scholarly journals The application of pattern recognition techniques in metabolite fingerprinting of six differentPhyllanthusspp.

2011 ◽  
Vol 26 (1) ◽  
pp. 69-78 ◽  
Author(s):  
Saravanan Dharmaraj ◽  
Lay-Harn Gam ◽  
Shaida Fariza Sulaiman ◽  
Sharif Mahsufi Mansor ◽  
Zhari Ismail
Keyword(s):  
Pattern Recognition ◽  
Principal Component ◽  
Canonical Variate ◽  
Batch Mode ◽  
Mid Infrared ◽  
Linear Discriminant ◽  
Pattern Recognition Techniques ◽  
Pattern Recognition Methods ◽  
Ftir Spectrometer ◽  
Component Models

FTIR spectroscopy was used together with multivariate analysis to distinguish six different species ofPhyllanthus. Among these speciesP. niruri,P. debilisandP. urinariaare morphologically similar whereasP. acidus,P. emblicaandP. myrtifoliusare different. The FTIR spectrometer was used to obtain the mid-infrared spectra of the dried powdered leaves in the region of 400–4000 cm−1. The region of 400–2000 cm−1was analyzed with four different pattern recognition methods. Initially, principal component analysis (PCA) was used to reduce the spectra to six principal components and these variables were used for linear discriminant analysis (LDA). The second technique used LDA on most discriminating wavenumber variables as searched by genetic algorithm using canonical variate approach for either 30 or 60 generations. SIMCA, which consisted of constructing an enclosure for each species using separate principal component models, was the third technique. Finally, multi-layer neural network with batch mode of backpropagation learning was used to classify the samples. The best results were obtained with GA of 60 gens. When LDA was run with the six wavenumbers chosen (1151, 1578, 1134, 609, 876 and 1227), 100% of the calibration spectra and 96.3% of the validation spectra were correctly assigned.

Application of Pattern Recognition Techniques to Breast Cancer Detection: Ultrasonic Analysis of 100 Pathologically Confirmed Tissue Areas

1982 ◽  
Vol 4 (4) ◽  
pp. 378-396 ◽  
Author(s):  
Morris S. Good ◽  
Joseph L. Rose ◽  
Barry B. Goldberg
Keyword(s):  
Pattern Recognition ◽  
Ultrasonic Pulse ◽  
Waveform Analysis ◽  
Algorithm Performance ◽  
Linear Discriminant ◽  
Pattern Recognition Techniques ◽  
Pattern Recognition Methods ◽  
Jackknife Procedure ◽  
Pulse Echo

Ultrasonic pulse-echo rf waveform analysis and selected pattern recognition methods were applied to classification of breast tissue. Emphasis was placed on the classification of solid tissue areas since fluid areas are easily identified by present B-scan techniques. Pattern recognition techniques such as the Fisher Linear Discriminant (FLD), Probability Density Function (PDF) curves, jackknife estimate and committee vote were used to construct and evaluate a two class algorithm, malignant versus benign tissue areas. A data base consisting of frequency domain features from 100 pathologically confirmed tissue areas from 87 patients were used to train the algorithm. Algorithm performance was acquired via the generalized jackknife procedure to significantly reduce the bias frequently encountered in algorithm evaluation. Estimated values of algorithm performance are sensitivity and specificity values of 96 percent and 68 percent, respectively.

scholarly journals Quality parameters and pattern recognition methods as a tool in tracing regional origin of multifloral honey

2013 ◽  
Vol 78 (12) ◽  
pp. 1875-1892 ◽  
Author(s):  
Kristina Lazarevic ◽  
Jelena Trifkovic ◽  
Filip Andric ◽  
Zivoslav Tesic ◽  
Ivan Andjelkovic ◽  
...  
Keyword(s):  
Electrical Conductivity ◽  
Pattern Recognition ◽  
Optical Rotation ◽  
Sugar Content ◽  
Geographic Origin ◽  
Principal Component ◽  
Climate Conditions ◽  
Linear Discriminant ◽  
Pattern Recognition Methods ◽  
Multifloral Honey

The characterization of multifloral honey regarding the mineral composition, sugar content and basic physicochemical properties has been done. The total of 164 honey samples was collected from six regions of Serbia during 2009 harvesting season. Univariate data analysis (descriptive statistics and analysis of variance), geographic information system and pattern recognition methods (principal component analysis and cluster analysis) have been performed in order to identify geographical origin of honey. The content of Mg, K, and Cu, electrical conductivity, and optical rotation were established as useful indicators in tracing regional differences between honey samples. Samples originated from Zlatibor region were clearly distinguished from those from the rest of Serbia showing higher K and Mg content, as well as higher values of optical rotation, electrical conductivity, and free acidity. The influence of the soil composition, and climate conditions, as well as the presence of particular flora on the honey composition is stressed out. The modeling of geographic origin of honey has been attempted by the means of linear discriminant analysis.

