scholarly journals Application of Hyperspectral Imaging and Deep Learning for Robust Prediction of Sugar and pH Levels in Wine Grape Berries

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3459
Author(s):  
Véronique Gomes ◽  
Ana Mendes-Ferreira ◽  
Pedro Melo-Pinto
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Hyperspectral Imaging ◽  
Network Architecture ◽  
Sugar Content ◽  
Hyperspectral Data ◽  
Machine Learning Algorithms ◽  
Wine Grape ◽  
Sensing Technology ◽  
Test Sets

Remote sensing technology, such as hyperspectral imaging, in combination with machine learning algorithms, has emerged as a viable tool for rapid and nondestructive assessment of wine grape ripeness. However, the differences in terroir, together with the climatic variations and the variability exhibited by different grape varieties, have a considerable impact on the grape ripening stages within a vintage and between vintages and, consequently, on the robustness of the predictive models. To address this challenge, we present a novel one-dimensional convolutional neural network architecture-based model for the prediction of sugar content and pH, using reflectance hyperspectral data from different vintages. We aimed to evaluate the model’s generalization capacity for different varieties and for a different vintage not employed in the training process, using independent test sets. A transfer learning mechanism, based on the proposed convolutional neural network, was also used to evaluate improvements in the model’s generalization. Overall, the results for generalization ability showed a very good performance with RMSEP values of 1.118 °Brix and 1.085 °Brix for sugar content and 0.199 and 0.183 for pH, for test sets using different varieties and a different vintage, respectively, improving and updating the current state of the art.

scholarly journals Prediction of Sugar Content in Port Wine Vintage Grapes Using Machine Learning and Hyperspectral Imaging

Processes ◽  
2021 ◽  
Vol 9 (7) ◽  
pp. 1241
Author(s):  
Véronique Gomes ◽  
Marco S. Reis ◽  
Francisco Rovira-Más ◽  
Ana Mendes-Ferreira ◽  
Pedro Melo-Pinto
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Hyperspectral Imaging ◽  
Sugar Content ◽  
Hyperspectral Data ◽  
Machine Learning Algorithms ◽  
Port Wine ◽  
Monitoring And Control ◽  
High Quality ◽  
Harvesting Stage

The high quality of Port wine is the result of a sequence of winemaking operations, such as harvesting, maceration, fermentation, extraction and aging. These stages require proper monitoring and control, in order to consistently achieve the desired wine properties. The present work focuses on the harvesting stage, where the sugar content of grapes plays a key role as one of the critical maturity parameters. Our approach makes use of hyperspectral imaging technology to rapidly extract information from wine grape berries; the collected spectra are fed to machine learning algorithms that produce estimates of the sugar level. A consistent predictive capability is important for establishing the harvest date, as well as to select the best grapes to produce specific high-quality wines. We compared four different machine learning methods (including deep learning), assessing their generalization capacity for different vintages and varieties not included in the training process. Ridge regression, partial least squares, neural networks and convolutional neural networks were the methods considered to conduct this comparison. The results show that the estimated models can successfully predict the sugar content from hyperspectral data, with the convolutional neural network outperforming the other methods.

scholarly journals Blood Stain Classification with Hyperspectral Imaging and Deep Neural Networks

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6666
Author(s):  
Kamil Książek ◽  
Michał Romaszewski ◽  
Przemysław Głomb ◽  
Bartosz Grabowski ◽  
Michał Cholewa
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Hyperspectral Imaging ◽  
Network Architecture ◽  
Confusion Matrix ◽  
Hyperspectral Data ◽  
Matrix Analysis ◽  
Support Vector ◽  
Test Set

