Browse by section

Content of AGRICULTURE INFORMATION TECHNOLOGY in our journal

Published in last 1 year |

In last 2 years |

In last 3 years |

All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Crop Roots Configuration and Visualization: A Review WEN Wei-liang, GUO Xin-yu, ZHAO Chun-jiang, WANG Chuan-yu, XIAO Bo-xiang Scientia Agricultura Sinica    DOI: 10.3864/j.issn.0578-1752.2015.03.04

Select

The Agricultural Price Information Acquisition Method Based on Speech Recognition XU Jin-pu, ZHU Ye-ping Scientia Agricultura Sinica    2015, 48 (3): 449-459.   DOI: 10.3864/j.issn.0578-1752.2015.03.05 Abstract （356）   HTML （6）    PDF （453KB）（739）       Knowledge map    Save 【Objective】In this research, speech recognition technology was applied to collect agricultural price information. The aim of the research is to recognize the continuous speech which is limited in vocabulary and uttered by independent Chinese mandarin speakers, and to propose a robust speech recognition method suitable for the environment where agricultural product prices are collected. On the basis of Hidden Markov Model (HMM), we train the acoustic models for this environment, so as to relieve the decrease of recognition rate caused by the mismatching between the test environment and the training environment, and to make further improvement of the recognition rate. 【Method】 In the stage of acquiring and processing data, we first built the transformation grammar according to certain rules to recognize the limited vocabulary, and this grammar will be used to guide the recording of both train data and test data. Then we select different environments to collect agricultural product prices by different speakers. On this basis, we built a speech corpus in which speech data are artificially segmented with accuracy. In the stage of training model, we choose the continuous mixed density Hidden Markov Model with left-to-rigt and non-jump structure, and extract 39 demension MFCC feature vector from training dataset to train the HMMs. Firstly, we select monophones as the recognition unit to train male HMMs, female HMMs, and male-female mixed HMMs. Taking it into consideration that the monophones are poor in stability and vulnerable to coarticulation, we select context-dependent triphone as the decoding unit to retrain above HMMs. Since the number of triphones models will increase significantly when the triphones are chosen as modeling unit, we use the decision tree clustering to solve the insufficiency of training samples. In the process of building a decision tree, we divide all the finals and initials into different sets by using the phonetic knowledge. For the identification of initials, we appeal to their pronunciation way and place, and for the finals, we resort to their constitution and head vowels. In this way we realize the design of binary value questions. On this basis, we increase Gaussian mixture components to make the model more accurately described. Besides, in order to solve the problem of convolution noise in the communication channel, we adopt the CMN and CVN methods to alleviate the mismatching problem between test environment and training environment. Finally, the male and female HMMs are obtained respectively by training. In the stage of test, for the different models employing different methods mentioned above, we do the test experiments with the same test dataset respectively and obtain the sentence recognition rate, word recognition rate, and accuracy of every different method. 【Result】 The results show that recognition performance of triphone models are superior to monophone models. Both male and female HMMs perform better than the male and female mixed acoustic models. Though decision tree clustering method cannot promote recognition rate significantly, it can reduce the quantity of triphone models evidently. Gaussian mixture components improve the recognition rate on the one hand, but they bring a certain amount of increase in calculation on the other. CMN and CVN methods can significantly improve the performance of identification system. Through the different locations and different speaker test, the methods we have used demonstrated varying degrees improvement in the recognition performance. The ultimate recognition rate was 95.04% for males, and 97.62% for females.【Conclusion】It is feasible to apply speech recognition technology to the collection of agricultural product price information. In this paper, we proposed a method to improve the recognition rate in agricultural product price information acquisition. The experiment results show that the models trained by these methods have a good recognition performance. Furthermore, the approach adopted by our research lays a foundation for the development of the application system in the future. Reference | Related Articles | Metrics Cited: Baidu(2)

