Search

Tribolium castaneum (Herbst) has been one of the most destructive insects for cereals and products in the world. A rapid and accurate detection can be greatly contributed to the stored grain in recent years. In this study, an electronic nose detection device was developed to detect the pests in stored wheat grains using the feature optimization of the gas sensor array. The volatile odor information of Herbst in wheat was also collected with different population density gradients. Firstly, the response signal of the gas sensor array was analyzed and preprocessed after collection. Then, the feature extraction and selection were performed on the response curve of the sensor array, in order to obtain the feature information of the sample. A regression model was established to predict the population density of Herbst in wheat. The Relative Change value (RC), Relative Integral value (RI), and Mean Differential value (MD) of each sensor were extracted as the original feature matrix (10×3), according to the response curves collected by 10 gas sensors. A Genetic Algorithm (GA) was adopted as the feature selection to optimize the original multi-feature matrix, where the recognition accuracy was used as the evaluation index. Finally, Partial Least Squares Regression (PLSR), Principal Component Regression (PCR), and Support Vector Regression (SVR) were used for the regression prediction. The results show that the PLSR model achieved the best prediction. The Principal Component Analysis (PCA) and Cluster Analysis (CA) were used to analyze the discrimination and aggregation between different types of samples. It was found that the electronic nose device effectively distinguished the wheat samples from those infected by pests. The redundant information was removed from the optimized feature matrix, according to the recognition accuracy and PCA data. The recognition accuracy of the feature matrix increased from 82.85% to 97.14% after GA optimization. The number of feature variables was reduced by 60% from 30 to 12, and the number of sensors was reduced to 8. The PLSR, PCR, and SVR were used to establish the prediction model before and after the optimization of the matrix. The prediction set correlation coefficient (r) and root mean square error (RMSE) of the PLSR model were 0.828 and 11.293, respectively. By contrast, the prediction set r and RMSE of the PCR model were 0.764 and 13.859, respectively. The prediction set r and RMSE of the SVR model were 0.804 and 12.976, respectively. The results showed that the PLSR was the best model for the prediction of the population density of Herbst. Consequently, the feasibility and effectiveness of the sensor array multi-feature optimization can be verified for the electronic nose detection of stored grain pests. The finding can also provide a strong reference for the rapid detection of grain pests. [ABSTRACT FROM AUTHOR]

Tribolium castaneum (Herbst) has been one of the most destructive insects for cereals and products in the world. A rapid and accurate detection can be greatly contributed to the stored grain in recent years. In this study, an electronic nose detection device was developed to detect the pests in stored wheat grains using the feature optimization of the gas sensor array. The volatile odor information of Herbst in wheat was also collected with different population density gradients. Firstly, the response signal of the gas sensor array was analyzed and preprocessed after collection. Then, the feature extraction and selection were performed on the response curve of the sensor array, in order to obtain the feature information of the sample. A regression model was established to predict the population density of Herbst in wheat. The Relative Change value (RC), Relative Integral value (RI), and Mean Differential value (MD) of each sensor were extracted as the original feature matrix (10×3), according to the response curves collected by 10 gas sensors. A Genetic Algorithm (GA) was adopted as the feature selection to optimize the original multi-feature matrix, where the recognition accuracy was used as the evaluation index. Finally, Partial Least Squares Regression (PLSR), Principal Component Regression (PCR), and Support Vector Regression (SVR) were used for the regression prediction. The results show that the PLSR model achieved the best prediction. The Principal Component Analysis (PCA) and Cluster Analysis (CA) were used to analyze the discrimination and aggregation between different types of samples. It was found that the electronic nose device effectively distinguished the wheat samples from those infected by pests. The redundant information was removed from the optimized feature matrix, according