scholarly journals Detection of Adulteration in Infant Formula Based on Ensemble Convolutional Neural Network and Near-Infrared Spectroscopy

Foods ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 785
Author(s):  
Yisen Liu ◽  
Songbin Zhou ◽  
Wei Han ◽  
Chang Li ◽  
Weixin Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Infant Formula ◽  
Ensemble Learning ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Data Sets ◽  
Promising Tool ◽  
Random Initialization ◽  
Non Destructive

Adulteration in dairy products has received world-wide attention, and at the same time, near infrared (NIR) spectroscopy has proven to be a promising tool for adulteration detection given its advantages of real-time response and non-destructive analysis. Regardless, the accurate and robust NIR model for adulteration detection is hard to achieve in practice. Convolutional neural network (CNN), as a promising deep learning architecture, is difficult to apply to such chemometrics tasks due to the high risk of overfitting, despite the breakthroughs it has made in other fields. In this paper, the ensemble learning method based on CNN estimators was developed to address the overfitting and random initialization problems of CNN and applied to the determination of two infant formula adulterants, namely hydrolyzed leather protein (HLP) and melamine. Moreover, a probabilistic wavelength selection method based on the attention mechanism was proposed for the purpose of finding the best trade-off between the accuracy and the diversity of the sub-models in ensemble learning. The overall results demonstrate that the proposed method yielded superiority regression performance over the comparison methods for both studied data sets, and determination coefficients (R2) of 0.961 and 0.995 were obtained for the HLP and the melamine data sets, respectively.

scholarly journals Feasibility of Using VIS/NIR Spectroscopy and Multivariate Analysis for Pesticide Residue Detection in Tomatoes

Processes ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 196
Author(s):  
Araz Soltani Nazarloo ◽  
Vali Rasooli Sharabiani ◽  
Yousef Abbaspour Gilandeh ◽  
Ebrahim Taghinezhad ◽  
Mariusz Szymanek ◽  
...  
Keyword(s):  
Near Infrared ◽  
Cross Validation ◽  
Low Cost ◽  
Moving Average ◽  
Nir Spectroscopy ◽  
Control Treatment ◽  
Residue Detection ◽  
Non Destructive ◽  
Reflective Spectroscopy

The purpose of this work was to investigate the detection of the pesticide residual (profenofos) in tomatoes by using visible/near-infrared spectroscopy. Therefore, the experiments were performed on 180 tomato samples with different percentages of profenofos pesticide (higher and lower values than the maximum residual limit (MRL)) as compared to the control (no pesticide). VIS/near infrared (NIR) spectral data from pesticide solution and non-pesticide tomato samples (used as control treatment) impregnated with different concentrations of pesticide in the range of 400 to 1050 nm were recorded by a spectrometer. For classification of tomatoes with pesticide content at lower and higher levels of MRL as healthy and unhealthy samples, we used different spectral pre-processing methods with partial least squares discriminant analysis (PLS-DA) models. The Smoothing Moving Average pre-processing method with the standard error of cross validation (SECV) = 4.2767 was selected as the best model for this study. In addition, in the calibration and prediction sets, the percentages of total correctly classified samples were 90 and 91.66%, respectively. Therefore, it can be concluded that reflective spectroscopy (VIS/NIR) can be used as a non-destructive, low-cost, and rapid technique to control the health of tomatoes impregnated with profenofos pesticide.

scholarly journals Early Detection of Plant Viral Disease Using Hyperspectral Imaging and Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 742
Author(s):  
Canh Nguyen ◽  
Vasit Sagan ◽  
Matthew Maimaitiyiming ◽  
Maitiniyazi Maimaitijiang ◽  
Sourav Bhadra ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Early Detection ◽  
Convolutional Neural Network ◽  
Near Infrared ◽  
Hyperspectral Data ◽  
Viral Diseases ◽  
Support Vector ◽  
Spectral Features ◽  
Feature Spaces