Select

Platform Construction of Vegetable Safety Warning and Traceability Based on Modern Information Technology DIAO Hai-ting, NIE Yi-min Scientia Agricultura Sinica    2015, 48 (3): 460-468.   DOI: 10.3864/j.issn.0578-1752.2015.03.06 Abstract （468）   HTML （9）    PDF （1326KB）（787）       Knowledge map    Save 【Objective】 A study was made for the purpose of warning and tracing the quality safety of vegetables from production to sale by modern information technology.【Method】In this study of vegetables from Shouguang City, the national production and demonstration base of vegetables, the authors mainly addressed the gathering of information on vegetable quality, safety supervision and traceability management in that city, by means of the WebGIS, the Internet of things, bar code identification, and database technology. In this research, the vegetable logistics data acquisition and storage were studied, and the platform construction of the system of vegetable safety warning and traceability was explored.【Result】The authors used the networking data acquisition technology, established a set of attribute database using SQLServer2008 database consisting of data of vegetable production, processing, transport and sale. A set of vegetables safe spatial data were produced by means of GIS, which includes the Shandong road map, Shouguang sampling map, and Shouguang soil nutrient map. On that basis, a set of effective vegetable safety warning and traceability platform was established. The platform consists of a variety of information technology, with consideration of the business needs of the vegetable safe production of Shouguang City. The whole platform is divided into four modules: data query, vegetable quality safety warning, vegetable quality safety traceability, and auxiliary tool. The platform is designed for the following: the vegetable information inputting and editing, vegetable information query, warning traceability, vegetable information stereoscopic display, the best path analysis, vegetable soil nutrient statistics, vegetable soil nutrient interpolation, etc. The real-time early warning system can transmit the information of coordination, temperature, humidity and time to the server with network real-time data acquisition. The platform can also monitor and forecast vegetables temperature, humidity, shelf life, to ensure the quality and safety of vegetables. As for the function of vegetable quality safety traceability, the authors trace the path of logistics and distribution on the map according to the vegetable bar codes and logistics coordinate. To fulfill the path analysis function, one can design the path for the optimum according to the transport of vegetables and destination. The function of vegetables spatial information display can be achieved by means of the vertical surface of stereoscopic display from the soil to the ground and the atmosphere, namely, the integration of three-dimensional space and different times. 【Conclusion】This study demonstrates the process from vegetable production to sale using the GIS technology. The system under discussion is of great help to improve vegetable quality and safety management. To some degree, the system has been proved effective for the government departments concerned for the sake of supervision of vegetable safety. Reference | Related Articles | Metrics Cited: Baidu(4)

Select

Isolation of a Maize Wound-Induced Gene Promoter and Characterization of the Gene Expression in Maize LIAN Yun-1, 2 , LIU Yun-Jun-1, WANG Guo-Ying-1 Scientia Agricultura Sinica    2014, 47 (14): 2889-2896.   DOI: 10.3864/j.issn.0578-1752.2014.14.019 Abstract （371）   HTML （3）    PDF （590KB）（633）       Knowledge map    Save 【Objective】 Protease inhibitor is an important defense protein in plant for resistance to infection or feeding by pathogen and animals. Maize Wip1(wound-induced protein) is the member of Bowman-Birk inhibitor(BBI) gene family. To provide new information for the application of resistance gene to insect in plant, this experiment was designated to understand the activity of Wip1 promoter, assay spatial and temporal expression of Wip1 gene and its response to phytohormones and abiotic stresses.【Method】A clone containing the upstream region of Wip1 was isolated and sequenced from maize leaf cDNA. The promoter sequences of Wip1 gene was inserted into binary expression vector p1300 to produce recombinant plasmids p1300-Wip1-GUS, which was transferred into Agrobacterium LBA4404 by freeze thawing method. Functional analysis of the promoter was conducted through heterologous expression in maize callus by agro-infiltration method. Total RNA was isolated from maize tissues using hot phenol method. Purified RNA was subjected to formaldehyde-containing-agarose gel, blotted onto a nylon membrane, and Northern blotting was performed with [α-32P] dCTP-labeled probe to characterized tissue-speci?c location, phytohormones and abiotic stresses analysis of Wip1. 【Result】 Promoter region was 1 737 bp and coding sequence was 512 bp. The result showed that GUS activity driven by the Wip1 promoter was detected in maize callus tissues after infection by Agrobacterium haboring recombinant plasmids p1300-Wip1-GUS. The expression of Wip1 was assayed at various developmental stages. Northern blotting showed that Wip1 gene abundantly expressed in injured coleoptile, root, stem, leaf, ear, tassel, silk and husk, while expressed little in uninjured coleoptile and not expressed in other uninjured detection tissues. The results also showed that Wip1 was not affected by submergence, cold, dehydration, PEG, ABA, NaCl and IAA treatments. The dynamic expression of Wip1 gene under injure stress from 0 h to 24 h with 8 time points, was analyzed in maize leaf tissue. Wip1 gene was detected after stressing for 2 h, the expression level increased rapidly, and with a continually increasing trend from 4 h to 24 h. 【Conclusion】 Wip1 gene is induced by injure-specific stress. Wip1 promoter is an effective injure-specific promoter to express the desired genes in plants. Reference | Related Articles | Metrics Cited: Baidu(1)