to the recognition accuracy and PCA data. The recognition accuracy of the feature matrix increased from 82.85% to 97.14% after GA optimization. The number of feature variables was reduced by 60% from 30 to 12, and the number of sensors was reduced to 8. The PLSR, PCR, and SVR were used to establish the prediction model before and after the optimization of the matrix. The prediction set correlation coefficient (r) and root mean square error (RMSE) of the PLSR model were 0.828 and 11.293, respectively. By contrast, the prediction set r and RMSE of the PCR model were 0.764 and 13.859, respectively. The prediction set r and RMSE of the SVR model were 0.804 and 12.976, respectively. The results showed that the PLSR was the best model for the prediction of the population density of Herbst. Consequently, the feasibility and effectiveness of the sensor array multi-feature optimization can be verified for the electronic nose detection of stored grain pests. The finding can also provide a strong reference for the rapid detection of grain pests. [ABSTRACT FROM AUTHOR]

Soil nitrogen as an essential nutrient element is one of the most important indexes to measure soil fertility for crop growth and development. In this research, a new detection was proposed to quickly accurately determine the soil total nitrogen (STN) content using pyrolysis and electronic nose. Ten types of gas sensors were used to construct the sensor arrays. A response test was carried out under the different concentrations of methane, vinyl chloride, and ammonia standard gas. The test results showed that there were significant differences in responses of the sensor array to the types and the concentration, where the response intensity increased with the increase of the standard gas concentration. The sensor array also presented a high specificity and cross-sensitivity during data detection. Furthermore, the pyrolysis gas was obtained from the soil samples using the muffle furnace, further to detect the response curve using the gas sensor array. After that, a 121×10×7 feature space (121 soil samples, 10 number of sensors, and 7 eigenvalues) was constructed to extract the mean (Vmean), variance (Vvav), the maximum gradient (Vmgv), the maximum (Vmax), response area (Vrav), the eighth of the second transient (V8), and mean differential coefficient (Vmdc) of the response curve. A genetic algorithm and neural network model (GA-BP) feature optimization was used to reduce the eigenvalue to 33 dimensions, forming a new feature space of 121×33. More importantly, there was no redundant effect of the constructed sensor array on the new detection. Specifically, the sensors of TGS826, TGS2603, TGS2611, and TGS2600 contributed the most to the construction of the new feature space. The Vmean, Vmgv, Vrav, V8 and Vmdc were the important features to represent the internal relationship between the detection and STN content. The prediction model of feature space and STN content was then established using a back propagation neural network (BPNN), partial least squares regression (PLSR), and a combination of a back propagation neural network and partial least squares regression (PLSR-BPNN). The coefficient of determination (R²), root mean square error (RMSE), and residual prediction deviation (RPD) were used as the indicators of the model. As such, the R² of PLSR, BPNN and PLSR-BPNN models were 0.91, 0.81, and 0.93, respectively, where the RMSE were 0.25, 0.37, and 0.22, while the RPD were 3.24, 2.19, and 3.79, respectively. The predicted performance of the test sets demonstrated that the R² values of the three models were all greater than 0.81, and the RMSE<0.37, indicating that all the models presented the better prediction ability of STN content. However, both PLSR and PLSR-BPNN models presented a much better ability of quantitative prediction than that of the BPNN, from the perspective of RPD indicators. The R² of the PLSR-BPNN model increased by 2.90%, the RPD increased by 16.94%, and the RMSE was reduced by 14.48%, compared with the PLSR model. Therefore, the PLSR-BPNN prediction model can be expected to effectively improve the prediction accuracy of the PLSR model for the better generalization ability of the BPNN model, indicating a reliable relationship model for the STN measurement. The reason was that there was a certain degree of linear and nonlinear correlation between the STN content and characteristic space of the electronic nose. The PLSR-BPNN model greatly contributed to the strength of the nonlinear and linear relationship between the PLSR and BPNN model. Consequently, a more accurate PLSR-BPNN model was established to accurately predict the STN content. There was also a high correlation between the soil pyrolysis gas and STN content. [ABSTRACT FROM AUTHOR]

