scholarly journals Prediction of Coating Adhesion on Laser-Cleaned Metal Surfaces of Battery Cells Using Hyperspectral Imaging and Machine Learning

Coatings ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 1388
Author(s):  
Johannes Maximilian Vater ◽  
Florian Gruber ◽  
Wulf Grählert ◽  
Sebastian Schneider ◽  
Alois Christian Knoll
Keyword(s):  
Machine Learning ◽  
Quality Control ◽  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Support Vector ◽  
Electromagnetic Spectrum ◽  
Coating Adhesion ◽  
Cell Coating ◽  
The Cross ◽  
Battery Cells

Electric vehicles are shaping the future of the automotive industry. The traction battery is one of the most important components of electric cars. To ensure that the battery operates safely, it is essential to physically and electrically separate the cells facing each other. Coating a cell with varnish helps achieve this goal. Current studies use a destructive method on a sampling basis, the cross-cut test, to investigate the coating quality. In this paper, we present a fast, nondestructive and inline alternative based on hyperspectral imaging and artificial intelligence. Therefore, battery cells are measured with hyperspectral cameras in the visible and near-infrared (VNIR and NIR) parts of the electromagnetic spectrum before and after cleaning then coated and finally subjected to cross-cut test to estimate coating adhesion. During the cross-cut test, the cell coating is destroyed. This work aims to replace cross-cut tests with hyperspectral imaging (HSI) and machine learning to achieve continuous quality control, protect the environment, and save costs. Therefore, machine learning models (logistic regression, random forest, and support vector machines) are used to predict cross-cut test results based on hyperspectral data. We show that it is possible to predict with an accuracy of ~75% whether problems with coating adhesion will occur. Hyperspectral measurements in the near-infrared part of the spectrum yielded the best results. The results show that the method is suitable for automated quality control and process control in battery cell coating, but still needs to be improved to achieve higher accuracies.

scholarly journals Distinction of surgically resected gastrointestinal stromal tumor by near-infrared hyperspectral imaging

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Daiki Sato ◽  
Toshihiro Takamatsu ◽  
Masakazu Umezawa ◽  
Yuichi Kitagawa ◽  
Kosuke Maeda ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gastrointestinal Stromal Tumor ◽  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Submucosal Tumor ◽  
Stromal Tumor ◽  
Training Data ◽  
Support Vector ◽  
Gastric Gist ◽  
Mucosal Layer

AbstractThe diagnosis of gastrointestinal stromal tumor (GIST) using conventional endoscopy is difficult because submucosal tumor (SMT) lesions like GIST are covered by a mucosal layer. Near-infrared hyperspectral imaging (NIR-HSI) can obtain optical information from deep inside tissues. However, far less progress has been made in the development of techniques for distinguishing deep lesions like GIST. This study aimed to investigate whether NIR-HSI is suitable for distinguishing deep SMT lesions. In this study, 12 gastric GIST lesions were surgically resected and imaged with an NIR hyperspectral camera from the aspect of the mucosal surface. Thus, the images were obtained ex-vivo. The site of the GIST was defined by a pathologist using the NIR image to prepare training data for normal and GIST regions. A machine learning algorithm, support vector machine, was then used to predict normal and GIST regions. Results were displayed using color-coded regions. Although 7 specimens had a mucosal layer (thickness 0.4–2.5 mm) covering the GIST lesion, NIR-HSI analysis by machine learning showed normal and GIST regions as color-coded areas. The specificity, sensitivity, and accuracy of the results were 73.0%, 91.3%, and 86.1%, respectively. The study suggests that NIR-HSI analysis may potentially help distinguish deep lesions.

scholarly journals Application of Near-Infrared Hyperspectral Imaging with Machine Learning Methods to Identify Geographical Origins of Dry Narrow-Leaved Oleaster (Elaeagnus angustifolia) Fruits