Select

The Molecular Identification of Transgenic Hpa110-42 Wheat and Resistance Evaluation on Fusarium Head Blight YANG Min, QIN Bao-Ping, LIU Chang-Lai, CAI Hong-Sheng, WANG Zhen-Lin, LIANG Yuan-Cun, YIN Yan-Ping Scientia Agricultura Sinica    2013, 46 (4): 657-667.   DOI: 10.3864/j.issn.0578-1752.2013.04.001 Abstract （552）      PDF （614KB）（599）       Knowledge map    Save 【Objective】This study aims to screen Fusarium head blight (FHB) resistance plants in Hpa110-42 transgenic wheat plants and provide materials for FHB resistance breeding of wheat.【Method】T2 transgenic wheat plants were identified by PCR, Southern blot and RT-PCR, assuring whether the foreign Hpa110-42 gene was integrated and expressed in transgenic wheat plants. The resistance to FHB of transgenic wheat plants was evaluated by a dripping method to single flower, and its resistance physiology was studied.【Result】PCR, Southern blotting and RT-PCR analyses have confirmed successful integration of the foreign Hpa110-42 gene into the genome of the Yangmai 158 with 1 to 3 copies and stable inheritance and expression. Disease bioassays of transgenic plants revealed that the average percentage of diseased spikelets of transgenic lines T2-17, T2-15, T2-68, T2-44 and T2-36 were highly significantly lower than YM158. Compared with Sumai 3, the average percentage of diseased spikelets of all transgenic lines was highly significantly higher than Sumai 3 excepting line T2-17. In the transgenic lines, the average percentage of diseased spikelets of line T2-17 was significantly lower than other lines, in which T2-36, T2-11 and T2-20 have reached highly significant difference level. It is showed by physiological analysis that the activities of PAL, chitinase and β-1,3-glucanase in the high resistance transgenic plants increased faster than Yangmai 158 after inoculation. The soluble protein content in all plants had a downward trend, while its content in high resistance plants is consistently higher than others. Moreover, β-1,3-glucanase activity and soluble protein content were negatively correlated with resistance grade of FHB. 【Conclusion】 The foreign Hpa110-42 gene was stably inherited, normally expressed and positively participated in the regulation of FHB resistance, and Hpa110-42 transgenic wheat plants with resistance to FHB were obtained. Reference | Related Articles | Metrics

Select

The Effect of Different Nitrogen Concentrations on Fennel Plant Growth, Essential Oil Contents and Components (Foeniculum vulgare Mill.) HE Jin-Ming, XIAO Yan-Hui, WANG Yu-Mei, PAN Chun-Xiang Scientia Agricultura Sinica    2012, 45 (20): 4224-4232.   DOI: 10.3864/j.issn.0578-1752.2012.20.012 Abstract （748）      PDF （340KB）（630）       Knowledge map    Save 【Objective】 The objective of this study was to reveal the response characteristics and the internal correlation of plant growth and essential oil accumulation to nitrogen concentrations. 【Method】 Effect of different nitrogen concentrations on fennel plant growth, essential oil content and components was studied by using the method of solution culture, with Japanese garden formula’s nitrogen content as 1N, and 1/8N, 1/4N, 1/2N, 1N and 2N as designed treatment. 【Result】 With the increase of nitrogen concentration, the plant height, branch number, inflorescence number, number of nodes, shoot fresh weight (FW), fresh and dry weight (DW) of whole plant and yield of essential oil per plant had a trend that firstly increase then decrease, and the maximum values were all in 1N. Total nitrogen, protein nitrogen and pigment contents increased continuously, while total carbon, soluble sugar and essential oil contents and C/N ratio exhibited an opposite trend with increasing nitrogen concentrations. Correlation analysis showed that: total nitrogen content was significantly correlated to protein nitrogen content; total carbon and soluble sugar contents were significantly correlated to C/N ratio; total nitrogen, protein nitrogen contents were significantly and negatively correlated to total carbon content and soluble sugar contents and C/N ratio; essential oil content was significantly correlated with total carbon and soluble sugar contents; yield of essential oil per plant was significantly correlated to total nitrogen, protein nitrogen contents. A total of 23 kinds of components in essential oil were identified, but there were no differences in components of essential oil among different N concentration treatments. However, relative contents of components were significantly different when p<0.01 and p<0.05. (E)-anethole is the dominant essential oil component, contributing 63.89% to 79.28% of the total amount of oil. The second most abundant chemical was limonene, ranging from 5.65% to 18.28% in the total amount of oil, while dill apiol, the third abundant chemical, had the relative amount of  2.26% to 12.61%.【Conclusion】Different nitrogen concentrations not only affect the fennel plant growth, but also affect the yield and concentration of essential oil. Appropriate concentration of nitrogen can contribute to the high rate of plant growth and yield of essential oil. Reference | Related Articles | Metrics Cited: Baidu(8)

