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 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.

Characteristics of Permanent Teeth in Persons with Trisomy G

1976 ◽  
Vol 55 (4) ◽  
pp. 633-638 ◽  
Author(s):  
B. Prahl-Andersen ◽  
J. Oerlemans
Keyword(s):  
Discriminant Function ◽  
Discriminant Function Analysis ◽  
Function Analysis ◽  
Permanent Teeth ◽  
Tooth Size ◽  
Linear Discriminant ◽  
Second Molar ◽  
The Mean ◽  
Size And Morphology ◽  
Linear Discriminant Function Analysis

Tooth size and morphology in 35 participants with trisomy G and in 33 controls have been studied. Special attention has been paid to the mean cusp pattern of the upper first and second molar. The classification matrix for the linear discriminant function analysis between participants with trisomy G and controls based on five selected variables showed three misclassifications.

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 Optimized Kernel Extreme Learning Machine for Myoelectric Pattern Recognition

2018 ◽  
Vol 8 (1) ◽  
pp. 483
Author(s):  
Khairul Anam ◽  
Adel Al-Jumaily
Keyword(s):  
Pattern Recognition ◽  
Extreme Learning Machine ◽  
Healthy Subjects ◽  
Nearest Neighbor ◽  
Experimental Results ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Linear Discriminant ◽  
Kernel Extreme Learning Machine ◽  
Learning Machine

Myoelectric pattern recognition (MPR) is used to detect user’s intention to achieve a smooth interaction between human and machine. The performance of MPR is influenced by the features extracted and the classifier employed. A kernel extreme learning machine especially radial basis function extreme learning machine (RBF-ELM) has emerged as one of the potential classifiers for MPR. However, RBF-ELM should be optimized to work efficiently. This paper proposed an optimization of RBF-ELM parameters using hybridization of particle swarm optimization (PSO) and a wavelet function. These proposed systems are employed to classify finger movements on the amputees and able-bodied subjects using electromyography signals. The experimental results show that the accuracy of the optimized RBF-ELM is 95.71% and 94.27% in the healthy subjects and the amputees, respectively. Meanwhile, the optimization using PSO only attained the average accuracy of 95.53 %, and 92.55 %, on the healthy subjects and the amputees, respectively. The experimental results also show that SW-RBF-ELM achieved the accuracy that is better than other well-known classifiers such as support vector machine (SVM), linear discriminant analysis (LDA) and k-nearest neighbor (kNN).

Identification of Colonic Dysplasia and Neoplasia by Diffuse Reflectance Spectroscopy and Pattern Recognition Techniques

1998 ◽  
Vol 52 (6) ◽  
pp. 833-839 ◽  
Author(s):  
Zhengfang Ge ◽  
Kevin T. Schomacker ◽  
Norman S. Nishioka
Keyword(s):  
Pattern Recognition ◽  
Diffuse Reflectance ◽  
Diffuse Reflectance Spectroscopy ◽  
Reflectance Spectroscopy ◽  
Adenomatous Polyps ◽  
Hyperplastic Polyps ◽  
Neoplastic Tissue ◽  
Tissue Samples ◽  
Linear Discriminant ◽  
The Mean

Diffuse reflectance spectroscopy of colonic tissue was employed to determine whether the spectra can be used to distinguish between neoplastic and non-neoplastic tissue in vivo. A total of 224 spectra were obtained in the wavelength range of 350–800 nm from 107 non-neoplastic tissue samples (84 normal mucosa, 23 hyperplastic polyps) and 53 neoplastic tissue samples (44 adenomatous polyps, 9 adenocarcinomas). Pattern recognition algorithms including multiple linear regression (MLR), linear discriminant analysis (LDA), and backpropagating neural network (BNN) were used to distinguish between the two tissue classes. The spectra were randomly separated into training and prediction sets for data analyses. The mean predictive accuracies of distinguishing neoplastic tissue from non-neoplastic tissue with MLR, LDA, and BNN were 85, 82, and 85%, respectively. In a similar fashion, the more clinically relevant problem of distinguishing adenomatous polyps from hyperplastic polyps was assessed. The mean predictive accuracies of distinguishing adenomatous polyps from hyperplastic polyps with MLR, LDA, and BNN were 85, 81, and 82%, respectively. The major spectral differences between tissues were attributed to changes in blood volume, oxygen saturation of hemoglobin, mean vessel depth within tissue, and tissue scattering.

