Fuzzy Pattern Recognition Method Research Articles

Diagnosis of Parkinson’s Disease using Fuzzy C-Means Clustering and Pattern Recognition

Parkinson’s disease (PD) is a global public health problem of enormous dimension. In this study, we aimed to discriminate between healthy people and people with Parkinson’s disease (PD). Various studies revealed, that voice is one of the earliest indicator of PD, and for that reason, Parkinson dataset that contains biomedical voice of human is used. The main goal of this paper is to automatically detect whether the speech/voice of a person is affected by PD. We examined the performance of fuzzy c-means (FCM) clustering and pattern recognition methods on Parkinson’s disease dataset. The first method has the main aim to distinguish performance between two classes, when trying to differentiate between normal speaking persons and speakers with PD. This method could greatly be improved by classifying data first and then testing new data using these two patterns. Thus, second method used here is pattern recognition. The experimental results have demonstrated that the combination of the fuzzy c-means method and pattern recognition obtained promising results for the classification of PD.

Method of Evaluating the Complexity of Geometries for Free-Form Surfaces

In order to improve the ability to predict the manufacturability of the free-form surfaces, the complexity of geometries for free-form surfaces is defined and studied. The free-form surfaces are modeled, which is used to calculate the distribution feature values of the surfaces. According to the feature values, free-form surfaces are classified into several clusters based on the fuzzy clustering algorithm. Group patterns are established according to feature values of the samples in the clusters. Then, the method of fuzzy pattern recognition is used to evaluate the surface complexity. The surface samples in the same cluster have close geometry configuration, so they often have similar manufacturing processes. A case study shows that the method can quickly classify the surfaces, largely reflecting the complexity of the free-form surfaces, which can lay the foundation for manufacturability evaluation of the complex surfaces.

Vehicle Model Recognition Based on Fuzzy Pattern Recognition Method

The method based on the theory of Fuzzy Pattern Recognition is divided into three parts. Firstly, use Hough transformation to extract the feature points of vehicles, and use the ratio between two absolute distance of adjacent feature points as the characteristic values of vehicles; secondly, use Fuzzy C-mean Classification to handle feature data of 75 car model, then establish a degree of membership matrix as the sample space; thirdly, consider the classification algorithm based on fuzzy approach degree and the credibility of the vehicle feature to propose a weighted close- degree recognition algorithm. This recognition method has a good effect.

Fuzzy pattern recognition method for assessing soil erosion

In this paper a PSIAC-based multi-parameter fuzzy pattern recognition (MPFPR) model is proposed and applied for classifying and ranking the potential soil erosion (PSE). In this approach, standard value matrix is used to define the membership degrees of each catchment to each class and the feature values are used for alternative ranking. The characteristic of PSE for each class is expressed by linguistic variables. The proposed method is straightforward, easy to understand, very practical, and its results may easily be interpreted. To assess the performance of the model, the results of PSIAC MPFPR and original PSIAC method are interpreted and compared with the observed data. It is shown that the proposed approach reflects the fuzzy nature of the soil erosion more efficiently and is quite robust for application in real world cases.

Multi-Axle Moving Train Loads Identification by Using Fuzzy Pattern Recognition Technique

Identification of multi-axle moving loads on bridge is very important for bridge design, construction, and maintenance in engineering field. It is complicated and time consuming to identify the multi-axle moving train loads with general identification methods and far away from practical practice. Based on the theory of fuzzy pattern recognition, the fuzzy pattern recognition method for multi-axle moving train loads identification on bridge is presented in this paper. The multi-axle moving loads pattern library on a simply supported bridge is established with numerical methods. Effect of measurement noise on the proposed method is investigated in three situations. The results show that the proposed identification method has a certain resistance to measurement noise and can realize moving train loads identification with high accuracy.

Fuzzy pattern recognition method of flatness based on particle swarm theory

Pattern recognition of strip flatness is the key to flatness close-loop control system. The result of pattern recognition of strip flatness has the direct effects on strip flatness control precision. With the development of strip flatness control methods, higher demands are presented for pattern recognition of strip flatness. To overcome the disadvantage of poor anti-interference ability and uncertain approaching ranks in traditional flatness pattern recognition, the fuzzy pattern recognition method of flatness is given ac- cording to the fuzzy classification theory, and the flatness pattern is classified by selecting nearness principle of Euclidean distance. On the basis of fuzzy pattern recognition, particle swarm theory, developed since 1990s, with global optimization capability is ap- plied to optimize the result of pattern recognition. Compared with the simplex optimization method, validity of particle swarm theory applied in flatness pattern recognition is testified. The result after optimization can accurately control the flatness adjusting sets to meet the need of high precision flatness control.

Fuzzy pattern recognition method for assessing groundwater vulnerability to pollution in the Zhangji area

Based on the widely used DRASTIC method, a fuzzy pattern recognition and optimization method was proposed and applied to the fissured-karstic aquifer of Zhangji area for assessing groundwater vulnerability to pollution. The result is compared with DRASTIC method. It is shown that by taking the fuzziness into consideration, the fuzzy pattern recognition and optimization method reflects more efficiently the fuzzy nature of the groundwater vulnerability to pollution and is more applicable in reality.

