[Prediction of Greenhouse Cucumber Disease Based on Chlorophyll Fluorescence Spectrum Index].

The occurrence of greenhouse vegetable diseases and its epidemic seriously affect the production and management of facility agriculture, which greatly reduce the economic benefits of facility agriculture. In order to achieve nondestructive and accurate prediction of greenhouse vegetable diseases, this paper taking cucumber downy mildew disease as the research object, constructed spectrum characteristic index by using chlorophyll fluorescence induced by laser and established the prediction model of greenhouse vegetable diseases. In this paper, the experiment used comparative analysis method. The healthy leaves of the crops were inoculated with the pathogen spores, the spectrum curves of four groups of test samples: healthy, 2 d inoculated, 6 d inoculated and the ones with obvious symptoms were collected; then qualitative analysis was given to the variation regulation of the fluorescence intensity with the leaf samples infected with the pathogen spores. The chlorophyll fluorescence spectrum index k1=F685/F512 and k2=F734/F512 were created by using the peak and valley values of different bands. According to the range of values, set k1=20 and k2=10 as the characteristic value to judge the sample with obvious symptoms or with no obvious symptoms, and the accuracy rate of the judgment was 96% and 94% respectively. Based on spectrum index created and the classification results of sample health status, we selected the spectrum index F685/F512, F685-F734, F715/F612 to determine the health status of the sample and selected spectrum index F685/F512, F734/F512, F685-F734, F715/F612 as the inputs of quantitative analysis model. Regarding classification accuracy of prediction set as the evaluation criteria, we compared three data modeling methods: discriminant analysis, BP neural network and support vector machine. The results showed that the forecasting ability can reach 91.38% when the support vector machine was used as the modeling method for predicting the downy mildew disease. Use the method with chlorophyll fluorescence induced by laser to construct spectrum index to study the prediction of plant diseases, which has a good classification and identification effect.

[Prediction Model on Net Photosynthetic Rate of Soybean Plant Groups Based on Kernel Function and Visible Light Spectrum].

The paper uses MSR-16 portable multispectral radiometer made in the USA and computes the numbers of the test units by pulling the formula on the radiometer effective observation area, which solves the problem on the uncertain numbers of computing the times on region visible light band spectral radiation ratio M_D. The paper uses CI-310 portable photosynthesis measurement system made by American CID Company and measures the net photosynthetic rate of a group of soybean plant. M_D and C_D are normalized by the normalization method [0,1]. Then, the normalization data M_D1 and C_D1 are gained . Based on the different test time, M_D1 is divided of M_D11 and M_D12. C_D1 is divided of C_D11 and C_D12. The paper uses polynomial kernel function, gauss kernel function, sigmoid kernel function and bio-selfadaption kernel function constructed by us with Support Vector Machine. Penalty parameter c and parameter g separately are optimized with optimization algorithms such as grid-search，genetic algorithm and particle swarm optimization. Based on the formula epsilon-SVR and the formula nu-SVR with Support Vector Machine, the paper constructs the prediction model on the net photosynthetic rate of a group of soybean plant by using of the cross combination with four kernel functions, three optimization methods and two formulas. The test results are as follows: in the condition of S=17 m2 which is the test plan area of soybean plant and the H=2 m which is the high on MSR-16 portable multispectral radiometer above the canopy of soybean plant, the prediction accuracy is up to 85% on the No.1 prediction set C_D12 and the prediction accuracy is up to 82% on the No.2 prediction set C_D12 based on the model epsilon-SVR-bio-selfadaption-grid-search. In the condition of other combinations with S and H, the prediction accuracy is up to 81% on the No.2 prediction set C_D12 based on the model epsilon-SVR-bio-selfadaption-grid-search. The model epsilon-SVR-bio-selfadaption-grid-search indicates the validity of bio-selfadaption kernel functions which is constructed by our previous research with support vector machine. The model epsilon-SVR-bio-selfadaption-grid-search indicates the rationality of the measure method on visible spectral data in the test area. The model epsilon-SVR-bio-selfadaption-grid-search indicates the feasibility of the prediction method on net photosynthetic rate of soybean plant groups by using of visible spectrum.

[Rice blast prediction model based on analysis of chlorophyll fluorescence spectrum].

In order to detect rice blast more rapidly, accurately and nondestructively, the identification and early warning models of rice blast were established in the present research. First of all, rice blast was divided into three grades according to the relative area of disease spots in rice leaf and laser induced chlorophyll fluorescence spectra of rice leaves at different disease levels were measured in the paddy fields. Meanwhile, 502-830 nm bands of laser-induced chlorophyll fluorescence spectra were selected for the study of rice blast. Savitzky-Golay(SG) smoothing and First Derivative Transform(FDT) were applied for the pretreatment of laser-induced chlorophyll fluorescence spectra. Then the method of Principal Components Analysis (PCA) was used to achieve the dimension reduction on spectral information, three principal components whose variance are greater than 1 and cumulative credibility is 99.924% were extracted by this method. Furthermore, the tentative data were divided into calibration set and validation set, the levels of rice blast were taken as the predictors. Combined with the calibration set which contains the disease and spectral information of 133 leaves, Discriminant Analysis (DA), Multiple Logistic Regression Analysis (MLRA) and Multilayer Perceptron (MLP) were used respectively to establish the identification and early warning models of rice blast. The Prediction examinations of the three models were made based on the validation set which contains the disease and spectral information of 89 leaves. The results show that all the models of PCA-DA, PCA-MLRA and PCA-MLP can carry on the prediction of rice blast, and the average prediction accuracy of PCA-MLP prediction model is 91.7% which is improved compared with PCA- DA and PCA- MLRA.

