Pub Date : 2019-08-01DOI: 10.1109/ICMIC48233.2019.9068562
Xiaotan Zhang, Wenshan Su, Lei Chen
A method of designing and controlling formation configuration based on bearing measurement information of adjacent agents is proposed, in order to solve the problem of difficulty on improving the multi-agent formation control accuracy under the condition of inaccurate positioning. According to the relationship between geometric configuration and the angle between vertices, a method is proposed to define the expected configuration of formation by using the angles between agents. On this basis, a control method is designed to converge the multi-agent formation to the desired configuration only using the bearing measurement information of the adjacent agents. A Lyapunov function is designed to prove the asymptotic stability of the formation control law. The simulation results show that the multi-agent formation can be controlled only by bearing measurement information, which verifies the effectiveness of the proposed method.
{"title":"A Multi-Agent Formation Control Method Based on Bearing Measurement","authors":"Xiaotan Zhang, Wenshan Su, Lei Chen","doi":"10.1109/ICMIC48233.2019.9068562","DOIUrl":"https://doi.org/10.1109/ICMIC48233.2019.9068562","url":null,"abstract":"A method of designing and controlling formation configuration based on bearing measurement information of adjacent agents is proposed, in order to solve the problem of difficulty on improving the multi-agent formation control accuracy under the condition of inaccurate positioning. According to the relationship between geometric configuration and the angle between vertices, a method is proposed to define the expected configuration of formation by using the angles between agents. On this basis, a control method is designed to converge the multi-agent formation to the desired configuration only using the bearing measurement information of the adjacent agents. A Lyapunov function is designed to prove the asymptotic stability of the formation control law. The simulation results show that the multi-agent formation can be controlled only by bearing measurement information, which verifies the effectiveness of the proposed method.","PeriodicalId":404646,"journal":{"name":"2019 4th International Conference on Measurement, Information and Control (ICMIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128868870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-01DOI: 10.1109/icmic48233.2019.9068529
{"title":"ICMIC 2019 Table of Contents","authors":"","doi":"10.1109/icmic48233.2019.9068529","DOIUrl":"https://doi.org/10.1109/icmic48233.2019.9068529","url":null,"abstract":"","PeriodicalId":404646,"journal":{"name":"2019 4th International Conference on Measurement, Information and Control (ICMIC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121629730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-01DOI: 10.1109/ICMIC48233.2019.9068570
Xi-zhen Zhang, Xiaoyan Sun, Chen-hong Yao, Zhihui Wang
Most vision control of the existing power-line insulator robot system needs to be realized indirectly through the remote computer. The vision system itself does not have the ability of vision control, and the level of automation is low. In order to improve the visual control ability and automation level of the power-line insulator robot, an on-line spatial control parameter acquisition algorithm for insulator is presented based on target extraction. The algorithm can be embedded in the hardware platform of visual system to automatically measure the relative distance of insulators. The results of hardware implementation show that the proposed algorithm can measure the relative distance accurately on the hardware platform of visual system. The error rate of distance measurement is basically less than 3%, which achieves the desired effect and design requirements.
{"title":"Acquisition Algorithm of Spatial Control Parameter Relative Distance for On-line Insulation","authors":"Xi-zhen Zhang, Xiaoyan Sun, Chen-hong Yao, Zhihui Wang","doi":"10.1109/ICMIC48233.2019.9068570","DOIUrl":"https://doi.org/10.1109/ICMIC48233.2019.9068570","url":null,"abstract":"Most vision control of the existing power-line insulator robot system needs to be realized indirectly through the remote computer. The vision system itself does not have the ability of vision control, and the level of automation is low. In order to improve the visual control ability and automation level of the power-line insulator robot, an on-line spatial control parameter acquisition algorithm for insulator is presented based on target extraction. The algorithm can be embedded in the hardware platform of visual system to automatically measure the relative distance of insulators. The results of hardware implementation show that the proposed algorithm can measure the relative distance accurately on the hardware platform of visual system. The error rate of distance measurement is basically less than 3%, which achieves the desired effect and design requirements.","PeriodicalId":404646,"journal":{"name":"2019 4th International Conference on Measurement, Information and Control (ICMIC)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114241571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-01DOI: 10.1109/icmic48233.2019.9068558
Kai Yu, L. Han
With the development of modern industry and the growth of population, water shortage has become a growing concern for the world. In this paper, from the influencing factors of supply and demand, the relationship between supply and demand is established to measure the ability to provide clean water in one region. And to analyze the factors that affect water scarcity specifically, Beijing is selected as the research object. The data show that the over-exploitation of groundwater is the main reason for water shortage in Beijing. Then all kinds of water resource are predicted in the following years by BP Neural Network. However, the result is not consistent with the actuals. So an improved BP neural network is proposed to reforecast, the result of this improved BP Neural Network is closer to the actuals. In addition, gray system theory is also used to predict the monotonous water quantity.