Early detection of grapevine viral diseases is critical for early interventions in order to prevent the disease from spreading to the entire vineyard. Hyperspectral remote sensing can potentially detect and quantify viral diseases in a nondestructive manner. This study utilized hyperspectral imagery at the plant level to identify and classify grapevines inoculated with the newly discovered DNA virus grapevine vein-clearing virus (GVCV) at the early asymptomatic stages. An experiment was set up at a test site at South Farm Research Center, Columbia, MO, USA (38.92 N, −92.28 W), with two grapevine groups, namely healthy and GVCV-infected, while other conditions were controlled. Images of each vine were captured by a SPECIM IQ 400–1000 nm hyperspectral sensor (Oulu, Finland). Hyperspectral images were calibrated and preprocessed to retain only grapevine pixels. A statistical approach was employed to discriminate two reflectance spectra patterns between healthy and GVCV vines. Disease-centric vegetation indices (VIs) were established and explored in terms of their importance to the classification power. Pixel-wise (spectral features) classification was performed in parallel with image-wise (joint spatial–spectral features) classification within a framework involving deep learning architectures and traditional machine learning. The results showed that: (1) the discriminative wavelength regions included the 900–940 nm range in the near-infrared (NIR) region in vines 30 days after sowing (DAS) and the entire visual (VIS) region of 400–700 nm in vines 90 DAS; (2) the normalized pheophytization index (NPQI), fluorescence ratio index 1 (FRI1), plant senescence reflectance index (PSRI), anthocyanin index (AntGitelson), and water stress and canopy temperature (WSCT) measures were the most discriminative indices; (3) the support vector machine (SVM) was effective in VI-wise classification with smaller feature spaces, while the RF classifier performed better in pixel-wise and image-wise classification with larger feature spaces; and (4) the automated 3D convolutional neural network (3D-CNN) feature extractor provided promising results over the 2D convolutional neural network (2D-CNN) in learning features from hyperspectral data cubes with a limited number of samples.

Non-destructive analysis the dating of paper based on convolutional neural network

2021 ◽  
Vol 248 ◽  
pp. 119290
Author(s):  
Jingjing Xia ◽  
Xiayu Du ◽  
Weixin Xu ◽  
Yun Wei ◽  
Yanmei Xiong ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Destructive Analysis ◽  
Non Destructive

scholarly journals Spectral Convolution Feature-Based SPD Matrix Representation for Signal Detection Using a Deep Neural Network

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 949
Author(s):  
Jiangyi Wang ◽  
Min Liu ◽  
Xinwu Zeng ◽  
Xiaoqiang Hua
Keyword(s):  
Neural Network ◽  
Signal Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Network ◽  
Detection Method ◽  
Learning Algorithm ◽  
Simulated Data ◽  
Data Sets ◽  
Feature Maps ◽  
Simulated Data Sets

Convolutional neural networks have powerful performances in many visual tasks because of their hierarchical structures and powerful feature extraction capabilities. SPD (symmetric positive definition) matrix is paid attention to in visual classification, because it has excellent ability to learn proper statistical representation and distinguish samples with different information. In this paper, a deep neural network signal detection method based on spectral convolution features is proposed. In this method, local features extracted from convolutional neural network are used to construct the SPD matrix, and a deep learning algorithm for the SPD matrix is used to detect target signals. Feature maps extracted by two kinds of convolutional neural network models are applied in this study. Based on this method, signal detection has become a binary classification problem of signals in samples. In order to prove the availability and superiority of this method, simulated and semi-physical simulated data sets are used. The results show that, under low SCR (signal-to-clutter ratio), compared with the spectral signal detection method based on the deep neural network, this method can obtain a gain of 0.5–2 dB on simulated data sets and semi-physical simulated data sets.

scholarly journals Using a One-Dimensional Convolutional Neural Network on Visible and Near-Infrared Spectroscopy to Improve Soil Phosphorus Prediction in Madagascar

2021 ◽  
Vol 13 (8) ◽  
pp. 1519
Author(s):  
Kensuke Kawamura ◽  
Tomohiro Nishigaki ◽  
Andry Andriamananjara ◽  
Hobimiarantsoa Rakotonindrina ◽  
Yasuhiro Tsujimoto ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Near Infrared ◽  
Soil Phosphorus ◽  
Predictive Ability ◽  
Available P ◽  
Accurate Estimation ◽  
One Dimensional ◽  
P Content ◽  
Soil Available P