Foods ◽  
2019 ◽  
Vol 8 (12) ◽  
pp. 620 ◽  
Author(s):  
Pan Gao ◽  
Wei Xu ◽  
Tianying Yan ◽  
Chu Zhang ◽  
Xin Lv ◽  
...  
Keyword(s):  
Machine Learning ◽  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Support Vector ◽  
Elaeagnus Angustifolia ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Discriminant Models ◽  
Second Derivative Spectra ◽  
Origin Identification

Narrow-leaved oleaster (Elaeagnus angustifolia) fruit is a kind of natural product used as food and traditional medicine. Narrow-leaved oleaster fruits from different geographical origins vary in chemical and physical properties and differ in their nutritional and commercial values. In this study, near-infrared hyperspectral imaging covering the spectral range of 874–1734 nm was used to identify the geographical origins of dry narrow-leaved oleaster fruits with machine learning methods. Average spectra of each single narrow-leaved oleaster fruit were extracted. Second derivative spectra were used to identify effective wavelengths. Partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) were used to build discriminant models for geographical origin identification using full spectra and effective wavelengths. In addition, deep convolutional neural network (CNN) models were built using full spectra and effective wavelengths. Good classification performances were obtained by these three models using full spectra and effective wavelengths, with classification accuracy of the calibration, validation, and prediction set all over 90%. Models using effective wavelengths obtained close results to models using full spectra. The performances of the PLS-DA, SVM, and CNN models were close. The overall results illustrated that near-infrared hyperspectral imaging coupled with machine learning could be used to trace geographical origins of dry narrow-leaved oleaster fruits.

scholarly journals Supervised Machine Learning Methods and Hyperspectral Imaging Techniques Jointly Applied for Brain Cancer Classification

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3827
Author(s):  
Gemma Urbanos ◽  
Alberto Martín ◽  
Guillermo Vázquez ◽  
Marta Villanueva ◽  
Manuel Villa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Blood Vessel ◽  
Hyperspectral Imaging ◽  
Imaging Techniques ◽  
Venous Blood ◽  
Healthy Tissue ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Arterial Blood

Hyperspectral imaging techniques (HSI) do not require contact with patients and are non-ionizing as well as non-invasive. As a consequence, they have been extensively applied in the medical field. HSI is being combined with machine learning (ML) processes to obtain models to assist in diagnosis. In particular, the combination of these techniques has proven to be a reliable aid in the differentiation of healthy and tumor tissue during brain tumor surgery. ML algorithms such as support vector machine (SVM), random forest (RF) and convolutional neural networks (CNN) are used to make predictions and provide in-vivo visualizations that may assist neurosurgeons in being more precise, hence reducing damages to healthy tissue. In this work, thirteen in-vivo hyperspectral images from twelve different patients with high-grade gliomas (grade III and IV) have been selected to train SVM, RF and CNN classifiers. Five different classes have been defined during the experiments: healthy tissue, tumor, venous blood vessel, arterial blood vessel and dura mater. Overall accuracy (OACC) results vary from 60% to 95% depending on the training conditions. Finally, as far as the contribution of each band to the OACC is concerned, the results obtained in this work are 3.81 times greater than those reported in the literature.

scholarly journals Identification of peat type and humification by laboratory VNIR/SWIR hyperspectral imaging of peat profiles with focus on fen-bog transition in aapa mires

2020 ◽  
Author(s):  
L. Granlund ◽  
M. Keinänen ◽  
T. Tahvanainen
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Support Vector ◽  
High Resolution Imaging ◽  
Factors Affecting ◽  
Vector Machines ◽  
Resolution Imaging ◽  
Shortwave Infrared ◽  
Type Classification ◽  
Wide Potential