Determination of Stability of Rock Slope Using Intelligent Pattern Recognition Techniques

2016 ◽  
pp. 167-184
Author(s):  
Swaptik Chowdhury ◽  
Pratik Goyal ◽  
R. Hariharan ◽  
Pijush Samui
Keyword(s):  
Pattern Recognition ◽  
Rock Slope ◽  
Slope Angle ◽  
Classification Problem ◽  
Unit Weight ◽  
Pattern Recognition Techniques ◽  
Robust Model ◽  
Learning Machine ◽  
Stability Of Rock Slope

This article adopts Minimax Probability Machine (MPM) and Extreme Learning Machine (ELM) for prediction of stability status of rock slope. The proposed MPM and ELM models use unit weight (?), cohesions (cA) and (cB), angles of internal friction (?A) and ?B, angle of the line of intersection of the two joint-sets (?p), slope angle (?f), and height (H) as input parameters. For this chapter the determination of stability of rock slope has been adopted as classification problem. The developed MPM and ELM have been compared with each other. The results of this article shows that the developed MPM is robust model for prediction of stability status of rock slope.

Generation of Simulated Mass Spectra of Small Organic Molecules by Computerized Pattern Recognition Techniques

1973 ◽  
Vol 27 (1) ◽  
pp. 30-40 ◽  
Author(s):  
Joseph Schechter ◽  
Peter C. Jurs
Keyword(s):  
Pattern Recognition ◽  
Mass Spectra ◽  
Organic Molecules ◽  
Molecular Descriptor ◽  
Empirical Method ◽  
Molecular Structures ◽  
Small Organic Molecules ◽  
Mass Spectral ◽  
Pattern Recognition Techniques ◽  
System A

An empirical method employing computerized pattern recognition techniques has been applied to the generation of simulated mass spectra of small organic molecules. Molecular structures are represented in computer-compatible form through the use of a fragmentation code which assigns code designations to specific groups of atoms and/or bonds within the molecules. Using such descriptions of molecules, pattern classifiers have been developed to predict the presence or absence of mass spectral peaks in each of 60 nominal m/e positions and to give a measure of the intensity of peaks in 11 of these. Information in the molecular descriptor lists which correlates with the appearance of specific peaks is shown to be present in relatively few of the descriptors developed. To test the complete system, a number of entire mass spectra were developed; in this test, 93% of the classifications were made correctly.

Statistical Pattern Recognition Techniques for Early Diagnosis of Diabetic Neuropathy by Posturographic Data

2012 ◽  
pp. 17-28
Author(s):  
Claudia Diamantini ◽  
Sandro Fioretti ◽  
Domenico Potena
Keyword(s):  
Pattern Recognition ◽  
Early Diagnosis ◽  
Diabetic Neuropathy ◽  
Statistical Pattern Recognition ◽  
Classification Model ◽  
Linear Discriminant ◽  
Peripheral Diabetic Neuropathy ◽  
Pattern Recognition Techniques ◽  
Vector Quantizer ◽  
Statistical Pattern

The goal of this chapter is to describe the use of statistical pattern recognition techniques in order to build a classification model for the early diagnosis of peripheral diabetic neuropathy. In particular, the authors present two experimental methodologies, based on linear discriminant analysis and Bayes vector quantizer algorithms respectively. The former algorithm has demonstrated the best performance in distinguish between non-neuropathic and neuropathic patients, while the latter is able to build models that recognize the severity of the neuropathy.

Recognizing Molecular Structural Features by Pattern Recognition Techniques

2021 ◽  
Author(s):  
Qing Lu ◽  
Wensheng Bian
Keyword(s):  
Pattern Recognition ◽  
Convex Hull ◽  
Structural Features ◽  
Machine Learning Techniques ◽  
Pattern Recognition Techniques ◽  
Blob Detection ◽  
Learning Techniques ◽  
Adsorption Processes ◽  
Non Covalent Interactions ◽  
Covalent Interactions

Abstract Recognition of molecular structural features is one of the most attractive fields in chemistry, especially when combining with machine learning techniques. Pattern recognition techniques are straightforward in recognizing graphic features, but little attention was given to recognize molecular structural features. In this work, we propose a new method taking advantage of pattern recognition techniques to analyze structural features and obtain novel chemical insights. Specifically, the cluster analysis is presented to recognize structural features, which provides an alternative to the most widely used root mean square deviation (RMSD) method and the recently proposed blob detection method. Based on this, the convex hull of the molecule is constructed. The convex hull of molecules is highly appealing in the sense that one can introduce established theorems and properties from other disciplines into chemistry. Novel molecular descriptors based on convex hulls can be defined and show encouraging results, especially in providing new insights in understanding non-covalent interactions, adsorption processes, etc.

Sign in / Sign up

Export Citation Format

Share Document