scholarly journals Near Infrared Spectroscopy Based on Supervised Pattern Recognition Methods for Rapid Identification of Adulterated Edible Gelatin

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Hao Zhang ◽  
Haifeng Sun ◽  
Ling Wang ◽  
Shun Wang ◽  
Wei Zhang ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Near Infrared ◽  
Scatter Correction ◽  
Recognition Rate ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Support Vector ◽  
Linear Discriminant ◽  
Pattern Recognition Methods ◽  
Gelatin Gels

The aim of this work is to identify the adulteration of edible gelatin using near-infrared (NIR) spectroscopy combined with supervised pattern recognition methods. The spectral data obtained from a total of 144 samples consisting of six kinds of adulterated gelatin gels with different mixture ratios were processed with multiplicative scatter correction (MSC), Savitzky–Golay (SG) smoothing, and min-max normalization. Principal component analysis (PCA) was first carried out for spectral analysis, while the six gelatin categories could not be clearly distinguished. Further, linear discriminant analysis (LDA), soft independent modelling of class analogy (SIMCA), backpropagation neural network (BPNN), and support vector machine (SVM) were introduced to establish discrimination models for identifying the adulterated gelatin gels, which gave a total correct recognition rate of 97.44%, 100%, 97.44%, and 100%, respectively. For the SIMCA model with significant level α = 0.05, sample overlapping clustering appeared; thus, the SVM model presents the best recognition ability among these four discrimination models for the classification of edible gelatin adulteration. The results demonstrate that NIR spectroscopy combined with unsupervised pattern recognition methods can quickly and accurately identify edible gelatin with different adulteration levels, providing a new possibility for the detection of industrial gelatin illegally added into food products.

Classification and Prediction of Goldfish Population and Water Quality Using a Potentiometric E-Tongue

2017 ◽  
Vol 60 (4) ◽  
pp. 1037-1044
Author(s):  
Zhenbo Wei ◽  
Yu Zhao ◽  
Jun Wang
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Pattern Recognition ◽  
Comprehensive Evaluation ◽  
Back Propagation ◽  
Correlation Coefficients ◽  
Principal Component ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Pattern Recognition Methods

Abstract. In this study, a potentiometric E-tongue was employed for comprehensive evaluation of water quality and goldfish population with the help of pattern recognition methods. Four water quality parameters, i.e., pH and concentrations of dissolved oxygen (DO), nitrite (NO2-N), and ammonium (NH3-N), were tested by conventional analysis methods. The differences in water quality parameters between samples were revealed by two-way analysis of variance (ANOVA). The cultivation days and goldfish population were classified well by principal component analysis (PCA) and canonical discriminant analysis (CDA), and the distribution of each sample was clearer in CDA score plots than in PCA score plots. The cultivation days, goldfish population, and water parameters were predicted by a T-S fuzzy neural network (TSFNN) and back-propagation artificial neural network (BPANN). BPANN performed better than TSFNN in the prediction, and all fitting correlation coefficients were >0.90. The results indicated that the potentiometric E-tongue coupled with pattern recognition methods could be applied as a rapid method for the determination and evaluation of water quality and goldfish population. Keywords: Classify, E-tongue, Goldfish water, Prediction.

scholarly journals Electronic Nose-Based Technique for Rapid Detection and Recognition of Moldy Apples

2019 ◽  
Author(s):  
Wenshen Jia ◽  
Gang Liang ◽  
Hui Tian ◽  
Jing Sun ◽  
Cihui Wan
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Electronic Nose ◽  
Gas Sensors ◽  
Penicillium Expansum ◽  
Support Vector ◽  
Linear Discriminant ◽  
Pattern Recognition Methods ◽  
Group A ◽  
Group B