{"title":"The Forecasting of Water Resource Based on Neural Network","authors":"Kai Yu, L. Han","doi":"10.1109/icmic48233.2019.9068558","DOIUrl":"https://doi.org/10.1109/icmic48233.2019.9068558","url":null,"abstract":"With the development of modern industry and the growth of population, water shortage has become a growing concern for the world. In this paper, from the influencing factors of supply and demand, the relationship between supply and demand is established to measure the ability to provide clean water in one region. And to analyze the factors that affect water scarcity specifically, Beijing is selected as the research object. The data show that the over-exploitation of groundwater is the main reason for water shortage in Beijing. Then all kinds of water resource are predicted in the following years by BP Neural Network. However, the result is not consistent with the actuals. So an improved BP neural network is proposed to reforecast, the result of this improved BP Neural Network is closer to the actuals. In addition, gray system theory is also used to predict the monotonous water quantity.","PeriodicalId":404646,"journal":{"name":"2019 4th International Conference on Measurement, Information and Control (ICMIC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125157460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-01DOI: 10.1109/ICMIC48233.2019.9068594
W. Gao, Donglai Zhang, Enchao Zhang, Xiaolan Yan
The traction technology used for elevators in the current market has gradually changed from wire rope-type to steel strip technology. The traditional nondestructive testing of elevator wire ropes mainly involves manual observation. The steel strip is composed of both rubber and multiple wire ropes. Therefore, manual observation can only detect wear of the rubber surface or wire leakage and cannot detect internal defects in the wire ropes. The wire ropes in the steel strip are thus generally electrified to determine whether or not any of these wire ropes have broken. This approach cannot detect whether the wire ropes contain small defects. In this paper, different modes are designed for magnetostrictive guided wave sensors according to the structural characteristics of elevator steel strips. The different sensor modes are determined by comparing the detection effects of the various sensors. Finally, the magnetostrictive guided wave sensors are used to detect defects in the steel strip. The experiments show that the sensor designed in this paper can detect defects within the steel strip effectively.
{"title":"Study of Magnetostrictive Guided Wave Detection of Defects in Steel Strip for Elevator Traction","authors":"W. Gao, Donglai Zhang, Enchao Zhang, Xiaolan Yan","doi":"10.1109/ICMIC48233.2019.9068594","DOIUrl":"https://doi.org/10.1109/ICMIC48233.2019.9068594","url":null,"abstract":"The traction technology used for elevators in the current market has gradually changed from wire rope-type to steel strip technology. The traditional nondestructive testing of elevator wire ropes mainly involves manual observation. The steel strip is composed of both rubber and multiple wire ropes. Therefore, manual observation can only detect wear of the rubber surface or wire leakage and cannot detect internal defects in the wire ropes. The wire ropes in the steel strip are thus generally electrified to determine whether or not any of these wire ropes have broken. This approach cannot detect whether the wire ropes contain small defects. In this paper, different modes are designed for magnetostrictive guided wave sensors according to the structural characteristics of elevator steel strips. The different sensor modes are determined by comparing the detection effects of the various sensors. Finally, the magnetostrictive guided wave sensors are used to detect defects in the steel strip. The experiments show that the sensor designed in this paper can detect defects within the steel strip effectively.","PeriodicalId":404646,"journal":{"name":"2019 4th International Conference on Measurement, Information and Control (ICMIC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128405183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-01DOI: 10.1109/ICMIC48233.2019.9068564
Yamin Ji, Laijun Sun
A rapid classification method of potatoes based on the combination of hyperspectral imaging(HSI) technology and integrated learning algorithm was proposed in this paper. Here, potatoes were divided into six types: intact ones, green skin, germination, dry rot, wormhole and damage. Firstly, visible-near infrared (VNIR) hyperspectral imaging system with the band range of 400-1000nm was used to collect the potato hyperspectral image information in the experiment. Further, after the image masked, K-means clustering method was used to segmentate images. Extract the average spectrum of the defect areas and the intact areas as the classification data set. Based on the traditional machine learning algorithm (support vector machine, decision tree) and the integrated learning algorithm (random forest, gradient promotion decision tree), the classification model of potato defects was established and compared. The results show that among all classification algorithms, the classification accuracy of potato defects can be significantly improved by using the decision tree of gradient lifting. By comparing the feature importance of each band, the model accuracy was maintained above 80%. Furthermore, in order to improve the discrimination ability of data and reduce the dimension of data, linear discrimination analysis method was used to process spectral data, and the accuracy of the established model was finally improved to 84.62%.