[Chlorophyll fluorescence spectrum analysis of greenhouse cucumber disease and insect damage].

The present paper is based on chlorophyll fluorescence spectrum analysis. The wavelength 685 nm was determined as the primary characteristic point for the analysis of healthy or disease and insect damaged leaf by spectrum configuration. Dimensionality reduction of the spectrum was achieved by combining simple intercorrelation bands selection and principal component analysis (PCA). The principal component factor was reduced from 10 to 5 while the spectrum information was kept reaching 99.999%. By comparing and analysing three modeling methods, namely the partial least square regression (PLSR), BP neural network (BP) and least square support vector machine regression (LSSVMR), regarding correlation coefficient of true value and predicted value as evaluation criterion, eventually, LSSVMR was confirmed as the appropriate method for modeling of greenhouse cucumber disease and insect damage chlorophyll fluorescence spectrum analysis.

[Fluorescence spectrum monitor for early warning of greenhouse cucumber aphis pests].

The infection and degree of cucumber aphis pests was studied by analyzing chlorophyllfluorescence spectrum in greenhouse. Based on the configuration of the spectrum, characteristic points were established, in which the intensity of waveband F632 was the first characteristic point between healthy and aphis pests leaves. The second characteristic point was K which was the change rate of spectral curve from waveband F512 to F632. The early warning could be executed on plants depending on these two points. The models of the infection and degrees of aphis pests were established for different wavebands by the least square support vector machine classification method (LSSVMR) radial basis function(RBF). The accuracy rate of classification and prediction of the models was compared by different peaks and valleys value in wavebands. The results indicated that the prediction accuracy of the model established by waveband F632 was the most perfect (96.34%).

[Prediction model of net photosynthetic rate of ginseng under forest based on optimized parameters support vector machine].

Using K-fold cross validation method and two support vector machine functions, four kernel functions, grid-search, genetic algorithm and particle swarm optimization, the authors constructed the support vector machine model of the best penalty parameter c and the best correlation coefficient. Using information granulation technology, the authors constructed P particle and epsilon particle about those factors affecting net photosynthetic rate, and reduced these dimensions of the determinant. P particle includes the percent of visible spectrum ingredients. Epsilon particle includes leaf temperature, scattering radiation, air temperature, and so on. It is possible to obtain the best correlation coefficient among photosynthetic effective radiation, visible spectrum and individual net photosynthetic rate by this technology. The authors constructed the training set and the forecasting set including photosynthetic effective radiation, P particle and epsilon particle. The result shows that epsilon-SVR-RBF-genetic algorithm model, nu-SVR-linear-grid-search model and nu-SVR-RBF-genetic algorithm model obtain the correlation coefficient of up to 97% about the forecasting set including photosynthetic effective radiation and P particle. The penalty parameter c of nu-SVR-linear-grid-search model is the minimum, so the model's generalization ability is the best. The authors forecasted the forecasting set including photosynthetic effective radiation, P particle and epsilon particle by the model, and the correlation coefficient is up to 96%.

[Cucumber downy mildew prediction model based on analysis of chlorophyll fluorescence spectrum].

In order to achieve quick and nondestructive prediction of cucumber disease, a prediction model of greenhouse cucumber downy mildew has been established and it is based on analysis technology of laser-induced chlorophyll fluorescence spectrum. By assaying the spectrum curve of healthy leaves, leaves inoculated with bacteria for three days and six days and after feature information extraction of those three groups of spectrum data using first-order derivative spectrum preprocessing with principal components and data reduction, principal components score scatter diagram has been built, and according to accumulation contribution rate, ten principal components have been selected to replace derivative spectrum curve, and then classification and prediction has been done by support vector machine. According to the training of 105 samples from the three groups, classification and prediction of 44 samples and comparing the classification capacities of four kernel function support vector machines, the consequence is that RBF has high quality in classification and identification and the accuracy rate in classification and prediction of cucumber downy mildew reaches 97.73%.

[Diagnosis of cucumber diseases and insect pests by fluorescence spectroscopy technology based on PCA-sVM].

The diagnosis model of the cucumber diseases and insect pests was established by laser-induced chlorophyll fluorescence (LICF) spectroscopy technology combined with support vector machines (SVM) algorithm in the present research. This model would be used to realize the fast and exact diagnosis of the cucumber diseases and insect pests. The noise of original spectrum was reduced by three methods, including Savitzky-Golay smoothing (SG), Savitzky-Golay smoothing combined with fast Fourier transform (FFT) and Savitzy-Golay smoothing combined with first derivative transform (FDT). According to the accumulative reliabilities (AR) seven principal components (PCs) were selected to replace the complex spectral data. The one hundred fifty samples were randomly separated into the calibration set and the validation set. Support vector machines (SVM) algorithm with four kinds of kernel functions was used to establish diagnosis models of the cucumber diseases and insect pests based on the calibration set, then these models were applied to the diagnosis of the validation set. According to the best diagnosis accuracy of cross-validation method in calibration set, the parameters of four kinds of kernel function models were optimized, and the capabilities of SVM with different kernel function were compared. Results showed that SVM with the ploy kernel function had the best identification capabilities and the accuracy was 98. 3% after the original spectrum noise was reduced by SG+FDT+ PCA. This research indicated that the method of PCA-SVM had a good identification effect and could realize rapid diagnosis of the cucumber diseases and insect pests as a new method.