In this paper, PEN3 electronic nose was used to detect and recognize fresh and moldy apples (inoculated with Penicillium expansum and Aspergillusniger) taken Golden Delicious apples as model subject. Firstly, the apples were divided into two groups: apples only inoculated with different molds (Group A) and mixed apples of inoculated apples with fresh apples (Group B). Then the characteristic gas sensors of the PEN3 electronic nose that were most closely correlated with the flavor information of the moldy apples were optimized and determined, which can simplify the analysis process and improve the accuracy of results. Four pattern recognition methods, including linear discriminant analysis (LDA), backpropagation neural network (BPNN), support vector machines (SVM) and radial basis function neural network (RBFNN), were then applied to analyze the data obtained from the characteristic sensors, respectively, aiming at establishing the prediction model of flavor information and fresh/moldy apples. The results showed that only the gas sensors of W1S, W2S, W5S, W1W and W2W in the PEN3 electronic nose exhibited strong signal response to the flavor information, indicating were most closely correlated with the characteristic flavor of apples and thus the data obtained from these characteristic sensors was used for modeling. The results of the four pattern recognition methods showed that BPNN presented the best prediction performance for the training and validation sets for both the Group A and Group B, with prediction accuracies of 96.29% and 90.00% (Group A), 77.70% and 72.00% (Group B), respectively. Therefore, it first demonstrated that PEN3 electronic nose can not only effectively detect and recognize the fresh and moldy apples, but also can distinguish apples inoculated with different molds.

Pattern recognition and interpretation of nucleoside mass spectra

1980 ◽  
Vol 33 (7) ◽  
pp. 1401 ◽  
Author(s):  
RGAR Maclagan ◽  
MJ Mitchell
Keyword(s):  
Pattern Recognition ◽  
Mass Spectra ◽  
Figure Of Merit ◽  
Function Analysis ◽  
Structural Features ◽  
Nearest Neighbour ◽  
Linear Discriminant ◽  
Pattern Recognition Techniques ◽  
The Mean ◽  
Learning Machine

Four pattern-recognition techniques-distance from the mean, the learning machine approach, a statistical linear discriminant function analysis and the k-nearest-neighbour method-have been applied to a set of 125 nucleoside mass spectra. Twenty-one structural features, comprising elemental compositions and substitution types, were predicted from binary and logarithmic transforms of the spectra. The best classification was given by the distance from the mean method with logarithmic data. With this method prediction success averaged 79 % over the 21 categories, or in terms of the figure of merit 0.27.

scholarly journals ELECTRONIC NOSE FOR ANCHOVY FRESHNESS MONITORING BASED ON SENSOR ARRAY AND PATTERN RECOGNITION METHODS: PRINCIPAL COMPONENTS ANALYSIS, LINEAR DISCRIMINANT ANALYSIS AND SUPPORT VECTOR MACHINE

2014 ◽  
pp. 61-67
Author(s):  
A. Amari ◽  
N. El Bari ◽  
B. Bouchikhi
Keyword(s):  
Support Vector Machine ◽  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Electronic Nose ◽  
Tin Dioxide ◽  
Principal Component ◽  
Support Vector ◽  
Current Pattern ◽  
Linear Discriminant ◽  
Pattern Recognition Methods

An electronic nose based system, which employs an array of six inexpensive commercial gas sensors based on tin dioxide (Figaro Engineering Inc., Japan), has been used to analyse the freshness states of anchovies. Fresh anchovies were stored in a refrigerator at 4 ± 1°C over a period of 15 days. Electronic nose measurements need no sample preparation and the results indicated that the spoilage process of anchovies could be followed by using this technique. Conductance responses of volatile compounds produced during storage of anchovy were monitored and the result were analysed by multivariate analysis methods. In this paper principal component analysis (PCA) and linear discriminant analysis (LDA) were used to investigate whether the electronic nose was able to distinguishing among different freshness states (fresh, moderated and non-fresh samples). The loadings analysis was used to identify the sensors responsible for discrimination in the current pattern file. Therefore, the support vector machines (SVM) method was applied to the new subset, with only the selected sensors, to confirm that a subset of a few sensors can be chosen to explain all the variance. The results obtained prove that the electronic nose can discriminate successfully different freshness state using LDA analysis. Some sensors have the highest influence in the current pattern file for electronic nose. Support vector machine (SVM) model, applied to the new subset of sensors show the good performance.

scholarly journals Can FT-Mid-Infrared Spectroscopy of Milk Samples Discriminate Different Dietary Regimens of Sheep Grazing With Restricted Access Time?

