Infrared spectra analysis method of multi-component mixed gas concentration based on support vector machine

2007 ◽  
Author(s):  
Wenjun Xie ◽  
Peng Bai ◽  
Lei Xiao
Keyword(s):  
Support Vector Machine ◽  
Infrared Spectra ◽  
Support Vector ◽  
Analysis Method ◽  
Mixed Gas ◽  
Spectra Analysis ◽  
Gas Concentration

SVM Analysis Method for Infrared Spectra of Mixed Gas

2011 ◽  
Vol 58-60 ◽  
pp. 1681-1684
Author(s):  
Peng Bai ◽  
Yan Li ◽  
Peng Liu
Keyword(s):  
Infrared Spectra ◽  
Absolute Error ◽  
Experimental Result ◽  
Component Concentration ◽  
Support Vector ◽  
Model Parameters ◽  
Calibration Model ◽  
Mixed Gas ◽  
Spectra Analysis ◽  
Key Technologies

In order to solving the problem that the mass samples of mixed gas spectra data samples being unable to obtain, characteristic absorption spectrum line of the component gas for mixed gas being overlap, and the problem of randomness of component concentration distribution for mixed gas and so on, support vector machine is introduced for the infrared spectra analysis for the mixed gas. Key technologies as feature selection of spectra data samples, data preprocessing, SVM calibration model parameters optimization and level structure for spectrum analysis of a mixed gas is proposed in the paper. The influence of above-mentioned four key technologies to the analysis results is discussed by using experimental means. The experimental result shows that with adoption of the key technologies, the maximum absolute error of component concentration analysis for the mixed gas is 2.93%, and the maximum average absolute error is of 0.73%. The method can also be used for infrared spectra analysis for other mixed gas, and it has practical application value.

Fuzzy-support vector machine geotechnical risk analysis method based on Bayesian network

2019 ◽  
Vol 16 (8) ◽  
pp. 1975-1985 ◽  
Author(s):  
Yang Liu ◽  
Jian-jing Zhang ◽  
Chong-hao Zhu ◽  
Bo Xiang ◽  
Dong Wang
Keyword(s):  
Support Vector Machine ◽  
Risk Analysis ◽  
Bayesian Network ◽  
Support Vector ◽  
Analysis Method ◽  
Fuzzy Support Vector Machine ◽  
Geotechnical Risk

scholarly journals Determination Of Gas Mixture Components Using Fluctuation Enhanced Sensing And The LS-SVM Regression Algorithm

2015 ◽  
Vol 22 (3) ◽  
pp. 341-350 ◽  
Author(s):  
Łukasz Lentka ◽  
Janusz M. Smulko ◽  
Radu Ionescu ◽  
Claes G. Granqvist ◽  
Laszlo B. Kish
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Temperature Change ◽  
Nonlinear Regression ◽  
Ultraviolet Irradiation ◽  
Support Vector ◽  
Gas Mixture ◽  
Gas Concentration ◽  
Single Sensor

Abstract This paper analyses the effectiveness of determining gas concentrations by using a prototype WO3 resistive gas sensor together with fluctuation enhanced sensing. We have earlier demonstrated that this method can determine the composition of a gas mixture by using only a single sensor. In the present study, we apply Least-Squares Support-Vector-Machine-based (LS-SVM-based) nonlinear regression to determine the gas concentration of each constituent in a mixture. We confirmed that the accuracy of the estimated gas concentration could be significantly improved by applying temperature change and ultraviolet irradiation of the WO3 layer. Fluctuation-enhanced sensing allowed us to predict the concentration of both component gases.

A Two-Component Gas Analyzer Based on Self-Sustaining Dark Discharge Carbon Nanotube Film Cathode Gas Sensor

2010 ◽  
Vol 121-122 ◽  
pp. 188-191
Author(s):  
Ji Peng Lin ◽  
Jun Hua Liu
Keyword(s):  
Support Vector Machine ◽  
Carbon Nanotube ◽  
Gas Sensor ◽  
Support Vector ◽  
Gas Analyzer ◽  
Mixed Gas ◽  
Accuracy Measurement ◽  
Carbon Nanotube Film ◽  
Two Component ◽  
New Type

A new type of cathode gas sensor based on carbon nanotube film is presented to analyze CO and CH4 mixed gas. The structure and measuring principle of breakdown voltages are proposed to build support vector machine nonlinear model. As a result, the max relative error of CO and CH4 is 3.8% and 6.0%, respectively. This hints the sensor acts an accuracy measurement.

Application of Visible-Near Infrared Spectra Technique Based on to the Non-Destructive Measurement of the Salmon Quality

2014 ◽  
Vol 926-930 ◽  
pp. 961-964
Author(s):  
Jiao Jiao Yin
Keyword(s):  
Infrared Spectra ◽  
Near Infrared ◽  
Principal Component ◽  
Support Vector ◽  
Analysis Method ◽  
Linear Discriminant ◽  
Near Infrared Spectra ◽  
Destructive Measurement ◽  
Non Destructive

Because the reflectivity of astaxanthin vary in different bands (mainly 400nm-600nm), so we use the visible-near infrared spectra technique to irradiate the salmon. Because in daily life, people grade the salmon flesh with a color card. In this paper, we first use principal component analysis to reduce the dimensionality of the spectral data of salmon, then use linear discriminant analysis method, least squares support vector machine classification method to distinguish the flesh quality. The correct classification rates are 60%and73.3%. The results show that we can use visible – near infrared spectra to distinguish the quality of the salmon which doesn’t be dissected.

