Laijun Sun

Prediction of Benzoyl Peroxide in Flour Using Near Infrared Spectroscopy Technique

This research proposed to design a prediction model based on radial basis function neural network and near infrared reflectance spectroscopy in detecting concentration of benzoyl peroxide in flour. Near infrared reflectance spectra acquired from 100 different concentration samples were pre-processed by the standard normal variate method, detection of leverage, and student residual. Near infrared reflectance spectroscopy models were designed to predict benzoyl peroxide in the 36 samples by means of partial least squares, back propagation neural network, and radial basis function, respectively. The results demonstrated that the radial basis function model, with prediction correlation coefficient (R), root mean squared error of prediction, and ratio of performance to standard deviate reaching 0.9937, 15.5095, and 8.8216, respectively, had optimal prediction accuracy and feasibility providing quality evaluation and dynamic monitoring service for quality inspection department and consumers.

Pixel based bruise region extraction of apple using Vis-NIR hyperspectral imaging

Abstract Bruises on apples will directly influence its preservation and marketing for they can cause the internal decomposition and flaws of the appearance of apples. Therefore, an effective pixel based bruise region extraction method was proposed in this study to obtain the complete bruise region. Hyperspectral images of 60 apples were obtained via the hyperspectral imaging (HSI) system at 0, 12 and 18u202fh after the damage experiment. Principal Component Analysis (PCA) was used to compression data size and eliminating redundant data of hyperspectral image cubes. After the selection of the region of interest (ROI) by certain rules, different pixel based apple bruise extraction models were built and compared. The result shows that Random Forest (RF) model have a high and stable classification accuracy, which turns out that RF algorithm is more suitable for classifying bruises on apples than others. The average accuracy of bruise extraction models reached 99.9%. Compared with the most used image processing method in recent literature for extracting bruises of apples, the bruising region predicted by RF model was more consistent with the true bruise region. Additionally, two characteristic wavebands around 675u202fnm and 960u202fnm related to the bruise region were singled out for reducing the dimensionality of data by analyzing the feature importance scores of the built RF model. The overall results indicated that the proposed method has a great potential to detect complete bruise region on apples based on hyperspectral imaging for improving the efficiency of apple grading and sorting.

Non-destructive prediction of protein content in wheat using NIRS

A steady and accurate model used for quality detection depends on precise data and appropriate analytical methods. In this study, the authors applied partial least square regression (PLSR) to construct a model based on the spectral data measured to predict the protein content in wheat, and proposed a new method, global search method, to select PLSR components. In order to select representative and universal samples for modeling, Monte Carlo cross validation (MCCV) was proposed as a tool to detect outliers, and identified 4 outlier samples. Additionally, improved simulated annealing (ISA) combined with PLSR was employed to select most effective variables from spectral data, the datas dimensionality reduced from 100 to 57, and the standard error of prediction (SEP) decreased from 0.0716 to 0.0565 for prediction set, as well as the correlation coefficients (R2) between the predicted and actual protein content of wheat increased from 0.9989 to 0.9994. In order to reduce the dimensionality of the data further, successive projections algorithm (SPA) was then used, the combination of these two methods was called ISA-SPA. The results indicated that calibration model built using ISA-SPA on 14 effective variables achieved the optimal performance for prediction of protein content in wheat comparing with other developed PLSR models (ISA or SPA) by comprehensively considering the accuracy, robustness, and complexity of models. The coefficient of determination increased to 0.9986 and the SEP decreased to 0.0528, respectively.

Application of Visible/Near-Infrared Spectroscopy in the Prediction of Azodicarbonamide in Wheat Flour

Azodicarbonamide is wildly used in flour industry as a flour gluten fortifier in many countries, but it was proved by some researches to be dangerous or unhealthy for people and not suitable to be added in flour. Applying a rapid, convenient, and noninvasive technique in food analytical procedure for the safety inspection has become an urgent need. This paper used Vis/NIR reflectance spectroscopy analysis technology, which is based on the physical property analysis to predict the concentration of azodicarbonamide in flour. Spectral data in range from 400 to 2498xa0nm were obtained by scanning 101 samples which were prepared using the stepwise dilution method. Furthermore, the combination of leave-one-out cross-validation and Mahalanobis distance method was used to eliminate abnormal spectral data, and correlation coefficient method was used to choose characteristic wavebands. Partial least squares, back propagation neural network, and radial basis function were used to establish prediction model separately. By comparing the prediction results between 3 models, the radial basis function model has the best prediction results whose correlation coefficients (R), root mean square error of prediction (RMSEP), and ratio of performance to deviation (RPD) reached 0.99996, 0.5467, and 116.5858, respectively.nnnPRACTICAL APPLICATIONnAzodicarbonamide has been banned or limited in many countries. This paper proposes a method to predict azodicarbonamide concentrate in wheat flour, which will be used for a rapid, convenient, and noninvasive detection device.

