Unlock instant, AI-driven research and patent intelligence for your innovation.

A hybrid k-harmonic clustering method for near-infrared spectroscopy classification of apple varieties

A technology of near-infrared spectroscopy and classification methods, applied in the field of apple variety classification based on hybrid K-harmonic clustering method and near-infrared spectroscopy technology, can solve the problems of low classification accuracy and difficulty in realizing correct fruit classification, and achieve high accuracy , Fast detection speed and high efficiency

Inactive Publication Date: 2016-04-06
JIANGSU UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When there are no learning samples, or when the learning samples are relatively small, using the above method for fruit classification will result in low classification accuracy and it is difficult to achieve the correct classification of fruits

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
  • A hybrid k-harmonic clustering method for near-infrared spectroscopy classification of apple varieties
  • A hybrid k-harmonic clustering method for near-infrared spectroscopy classification of apple varieties
  • A hybrid k-harmonic clustering method for near-infrared spectroscopy classification of apple varieties

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] Step 1: Take three kinds of apple samples: Red Fuji, Huaniu, and Ghana, 50 samples of each apple. The apple samples were stored in the laboratory at a temperature of 20-25°C for 12 hours, and the Antaris II near-infrared spectrum analyzer was turned on and preheated for 1 hour. The near-infrared spectrum of apples was collected in reflection integrating sphere mode, and the near-infrared spectrum analyzer scanned each sample 32 times to obtain the average diffuse reflectance spectrum of the sample. The wavenumber of spectral scanning is 10000~4000cm-1, and the scanning interval is 3.856cm-1. The collected spectrum of each sample is 1557-dimensional data. In order to reduce the error, each apple sample was sampled three times along the equatorial trajectory, and the average value was taken as the final experimental data. Near-infrared spectra of 150 apple samples such as figure 2 shown.

[0038] Step 2: Dimensionality reduction processing of the near-infrared spectru...

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

A disclosed apple cultivar near-infrared-spectrum sorting method based on hybrid K-harmonic means clustering comprises the following steps: (1) performing near infrared spectroscopy acquisition on apple samples; (2) performing dimension reduction processing on the near infrared spectroscopy of the apple samples; and (3) employing a hybrid K-harmonic means clustering method to sort apple cultivar. The method has the advantages of rapid detection speed, high sorting accuracy rate, high sorting efficiency, no damage to apples and the like, and is capable of realizing correct sorting of apple cultivar.

Description

technical field [0001] The invention relates to a method for classifying apple varieties, in particular to a method for classifying apple varieties based on a mixed K-harmonic clustering method and near-infrared spectrum technology. Background technique [0002] Apple is one of the fruits that people often eat. Apple fruit contains some components related to health and senses, including simple sugars, minerals, dietary fiber and various living substances, such as vitamin C and phenolic compounds. Different varieties of apples have different internal sugar content, acidity and soluble solids. That is, different varieties of apples have different internal qualities. Therefore, it is an important task for agricultural science and technology personnel to select good varieties of apples. [0003] Near-infrared spectroscopy is a non-destructive detection technique that uses the properties of light absorption, scattering, reflection, and transmission of substances to determine t...

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 Patents(China)
IPC IPC(8): G01N21/3563G01N21/359
Inventor 武小红武斌孙俊李敏
Owner JIANGSU UNIV