NL2027491A - Method for rapidly identifying identities of pumpkin seeds - Google Patents
Method for rapidly identifying identities of pumpkin seeds Download PDFInfo
- Publication number
- NL2027491A NL2027491A NL2027491A NL2027491A NL2027491A NL 2027491 A NL2027491 A NL 2027491A NL 2027491 A NL2027491 A NL 2027491A NL 2027491 A NL2027491 A NL 2027491A NL 2027491 A NL2027491 A NL 2027491A
- Authority
- NL
- Netherlands
- Prior art keywords
- pumpkin
- thz
- spectroscopic
- layer
- rapidly identifying
- Prior art date
Links
- 235000020236 pumpkin seed Nutrition 0.000 title claims abstract description 28
- 241000408747 Lepomis gibbosus Species 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 26
- 235000009854 Cucurbita moschata Nutrition 0.000 claims abstract description 79
- 240000001980 Cucurbita pepo Species 0.000 claims abstract description 77
- 235000009804 Cucurbita pepo subsp pepo Nutrition 0.000 claims abstract description 77
- 235000000832 Ayote Nutrition 0.000 claims abstract description 71
- 235000015136 pumpkin Nutrition 0.000 claims abstract description 71
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 19
- 230000003595 spectral effect Effects 0.000 claims abstract description 19
- 230000006870 function Effects 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 5
- 230000007423 decrease Effects 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 239000002655 kraft paper Substances 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 claims description 3
- 230000008555 neuronal activation Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims 1
- 238000009395 breeding Methods 0.000 abstract description 3
- 230000001488 breeding effect Effects 0.000 abstract description 3
- 238000013145 classification model Methods 0.000 description 10
- 235000009852 Cucurbita pepo Nutrition 0.000 description 8
- 238000001514 detection method Methods 0.000 description 8
- 238000011176 pooling Methods 0.000 description 8
- 235000020354 squash Nutrition 0.000 description 8
- 238000012360 testing method Methods 0.000 description 8
- 241000219130 Cucurbita pepo subsp. pepo Species 0.000 description 6
- 235000009364 Cucurbita pepo var ovifera Nutrition 0.000 description 6
- 238000009402 cross-breeding Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000001328 terahertz time-domain spectroscopy Methods 0.000 description 4
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 241000219122 Cucurbita Species 0.000 description 2
- 206010024229 Leprosy Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 235000016709 nutrition Nutrition 0.000 description 2
- 208000004998 Abdominal Pain Diseases 0.000 description 1
- 206010000060 Abdominal distension Diseases 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 240000009087 Crescentia cujete Species 0.000 description 1
- 235000005983 Crescentia cujete Nutrition 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 206010062717 Increased upper airway secretion Diseases 0.000 description 1
- 241000221089 Jatropha Species 0.000 description 1
- 235000009797 Lagenaria vulgaris Nutrition 0.000 description 1
- 208000002193 Pain Diseases 0.000 description 1
- 208000030852 Parasitic disease Diseases 0.000 description 1
- 208000004880 Polyuria Diseases 0.000 description 1
- 208000025844 Prostatic disease Diseases 0.000 description 1
- 244000062793 Sorghum vulgare Species 0.000 description 1
- 229930182558 Sterol Natural products 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 244000098338 Triticum aestivum Species 0.000 description 1
- 235000001014 amino acid Nutrition 0.000 description 1
- 150000001413 amino acids Chemical class 0.000 description 1
- 239000009824 changtong Substances 0.000 description 1
- 239000003610 charcoal Substances 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000014113 dietary fatty acids Nutrition 0.000 description 1
- 230000035619 diuresis Effects 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 229930195729 fatty acid Natural products 0.000 description 1
- 239000000194 fatty acid Substances 0.000 description 1
- 150000004665 fatty acids Chemical class 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012165 high-throughput sequencing Methods 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 235000019713 millet Nutrition 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 244000045947 parasite Species 0.000 description 1
- 208000026435 phlegm Diseases 0.000 description 1
- 235000018102 proteins Nutrition 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 150000003432 sterols Chemical class 0.000 description 1