Select

Dynamic Characteristics of Summer Maize Yield Performance in Different Planting Dates and Its Effect of Ecological Factors LI Xiang-Ling, LI Cong-Feng, HOU Yu-Hong, HOU Hai-Peng, GE Jun-Zhu, ZHAO Ming Scientia Agricultura Sinica    2012, 45 (6): 1074-1083.   DOI: 10.3864/j.issn.0578-1752.2012.06.005 Abstract （1101）      PDF （443KB）（1200）       Knowledge map    Save 【Objective】Ecological factors play an important role in maize yield. In order to clarify the relationship between light, temperature, water in the growing period and yield performance of maize, provide a reference to the high yield of maize in the North China Plain. 【Method】 Three types of cultivars (YN 103, XY335, ZD 958 and DH 661) were used as materials, and three sowing dates (May 3rd, May 28th, and June 22nd) and four density treatments (45 000, 60 000, 75 000 and 90 000 plants/hm2) were designed. The dynamic of leaf area index, grain yield were measured and the growing period and ecological factors were recorded. 【Result】 Yield showed an order of XY335>ZD958> DH661>YN103, early sowing date>medium sowing date >late sowing date. Ecological factors had a regulatory effect on yield and yield performance indexes, effective temperature after silking affected the average leaf area index and mean net assimilation rate, daily average temperature affected the growth days and harvest index, total rainfall and sunshine hours affected grains number per spike and grain weight. Effective temperature of whole growth period, especially after silking was the most important ecological factors affecting grain yield. The order of correlation coefficient was that ，the effective temperature of whole growth period(0.64**)，the effective temperature after silking(0.55**), the daily average temperature after silking (0.51**), the daily average temperature of whole growth period(-0.49*), the rainfall after silking(-0.47*), the sunshine and silking(0.42*). The effective temperature was the main effective factor on yield. 【Conclusion】 Two-crop a year system is practiced in Huanghuaihai area, so medium maturing cultivars, such as ZD 958, should be selected, optimum early sowing should be practiced to ensure adequate and effective accumulated temperature of grain sufficient filling time for further enhancing corn yield in this area. Reference | Related Articles | Metrics

Select

Correlation Between the SCS and the Amount and Composition of Fatty Acids in Milk of Chinese Holstein MAO Yong-Jiang, CHANG Ling-Ling, YANG Zhang-Ping, WU Hai-Tao, CHEN Ying, SHI Xue-Kui, LI Yun-Long, LIANG Xiang-Huan, YIN Zhao-Hua Scientia Agricultura Sinica    2011, 44 (24): 5073-5082.   DOI: 10.3864/j.issn.0578-1752.2011.24.013 Abstract （827）      PDF （316KB）（646）       Knowledge map    Save 【Objective】 The objective of this study was to investigate the correlation between the SCC and the amount and composition of fatty acids in milk of Chinese Holstein 【Method】 Mixed milk samples were collected in the morning, noon and at night from 121 Chinese Holstein cows that free of clinical mastitis, and the parity was two or three, day in milk was from 100 to 300. The amounts of fatty acid of milk were determined by gas chromatography. The effects of SCS on fat percentage and fatty acid composition of milk were analyzed by one-way ANOVA. The SPSS software was used to analyze SCS and milk fatty acids composition of correlation and regression. 【Result】 Twenty-one fatty acids which are from C4 to C22 can be found out. Season had significant effects on the quantity and composition of fatty acids (P＜0.05), and the milking stage had minor effects on the quantity and composition of fatty acids. The effects of SCS on fat percentage and the amount of fatty acids were significant at 0.05 except eight fatty acids (C14：1, C16：1, C17：0, C18：0, C18：2n6c, C20：0, C20：3, C20：4 and PUFA). With the increasing of SCS in milk, fat percentage, the amount of total fatty acid, SFA, MUFA, short chain FA, medium chain FA and long chain FA were decreasing. The SCS showed no significant effects on the relative amount of twenty-three FA including SFA, MUFA, PUFA, short chain FA, medium chain FA and long chain FA except four low content of FA (C11：0, C20：0, C20：3 and DHA). SCS a showed significant negative relationship with the amounts of SFA, MUFA, short chain FA, medium chain FA and long chain FA (P＜0.05), and a significant positive relationship with the relative amount of PUFA and long chain FA. SCS showed a significant negative relationship with the relative amount of SFA, short chain FA and medium chain FA (P＜0.05). Logarithm equations were optimum for the amount of total FA, SFA, MUFA, short chain FA, medium chain FA and long chain FA depending on SCS, and the fitness of the equations were above 0.9. Exponent equations were optimum for the relative amount of SFA depending on SCS, and the fitness of the equations were also above 0.9. The fitness of other equations with the relative amount of FA depending on SCS were below 0.9. 【Conclusion】These results have provided a useful foundation for the prediction and evaluation of FA through SCS. Reference | Related Articles | Metrics Cited: Baidu(4)