Abstract Aims Hyperspectral imaging (HSI) has high potential for analysing peat cores, but methodologies are deficient. We aimed for robust peat type classification and humification estimation. We also explored other factors affecting peat spectral properties. Methods We used two laboratory setups: VNIR (visible to near-infrared) and SWIR (shortwave infrared) for high resolution imaging of intact peat profiles with fen-bog transitions. Peat types were classified with support vector machines, indices were developed for von Post estimation, and K-means clustering was used to analyse stratigraphic patterns in peat quality. With separate experiments, we studied spectral effects of drying and oxidation. Results Despite major effects, oxidation and water content did not impede robust HSI classification. The accuracy between Carex peat and Sphagnum peat in validation was 80% with VNIR and 81% with SWIR data. The spectral humification indices had accuracies of 82% with VNIR and 56%. Stratigraphic HSI patterns revealed that 36% of peat layer shifts were inclined by over 20 degrees. Spectral indices were used to extrapolate visualisations of element concentrations. Conclusions HSI provided reliable information of basic peat quality and was useful in visual mapping, that can guide sampling for other analyses. HSI can manage large amounts of samples to widen the scope of detailed analysis beyond single profiles and it has wide potential in peat research beyond the exploratory scope of this paper. We were able to confirm the capacity of HSI to reveal shifts of peat quality, connected to ecosystem-scale change.

scholarly journals Machine learning enables discovery of DNA-carbon nanotube sensors for serotonin

2021 ◽  
Author(s):  
Payam Kelich ◽  
Sanghwa Jeong ◽  
Nicole Navarro ◽  
Jaquesta Adams ◽  
Xiaoqi Sun ◽  
...  
Keyword(s):  
Machine Learning ◽  
Carbon Nanotube ◽  
Dna Sequences ◽  
Regression Models ◽  
Near Infrared ◽  
Optical Response ◽  
Support Vector ◽  
Single Walled Carbon Nanotube ◽  
Nir Fluorescence ◽  
Selective Evolution

AbstractDNA-wrapped single walled carbon nanotube (SWNT) conjugates have remarkable optical properties leading to their use in biosensing and imaging applications. A critical limitation in the development of DNA-SWNT sensors is the current inability to predict unique DNA sequences that confer a strong analyte-specific optical response to these sensors. Here, near-infrared (nIR) fluorescence response datasets for ~100 DNA-SWNT conjugates, narrowed down by a selective evolution protocol starting from a pool of ~1010 unique DNA-SWNT candidates, are used to train machine learning (ML) models to predict new unique DNA sequences with strong optical response to neurotransmitter serotonin. First, classifier models based on convolutional neural networks (CNN) are trained on sequence features to classify DNA ligands as either high response or low response to serotonin. Second, support vector machine (SVM) regression models are trained to predict relative optical response values for DNA sequences. Finally, we demonstrate with validation experiments that integrating the predictions of ensembles of the highest quality CNN classifiers and SVM regression models leads to the best predictions of both high and low response sequences. With our ML approaches, we discovered five new DNA-SWNT sensors with higher fluorescence intensity response to serotonin than obtained previously. Overall, the explored ML approaches introduce an important new tool to predict useful DNA sequences, which can be used for discovery of new DNA-based sensors and nanobiotechnologies.

scholarly journals Image and Point Data Fusion for Enhanced Discrimination of Ore and Waste in Mining

Minerals ◽  
2020 ◽  
Vol 10 (12) ◽  
pp. 1110
Author(s):  
Feven Desta ◽  
Mike Buxton
Keyword(s):  
Near Infrared ◽  
Methodological Approach ◽  
Relevant Information ◽  
Waste Materials ◽  
Support Vector ◽  
Electromagnetic Spectrum ◽  
Sulphide Deposit ◽  
Data Volume ◽  
Point Data