- 235000003702 sterols Nutrition 0.000 description 1
- 239000011573 trace mineral Substances 0.000 description 1
- 235000013619 trace mineral Nutrition 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
- 239000011782 vitamin Substances 0.000 description 1
- 229940088594 vitamin Drugs 0.000 description 1
- 229930003231 vitamin Natural products 0.000 description 1
- 235000013343 vitamin Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3581—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation
- G01N21/3586—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation by Terahertz time domain spectroscopy [THz-TDS]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/41—Refractivity; Phase-affecting properties, e.g. optical path length
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
- G01N2201/1296—Using chemometrical methods using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Toxicology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The present disclosure discloses a method for rapidly identifying identities of pumpkin seeds and belongs to the technical field of phenotype acquisition in crop breeding. The method includes: keeping pumpkin seeds of all varieties indoors at a constant temperature and a constant humidity; using terahertz (THZ) pulses to acquire THz image signals of pumpkin samples and deriving original THz spectroscopic time-domain transform spectral lines; where, the spectral line is denoted as X and a variety of pumpkin in the sample is denoted as Y; according to the original THz spectroscopic time-domain transform spectral line X, finding a characteristic frequency domain value corresponding to a pumpkin; extracting THz spectroscopic refractive index data corresponding to the characteristic frequency domain value of pumpkin from X, which are denoted as X1, and dividing obtained data (X1, Y) into a modeling set and a prediction set; with X1 and Y in the modeling set as input and output; respectively; building a convolutional neural network (CNN) multi-classif1cation model of pumpkin varieties and refractive indexes of corresponding THz time-domain transform spectral lines; and substituting the spectroscopic refractive index X1 of a pumpkin in the prediction set into the CNN multi-classif1cation model to obtain a corresponding variety of the pumpkin to be tested.
Description
METHOD FOR RAPIDLY IDENTIFYING IDENTITIES OF PUMPKIN SEEDS The present disclosure relates to the technical field of phenotype acquisition in crop breeding, and in particular to a method for rapidly identifying identities of pumpkin seeds.
Pumpkin is a healthy vegetable with high nutritional value, and has high development and utilization value and potential. Pumpkin itself has high nutritional and healthy values, and pumpkin seeds are also rich in fatty acids, amino acids, sterols, proteins, vitamins, and other trace elements, exhibiting the effects of lung nourishing, phlegm reducing, pain alleviating, diuresis, and the like. Pumpkin can resist oxidation, prevent and treat prostatic diseases, lower cholesterol, alleviate high blood pressure, prevent and relieve cardiovascular diseases. Moreover, an extract of pumpkin has the effect of expelling parasites and is also used in clinical treatment of abdominal pain and fullness and parasitic diseases. Therefore, pumpkin is a food with health care functions.
With the development of cross breeding, it is necessary to dig deeper into genetic information, so that huge breakthroughs have been made in the field of genetics. However, traditional methods for acquiring crop phenotypes in cross breeding cannot meet the requirements of the development of high-throughput sequencing technology. Therefore, there is a need for a high-throughput phenotype acquisition method that can achieve rapid determination of phenotypic information in pumpkin cross breeding.
Terahertz time-domain spectroscopy (THz-TDS) is a spectroscopic detection technique where medium information carried in broadband terahertz (THz) pulses is used to extract internal information of a material, which is often used in the field of nondestructive testing of materials. THz-TDS is one of the emerging spectroscopic detection techniques in detection research and has received extensive attention in the detection of crop phenotypes. Because the physiological and morphological information of a test sample is acquired in a non-contact and non-destructive manner, the phenotypic information of a crop can be obtained in real time, which provides a strong technical support for testing and screening in pumpkin cross breeding.
