Method for identifying Chinese herbal medicine by using THz-TDS (terahertz-total dissolved solids) in combination with fuzzy rule expert system
An expert system and Chinese herbal medicine technology, applied in the direction of color/spectral characteristic measurement, etc., can solve the problems of large identification error, difficult identification and analysis of Chinese herbal medicine, complex and time-consuming information processing process, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0043] In this embodiment, THz-TDS combined with fuzzy rule expert system is used to identify rhubarb, wherein Savitzky-Golay (S-G) first-order derivative combined with EOSC method is used to preprocess the time-domain spectrum, which includes the following steps:
[0044] (1) 41 rhubarb samples provided by the Scientific Research Institute of Beijing Tongrentang Co., Ltd. were used to establish the model, of which 17 were authentic rhubarb and 24 were non-authentic rhubarb; the preparation methods of the 41 rhubarb samples were exactly the same, and the preparation of each rhubarb sample The steps are: (a) drying the rhubarb sample and pulverizing it into a 60-mesh powder; (b) vacuum-drying the powder again, taking a certain amount of sample and transferring it to an agate mortar for grinding to obtain a fine powder; (c ) Finally, under a pressure of 6.5t, the fine powder is made into a thin slice with a diameter of 13mm and a thickness of 0.9-1.2mm as the rhubarb sample to be...
Embodiment 2
[0082] In this embodiment, the same self-service Latin partitioning method as in Embodiment 1 is used for division, and the same fuzzy rule expert system is used to establish a qualitative analysis model, so as to use THz-TDS in conjunction with the fuzzy rule expert system to identify rhubarb. The difference is only in embodiment 1. The S-G first derivative combined with the EOSC method is used for preprocessing, and this embodiment uses the S-G first derivative combined with the PC-OSC method for preprocessing.
[0083] The PC-OSC method is generated by Harrington based on PCA, and is used to remove information irrelevant to the property matrix in the original spectral matrix, so as to achieve the purpose of spectral correction. The algorithm of the PC-OSC method is simple and easy to understand, and the calculation speed is fast. The specific algorithm of the PC-OSC method is as follows:
[0084] 1) Centralized raw data:
[0085] X 1 ...
Embodiment 3
[0101] This embodiment uses the same pretreatment method and the same qualitative analysis model as in Example 1 to identify the rhubarb by using THz-TDS in conjunction with the fuzzy rule expert system. In this example, the random method in the prior art is used to divide the rhubarb samples, and the results show that when the number of corrected main factors is 6, the maximum correct rate of identification is 93.64±0.52.
[0102] As shown in Table 3, the method of this embodiment shows the relevant data of the correct rate of identification when the number of corrected principal factors is 6.
[0103] Table 3 The results after processing by random method (the number of corrected main factors=6)
[0104]
PUM
Property | Measurement | Unit |
---|---|---|
Diameter | aaaaa | aaaaa |
Thickness | aaaaa | aaaaa |
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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