2021 ◽  
Vol 8 ◽  
Author(s):  
Giovanni Molle ◽  
Andrea Cabiddu ◽  
Mauro Decandia ◽  
Maria Sitzia ◽  
Ignazio Ibba ◽  
...  
Keyword(s):  
Principal Component ◽  
Italian Ryegrass ◽  
Access Time ◽  
Sheep Grazing ◽  
Forage Crops ◽  
Mid Infrared ◽  
Linear Discriminant ◽  
Best Fitting ◽  
Grazing Period ◽  
Mir Spectra

Milk obtained from sheep grazing natural pastures and some forage crops may be worth a plus value as compared to milk obtained from stall-fed sheep, due to their apparently higher content of beneficial fatty acids (FAs). Fourier transformed mid-infrared (FT-MIR) analysis of FA can help distinguish milk from different areas and diverse feeding systems. The objective was to discriminate milk from sheep and milk from dairy sheep rotationally grazing Italian ryegrass or berseem clover for 2, 4, or 6 h/day. To test this hypothesis, a data-mining study was undertaken using a database of 1,230 individual milk spectra. Data were elaborated by principal component analysis (PCA) and analyzed by linear discriminant analysis (LDA) with or without the use of genetic algorithm (GA) as a variable selection tool with the primary aim to discriminate grazed forages (grass vs. legume), access time (2, 4, or 6 h/day), grazing day (first vs. last grazing day during the 7-day grazing period), and the milking time (morning vs. afternoon milking). The best-fitting discriminant models of FT-MIR spectra were able to correctly predict 100% of the samples differing for the pasture forage, 91.9% of the samples differing for grazing day, and 97.1% of the samples regarding their milking time. The access time (AT) to pasture was correctly predicted by the model in 60.3% of the samples, and the classification ability was improved to 77.0% when considering only the 2 and 6 h/day classes.

Moving Window Partial Least-Squares Discriminant Analysis for Identification of Different Kinds of Bezoar Samples by near Infrared Spectroscopy and Comparison of Different Pattern Recognition Methods

2007 ◽  
Vol 15 (5) ◽  
pp. 291-297 ◽  
Author(s):  
Hai-Yan Fu ◽  
Shuang-Yan Huan ◽  
Lu Xu ◽  
Li-Juan Tang ◽  
Jian-Hui Jiang ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Discriminant Analysis ◽  
Least Squares ◽  
Partial Least Squares ◽  
Near Infrared ◽  
Geographical Origin ◽  
Quality Analysis ◽  
Moving Window ◽  
Linear Discriminant ◽  
Pattern Recognition Methods

Moving window partial least-squares (MWPLS) regression was coupled with near infrared (NIR) spectra as an interval selection method to improve the performance of partial least squares discriminant analysis (PLSDA) models. This method was applied to the identification of artificial bezoar, natural bezoar and artificial bezoar in natural bezoar and compared with some traditional pattern recognition methods, such as principal component analysis (PCA), linear discriminant analysis (LDA) and PLSDA. The introduction of MWPLS enhanced the performance of PLSDA model. The results obtained showed that moving window partial least-squares discriminant analysis (MWPLSDA) can extract wavelength intervals with useful information and build simple yet effective classification models that can significantly improve the classification accuracy. Then MWPLSDA was used to identify natural bezoar by geographical origin; a promising result was achieved. The work showed that MWPLSDA could be a promising method for quality analysis and discrimination of chinese medical herbs according to geographical origin.

A New Damage Index Using FRF Data, 2D-PCA Method and Pattern Recognition Techniques

2017 ◽  
Vol 17 (08) ◽  
pp. 1750090 ◽  
Author(s):  
F. Khoshnoudian ◽  
S. Talaei
Keyword(s):  
Pattern Recognition ◽  
Damage Detection ◽  
Damage Identification ◽  
Damage Index ◽  
Principal Component ◽  
Frame Structure ◽  
Damage Scenarios ◽  
Pattern Recognition Techniques ◽  
Damage Indices ◽  
Truss Bridge

A pattern recognition-based damage detection method using a brand-new damage index (DI) obtained from the frequency response function (FRF) data is proposed in this paper. One major issue of using the FRF data is the large size of input variables. The proposed method reduces the dimension of the initial FRF data and transforms it into new damage indices by applying a data reduction technique called the two-dimensional principal component analysis (2D-PCA). The proposed damage indices can be used as the unique patterns. After introducing the damage indices, a dataset of damage scenarios and related patterns is composed. Pattern recognition techniques such as the artificial neural networks and look-up-table (LUT) method are employed to find the most similar known DI to the unknown DI obtained for the damaged structure. As the result of this procedure, the actual damage location and severity can be determined. In this paper, the 2D-PCA and LUT method for damage detection is introduced for the first time. The damage identification of a truss bridge and a two-story frame structure is performed for verification of the proposed method, considering all single damage cases as well as many multiple damage scenarios. In addition, the robustness of the proposed algorithm to measurement noise was investigated by polluting the FRF data with 5%, 10%, 15% and 20% noises.

Sign in / Sign up

Export Citation Format

Share Document