Chinese patent CN106841054A discloses a method for identifying seed varieties, including the following steps: acquiring P terahertz images of each sample seed in a test set at P bands; acquiring characteristic parameters for each sample seed according to the P terahertz images; inputting the characteristic parameters into a classification model to obtain a predicted variety for each sample seed; selecting a predetermined sample seed from the test set according to the predicted variety, and updating the classification model according to the predetermined sample 1 seed; and using an updated classification model to identify a variety of a sample seed in the test set.
When the above method is used to identify seed varieties, the classification model of resumes is unstable and cannot achieve the purpose of rapid identification.
The present disclosure is intended to provide a method for rapidly identifying identities of pumpkin seeds, which can realize the acquisition and rapid identification of pumpkin variety phenotype information in cross breeding.
To achieve the above purpose, the present disclosure provides a method for rapidly identifying identities of pumpkin seeds, including the following steps: 1) keeping pumpkin seeds of all varieties indoors at a constant temperature and a constant humidity; 2) using THz pulses to acquire THz image signals of pumpkin samples and deriving original THz spectroscopic time-domain transform spectral lines, where, the spectral line is denoted as X and a variety of pumpkin in the sample is denoted as Y; 3) according to the original THz spectroscopic time-domain transform spectral line X, finding a characteristic frequency domain value corresponding to a pumpkin; 4) extracting THz spectroscopic refractive index data corresponding to the characteristic frequency domain value of pumpkin in step 3) from X, which are denoted as X1, and dividing obtained data (X1, Y) into a modeling set and a prediction set in proportion; 5) with X1 and Y in the modeling set as input and output, respectively, building a convolutional neural network (CNN) multi-classification model of pumpkin varieties and refractive indexes of corresponding THz time-domain transform spectral lines; and 6) substituting the spectroscopic refractive index X1 of a pumpkin in the prediction set into the CNN multi-classification model to obtain a corresponding variety of the pumpkin to be tested.
In the above technical solution, the rapid identification of identities of pumpkin seeds is realized, which has the characteristics of simple operation, low detection cost, high-throughput acquisition, and high accuracy, and effectively overcomes the shortcomings of the traditional methods for acquiring and detecting phenotypic information in breeding, such as complex operation, high cost, and large damage to samples.
Preferably, in step 1), all pumpkin seeds may be kept in a kraft paper bag under the same external conditions, and only the variety is set as a variable.
Preferably, in step 2), the original THz spectroscopic time-domain transform spectral line may be obtained by subjecting time-domain spectroscopic information obtained by a THz 2 time-domain spectrometer and sample thickness data to Fourier transform (FT).
Preferably, in step 2), parameters of a signal acquisition system may be optimized, and optimized parameters may be as follows: 1,560 nm femtosecond laser, and 780 nm femtosecond pulse with a bandwidth of 100 fs.
Preferably, in step 5), the CNN multi-classification model may include five modules of input layer, convolutional layer, pooling layer, fully connected layer, and output layer; the convolution module may have five layers, consisting of five convolutional layers and five max-pooling layers, with convolutional kernels of 3 x 3; the number of filters may decrease sequentially from 256; the max-pooling may adopt 2 x 2; there may be three fully connected layers; the number of neural nodes may decrease sequentially from 512; during an identification process, a neuronal activation function of elu may be always used; and finally, at the output layer, a multi-classification activation function of softmax may be used to obtain an output of pumpkin variety.
Preferably, the CNN deep learning mode may explore more representative characteristic information of a pumpkin THz spectrum layer by layer through the convolutional layers and the fully connected layers; an optimization algorithm may be introduced to generate more accurate weight and bias values; and the optimization algorithm may adopt SGD learning rate: 1r0.01, momentum parameter: momentum0.9, and learning rate attenuation value for each update: 0.
In order to prevent over-fitting, preferably, Batch Normalization may be added to the convolution module to improve the generalization ability of the model, which is located after the convolutional layer and before the max-pooling.