In recent years, growing interest in deep learning neural networks has raised a question on how they can be used for effective processing of high-dimensional datasets produced by hyperspectral imaging (HSI). HSI, traditionally viewed as being within the scope of remote sensing, is used in non-invasive substance classification. One of the areas of potential application is forensic science, where substance classification on the scenes is important. An example problem from that area—blood stain classification—is a case study for the evaluation of methods that process hyperspectral data. To investigate the deep learning classification performance for this problem we have performed experiments on a dataset which has not been previously tested using this kind of model. This dataset consists of several images with blood and blood-like substances like ketchup, tomato concentrate, artificial blood, etc. To test both the classic approach to hyperspectral classification and a more realistic application-oriented scenario, we have prepared two different sets of experiments. In the first one, Hyperspectral Transductive Classification (HTC), both a training and a test set come from the same image. In the second one, Hyperspectral Inductive Classification (HIC), a test set is derived from a different image, which is more challenging for classifiers but more useful from the point of view of forensic investigators. We conducted the study using several architectures like 1D, 2D and 3D convolutional neural networks (CNN), a recurrent neural network (RNN) and a multilayer perceptron (MLP). The performance of the models was compared with baseline results of Support Vector Machine (SVM). We have also presented a model evaluation method based on t-SNE and confusion matrix analysis that allows us to detect and eliminate some cases of model undertraining. Our results show that in the transductive case, all models, including the MLP and the SVM, have comparative performance, with no clear advantage of deep learning models. The Overall Accuracy range across all models is 98–100% for the easier image set, and 74–94% for the more difficult one. However, in a more challenging inductive case, selected deep learning architectures offer a significant advantage; their best Overall Accuracy is in the range of 57–71%, improving the baseline set by the non-deep models by up to 9 percentage points. We have presented a detailed analysis of results and a discussion, including a summary of conclusions for each tested architecture. An analysis of per-class errors shows that the score for each class is highly model-dependent. Considering this and the fact that the best performing models come from two different architecture families (3D CNN and RNN), our results suggest that tailoring the deep neural network architecture to hyperspectral data is still an open problem.

scholarly journals A Novel Multi Hidden Layer Convolutional Neural Network for Content Based Image Retrieval

2020 ◽  
Vol 9 (3) ◽  
pp. 365-370
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Retrieval ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Content Based Image Retrieval ◽  
Neural Network Architecture ◽  
Query Image

The applications of a content-based image retrieval system in fields such as multimedia, security, medicine, and entertainment, have been implemented on a huge real-time database by using a convolutional neural network architecture. In general, thus far, content-based image retrieval systems have been implemented with machine learning algorithms. A machine learning algorithm is applicable to a limited database because of the few feature extraction hidden layers between the input and the output layers. The proposed convolutional neural network architecture was successfully implemented using 128 convolutional layers, pooling layers, rectifier linear unit (ReLu), and fully connected layers. A convolutional neural network architecture yields better results of its ability to extract features from an image. The Euclidean distance metric is used for calculating the similarity between the query image and the database images. It is implemented using the COREL database. The proposed system is successfully evaluated using precision, recall, and F-score. The performance of the proposed method is evaluated using the precision and recall.

scholarly journals Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network

2020 ◽  
Vol 50 (3) ◽  
Author(s):  
Wang Xiaoyan ◽  
Li Zhiwei ◽  
Wang Wenjun ◽  
Wang Jiawei
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Least Squares ◽  
Chlorophyll Content ◽  
Hyperspectral Imaging ◽  
Vegetation Index ◽  
Characteristic Parameter ◽  
Hyperspectral Data ◽  
Growth And Yield ◽  
Support Vector

ABSTRACT: Chlorophyll is a major factor affecting photosynthesis; and consequently, crop growth and yield. In this study, we devised a chlorophyll-content detection model for millet leaves in different stages of growth based on hyperspectral data. The hyperspectral images of millet leaves were obtained under a wavelength range of 380-1000 nm using a hyperspectral imager. Threshold segmentation was performed with near-infrared (NIR) reflectance and normalized difference vegetation index (NDVI) to intelligently acquire the regions of interest (ROI). Furthermore, raw spectral data were preprocessed using multivariate scatter correction (MSC). A correlation coefficient-successive projections algorithm (CC-SPA) was used to extract the characteristic wavelengths, and the characteristic parameters were extracted based on the spectral and image information. A partial least squares regression (PLSR) prediction model was established based on the single characteristic parameter and multi-characteristic parameter fusion. The determination coefficient (Rv 2) and the root-mean-square error (RMSEv) of the validation set for the multi-characteristic parameter fusion model were reported to be 0.813 and 1.766, respectively, which are higher than those obtained by the single characteristic parameter model. Based on the multi-characteristic parameter fusion, an attention-convolutional neural network (attention-CNN) (Rv 2 = 0.839, RMSEv = 1.451, RPD = 2.355) was established, which is more effective than the PLSR (Rv 2 = 0.813, RMSEv = 1.766, RPD = 2.167) and least squares support vector machine (LS-SVM) models (Rv 2 = 0.806, RMSEv = 1.576, RPD = 2.061). These results indicated that the combination of hyperspectral imaging and attention-CNN is beneficial to the application of nutrient element monitoring of crops.

