Application of multiple regression methods and automatic testing equipment to the characterization of ‘smart’ sensors

Legras, J C; Priel, Marc; Ranson, C.

doi:10.1016/0250-6874(87)80037-9

Cited by 9 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A number of pattern recognition (PR) techniques have been employed to an array of gas sensor data with partially overlapping characteristics the general nonlinear response of individual sensors in an array to varying gas concentrations has led to exploration of different pattern recognition techniques. Partial Model Building [4], Fourier Transform Techniques [5], Cluster Method [6], Transformed cluster Analysis [7], Multiple Regression Method [8], Discriminant Function Analysis [9], etc. have used to analyze sensor array response with different identification capabilities.…”

Section: Introductionmentioning

confidence: 99%

Effect on Neural Pattern Classifier for Intelligent Gas Sensor by Increasing Number of Hidden Layer

Srivastava¹

2021

IJRASET

View full text Add to dashboard Cite

Neural networks are used to solve complex problem viz., speech and image recognition, pattern recognition (Pattern classification), computer vision etc. Pattern classification by using Back Propagation algorithm for an intelligent gas sensor application is presented. The classifier is trained using published data of thick film tin oxide sensor array. Its superior classification and learning performance is demonstrated for discrimination of alcohols and alcoholic beverages by increasing number of hidden layer. The new model proposed in this article give steep and monotone learning curve and better classification efficiency. Keywords: Neural Network classifier, Back Propagation Algorithm, system error, classification efficiency, learning curve

show abstract

Section: Introductionmentioning

confidence: 99%

Effect on Neural Pattern Classifier for Intelligent Gas Sensor by Increasing Number of Hidden Layer

Srivastava¹

2021

IJRASET

View full text Add to dashboard Cite

show abstract

“…In an array, the response generated by a sensor to a particular odor/gas is complemented by the responses of other sensors of the array to the same odor/gas giving a unique pattern of responses after which the classification can be done by applying various pattern recognition techniques [8]. Partial model building [9], Fourier Manuscript received April 11, 2009 transform technique [10], multiple regression method [11], discriminant function analysis [12], and transformed cluster analysis (TCA) [13] are some of the conventional pattern recognition techniques whose applicability has been limited by the fact that these techniques are unable to handle nonlinear transduction properties of the sensors. This has led to the shifting of the interest of researchers towards artificial neural network (ANN) techniques which apart from being massively parallel in nature, are also capable of handling nonlinear transduction properties.…”

Section: Introductionmentioning

confidence: 99%

A Radial Basis Function Neural Network Classifier for the Discrimination of Individual Odor Using Responses of Thick-Film Tin-Oxide Sensors

et al. 2009

View full text Add to dashboard Cite

This paper presents a novel approach to odor discrimination of alcohols and alcoholic beverages using published data obtained from the responses of thick film tin oxide sensor array fabricated at our laboratory and employing a combination of transformed cluster analysis and radial basis function neural network. The performance of the new classifier was compared with others based on backpropagation (BP) algorithm. The new model has superior discrimination power with a much lower discrimination error. Also, it was found to be less sensitive to the variations in learning parameters apart from being significantly faster than the conventional models based on BP algorithm. Both raw data and data preprocessed by transformed cluster analysis (TCA) were used to train radial basis function neural network (RBFNN) and backpropagation network (BPN). Superior learning and classification performance was obtained using proposed model constituting TCA processed data and RBF network.

show abstract

“…In an array, the response generated by a sensor to a particular odor/gas is complemented by the responses of other sensors of the array to the same odor/gas giving a unique pattern of responses after which the classification can be done by applying various pattern recognition techniques [8]. Partial Model Building [9], Fourier Transform Technique [10], Multiple Regression Method [11], Discriminant Function Analysis [12], and Transformed Cluster Analysis (TCA) [13] are some of the conventional pattern recognition techniques whose applicability has been limited by the fact that these techniques are unable to handle non-linear transduction properties of the sensors. This has led to the shifting of the interest of researchers towards Artificial Neural Network (ANN) techniques which apart from being massively parallel in nature, are also capable of handling non-linear transduction properties.…”

Section: Introductionmentioning

confidence: 99%

A fuzzy logic based neural network classifier for qualitative classification of odors/gases

Kumar

Das

Mishra

et al. 2009

2009 International Conference on Emerging Trends in Electronic and Photonic Devices &Amp; Systems

View full text Add to dashboard Cite

This paper presents a novel approach to odor discrimination using data obtained from the responses of thick film tin oxide sensor array fabricated at our laboratory and employing backpropagation algorithm trained artificial neural network based on fuzzy logic. Fuzzy membership values were used as target vectors to the proposed neural classifier. Three different versions of backpropagation algorithm were used to train the network and their performances have been compared. Superior learning and classification performance was obtained using proposed model trained with TRAINLM version of the backpropagation algorithm.

show abstract

Application of multiple regression methods and automatic testing equipment to the characterization of ‘smart’ sensors

Cited by 9 publications

References 0 publications

Effect on Neural Pattern Classifier for Intelligent Gas Sensor by Increasing Number of Hidden Layer

Effect on Neural Pattern Classifier for Intelligent Gas Sensor by Increasing Number of Hidden Layer

A Radial Basis Function Neural Network Classifier for the Discrimination of Individual Odor Using Responses of Thick-Film Tin-Oxide Sensors

A fuzzy logic based neural network classifier for qualitative classification of odors/gases

Contact Info

Product

Resources

About