Select

Analysis on Dynamic and Pattern of Land Use/Cover Change in Guanzhong Area HAO Hui-Mei, HAO Yong-Li, REN Zhi-Yuan Scientia Agricultura Sinica    2011, 44 (21): 4525-4536.   DOI: 10.3864/j.issn.0578-1752.2011.21.022 Abstract （703）      PDF （1875KB）（846）       Knowledge map    Save 【Objective】Understanding the process and pattern of regional land use and land cover change is essential for intensive and highly efficient，scientific and rational utilization of land resources.【Method】Based on technology of remote sensing (RS) and geographical information system (GIS), various land-use change models such as Markov transfer matrix model，amendatory land use dynamic model as well asland use degree change model were applied to simulate and analyze the scenario of land use changes from 1990 to 2007 in Guanzhong Area.【Result】The results showed that the land use change in Guanzhong Area was obvious and complicated. And mutual inverse of land use transfer among arable land，forest land and grasslands was happened almost simultaneously in space，especially during the former period (1990-2000). During the latter period，however，land use change was more orderly and stable. The amount of arable land changed into construction land from 1990 to 2007 was 183.3 thousand hm2，and most of them happened in Guangzhong basin area, and during the latter period. Index of amendatory land use dynamic can indicate intensity of land use changes，which also could be used to compare rates of land use changes in different districts and to imply the order degree of land use change in some area during certain period. 【Conclusion】The land use policy and economic benefits are the main drivers of regional land use change. To strengthen protection of arable land in the central Shaanxi basin , and to stabilize and promote ecological restoration and construction in the North Wei plateau and Qinling-Guanshan mountains are key links of land utilization in the future. Reference | Related Articles | Metrics Cited: Baidu(5)

Select

BAO Wen-Lei Scientia Agricultura Sinica    DOI: 10.3864/j.issn.0578-1752.sas-2010-07479 Accepted: 07 September 2011

Select

GAO Chao Scientia Agricultura Sinica    DOI: 10.3864/j.issn.0578-1752.sas-104471 Accepted: 07 September 2011

Select

ZHOU Cai-Yuan Scientia Agricultura Sinica    DOI: 10.3864/j.issn.0578-1752.sas-10133 Accepted: 07 September 2011

Select

LI Hong-Juan Scientia Agricultura Sinica    DOI: 10.3864/j.issn.0578-1752.sas-2010-07323 Accepted: 07 September 2011

Select

LIU Yan-Na Scientia Agricultura Sinica    DOI: 10.3864/j.issn.0578-1752.sas-10041 Accepted: 07 September 2011

Select

LIU Yi-Fan Scientia Agricultura Sinica    DOI: 10.3864/j.issn.0578-1752.sas-10058 Accepted: 07 September 2011

Select

SUN Jian-Guang Scientia Agricultura Sinica    DOI: 10.3864/j.issn.0578-1752.sas-10469 Accepted: 07 September 2011

Select

XIAO Hong-Yan Scientia Agricultura Sinica    DOI: 10.3864/j.issn.0578-1752.sas-10254 Accepted: 07 September 2011