{"title":"Nondestructive Classification of Potatoes Based on HSI and Clustering","authors":"Yamin Ji, Laijun Sun","doi":"10.1109/ICMIC48233.2019.9068564","DOIUrl":"https://doi.org/10.1109/ICMIC48233.2019.9068564","url":null,"abstract":"A rapid classification method of potatoes based on the combination of hyperspectral imaging(HSI) technology and integrated learning algorithm was proposed in this paper. Here, potatoes were divided into six types: intact ones, green skin, germination, dry rot, wormhole and damage. Firstly, visible-near infrared (VNIR) hyperspectral imaging system with the band range of 400-1000nm was used to collect the potato hyperspectral image information in the experiment. Further, after the image masked, K-means clustering method was used to segmentate images. Extract the average spectrum of the defect areas and the intact areas as the classification data set. Based on the traditional machine learning algorithm (support vector machine, decision tree) and the integrated learning algorithm (random forest, gradient promotion decision tree), the classification model of potato defects was established and compared. The results show that among all classification algorithms, the classification accuracy of potato defects can be significantly improved by using the decision tree of gradient lifting. By comparing the feature importance of each band, the model accuracy was maintained above 80%. Furthermore, in order to improve the discrimination ability of data and reduce the dimension of data, linear discrimination analysis method was used to process spectral data, and the accuracy of the established model was finally improved to 84.62%.","PeriodicalId":404646,"journal":{"name":"2019 4th International Conference on Measurement, Information and Control (ICMIC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123788418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-01DOI: 10.1109/ICMIC48233.2019.9068555
Jinlong Li, Laijun Sun
In the process of deep frying, oil can produce deleterious compounds which are harmful to human health. On the basis of analyzing the changing mechanisms of chemistries in repeatedly used oil, the study proposed a method for rapid detecting the frying times of oil based on near infrared spectroscopy (NIRS) technology. First derivative (D1), second derivative (D2) and standard normal variable transformation (SNV) were served as pretreatment methods, and characteristic wavelengths which sensitive to frying times were extracted by correlation coefficient (CC) method. Support vector machine (SVM), partial least squares regression (PLSR) and radial basis function neural network (RBFNN) were utilized to establish qualitative and quantitative analysis models. It turned out that the qualitative and quantitative analysis models had the best performance when D2 was used to pretreatment spectra and six characteristic wavelengths were extracted. More precisely, classification accuracy of the best SVM model reached 94%. Also, the performance of the best PLSR model was superior to the best RBFNN model, in which the values of correlation coefficient (R2), root mean square error of prediction (RMSEP), residual predictive deviation (RPD) were 0.9937, 0.3477 and 12.5803 respectively. The overall results indicated that the proposed method had a great potential to accurate detect frying times of oil.