Prediction of Azodicarbonamide in Flour Using Near-Infrared Spectroscopy Technique

AbstractsAzodicarbonamide is wildly used as a flour gluten fortifier in many countries, but according to the research results of toxicology of azodicarbonamide, its acute toxicity is slightly toxic. A dosage of 10xa0g/kg is lethal to mice, and it was proved by some researches to be dangerous or unhealthy for people and not suitable to be added in flour; hence, there is a need to identify the concentration of azodicarbonamide in flour quickly. Compared to traditional methods like high-performance liquid chromatography, the core advantage of near-infrared reflectance spectroscopy is rapid and economical. Spectral data in a range of 850 to 1050xa0nm were obtained by scanning 101 samples with different concentrations. The Mahalanobis distance method was used to distinguish abnormal spectral data, and the correlation coefficient method was used to choose characteristic wave bands. Radial basis function in combination with near-infrared reflectance spectroscopy was used to establish models in accordance. The limit of quantitation and the limit of detection of the first model were 72 and 15xa0mg/kg, respectively. Through analyzing the relative tolerances of predictive values and true values, the method of secondary modeling was proposed for low-concentration (72xa0mg/kg) samples. The predictions showed that near-infrared reflectance spectroscopy could be used for detecting the content of azodicarbonamide added to flour.

The feasibility of early detection and grading of apple bruises using hyperspectral imaging: Early detection and grading of apple bruises

The ability to determine if an apple is bruised and to provide quantitative and objective descriptions of the degree of bruising is not the only important basis for assessing apple quality but also has significance for improving the postharvest handling of apples. In this study, segmented principal component analysis for hyperspectral images in the spectral range of 401 to 1037 nm was carried out, and seven characteristic wavelengths were selected based on the weight coefficients of the principal component images. By using the principal component analysis operations with the selected wavelengths and image processing methods, an accurate recognition algorithm for apple bruises was proposed. For 40 intact samples and 160 bruised samples, the average correct recognition rate was 99.1%. Moreover, this paper obtained the average spectra of 157 segmented bruised regions by applying a binary mask. A characteristic wavelength selection method that combines competitive adaptive reweighted sampling with correlation coefficient methods and supports vector machine modeling methods based on grid parameter optimization was put forward for the classification and identification of the bruising degrees of apples. The results showed that the classification accuracy was as high as 97.5% for the test set. Overall, this study demonstrated that hyperspectral imaging technology can be used to accurately and effectively identify early bruises and determine the bruising degree of apples, which provides a new method for on‐line, nondestructive detection, and grading of early bruises in apples.

Determination of bruised potatoes by GLCM based on hyperspectral imaging technique

A texture recognition method based on hyperspectral imaging technology was proposed for the difficulty in bruise detection of potatoes. Firstly, the hyperspectral images of healthy and bruised potatoes were collected, and then they were used to generate principal component images by using PCA method. To enhance the features of bruised region in these principal component images, the histogram equalization, mean smoothing, and gradient method were used, respectively, which proved that the histogram equalization method was the most suitable. Extra, through the selection of parameters of gray level co-occurrence matrix (gray level L and distance D), the best prediction results were obtained when L=8 and D=8. Finally, SA method was applied to reduce the dimension of the texture data, and the recognition rate reached 93.75%.

A novel approach of low-light image used for face recognition

Illumination variation is a challenge of face recognition, especially in low light environments. In order to overcome the influence of low illumination image, this paper proposed a face recognition method of face image preprocessing before recognition, with illumination- reflection model of homomorphic filtering and image multiplication method of image preprocessing for getting the enhancement of human face recognition rate. Homomorphic filtering can reduce low frequency noise in the frequency domain and enhance image details at same time reduce the high frequency noise of the image. By changing the image multiplication coefficient can change the brightness of the image. The YALE database results show that this approach can be a very good solution to the problem of face recognition under low light conditions. Human face recognition rate can increase 10%. The experiment proved that the pretreatment method can well solve the problem of face recognition under low light.

The design and implementation of a wireless data transceiver

We designed a wireless data transceiver which is based on ATMEGA128 controller and SIM900A. By using the SIM900A chip, it can send data wirelessly through GSM/ GPRS, and by using the ATMEGA128 controller, it can process the data, order and control SIM900A, and then we can transfer data to the remote terminal wirelessly. According to a large number of experiments, we know that: this system is stable, at low cost, easy to take the secondary development, and it will be applied widely in the further.

The design and implementation of a RFID reader based on MFRC531

The radio frequency identification is a technology which is using a radio frequency communication to achieve non-contact and automatic identification. It also takes advantage of the radio frequency signals spatial coupling (alternating magnetic or electromagnetic fields) to achieve non-contact transmission of information. Meanwhile, it can achieve the purpose of identifying the object by passing the information. The readers system of the RFID is based on Phillips MFRC531. Its read-distance is about 10cm. The design introduces this system in detail from the hardwares design and softwares programming. The design of the hardware is made up of the MCU (AT89S51) circuit, the RF circuit (MFRC531), the antenna circuit, the memory circuit (AT24C16), the serial communication and the power circuit. The programming of the software contains the RFs initialization, the reading and writing to the card, the verification to the key, the communication between the microcontroller and the PC through UART.