scholarly journals Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4065 ◽  
Author(s):  
Zhu ◽  
Zhou ◽  
Zhang ◽  
Bao ◽  
Wu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Hyperspectral Imaging ◽  
Stress Resistance ◽  
Classification Accuracy ◽  
Near Infrared ◽  
Majority Vote ◽  
Hyperspectral Data ◽  
Soybean Variety

Soybean variety is connected to stress resistance ability, as well as nutritional and commercial value. Near-infrared hyperspectral imaging was applied to classify three varieties of soybeans (Zhonghuang37, Zhonghuang41, and Zhonghuang55). Pixel-wise spectra were extracted and preprocessed, and average spectra were also obtained. Convolutional neural networks (CNN) using the average spectra and pixel-wise spectra of different numbers of soybeans were built. Pixel-wise CNN models obtained good performance predicting pixel-wise spectra and average spectra. With the increase of soybean numbers, performances were improved, with the classification accuracy of each variety over 90%. Traditionally, the number of samples used for modeling is large. It is time-consuming and requires labor to obtain hyperspectral data from large batches of samples. To explore the possibility of achieving decent identification results with few samples, a majority vote was also applied to the pixel-wise CNN models to identify a single soybean variety. Prediction maps were obtained to present the classification results intuitively. Models using pixel-wise spectra of 60 soybeans showed equivalent performance to those using the average spectra of 810 soybeans, illustrating the possibility of discriminating soybean varieties using few samples by acquiring pixel-wise spectra.

Visual Speech Recognition using VGG16 Convolutional Neural Network

2021 ◽  
Author(s):  
Shashidhar R ◽  
S Patilkulkarni ◽  
Nishanth S Murthy
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Convolutional Neural Network ◽  
Hearing Impairment ◽  
Network Architecture ◽  
Research Work ◽  
Machine Learning Algorithms ◽  
Visual Speech ◽  
Neural Network Architecture ◽  
Visual Speech Recognition

Abstract Communication is all about expressing one’s thoughts to another person through speech and facial expressions. But for people with hearing impairment, it is difficult to communicate without any assistance. In most of these cases Visual speech recognition (VSR) systems simplify the tasks by using Machine Learning algorithms and assisting them to understand speech and socialize without depending on the auditory perception. Thus, one can visualize VSR system as a lifeline for people with hearing impairment which helps them in providing a way to understand the words that are being tried to convey to them through speech. In this work we used VGG16 convolutional neural network architecture for Kannada and English datasets. We used custom dataset for the research work and got the accuracy of 90.10% for English database and 91.90% for Kannada database.

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

2020 ◽  
Vol 2020 (10) ◽  
pp. 181-1-181-7
Author(s):  
Takahiro Kudo ◽  
Takanori Fujisawa ◽  
Takuro Yamaguchi ◽  
Masaaki Ikehara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Blind Deconvolution ◽  
Training Dataset ◽  
Image Deconvolution ◽  
Classic Problem ◽  
Key Points ◽  
Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

scholarly journals Data-Driven Stability Assessment of Multilayer Long Short-Term Memory Networks

2021 ◽  
Vol 11 (4) ◽  
pp. 1829
Author(s):  
Davide Grande ◽  
Catherine A. Harris ◽  
Giles Thomas ◽  
Enrico Anderlini
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Short Term Memory ◽  
Moving Average ◽  
Machine Learning Algorithms ◽  
Physical Models ◽  
Data Driven ◽  
The Stability ◽  
And Control ◽  
Nonlinear Autoregressive

Recurrent Neural Networks (RNNs) are increasingly being used for model identification, forecasting and control. When identifying physical models with unknown mathematical knowledge of the system, Nonlinear AutoRegressive models with eXogenous inputs (NARX) or Nonlinear AutoRegressive Moving-Average models with eXogenous inputs (NARMAX) methods are typically used. In the context of data-driven control, machine learning algorithms are proven to have comparable performances to advanced control techniques, but lack the properties of the traditional stability theory. This paper illustrates a method to prove a posteriori the stability of a generic neural network, showing its application to the state-of-the-art RNN architecture. The presented method relies on identifying the poles associated with the network designed starting from the input/output data. Providing a framework to guarantee the stability of any neural network architecture combined with the generalisability properties and applicability to different fields can significantly broaden their use in dynamic systems modelling and control.

Sign in / Sign up

Export Citation Format

Share Document