Classification of water contamination developed by 2-D Gabor wavelet analysis and support vector machine based on fluorescence spectroscopy

Huang, Pingjie; Mao, Tingting; Yu, Qiaojun; Cao, Yanjun; Yu, Jie; Zhang, G.; Hou, Dibo

doi:10.1364/oe.27.005461

Cited by 11 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fluorescence data consisted of excitation data and emission data that combined with the data from a series of samples to construct three-dimensional data. The multiway PARAFAC method is found to be very efficient for data of more than two dimensions (Bro, 1997; Li et al , 2014; Huang et al , 2019). Also, a series of studies on fluorescence data were analysed using the PARAFAC method (Stedmon and Bro, 2008; Wünsch et al , 2017; Acković et al , 2018).…”

Section: Methodsmentioning

confidence: 99%

Feasibility study for the analysis of coconut water using fluorescence spectroscopy coupled with PARAFAC and SVM methods

Liu

Huang

et al. 2020

BFJ

View full text Add to dashboard Cite

PurposeParallel factor analysis (PARAFAC) coupled with support-vector machine (SVM) was carried out to identify and discriminate between the fluorescence spectroscopies of coconut water brands.Design/methodology/approachPARAFAC was applied to reduce three-dimensional data of excitation emission matrix (EEM) to two-dimensional data. SVM was applied to discriminate between six commercial coconut water brands in this study. The three largest variation data from fluorescence spectroscopy were extracted using the PARAFAC method as the input data of SVM classifiers.FindingsThe discrimination results of the six commercial coconut water brands were achieved by three SVM methods (Ga-SVM, PSO-SVM and Grid-SVM). The best classification accuracies were 100.00%, 96.43% and 94.64% for the training set, test set and CV accuracy.Originality/valueThe above results indicate that fluorescence spectroscopy combined with PARAFAC and SVM methods proved to be a simple and rapid detection method for coconut water and perhaps other beverages.

show abstract

Section: Methodsmentioning

confidence: 99%

Feasibility study for the analysis of coconut water using fluorescence spectroscopy coupled with PARAFAC and SVM methods

Liu

Huang

et al. 2020

BFJ

View full text Add to dashboard Cite

show abstract

“…Support vector machine (SVM) was a binary classifier that established a discrimination hyper-plane with the maximal margin between two groups of samples [27]. SVM has been widely used to predict the biomedical patterns from the imaging [28], [29] and genetic data [30]. Naïve bayes (NBayes) was another popular classifier based on the Bayesian theory and it estimated the probability of a sample belonging to each of the investigated phenotypes [31].…”

Section: Classificationmentioning

confidence: 99%

The Transverse Ultrasonogram of Thyroid Papillary Carcinoma Has a Better Prediction Accuracy Than the Longitudinal One

Wang

Zhu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Thyroid produces multiple essential hormones for vital life processes. Thyroid cancer has no symptoms and may be detected by ultrasound imaging incidentally for other medical conditions. An accurate computational detection model may help the precise diagnose of thyroid papillary cancer (TPC). A standard protocol captures at least the transverse and longitudinal ultrasonograms of the thyroid. This study investigated the detection problem of thyroid cancer using the ultrasound images. Our data suggested that the original local binary pattern (LBP) features extracted from the ultrasonograms were very sparse and the compressed LBP features outperformed the original version. And the best model (Acc = 0.9829) was achieved by the fivefold cross validation of the classifier support vector machine (SVM). Other sources of biomedical data may be integrated to further improve the TPC detection model in future studies.INDEX TERMS Thyroid pappilary carcinoma (TPC), transverse ultrasonogram, longitudinal ultrasonogram, support vector machine (SVM), local binary pattern (LBP).

show abstract

“…Wang et al [28] used the 2D Gabor wavelet algorithm in the field of image recognition to extract and classify features from the synchronous 3D fluorescence spectra of different oil products, verifying the feasibility and effectiveness of the 2D Gabor wavelet algorithm applied to spectral image feature extraction tasks. Huang et al [29] utilized 2D Gabor wavelet coupled with block statistics to extract the 3D fluorescence spectral characteristics of drinking water and used support vector machine for multi-classification and identification of pollutants with closely positioned or overlapping peaks. Yin et al [30] designed a convolutional neural network method coupled with a wavelength-encoding module of spectra to obtain feature vectors from excitation emission matrix (EEM) data, which can effectively address the problem of open set recognition of unknown organic pollutants in drinking water, the results demonstrate that the combination of spectral wavelength information can enrich spectral features and improve recognition accuracy.…”

Section: Introductionmentioning

confidence: 99%

Anomaly detection method for urban river water quality based on background model prediction using three-dimensional fluorescence

Zhang,

Yu,

Shi

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Three-dimensional fluorescence spectroscopy has great potential for detecting water quality anomalies in urban rivers and protecting against organic pollution. However, current detection methods inadequately address critical application scenarios, such as fluctuations in river water background, low concentration of pollutants, and the fluorescence peaks overlap between pollutants and background. In this paper, a fluorescence spectrum feature extraction method which is effective for the above scenarios was proposed. The proposed method involves a sequential process. First, the original spectrum undergoes preprocessing using a novel method. Next, an alternating residual tri-linearization technique is applied to establish a predictive model for river water spectrum changes. Subsequently, the background model is utilized for spectrum decomposition and reconstruction of the test sample. This reconstructed spectrum is then used to derive the residual spectrum by comparison with the original. Finally, frequency domain features are extracted from the residual spectrum to enable classification, while the background model undergoes real-time updates. In the three meaningful scenarios mentioned above, the accuracy of the proposed method for anomaly detection reached 99%, 82%, and 98%, respectively. Our accuracy is higher than several typical benchmark methods.

show abstract

Classification of water contamination developed by 2-D Gabor wavelet analysis and support vector machine based on fluorescence spectroscopy

Cited by 11 publications

References 21 publications

Feasibility study for the analysis of coconut water using fluorescence spectroscopy coupled with PARAFAC and SVM methods

Feasibility study for the analysis of coconut water using fluorescence spectroscopy coupled with PARAFAC and SVM methods

The Transverse Ultrasonogram of Thyroid Papillary Carcinoma Has a Better Prediction Accuracy Than the Longitudinal One

Anomaly detection method for urban river water quality based on background model prediction using three-dimensional fluorescence

Contact Info

Product

Resources

About