Sensor technologies provide relevant information on the key geological attributes in mining. The integration of data from multiple sources is advantageous in making use of the synergy among the outputs for the enhanced characterisation of materials. Sensors produce various types of data. Thus, the fusion of these data requires innovative data-driven strategies. In the present study, the fusion of image and point data is proposed, aiming for the enhanced classification of ore and waste materials in a polymetallic sulphide deposit at 3%, 5% and 7% cut-off grades. The image data were acquired in the visible-near infrared (VNIR) and short-wave infrared (SWIR) regions of the electromagnetic spectrum. The point data cover the mid-wave infrared (MWIR) and long-wave infrared (LWIR) spectral regions. A multi-step methodological approach was developed for the fusion of the image and point data at multiple levels using the supervised and unsupervised classification techniques. Several possible combinations of the data blocks were evaluated to select the optimal combinations in an optimised way. The obtained results indicate that the individual image and point techniques resulted in a successful classification of ore and waste materials. However, the classification performance greatly improved with the fusion of image and point data, where the K-means and support vector classification (SVC) models provided acceptable results. The proposed approach enables a significant reduction in data volume while maintaining the relevant information in the spectra. This is principally beneficial for the integration of data from high-throughput and large data volume sources. Thus, the effectiveness and practicality of the approach can permit the enhanced separation of ore and waste materials in operational mines.

scholarly journals Most Relevant Spectral Bands Identification for Brain Cancer Detection Using Hyperspectral Imaging

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5481 ◽  
Author(s):  
Beatriz Martinez ◽  
Raquel Leon ◽  
Himar Fabelo ◽  
Samuel Ortega ◽  
Juan F. Piñeiro ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Brain Cancer ◽  
Near Infrared ◽  
Relevant Information ◽  
Support Vector ◽  
Algorithm Optimization ◽  
Spectral Bands ◽  
Tumor Identification ◽  
Spectral Ranges

Hyperspectral imaging (HSI) is a non-ionizing and non-contact imaging technique capable of obtaining more information than conventional RGB (red green blue) imaging. In the medical field, HSI has commonly been investigated due to its great potential for diagnostic and surgical guidance purposes. However, the large amount of information provided by HSI normally contains redundant or non-relevant information, and it is extremely important to identify the most relevant wavelengths for a certain application in order to improve the accuracy of the predictions and reduce the execution time of the classification algorithm. Additionally, some wavelengths can contain noise and removing such bands can improve the classification stage. The work presented in this paper aims to identify such relevant spectral ranges in the visual-and-near-infrared (VNIR) region for an accurate detection of brain cancer using in vivo hyperspectral images. A methodology based on optimization algorithms has been proposed for this task, identifying the relevant wavelengths to achieve the best accuracy in the classification results obtained by a supervised classifier (support vector machines), and employing the lowest possible number of spectral bands. The results demonstrate that the proposed methodology based on the genetic algorithm optimization slightly improves the accuracy of the tumor identification in ~5%, using only 48 bands, with respect to the reference results obtained with 128 bands, offering the possibility of developing customized acquisition sensors that could provide real-time HS imaging. The most relevant spectral ranges found comprise between 440.5–465.96 nm, 498.71–509.62 nm, 556.91–575.1 nm, 593.29–615.12 nm, 636.94–666.05 nm, 698.79–731.53 nm and 884.32–902.51 nm.

scholarly journals Spatiotemporal Approaches for Quality Control and Error Correction of Atmospheric Data through Machine Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-12 ◽  
Author(s):  
Hye-Jin Kim ◽  
Sung Min Park ◽  
Byung Jin Choi ◽  
Seung-Hyun Moon ◽  
Yong-Hyuk Kim
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Quality Control ◽  
Mean Squared Error ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Weather Element ◽  
Applied Machine Learning ◽  
Squared Error ◽  
Atmospheric Data

We propose three quality control (QC) techniques using machine learning that depend on the type of input data used for training. These include QC based on time series of a single weather element, QC based on time series in conjunction with other weather elements, and QC using spatiotemporal characteristics. We performed machine learning-based QC on each weather element of atmospheric data, such as temperature, acquired from seven types of IoT sensors and applied machine learning algorithms, such as support vector regression, on data with errors to make meaningful estimates from them. By using the root mean squared error (RMSE), we evaluated the performance of the proposed techniques. As a result, the QC done in conjunction with other weather elements had 0.14% lower RMSE on average than QC conducted with only a single weather element. In the case of QC with spatiotemporal characteristic considerations, the QC done via training with AWS data showed performance with 17% lower RMSE than QC done with only raw data.

Sign in / Sign up

Export Citation Format

Share Document