and matured by modern physiology, psychology, statistics and other disciplines. In the entire evaluation system, sensory professionals are involved in the development of new products, basic research, adjustment of ingredients and processes, It plays a decisive role in the evaluation of cost reduction, quality assurance and product optimization. With the development of science and technology, more and more precision instruments for analyzing flavor substances have emerged as the times require. However, only relying on instrumental analysis cannot fully reflect the real feeling of the human body, so the sensory evaluation of the human body still occupies an importan...

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
IPC IPC(8): A61B5/0484G06K9/62G06K9/00
CPCA61B5/4011A61B5/4076A61B5/7203A61B5/7267A61B5/381G06F2218/04G06F2218/08G06F2218/12G06F18/2411
Inventor 门洪巩芙榕焦雅楠石岩刘晶晶房海瑞韩晓菊姜文娟
Owner NORTHEAST DIANLI 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