The electronic nose and electronic tongue were used to detect adulterated chicken rapidly. In this research, electronic nose and electronic tongue were used to detect the content of soybean protein and starch in chicken meat. Soy protein (0, 2.5%, 5.0%, 7.5%, and 10.0%) was mixed into minced chicken meat to prepare adulterated chicken samples, the total sample weight was 10 g. The 2 mL of distilled water and 0.006 g of neutral protease were added in sequence in a 50 ℃ water bath. After 15 min, the above samples were raised to 90 ℃ to inactivate the enzyme. And incorporated with 0.1 g of D-ribose, Maillard reaction was carried out for 20 min. Then the reaction was terminated at 20 ℃. The processed samples were put into the measuring bottle for electronic nose detection. The 50 mL of 0.1 mol/L potassium chloride extract was added to each group of prepared electronic nose samples. After 30 min, the filtrate was taken for electronic tongue detection. Twenty-four samples in each group were made in parallel, including 18 modeling sets and 6 detection sets. Starch (0, 2.5%, 5.0%, 7.5%, 10.0% and 15.0%) was mixed into minced chicken meat to prepare adulterated chicken samples, the total sample weight was 10 g. The 2 mL of distilled water and 0.006 g of α-amylase were added to each group of samples in a 45 ℃ water bath. After 15 min, the above samples were raised to 90 ℃ to inactivate the enzyme. When incorporating with 0.1 g of glycine, the Maillard reaction was carried out for 20 min. Then the reaction was terminated at 20 ℃. The processed samples were put into the measuring bottle for electronic nose detection. The 50 mL of 0.1 mol/L potassium chloride extract was added to each group of prepared electronic nose samples. After 30 min, the filtrate was taken for electronic tongue detection. Twenty-four samples in each group were made in parallel, including 18 modeling sets and 6 detection sets. The data was statistically analyzed by Principal Component Analysis (PCA) and Partial Least Squares Regression (PLSR). By PCA, the results showed that the contribution rates of first principal component and second principal component combinedly detected by electronic nose and electronic tongue for minced chicken meat adulterated with soy protein were 99.2% and 0.6%, respectively, and the total contribution rate was 99.8%. By PLSR, the coefficient of determination detected by electronic nose or electronic tongue was 0.989 and 0.972, the root mean square error was 3.9% and 5.4%, respectively. The coefficient of determination and the root mean square error of combinedly detected by electronic nose and electronic tongue were 0.992 and 2.8%. By PCA, the results showed that the contribution rates of first principal component and second principal component combinedly detected by electronic nose and electronic tongue for minced chicken meat adulterated with starch were 97.0% and 2.1%, respectively, and the total contribution rate was 99.1%. By PLSR, the coefficient of determination detected by electronic nose or electronic tongue was 0.977 and 0.976, the root mean square error was 5.0% and 5.2%, respectively. The coefficient of determination and the root mean square error of combinedly detected by electronic nose and electronic tongue were 0.996 and 2.4%. The performance of combined detection by electronic nose and electronic tongue for soy protein was better than for starch. The combined detection using electronic nose and electronic tongue sensors has a potential ability to distinguish and predict soy protein-based or starch-based adulteration in minced chicken meat and has also been proved to be a useful authentication method for meat adulteration detection with high efficiency and accuracy. [ABSTRACT FROM AUTHOR]

The cotton pests have the characteristics of concealment, migration, and sudden burst, and there are many influencing factors involved. The accurate diagnosis of cotton pests is a difficult problem in the agricultural field. Previous studies have demonstrated that cotton plants produce blends of volatile compounds in response to herbivores serve as cues for parasitic and predatory insects. Therefore, it is possible to obtain information about cotton pests by detecting volatile compounds in cotton. In this study, an electronic nose was used to detect the volatiles emitted by cotton plants damaged by cotton bollworm at the flowering period. The cotton samples were divided into four infested cotton treatments. According to the number of pests in each pot of cotton seedlings, the treatments inoculated with 0, 1, 2, and 3 bollworm larvae were marked as 0-P, 1-P, 2-P, and 3-P, respectively. The 