{"title":"Study on Detection Methods for Frying Times of Soybean Oil Based on NIRS","authors":"Jinlong Li, Laijun Sun","doi":"10.1109/ICMIC48233.2019.9068555","DOIUrl":"https://doi.org/10.1109/ICMIC48233.2019.9068555","url":null,"abstract":"In the process of deep frying, oil can produce deleterious compounds which are harmful to human health. On the basis of analyzing the changing mechanisms of chemistries in repeatedly used oil, the study proposed a method for rapid detecting the frying times of oil based on near infrared spectroscopy (NIRS) technology. First derivative (D1), second derivative (D2) and standard normal variable transformation (SNV) were served as pretreatment methods, and characteristic wavelengths which sensitive to frying times were extracted by correlation coefficient (CC) method. Support vector machine (SVM), partial least squares regression (PLSR) and radial basis function neural network (RBFNN) were utilized to establish qualitative and quantitative analysis models. It turned out that the qualitative and quantitative analysis models had the best performance when D2 was used to pretreatment spectra and six characteristic wavelengths were extracted. More precisely, classification accuracy of the best SVM model reached 94%. Also, the performance of the best PLSR model was superior to the best RBFNN model, in which the values of correlation coefficient (R2), root mean square error of prediction (RMSEP), residual predictive deviation (RPD) were 0.9937, 0.3477 and 12.5803 respectively. The overall results indicated that the proposed method had a great potential to accurate detect frying times of oil.","PeriodicalId":404646,"journal":{"name":"2019 4th International Conference on Measurement, Information and Control (ICMIC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124507559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-01DOI: 10.1109/ICMIC48233.2019.9068578
Gang Liu, Sennan Zhang, Wangyang Liu, Yang Cao, Xue-feng Li
Improving audit intelligence requires computers to understand the semantics of audit information. At present, the researches on the related field of the intelligent information processing show that, the basis of intelligent information processing is the natural language understanding. This paper which combines the construction technology of corpus researches the basic methods and techniques on the construction of audit corpus. According to the text features in social security audit field, the paper proposed dual dictionary secondary forward traversal keyword extraction method which combines the specialized dictionaries obtained and general dictionaries, which is applied to text processing in social security audit, acquiring corpus of the field. The experimental results show that the proposed method can well divide, extract and discover the conceptual knowledge of field.
{"title":"A Domain-Oriented Double Dictionary Forward Traversal Method for Fine Corpus Extraction","authors":"Gang Liu, Sennan Zhang, Wangyang Liu, Yang Cao, Xue-feng Li","doi":"10.1109/ICMIC48233.2019.9068578","DOIUrl":"https://doi.org/10.1109/ICMIC48233.2019.9068578","url":null,"abstract":"Improving audit intelligence requires computers to understand the semantics of audit information. At present, the researches on the related field of the intelligent information processing show that, the basis of intelligent information processing is the natural language understanding. This paper which combines the construction technology of corpus researches the basic methods and techniques on the construction of audit corpus. According to the text features in social security audit field, the paper proposed dual dictionary secondary forward traversal keyword extraction method which combines the specialized dictionaries obtained and general dictionaries, which is applied to text processing in social security audit, acquiring corpus of the field. The experimental results show that the proposed method can well divide, extract and discover the conceptual knowledge of field.","PeriodicalId":404646,"journal":{"name":"2019 4th International Conference on Measurement, Information and Control (ICMIC)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124187900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-01DOI: 10.1109/ICMIC48233.2019.9068530
Zhiyong Ran, Laijun Sun, Jinlong Li
Aiming at the food safety problem of edible oil, this paper proposes a new method based on Near Infrared Reflectance Spectroscopy (NIRS) for rapid non-destructive testing of the frying times of frying oils. Peanut oil is used as a research object, and frozen French fries are used as a frying medium. Peanut oil is subjected to 10 experiments, and each experiment is fried 15 times in the same batch, and the samples are collected in the near-infrared original spectra at 400 nm-2500 nm. The original spectra are preprocessed and combined with the data dimensionality reduction algorithm to establish the classification model and the regression model of frying times of peanut oil, and the accuracy of the model prediction is tested. Choose the first derivative as the pretreatment method and the Linear Discriminant Analysis (LDA) algorithm is used to reduce the dimensionality of the preprocessed spectral data to establish a K-Nearest-Neighbors (KNN) classification model for peanut oil. The prediction effect of the Random Forest Regression (RFR) regression model based on the spectral data after dimensionality reduction is slightly better than that of the Partial Least Squares Regression (PLSR) regression model. The Determination Coefficient (R2), Root Means Square Error (RMSEP), and Relative Analysis Error (RPD) of the peanut oil in RFR regression models are 0.9978, 0.1823, 21.2776. Therefore, the method used in this study can effectively detect the frying times of peanut oil and provide a technical guarantee for the rapid detection of food safety.
