Classifying NIR spectra of textile products with kernel methods

Langeron, Yves; Doussot, Michel; Hewson, David J.; Duchêne, Jacques

doi:10.1016/j.engappai.2006.07.001

Cited by 56 publications

(35 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SVM method proposed by Vapnik can simultaneously minimize estimation errors and model dimensions, has superior generalization and accurate prediction capabilities, and can prevent overfitting problems (Borin et al 2006;Durand et al 2007;Langeron et al 2007;Pierna et al 2004). During SVM model development, the determination of the optimal combination of C and g is greatly important in constructing high-performance regression models.…”

Section: Results Of Svm Modelmentioning

confidence: 99%

Prediction of dissolved oxygen concentration in hypoxic river systems using support vector machine: a case study of Wen-Rui Tang River, China

Shang

Dahlgren

et al. 2017

Environ Sci Pollut Res

View full text Add to dashboard Cite

Accurate quantification of dissolved oxygen (DO) is critically important for managing water resources and controlling pollution. Artificial intelligence (AI) models have been successfully applied for modeling DO content in aquatic ecosystems with limited data. However, the efficacy of these AI models in predicting DO levels in the hypoxic river systems having multiple pollution sources and complicated pollutants behaviors is unclear. Given this dilemma, we developed a promising AI model, known as support vector machine (SVM), to predict the DO concentration in a hypoxic river in southeastern China. Four different calibration models, specifically, multiple linear regression, back propagation neural network, general regression neural network, and SVM, were established, and their prediction accuracy was systemically investigated and compared. A total of 11 hydro-chemical variables were used as model inputs. These variables were measured bimonthly at eight sampling sites along the ruralsuburban-urban portion of Wen-Rui Tang River from 2004 to 2008. The performances of the established models were assessed through the mean square error (MSE), determination coefficient (R 2 ), and Nash-Sutcliffe (NS) model efficiency. The results indicated that the SVM model was superior to other models in predicting DO concentration in Wen-Rui Tang River. For SVM, the MSE, R 2 , and NS values for the testing subset were 0.9416 mg/L, 0.8646, and 0.8763, respectively. Sensitivity analysis showed that ammonium-nitrogen was the most significant input variable of the proposal SVM model. Overall, these results demonstrated that the proposed SVM model can efficiently predict water quality, especially for highly impaired and hypoxic river systems.

show abstract

Section: Results Of Svm Modelmentioning

confidence: 99%

Prediction of dissolved oxygen concentration in hypoxic river systems using support vector machine: a case study of Wen-Rui Tang River, China

Shang

Dahlgren

et al. 2017

Environ Sci Pollut Res

View full text Add to dashboard Cite

show abstract

“…target or non-target, respectively. To represent this optimization problem, a Lagrange function is used [6][7][8]:…”

Section: Support Vector Machinesmentioning

confidence: 99%

“…The kernel alignment method is employed to automatically and quickly obtain the value of d, that provides a learning machine with the best performance [8]. This method measures the similarity between the distance matrix obtained in the feature space of each data point with respect to the others and a target distance matrix containing the data labels.…”

Section: Kernel Alignmentmentioning

confidence: 99%

“…The presence of such traces can result in a significant reduction in the welding seam strength [2]. A LIBS set-up [4][5] has been used to obtain the spectral information of steel sheets with different degrees of protective coating removal, and these spectra have been discriminated and classified with an optimized SVM algorithm [6][7][8]. The following sections deal with the fundamentals of the spectral processing of LIBS spectra, SVM theory, experimental works performed at the laboratory, and a result discussion.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic classification of steel plates based on laser induced breakdown spectroscopy and support vector machines

et al. 2010

View full text Add to dashboard Cite

Welding processes are one of the most widely spread industrial activities, and their quality control is an important area of research. The presence of residual traces from the protective antioxidant coating, is a problematic issue since it causes a significant reduction in the welding seam strength. In this work, a solution based on a Laser Induced Breakdown Spectroscopy (LIBS) setup and a Support Vector Machines (SVMs) classifier to detect and discriminate antioxidant coating residues in the welding area without destroying the sample before the welding procedure is proposed. This system could be an interesting and fast tool to detect aluminium impurities.

show abstract

“…Zhao et al (2006) utilized NIR spectroscopy combined with SVM to identify green, black, and oolong teas. Langeron et al(2007) used SVM to classify NIR spectra of tissue samples. Acevedo et al(2007) discriminated wines according to their denomination of origin by ultraviolet (UV)-visible spectrophotometric techniques combined with SVM.…”

Section: Introductionmentioning

confidence: 99%

Use of near-infrared spectroscopy and least-squares support vector machine to determine quality change of tomato juice

Xie

2009

J. Zhejiang Univ. Sci. B

View full text Add to dashboard Cite

Near-infrared (NIR) transmittance spectroscopy combined with least-squares support vector machine (LS-SVM) was investigated to study the quality change of tomato juice during the storage. A total of 100 tomato juice samples were used. The spectrum of each tomato juice was collected twice: the first measurement was taken when the tomato juice was fresh and had not undergone any changes, and the second measurement was taken after a month. Principal component analysis (PCA) was used to examine a potential capability of separating juice before and after the storage. The soluble solid content (SSC) and pH of the juice samples were determined. The results show that changes in certain compounds between tomato juice before and after the storage period were obvious. An excellent precision was achieved by LS-SVM model compared with discriminant partial least-squares (DPLS), soft independent modeling of class analogy (SIMCA), and discriminant analysis (DA) models, with 100% of a total accuracy. It can be found that NIR spectroscopy coupled with LS-SVM, DPLS, SIMCA, and DA can be used to control the quality change of tomato juice during the storage.

show abstract

Classifying NIR spectra of textile products with kernel methods

Cited by 56 publications

References 10 publications

Prediction of dissolved oxygen concentration in hypoxic river systems using support vector machine: a case study of Wen-Rui Tang River, China

Prediction of dissolved oxygen concentration in hypoxic river systems using support vector machine: a case study of Wen-Rui Tang River, China

Automatic classification of steel plates based on laser induced breakdown spectroscopy and support vector machines

Use of near-infrared spectroscopy and least-squares support vector machine to determine quality change of tomato juice

Contact Info

Product

Resources

About