0-P was healthy cotton as a control treatment. The cotton bollworm feeding lasted 48 h. During this period, the electronic nose detection tests were performed every 6 h, and a total of 8 repeated tests were performed. Appropriate pattern recognition techniques were applied to construct reliable algorithms for interpreting the acquired signal in cotton. Principal Component Analysis (PCA), discriminant function analysis, cluster analysis, and Radial Basis Function Neural Network (RBFNN) were applied to evaluate the data. The results of PCA and discrimination values of the healthy cotton treatment showed that the volatiles released by healthy cotton had obvious circadian rhythm. For the three infested cotton treatments, whereas the distribution patterns of cotton samples were different from that of the healthy cotton treatment. The three infested cotton treatments had regular distribution trends that cotton samples changed along the direction of the first and second principal components. Cluster analysis results showed that the four cotton treatments were all finally divided into two categories, the healthy cotton treatment, and the three infested cotton treatments. All these results suggested that there was a significant difference between healthy and damaged cotton samples. Then RBFNN was used to analyze four treatments of cotton samples at 8 different times. The results showed that the total correct rate of the test sets was 73.4%, the correct rate of the healthy cotton treatment was 100%, and the misjudgment samples appeared among the three infested cotton treatments. Moreover, two unified consecutive prediction models were established regardless of the time factor. The RBFNN model was established by using four treatments of cotton samples. The correct rate of the training sets was 66.1%, and the correct rates of the test sets were 100 %, 79.7 %, 32.8 %, and 20.3 % for the 0-P, 1-P, 2-P, and 3-P treatments, respectively. In another RBFNN model based on 0-P, 1-P, and 3-P treatments, the correct rate of the training sets was 87.8%, and the correct rates of the test sets were 100 %, 78.1%, and 82.8% for the 0-P, 1-P, and 3-P treatments, respectively. Comparing the results of the two RBFNN models, the prediction accuracy of the second model had been greatly improved. At the same time, it was also found that the prediction accuracy of all RBFNN models for healthy cotton treatment reached 100%. Therefore, the electronic nose could be used as an effective monitoring method for the occurrence of cotton bollworm in the cotton plants. It should have a potential application for crop pest monitoring in the field. [ABSTRACT FROM AUTHOR]

In order to investigate the flavor changes of beef sao zi industrial semi-finished products in different stir-frying stages. Sensory evaluation and instrumental analysis of tenderness were applied to optimize the processing parameters. For the overall odor perception, electronic nose (e-nose) can be used to distinguish the different odors of raw materials and processed samples. The volatile compounds were identified by headspace solid-phase microextraction (HS-SPME) and gas chromatography-mass spectrometry (GC-MS). A total of 144 volatile components were detected by HS-SPME-GC-MS, 52 of which were screened by t-test (P < 0.01).In the whole process, aldehydes were the major volatile flavor compounds in beef sao zi, which was consistent with the results of electronic nose in the stir-fry fat (SFF) stage. According to the results of partial least squares discriminant analysis (PLS-DA), the odor formation in stir-fried beef sao zi was divided into four steps including raw, stir-fry to remove water(SFMRW), stir-fry fat (SFF) and mixed stir-fry (MSF). The results showed that the method could effectively distinguish the different processing stages of beef sao zi. There were 27 volatile compounds in raw and SFMRW, 103 volatile compounds in SFF, and 14 volatile compounds in MSF. Among these stages, SFF stage plays important role in the flavor change of beef sao zi. Even in PLS-DA evaluation of scatter plot, the raw and SFMRW were in the fourth quadrant, but their samples could be clearly separated. In the fourth quadrant, there were 27 kinds of volatile compounds, among which 5 kinds of volatile compounds were unique to raw, 5 kinds were specific for SFMRW, and 17 kinds were common for raw and SFMRW. There were 103 volatile compounds in the second and third quadrants of PLS-DA evaluation of scatter plot, of which 25 were specific to SFF, and the remaining 78 were common in three processing stages. There were 14 volatile compounds in the first quadrant of the PLS-DA evaluation of scatter plot, which were shared with e MSF, raw, SFMRW