Reliability Analysis of Foundation Pit Based on Response Surface of Support Vector Machine

2013 ◽  
Vol 671-674 ◽  
pp. 240-244
Author(s):  
Chang Ning Sun ◽  
Jing Cao ◽  
Hai Ming Liu ◽  
Hui Min Zhao
Keyword(s):  
Support Vector Machine ◽  
Reliability Analysis ◽  
Response Surface ◽  
Safety Factor ◽  
Lateral Displacement ◽  
Support Vector ◽  
Probability Density Distribution ◽  
Analysis Method ◽  
Foundation Pit ◽  
Random Samples

Traditional analysis methods of reliability in the foundation pit engineering have larger error and larger amount of calculation. Therefore, the response surface method has attracted much attention because it can effectively use the finite element analysis method (FEAM) and reduce the number of the numerical simulation. This paper combines uniform design (UD) with support vector machine (SVM). On this base, a reliability analysis method of the foundation pit is put forward based on the response surface of support vector machine (RSSVM). The UD structures random samples and the FEAM is used to obtain corresponding response parameters including the lateral displacement of wall, settlement of ground, safety factor of overall stability and safety factor of against overturning. Then, SVM trains the above random samples and corresponding response parameters to get response surface (RS) respectively. The probability density distribution of each response parameter is obtained by combining the Monte Carlo method with RSSVM. The instance analysis shows that the method has high computing efficiency and less amount of calculation, and the result is reasonable. It provides an effective way for the reliability analysis of the foundation pit engineering.

scholarly journals Determining damages in ceramic plates by using discrete wavelet packet transform and support vector machine

2020 ◽  
Vol 10 (5) ◽  
pp. 4759
Author(s):  
Mehmet Yumurtaci ◽  
Gokhan Gokmen ◽  
Tahir Cetin Akinci
Keyword(s):  
Support Vector Machine ◽  
Wavelet Packet ◽  
Wavelet Packet Transform ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Experimental Equipment ◽  
Analysis Method ◽  
Discrete Wavelet Packet Transform ◽  
Cracked Plates ◽  
Svm Model

In this study, an analysis was conducted by using discrete wavelet packet transform (DWPT) and support vector machine (SVM) methods to determine undamaged and cracked plates. The pendulum was used to land equal impacts on plates in this experimental study. Sounds, which emerge from plates as a result of the impacts applied to undamaged and cracked plates, are sound signals used in the analysis and DWPT of these sound signals were obtained with 128 decompositions for feature extraction. The first four components, reflecting the characteristics of undamaged and cracked plates within these 128 components, were selected for enhancing the performance of the classifier and energy values were used as feature vectors. In the study, the SVM model was created by selecting appropriate C and γ parameters for the classifier. Undamaged and cracked plates were seen to be successfully identified by an analysis of the training and testing phases. Undamaged and cracked statuses of the plates that are undamaged and have the analysis had identified different cracks. The biggest advantage of this analysis method used is that it is high-precision, is relatively low in cost regarding experimental equipment and requires hardware.

scholarly journals Texture classification of fabric defects using machine learning

2020 ◽  
Vol 10 (4) ◽  
pp. 4390
Author(s):  
Yassine Ben Salem ◽  
Mohamed Naceur Abdelkrim
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Comparative Study ◽  
Texture Classification ◽  
Support Vector ◽  
Defect Classification ◽  
Analysis Method ◽  
Fabric Defect ◽  
Novel Algorithm

In this paper, a novel algorithm for automatic fabric defect classification was proposed, based on the combination of a texture analysis method and a support vector machine SVM. Three texture methods were used and compared, GLCM, LBP, and LPQ. They were combined with SVM’s classifier. The system has been tested using TILDA database. A comparative study of the performance and the running time of the three methods was carried out. The obtained results are interesting and show that LBP is the best method for recognition and classification and it proves that the SVM is a suitable classifier for such problems. We demonstrate that some defects are easier to classify than others.

scholarly journals Auto Classification of Biomass through Characterization of their Pyrolysis Behaviors by using Thermogravimetric Analysis with Support Vector Machine Algorithm: Case Study for Tobacco

2020 ◽  
Author(s):  
Chao Yin ◽  
Xiaohua Deng ◽  
Zhiqiang Yu ◽  
Ruting Chen ◽  
Hongxiang Zhong ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Thermogravimetric Analysis ◽  
Oil Quality ◽  
Support Vector ◽  
Analysis Method ◽  
Biomass Pyrolysis ◽  
Svm Algorithm ◽  
Bio Oil

Abstract Background: During the biomass-to-bio-oil conversion process, many researches focus on the study of the association between the biomass and the bio-products by using near infrared spectra (NIR) and chemical analysis method. However, the characterization of biomass pyrolysis behaviors by using thermogravimetric analysis (TGA) with support vector machine (SVM) algorithm has not been reported. In this study, tobacco was chosen as the object for biomass, because the cigarette smoke (including water, tar and gases) released by tobacco pyrolysis reactions decide the sensory quality, which is similar to the use of biomass as a renewable resource through the pyrolysis process. Results: Support vector machine (SVM) has been employed to automatically classify the planting area and growing position of tobacco leaves by using thermogravimetric analysis data as the information source for the first time. 88 single-grade tobacco samples belonging to 4 grades and 8 categories were split into the training, validation and blind testing set. Our model showed excellent performances in both the training and validation set as well as in the blind test, with accuracy over 91.67%. Throughout the whole dataset of 88 samples, our model not only provides precise results on the planting area of tobacco leave, but also accurately distinguishes the major grades among the upper, lower and middle positions. Error only occurs in the classification of subgrades of the middle position. Conclusions: Our results not only validated the feasibility of using thermogravimetric analysis with SVM algorithm as an objective and rapid method for automatic classification of tobacco planting area and growing position, but also showed this new analysis method would be a promising way to exploring bio-oil quality prior to biomass pyrolysis production.

Sign in / Sign up

Export Citation Format

Share Document