Sliding Window-based DCT Features for Tea Quality Prediction Using Electronic Tongue

Saha, Pradip Kumar; Ghorai, Santanu; Tudu, Bipan; Bandyopadhyay, Rajib; Bhattacharyya, Nabarun

doi:10.1145/2708463.2709032

Cited by 4 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for features extraction, techniques such as features of raw response [15], peak-inflection point [10,16], Discrete wavelet transform (DWT) [17], Discrete cosine transform (DCT) [18], singular value decomposition (SVD) [19] and DCT fused with SVD (DCT + SVD) [20] were utilized as comparison methods. In terms of pattern recognition, several classifiers such as support vector machine (SVM) [9,12], the k-nearest neighbor (k-NN) [13], and random forest (RF) [14] were adopted to compare with the method we proposed.…”

Section: Comparison With Other Techniquesmentioning

confidence: 99%

“…For instance, Pradip Saha et al used discrete wavelet transform (DWT) with sliding windows to extract energy in different frequency bands as features [17]. Andrea Scozzari et al used discrete cosine transform (DCT) to extract features, and selected some coefficients as eigenvalues for tea classification [18]. In addition, Santanu Ghoraiand et al transformed the sampling data into matrices, decomposed the matrices into singular values (SVD), and selected several singular values as features for tea classification [19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Convolutional Neural Network Based Auto Features Extraction Method for Tea Classification with Electronic Tongue

Zhong

Zhang

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Feature extraction is a key part of the electronic tongue system. Almost all of the existing features extraction methods are "hand-crafted", which are difficult in features selection and poor in stability. The lack of automatic, efficient and accurate features extraction methods has limited the application and development of electronic tongue systems. In this work, a convolutional neural network-based auto features extraction strategy (CNN-AFE) in an electronic tongue (e-tongue) system for tea classification was proposed. First, the sensor response of the e-tongue was converted to time-frequency maps by short-time Fourier transform (STFT). Second, features were extracted by convolutional neural network (CNN) with time-frequency maps as input. Finally, the features extraction and classification results were carried out under a general shallow CNN architecture. To evaluate the performance of the proposed strategy, experiments were held on a tea database containing 5100 samples for five kinds of tea. Compared with other features extraction methods including features of raw response, peak-inflection point, discrete cosine transform (DCT), discrete wavelet transform (DWT) and singular value decomposition (SVD), the proposed model showed superior performance. Nearly 99.9% classification accuracy was obtained and the proposed method is an approximate end-to-end features extraction and pattern recognition model, which reduces manual operation and improves efficiency.

show abstract

Section: Comparison With Other Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Convolutional Neural Network Based Auto Features Extraction Method for Tea Classification with Electronic Tongue

Zhong

Zhang

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The method presented in this work using AR coefficients as features is easy to develop from the response of ET signal. The testing of a new sample in this method is fast compared to the sliding window based technique [16], [26]. Thus, classification of tea samples using AR model coefficients is observed effective for LAPV and staircase type of measurements.…”

Section: Discussionmentioning

confidence: 95%

“…The performance of the proposed method is compared to that of four other feature extraction methods, namely sliding window based Haar wavelet features [26], sliding window based DCT features [16], 6 th level discrete wavelet features with Haar wavelet [22] and first five principal component [20] of ET signals. In order to compare the quality of the features, the experiment is performed with different feature sets extracted from the ET signal under identical conditions by SVM classifier.…”

Section: ) Comparison With Other Methodsmentioning

confidence: 99%

“…For example, Scozarri et al [15] proposed qualitative analysis of water using ET with the help of discrete cosine transform (DCT) based techniques. Moving window-based DCT coefficients are also used by Saha et al [16] as features to classify by support vector machine (SVM) [17] and vector valued regularized kernel function approximation (VVRKFA) [18] for black tea quality discrimination. Valle et al [19] and Q. Chen et al [20] used principal component analysis (PCA) technique for the assessment of water and green tea, respectively, using ET.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tea Quality Prediction by Autoregressive Modeling of Electronic Tongue Signals

Saha¹,

Ghorai²,

Tudu

et al. 2016

IEEE Sensors J.

Self Cite

View full text Add to dashboard Cite

In this work, a novel method to model the responses of Electronic Tongue (ET) sensors using autoregressive (AR) and autoregressive moving average (ARMA) techniques is presented. The transient response of each electrode present in the sensor array of an electronic tongue is characterized with tea samples of different qualities. Models coefficients are used as characteristics features of the ET response corresponding to the tea samples. Three different classifiers, namely artificial neural network (ANN), vector valued regularized kernel function approximation (VVRKFA) and one vs. one support vector machine (OVO-SVM), are employed to evaluate the performance of these features to discriminate the quality of black tea. Experimental results on three types of voltammetric measurement data show that the proposed method may be very useful for prediction of tea quality. The present model based classification method is very straightforward and provides better or similar performance compared to some other methods proposed in literature for ET signal classification. Index Terms-Electronic tongue (ET), feature extraction, autoregressive (AR) model, autoregressive moving average (ARMA) model, OVO-SVM.

show abstract