Real-time automatic detection of weld defects in steel pipe

In order to detect weld defects in steel tube, a real-time imaging and detecting system is setup. In the extracted weld seam, based on spatial characteristics near defects—variance and contrast, defects such as slags, blowholes and incomplete penetration are automatically detected using the method of fuzzy pattern recognition, and the system will automatically alarm if the defect exceeds the national standard. Compared with other methods, it is simple and fast, and has fewer misinterpretations. It can detect weld defects in real-time.

Application of a fuzzy pattern recognition method in: borehole geophysics

Application of a fuzzy pattern recognition method in: borehole geophysics

Pattern recognition of machine tool faults with a fuzzy mathematics algorithm

The accuracy and precision of CNC machine tools directly affect the quality of machined parts. Automatic diagnosis of faults can improve the maintenance efficiency of CNC machine tools, and thus increase production uptime and improve product quality. In this study, the typical fault categories of CNC machine tools, such as cyclic, backlash, scale mismatch, etc., are taken as reference patterns and recognized by the fuzzy mathematics algorithm with the machine contouring trajectory measured by an inspection device. A primary component extraction (PCE) method is introduced to recognize multiple-cause faults. The study shows that the fuzzy pattern recognition method is able to identify major components of machine tool faults, their categories and direction simultaneously, with a small amount of sampling data. As a feature-based method of fault diagnosis, the PCE method can be integrated into the computeraided maintenance of manufacturing systems.

A Fuzzy Leakage Alarm Method of Liquid Steel

Abstract A fuzzy pattern recognition method based on an improved thermocouple layout is presented to forecast breakout of liquid steel from the mould in stead of the conventional logic analysis method. A fuzzy decision making network is set up for this purpose. Experiments show that the fuzzy prediction method not only can accurately recognize temperature patterns and forecast steel leakage but also can point out possible reasons and positions of steel leakage.

A fuzzy pattern recognition method to classify esophageal motility records.

Analysis and classification of esophageal motility records were investigated using signal processing and fuzzy-set pattern recognition techniques. A set of parameters has been extracted from the raw records and has previously been used as characterizing features. Improvements to these procedures were obtained by extracting these features from processed data, and some additional parameters were developed. The new set of features was used in the design of a fuzzy classifier, and classification accuracy was estimated using the leave-one-out technique. To our knowledge, this is the first report of the application of automatic classification to esophageal motility records.

Quantitative estimation of time-variable earthquake hazard by using fuzzy set theory

In this paper, the various methods of fuzzy set theory, called fuzzy mathematics, have been applied to the quantitative estimation of the time-variable earthquake hazard. The results obtained consist of the following. 1. (1) Quantitative estimation of the earthquake hazard on the basis of seismicity data. By using some methods of fuzzy mathematics, seismicity patterns before large earthquakes can be studied more clearly and more quantitatively, highly active periods in a given region and quiet periods of seismic activity before large earthquakes can be recognized, similarities in temporal variation of seismic activity and seismic gaps can be examined and, on the other hand, the time-variable earthquake hazard can be assessed directly on the basis of a series of statistical indices of seismicity. Two methods of fuzzy clustering analysis, the method of fuzzy similarity, and the direct method of fuzzy pattern recognition, have been studied is particular. One method of fuzzy clustering analysis is based on fuzzy netting, and another is based on the fuzzy equivalent relation. 2. (2) Quantitative estimation of the earthquake hazard on the basis of observational data for different precursors. The direct method of fuzzy pattern recognition has been applied to research on earthquake precursors of different kinds. On the basis of the temporal and spatial characteristics of recognized precursors, earthquake hazards in different terms can be estimated. This paper mainly deals with medium-short-term precursors observed in Japan and China.

A fuzzy pattern recognition approach to power system transient stability assessment

The aim of the paper is the fast transient stability assessment of electric power systems by using a fuzzy pattern recognition method. The assessment is performed by assuming several regions of stable and unstable classes for the purpose of classifying the system operating states, in order to avoid errors of classification. This method is suitable for on-line applications and its performance is illustrated by the transient stability analysis of a sample power system.

An application of the direct method of fuzzy pattern recognition to researches of earthquake precursors in the Tokai area.

The direct method of fuzzy pattern recognition has been applied to researches of earthquake precursors observed in the Tokai area and its vicinity. The precursors discussed are those in radon content in ground water, level, tilt, tide and volume strain. The basic technique of the method is to construct a suitable membership function for several kinds of precursors or for one kind of precursor observed at different stations. Possible precursor patterns for short-term earthquake prediction in the Tokai area are proposed. One is applied to a multi-approach analysis of several kinds of precursors observed at different stations, another is a synthetic analysis of one kind of precursor observed at different stations. By using the method, short-term earthquake precursors can be recognized more clearly. Moreover, some noises such as rainfall influence, seasonal variation and so on can be removed. Then on the basis of fuzzy recognition of earthquake precursors, the temporal and spatial characteristics of precursors before large earthquakes can be studied more quantitatively.