Compared with the prior art, the present disclosure has the following beneficial effects.
(1) The method for rapidly identifying identities of pumpkin seeds according to the present disclosure realizes the rapid identification of pumpkin seed varieties, which is beneficial to the development of portable sensing instruments for pumpkin seeds in cross breeding.
(2) The present disclosure utilizes a variety identification detection method based on a THz-TDS imaging technology, which effectively overcomes the disadvantages of traditional detection methods such as complicated procedures, high cost, and large damage to samples, and shows the characteristics of simple operation, low cost, fast, efficient and accurate detection, or the like.
FIG. 1 is a schematic structural diagram of a CNN for deep learning in an example of the present disclosure.
3
To make the objectives, technical solutions, and advantages of the present disclosure clearer, the present disclosure is further described below with reference to examples and accompanying drawings.
Example In this example, a method for rapidly identifying identities of pumpkin seeds included the following steps: Step S1: Samples were collected and stored. The pumpkin seed samples used in this example were provided by the Zhejiang Academy of Agricultural Sciences. The experimental subjects included 76 genotypes of pumpkin seed samples, namely, toad pumpkin, wheat cake ornamental gourd, Torreva grandis ornamental gourd, calabash ornamental gourd, landmine pumpkin, Dongyang old variety ornamental gourd, old ornamental gourd, Chengxi pumpkin, hard pumpkin, Wenling local pumpkin, high lamp squash, millet squash, large-petal squash, long squash, round squash, broad-seed summer pumpkin, long-stalked autumn pumpkin, round pumpkin, charcoal squash, jatropha squash, brushed skin pumpkin, tower ten sisters, powdery pumpkin, local round pumpkin, local pumpkin, coastal pumpkin, Putan pumpkin, Cha Kengtu pumpkin, old pumpkin, long leprosy pumpkin, leprosy pumpkin, pear-shaped pumpkin, flat pumpkin, lump pumpkin, golden wire squash, round pumpkin, Changtong pumpkin, Mapi pumpkin, 4 kinds of pockmarked pumpkin, 2 kinds of long pumpkin, 4 kinds of indigenous pumpkins, 14 kinds of ornamental gourds, and 21 kinds of other pumpkins. The pumpkin seed were all kept in a kraft paper bag and placed in a greenhouse with a constant temperature and humidity.
Step S2: THz imaging spectrum signals of the samples were acquired. A THz instrument was adjusted to the state of projection imaging module, and nitrogen was charged into a test chamber thereof for 30 min until the signal was stable, thus avoiding the influence of moisture as much as possible. A scotch tape was first pasted on a sample holder and placed in the test room to acquire a THz signal of the tape as a background signal; then pumpkin samples were fixed on the sample holder with the scotch tape and placed in the test room; THz imaging signals were acquired; and original THz spectroscopic time-domain transform spectral lines were derived. The spectral line was denoted as X and a variety of pumpkin in the sample was denoted as Y.
Step S3: According to the original THz spectroscopic time-domain transform spectral line X, a frequency domain value of the characteristic spectral line corresponding to main characteristics of a pumpkin.
Step S4: THz spectroscopic refractive index data corresponding to the characteristic frequency domain value of pumpkin in step 3) were extracted from X, which were denoted as X1, and obtained data (X1, Y) were divided into 5,000 modeling set samples and 2,500 prediction set 4 samples in a ratio of 2:1.
Step S5: With X1 and Y in the modeling set as input and output, respectively, a CNN multi-classification model of pumpkin varieties and refractive indexes of corresponding THz time-domain transform spectral lines was built.
Step S6: The spectroscopic refractive index Xl of a pumpkin in the prediction set was substituted into the CNN multi-classification model to obtain a corresponding variety of the pumpkin to be tested.