As a proximal soil sensing technique, laboratory visible and near-infrared (Vis-NIR) spectroscopy is a promising tool for the quantitative estimation of soil properties. However, there remain challenges for predicting soil phosphorus (P) content and availability, which requires a reliable model applicable for different land-use systems to upscale. Recently, a one-dimensional convolutional neural network (1D-CNN) corresponding to the spectral information of soil was developed to considerably improve the accuracy of soil property predictions. The present study investigated the predictive ability of a 1D-CNN model to estimate soil available P (oxalate-extractable P; Pox) content in soils by comparing it with partial least squares (PLS) and random forest (RF) regressions using soil samples (n = 318) collected from natural (forest and non-forest) and cultivated (upland and flooded rice fields) systems in Madagascar. Overall, the 1D-CNN model showed the best predictive accuracy (R2 = 0.878) with a highly accurate prediction ability (ratio of performance to the interquartile range = 2.492). Compared to the PLS model, the RF and 1D-CNN models indicated 4.37% and 23.77% relative improvement in root mean squared error values, respectively. Based on a sensitivity analysis, the important wavebands for predicting soil Pox were associated with iron (Fe) oxide, organic matter (OM), and water absorption, which were previously known wavelength regions for estimating P in soil. These results suggest that 1D-CNN corresponding spectral signatures can be expected to significantly improve the predictive ability for estimating soil available P (Pox) from Vis-NIR spectral data. Rapid and accurate estimation of available P content in soils using our results can be expected to contribute to effective fertilizer management in agriculture and the sustainable management of ecosystems. However, the 1D-CNN model will require a large dataset to extend its applicability to other regions of Madagascar. Thus, further updates should be tested in future studies using larger datasets from a wide range of ecosystems in the tropics.

scholarly journals AlexNet convolutional neural network to classify the types of Indonesian coffee beans

2021 ◽  
Vol 905 (1) ◽  
pp. 012059
Author(s):  
Y Hendrawan ◽  
B Rohmatulloh ◽  
F I Ilmi ◽  
M R Fauzy ◽  
R Damayanti ◽  
...  
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Sensitivity Analysis ◽  
Convolutional Neural Network ◽  
Confusion Matrix ◽  
Learning Rate ◽  
Agricultural Products ◽  
Coffee Bean ◽  
Coffee Beans ◽  
Non Destructive

Abstract Various types of Indonesian coffee are already popular internationally. Recently, there are still not many methods to classify the types of typical Indonesian coffee. Computer vision is a non-destructive method for classifying agricultural products. This study aimed to classify three types of Indonesian Arabica coffee beans, i.e., Gayo Aceh, Kintamani Bali, and Toraja Tongkonan, using computer vision. The classification method used was the AlexNet convolutional neural network with sensitivity analysis using several variations of the optimizer such as SGDm, Adam, and RMSProp and the learning rate of 0.00005 and 0.0001. Each type of coffee used 500 data for training and validation with the distribution of 70% training and 30% validation. The results showed that all AlexNet models achieved a perfect validation accuracy value of 100% in 1,040 iterations. This study also used 100 testing-set data on each type of coffee bean. In the testing confusion matrix, the accuracy reached 99.6%.

scholarly journals AI INFLUENCE IN COVID-19 DETECTION

2021 ◽  
Vol 23 (07) ◽  
pp. 1116-1120
Author(s):  
Cijil Benny ◽  
Keyword(s):  
Neural Network ◽  
Statistical Analysis ◽  
Convolutional Neural Network ◽  
Case Reports ◽  
Ct Scans ◽  
Data Sets ◽  
X Rays ◽  
Medical Field ◽  
Primary Key ◽  
Made In

This paper is on analyzing the feasibility of AI studies and the involvement of AI in COVID interrelated treatments. In all, several procedures were reviewed and studied. It was on point. The best-analyzing methods on the studies were Susceptible Infected Recovered and Susceptible Exposed Infected Removed respectively. Whereas the implementation of AI is mostly done in X-rays and CT- Scans with the help of a Convolutional Neural Network. To accomplish the paper several data sets are used. They include medical and case reports, medical strategies, and persons respectively. Approaches are being done through shared statistical analysis based on these reports. Considerably the acceptance COVID is being shared and it is also reachable. Furthermore, much regulation is needed for handling this pandemic since it is a threat to global society. And many more discoveries shall be made in the medical field that uses AI as a primary key source.