and SFF. The amount of volatile compounds in the MSF stage was less than that in the SFMRW stage. The results showed that volatile compounds in the MSF stage was less than that in the SFMRW stage, but the 14 volatile compounds can be used to distinguish MSF from other processing stages. MSF stage was the final stage of flavor formation of stir-frying beef sao zi. The content of volatile flavor compounds in this stage was lower than that in SFF stage. On the one hand, after the end of SFF, most of the butter in fat tissue has been already spilled, and the rate of autoxidation and thermal oxidation cracking of fat were weakened. On the other hand, adding 70% sfmrw sample to 30% SFF sample can reduce MSF temperature to 126 ℃.Compared with the heat treatment temperature (145 ℃) in the SFF stage, the reaction rates were weakened. At the same time, the addition of 70% of SFMRW also diluted the volatile compounds generating in the SFF stage. [ABSTRACT FROM AUTHOR]

Cotton bollborm is one of the main pests of cotton. Cotton is under threat of yield loss and poor quality because of the cotton bollworm. However, cotton bolworms tend to hide in the cotton plants so that there are limitations for conventional detection methods, such as acoustic signal method, image recognition method and spectral imaging technology. A lot of researches have shown that volatile organic compounds (VOCs) released by plants will change when they are attacked by pests. So it is possible to get the cotton bollworm damage information by detecting the volatiles. Currently, gas chromatograph-mass spectrometer (GC-MS) can accurately detect the composition and content of volatile matter. However, this method has some disadvantages in practical application, such as time-consuming, high cost and inconvenience. The electronic nose is composed of sensor array, which is an instrument to analyze, identify and detect most of the volatiles. In this study, electronic nose was used to detect the cotton plants infested with cotton bollworm of different amounts at an early stage. The volatile organic compounds (VOCs) in cotton were analyzed by GC-MS. The plant height of cotton used in the study was 50-70 cm, and the boll period was about 12 weeks. Cotton bollworms used in the study were at second-instar. The VOCs emitted by the undamaged and damaged cotton plants detected by GC-MS were different, which indicated that electronic nose had potential in the application of cotton bollworm detection. The curve of electronic nose sensor was obtained for cotton plants infected by different numbers of cotton bollworm. Then five kinds of feature parameters were extracted from the curves of electronic nose sensors : stable value, area value, mean differential value, wavelet energy value and the coefficients of the fitted quadratic polynomial function. Feature parameters were selected based on three kinds of neural network methods: multilayer perceptron neural network (MLPNN), radial basis neural network (RBFNN) and extreme learning machine (ELM). Then stable value, area value and mean differential value were selected because of their better classification performance among the five kinds of feature parameters. Multiple-features were combinations of single-features. The classification analysis was carried out based on multiple-features and three kinds of neural network methods. And support vector machine regression (SVR) models were established based on single-features and multiple-features, respectively. The results showed that the classification performance of multiple-features was better than that of single-features. The classification performance was best based on “stable value and mean differential value” features and ELM. The classification accuracy of training set and test set based on “stable value and mean differential value” features were both 100%. The regression models based on multiple-features were better than that based on single-features. And the regression model was the best based on “area value and mean differential value” features. The coefficient of determination (R²) and root mean square error (RMSE) of the regression model based on the training set of “area value and mean differential value” were 0.994 0 and 0.086 0. The R² and RMSE of the regression model based on the test set of “area value and mean differential value” were 0.923 0 and 0.370 9. The results show that feature election and multiple-features can improve the classification performance of the electronic nose for infested cotton plants. It can be concluded that electronic nose has strong potential for the application of detection of cotton plants infested with cotton bollworm at an early stage. [ABSTRACT FROM AUTHOR]