As shown in FIG. I, in this example, the CNN multi-classification model included five modules of input layer, convolutional layer, pooling layer, fully connected layer, and output layer; the convolution module had five layers, consisting of five convolutional layers and five max-pooling layers, with convolutional kernels of 3 x 3; the number of filters decreased sequentially from 256; the max-pooling adopted 2 * 2; in order to prevent over-fitting, Batch Normalization was added to a position after the convolutional layer and before the max-pooling, thus improving the generalization ability of the model; there were three fully connected layers; the number of neural nodes decreased sequentially from 512; during an identification process, a neuronal activation function of elu was always used; and finally, at the output layer, a multi-classification activation function of softmax was used to obtain an output of pumpkin variety.
In this example, the CNN deep learning mode explored more representative characteristic information of a pumpkin THz spectrum layer by layer through the convolutional layers and the fully connected layers; an optimization algorithm was introduced to generate more accurate weight and bias values; and the optimization algorithm adopted SGD parameters: learning rate: 1r0.01, momentum=0.9, and nesterov=False. This model was built using the third-party library keras in python 3. Results showed that an actual pumpkin variety was in excellent agreement with a variety corresponding to a THz time-domain transform spectrum predicted by the CNN model, with an accuracy of the prediction set reaching 94%.
The above results indicate that the method of the present disclosure can realize the rapid identification of pumpkin seed identities and has a promising application prospect.
5
Claims (7)
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010124608.0A CN111351766A (en) | 2020-02-27 | 2020-02-27 | Method for rapidly identifying identity of pumpkin seeds |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| NL2027491A true NL2027491A (en) | 2021-09-30 |
| NL2027491B1 NL2027491B1 (en) | 2022-03-11 |
Family
ID=71192332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| NL2027491A NL2027491B1 (en) | 2020-02-27 | 2021-02-03 | Method for rapidly identifying identities of pumpkin seeds |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111351766A (en) |
| NL (1) | NL2027491B1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112488233B (en) * | 2020-12-09 | 2021-12-17 | 中国农业科学院农业资源与农业区划研究所 | Coding and identifying method and device based on fruit pattern map information |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102013021898A1 (en) * | 2013-12-24 | 2015-06-25 | Kws Saat Ag | Method of classifying seeds |
| CN106841054A (en) | 2017-01-04 | 2017-06-13 | 江南大学 | Seed variety recognition methods and device |
| CN109916838A (en) * | 2019-03-29 | 2019-06-21 | 浙江省农业科学院 | A kind of detection method of the rice seed germination ability based on high light spectrum image-forming and artificial neural network |
| CN110068544A (en) * | 2019-05-08 | 2019-07-30 | 广东工业大学 | Material identification network model training method and tera-hertz spectra substance identification |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107328735A (en) * | 2017-08-30 | 2017-11-07 | 浙江大学 | Rape species discrimination method based on terahertz light spectral technology |
| CN108051395A (en) * | 2017-11-28 | 2018-05-18 | 北京工商大学 | A kind of maize variety identification method based on THz-ATR spectral techniques |
-
2020
- 2020-02-27 CN CN202010124608.0A patent/CN111351766A/en active Pending
-
2021
- 2021-02-03 NL NL2027491A patent/NL2027491B1/en active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102013021898A1 (en) * | 2013-12-24 | 2015-06-25 | Kws Saat Ag | Method of classifying seeds |
| CN106841054A (en) | 2017-01-04 | 2017-06-13 | 江南大学 | Seed variety recognition methods and device |
| CN109916838A (en) * | 2019-03-29 | 2019-06-21 | 浙江省农业科学院 | A kind of detection method of the rice seed germination ability based on high light spectrum image-forming and artificial neural network |