Focusing near Infrared Spectroscopy on the Business Objectives of Modern Pharmaceutical Production

1998 ◽  
Vol 6 (A) ◽  
pp. A13-A19 ◽  
Author(s):  
T.G. Axon ◽  
R. Brown ◽  
S.V. Hammond ◽  
S.J. Maris ◽  
F. Ting
Keyword(s):  
High Performance ◽  
Near Infrared ◽  
Real Life ◽  
Nir Spectroscopy ◽  
Raw Material ◽  
Develop Model ◽  
Data Sets ◽  
Total Quality ◽  
Model Free ◽  
Pharmaceutical Production

The early use of near infrared (NIR) spectroscopy in the pharmaceutical industry was for raw material identification, later moving on to some conventional “calibrations” for various ingredients in a variety of sample types. The approach throughout this development process has always been “conventional” with one measurement by NIR directly replacing some other slower method, be it Mid-IR identification, or determinations by Karl Fischer, high performance liquid chromatography (HPLC)etc. A significant change in approach was demonstrated by Plugge and Van der Vlies1 in 1993, where a qualitative system was used to provide “quantitative like” answers for potency of a drug substance. Following on from that key paper, there has been a realisation that the qualitative analysis ability of NIR, has the potential to be a powerful tool for process investigation, control and validation. The final step has been to develop “model free” approaches, that consider individual data sets as unique systems, and present the opportunity for NIR to escape the shackles of “calibration” in one form or another. The use of qualitative, or model free, approaches to NIR spectroscopy provides an effective tool for satisfying many of the demands of modern pharmaceutical production. “Straight through production,” “right first time,” “short cycle time” and “total quality management” philosophies can be realised. Eventually the prospect of parametric release may be materialised with a strong contribution from NIR spectroscopy. This paper will illustrate the above points with some real life examles.

Prediction of Stilbene Content from Heartwood Increment Cores of Scots Pine Using near Infrared Spectroscopy Methodology

2016 ◽  
Vol 24 (6) ◽  
pp. 517-528 ◽  
Author(s):  
Susanna Pulkka ◽  
Vincent Segura ◽  
Anni Harju ◽  
Tarja Tapanila ◽  
Johanna Tanner ◽  
...  
Keyword(s):  
Scots Pine ◽  
High Throughput ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Tree Breeding ◽  
Decay Resistance ◽  
Increment Core ◽  
Automatic Selection ◽  
Non Destructive ◽  
Selection Of

High-throughput and non-destructive methods for quantifying the content of the stilbene compounds of Scots pine ( Pinus sylvestris L.) heartwood are needed in the breeding for decay resistance of heartwood timber. In this study, near infrared (NIR) spectroscopy calibrations were developed for a large collection of solid heartwood increment core samples in order to predict the amount of the stilbene pinosylvin (PS), its monomethyl ether (PSM) and their sum (STB). The resulting models presented quite accurate predictions in an independent validation set with R2V values ranging between 0.79 and 0.91. The accuracy of the models strongly depended on the chemical being calibrated, with the lowest accuracy for PS, intermediate accuracy for PSM and highest accuracy for STB. The effect of collecting one, two or more (up to five) spectra per sample on the calibration models was studied and it was found that averaging multiple spectra yielded better accuracy as it may account for the heterogeneity of wood along the increment core within and between rings. Several statistical pretreatments of the spectra were tested and an automatic selection of wavenumbers prior to calibration. Without the automatic selection of wavenumbers, a first derivative of normalised spectra yielded the best accuracies, whereas after the automatic selection of wavenumbers, no particular statistical pretreatment appeared to yield better results than any other. Finally, the automatic selection of wavenumbers slightly improved the accuracy of the models for all traits. These results demonstrate the potential of NIR spectroscopy as a high-throughput and non-destructive phenotyping technique in tree breeding for the improvement of decay resistance in heartwood timber.

Sign in / Sign up

Export Citation Format

Share Document