{"title":"Rapid and Non-destructive Detecting Frying Times of Peanut Oil Based on Near Infrared Reflectance Spectroscopy","authors":"Zhiyong Ran, Laijun Sun, Jinlong Li","doi":"10.1109/ICMIC48233.2019.9068530","DOIUrl":"https://doi.org/10.1109/ICMIC48233.2019.9068530","url":null,"abstract":"Aiming at the food safety problem of edible oil, this paper proposes a new method based on Near Infrared Reflectance Spectroscopy (NIRS) for rapid non-destructive testing of the frying times of frying oils. Peanut oil is used as a research object, and frozen French fries are used as a frying medium. Peanut oil is subjected to 10 experiments, and each experiment is fried 15 times in the same batch, and the samples are collected in the near-infrared original spectra at 400 nm-2500 nm. The original spectra are preprocessed and combined with the data dimensionality reduction algorithm to establish the classification model and the regression model of frying times of peanut oil, and the accuracy of the model prediction is tested. Choose the first derivative as the pretreatment method and the Linear Discriminant Analysis (LDA) algorithm is used to reduce the dimensionality of the preprocessed spectral data to establish a K-Nearest-Neighbors (KNN) classification model for peanut oil. The prediction effect of the Random Forest Regression (RFR) regression model based on the spectral data after dimensionality reduction is slightly better than that of the Partial Least Squares Regression (PLSR) regression model. The Determination Coefficient (R2), Root Means Square Error (RMSEP), and Relative Analysis Error (RPD) of the peanut oil in RFR regression models are 0.9978, 0.1823, 21.2776. Therefore, the method used in this study can effectively detect the frying times of peanut oil and provide a technical guarantee for the rapid detection of food safety.","PeriodicalId":404646,"journal":{"name":"2019 4th International Conference on Measurement, Information and Control (ICMIC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129342048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-01DOI: 10.1109/ICMIC48233.2019.9068534
Shuang Zhou, Laijun Sun, Yamin Ji
Beet is an important sugar crop in China. The selection of beet seeds is a key link in the process of agricultural breeding. Hyperspectral technology has the advantages of fast, real-time, accurate and lossless acquisition of seed morphological characteristics, internal structural characteristics, chemical composition and other characteristic information, and has a good application prospect in seed quality testing, classification and identification. In this study, the near infrared hyperspectral image acquisition system was used to obtain the hyperspectral images of 3072 samples. The average spectrum of seed area was extracted as its characteristic spectrum. Ten characteristic wavelengths of characteristic spectrum were selected by continuous projection algorithm, and then the model was established by SVM-RBF algorithm. The model accuracy of this test device is 87.3%. The results show that high spectral imaging can predict the germination of beet seeds accurately, which provides a new idea for online nondestructive testing of beet seeds.
{"title":"Germination Prediction of Sugar Beet Seeds Based on HSI and SVM-RBF","authors":"Shuang Zhou, Laijun Sun, Yamin Ji","doi":"10.1109/ICMIC48233.2019.9068534","DOIUrl":"https://doi.org/10.1109/ICMIC48233.2019.9068534","url":null,"abstract":"Beet is an important sugar crop in China. The selection of beet seeds is a key link in the process of agricultural breeding. Hyperspectral technology has the advantages of fast, real-time, accurate and lossless acquisition of seed morphological characteristics, internal structural characteristics, chemical composition and other characteristic information, and has a good application prospect in seed quality testing, classification and identification. In this study, the near infrared hyperspectral image acquisition system was used to obtain the hyperspectral images of 3072 samples. The average spectrum of seed area was extracted as its characteristic spectrum. Ten characteristic wavelengths of characteristic spectrum were selected by continuous projection algorithm, and then the model was established by SVM-RBF algorithm. The model accuracy of this test device is 87.3%. The results show that high spectral imaging can predict the germination of beet seeds accurately, which provides a new idea for online nondestructive testing of beet seeds.","PeriodicalId":404646,"journal":{"name":"2019 4th International Conference on Measurement, Information and Control (ICMIC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125050979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：