| CN110068544A (en) * | 2019-05-08 | 2019-07-30 | 广东工业大学 | Material identification network model training method and tera-hertz spectra substance identification |
Non-Patent Citations (3)
| Title |
|---|
| GUA TIANTIAN ET AL: "Evaluation of wheat seeds by terahertz imaging", 2013 6TH UK, EUROPE, CHINA MILLIMETER WAVES AND THZ TECHNOLOGY WORKSHOP (UCMMT), IEEE, 9 September 2013 (2013-09-09), pages 1 - 2, XP032510392, DOI: 10.1109/UCMMT.2013.6641513 * |
| LI CHAO ET AL: "Analysis and Identification of Rice Adulteration Using Terahertz Spectroscopy and Pattern Recognition Algorithms", IEEE ACCESS, IEEE, USA, vol. 8, 31 January 2020 (2020-01-31), pages 26839 - 26850, XP011771900, DOI: 10.1109/ACCESS.2020.2970868 * |
| NIE PENGCHENG ET AL: "Classification of hybrid seeds using near-infrared hyperspectral imaging technology combined with deep learning", SENSORS AND ACTUATORS B: CHEMICAL, ELSEVIER BV, NL, vol. 296, 31 May 2019 (2019-05-31), XP085739748, ISSN: 0925-4005, [retrieved on 20190531], DOI: 10.1016/J.SNB.2019.126630 * |
Also Published As
| Publication number | Publication date |
|---|---|
| NL2027491B1 (en) | 2022-03-11 |
| CN111351766A (en) | 2020-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Hyperspectral imaging detection of decayed honey peaches based on their chlorophyll content | |
| CN108875913B (en) | Tricholoma matsutake rapid nondestructive testing system and method based on convolutional neural network | |
| CN109493287A (en) | A kind of quantitative spectra data analysis processing method based on deep learning | |
| Jie et al. | Review on the recent progress of non-destructive detection technology for internal quality of watermelon | |
| Zhou et al. | Hyperspectral imaging of beet seed germination prediction | |
| CN105868532B (en) | A kind of method and system of intelligent evaluation heart aging degree | |
| CN107271372A (en) | A kind of Apple Leaves chlorophyll remote sensing estimation method | |
| CN113011330B (en) | Electroencephalogram signal classification method based on multi-scale neural network and cavity convolution | |
| CN110082310A (en) | A kind of near infrared band EO-1 hyperion diagnostic method of rubber tree LTN content | |
| NL2027491B1 (en) | Method for rapidly identifying identities of pumpkin seeds | |
| CN108489927A (en) | Fish origin tracing method, electronic equipment, storage medium and device | |
| CN115063653A (en) | Method and system for measuring dominant chromaticness of built environment based on image brain sensitive data | |
| Jiang et al. | Quantitative analysis of aflatoxin B1 in moldy peanuts based on near-infrared spectra with two-dimensional convolutional neural network | |
| Zahid et al. | Machine learning enabled identification and real-time prediction of living plants’ stress using terahertz waves | |
| Zhang et al. | Hyperspectral imaging combined with CNN for maize variety identification | |
| Zhang et al. | Hyperspectral model based on genetic algorithm and SA-1DCNN for predicting Chinese cabbage chlorophyll content | |
| Fan et al. | Non-destructive detection of single-seed viability in maize using hyperspectral imaging technology and multi-scale 3D convolutional neural network | |
| Ning et al. | Study on apple damage detecting method based on relaxation single-wavelength laser and convolutional neural network | |
| Xiao et al. | Rapid detection of maize seed germination rate based on Gaussian process regression with selection kernel function | |
| Hu et al. | Research on rice seed fullness detection method based on terahertz imaging technology and feature extraction method | |
| CN108007917B (en) | Method for establishing Raman spectrum measurement model of nitrogen content in rice plant by Hilbert method | |
| Wang et al. | Determination of watermelon soluble solids content based on visible/near infrared spectroscopy with convolutional neural network | |
| CN105651727B (en) | The method that near-infrared spectrum analysis based on JADE and ELM differentiates apple shelf life | |
| CN109596577A (en) | The monitoring method that the construction method and wide angle of wheat powdery mildew state of illness monitoring model adapt to | |
| Zhang et al. | Research on a nondestructive model for the detection of the nitrogen content of tomato |