Select

The Study of Agricultural Scientific and Technical Information Core Metadata(ASTICM) Standard Framework and its Register System Scientia Agricultura Sinica    2007, 40 (4): 685-692.   DOI: 10.3864/j.issn.0578-1752.at-2006-7270 Abstract （1546）      PDF （680KB）（927）       Knowledge map    Save 【Objective】Establish the Agricultural Scientific and Technical Information Core Metadata (ASTICM) standard and its expand principle, develop the register system based on ASTICM.【Method】Study the policy and methods of DC, SDBCM and AgMES, take the proposed elements of the Dublin Core Metadata Initiative (DCMI) as a starting point, to confirm the related metadata elements and the expand principle. Analyze the requirement of a great number of users of agricultural information, and develop the register system with the thought of soft engineering. 【Result】Confirm 75 metadata elements, 5 expand principles and 7 application profile creation methods, and developed a register system based on B/S mode. 【Conclusion】The ASTICM framework and its register system support the search, sharing, integration exchange and other application effectively. Related Articles | Metrics

Select

Study on Maize leaf morphological modeling and mesh simplification of surface Scientia Agricultura Sinica    2007, 40 (4): 693-697.   DOI: 10.3864/j.issn.0578-1752.at-2006-7239 Abstract （1198）      PDF （278KB）（1186）       Knowledge map    Save The method of morphological modeling of maize leaf based on Non-Uniform Rational B-Splines (NURBS) interpolation combining with multi-line segment splitting algorithms and controllable mesh simplification of triangular surface was introduced. A group of three-dimensional data points used from a scanning device, the crop leaf crooked surface with third-dimension effect was constructed stepped by vector calculation, crooked surface control points resulted by interpolation calculation and etc. According to leaf morphological characteristic, leaf surface mesh amount was simplified by inverse operation of multi-line segment splitting algorithm, and mesh amount declined with available maintenance of surface characteristics. This method was used to calculate visualization and light distribution and the result showed that calculation effect could be improved clearly when calculation error was not increased remarkable. The method could reflect model details and provided the solution to harmonize the relation between visual effect and calculation efficiency of crop morphological model. Related Articles | Metrics

Select

Maize Disease Identifying System Based Image Recognition Scientia Agricultura Sinica    2007, 40 (4): 698-703.   DOI: 10.3864/j.issn.0578-1752.at-2006-7611 Abstract （1719）      PDF （273KB）（1151）       Knowledge map    Save 【Objective】 The recognition and diagnosis of main maize leaf disease is introduced by the technique of image recognition in the paper. 【Method】 It adopts threshold method to do image segmentation, and uses area-marking method calculating the num of disease as well as wiping off redundancy dots. And then it uses Freeman link code to calculate form feather. 【Result】The research presents the exclusive feather of main maize leaf disease and confirms the flow of disease diagnosis. The results indicate that the precision of six kinds of maize disease recognition is higher than 80%. 【Conclusion】 It shows that this method is available for recognizing maize disease. And it also provides technique support for the automatic recognition of maize disease by compiling the system with reasonable process flow. Related Articles | Metrics

Select

Classification of Field Cotton Grade Based on Sampling Using Machine Vision Scientia Agricultura Sinica    2007, 40 (4): 704-711.   DOI: 10.3864/j.issn.0578-1752.at-2006-7928 Abstract （1291）      PDF （345KB）（918）       Knowledge map    Save In order to assess the quality of seed cottons objectively, sorting classifiers were designed based on machine vision technologies to grade 305 seed cottons with 7 grades based on their size and adjusted colors according to Chinese government grading standards. Fisher-criterion based canonical discriminants show that size and impurity contributed much more for cotton grades, and the distances among high-grades centroids were long while the ones among low-grades centroids were short. Total samples were divided into the train set and the test set. Cross-validation and Bayes-criterion based classifiers selections on the train set show that various classifiers were selected on 10-fold validation set with accuracies from 75% to 93%, and the approximate optimized classifiers were selected according to their average accuracy of 83%. Classifier performances evaluations on the test set show that the optimized classifiers can classify cottons into 7 grade categories with an accuracy of nearly 88%, and the high-grades cottons from 1 to 3 can be discriminated with an accurary of 100%. It is feasible to classify cotton grades using machine vision technologies and it helps to improve the yield of high-quality cottons. Related Articles | Metrics

First page | Prev page | Next page | Last page

Page 1 of 1, 21 records