An Improved Fuzzy Neural Network for Solving Uncertainty in Pattern Classification and Identification
نویسندگان
چکیده مقاله:
Dealing with uncertainty is one of the most critical problems in complicatedpattern recognition subjects. In this paper, we modify the structure of a useful UnsupervisedFuzzy Neural Network (UFNN) of Kwan and Cai, and compose a new FNN with 6 types offuzzy neurons and its associated self organizing supervised learning algorithm. Thisimproved five-layer feed forward Supervised Fuzzy Neural Network (SFNN) is used forclassification and identification of shifted and distorted training patterns. It is generallyuseful for those flexible patterns which are not certainly identifiable upon their features. Toshow the identification capability of our proposed network, we used fingerprint, as the mostflexible and varied pattern. After feature extraction of different shapes of fingerprints, thepattern of these features, “feature-map”, is applied to the network. The network firstfuzzifies the pattern and then computes its similarities to all of the learned pattern classes.The network eventually selects the learned pattern of highest similarity and returns itsspecific class as a non fuzzy output. To test our FNN, we applied the standard (NISTdatabase) and our databases (with 176×224 dimensions). The feature-maps of thesefingerprints contain two types of minutiae and three types of singular points, each of themis represented by 22×28 pixels, which is less than real size and suitable for real timeapplications. The feature maps are applied to the FNN as training patterns. Upon its settingparameters, the network discriminates 3 to 7 subclasses for each main classes assigned toone of the subjects.
منابع مشابه
AN IMPROVED CONTROLLED CHAOTIC NEURAL NETWORK FOR PATTERN RECOGNITION
A sigmoid function is necessary for creation a chaotic neural network (CNN). In this paper, a new function for CNN is proposed that it can increase the speed of convergence. In the proposed method, we use a novel signal for controlling chaos. Both the theory analysis and computer simulation results show that the performance of CNN can be improved remarkably by using our method. By means of this...
متن کاملan improved controlled chaotic neural network for pattern recognition
a sigmoid function is necessary for creation a chaotic neural network (cnn). in this paper, a new function for cnn is proposed that it can increase the speed of convergence. in the proposed method, we use a novel signal for controlling chaos. both the theory analysis and computer simulation results show that the performance of cnn can be improved remarkably by using our method. by means of this...
متن کاملPattern classification by an incremental learning fuzzy neural network
A new learning algorithm suitable for pattern classification in machine condition health monitoring based on ficzzy neural networks called an 'Yncremental Learning F u q ~ Neuron Network" (I..B?l has been developed. 17re ILFN, using Gaussian neurons to represent the distributions of the input space, is an on-line, one-pass, and incremental learning algorithm. The network is a selforganized clas...
متن کاملFuzzy Miner - A Fuzzy System for Solving Pattern Classification Problems
The purpose of this paper is to study the problem of pattern classification as this is presented in the context of data mining. Among the various approaches we focus on the use of Fuzzy Logic for pattern classification, due to its close relation to human thinking. More specifically, this paper presents a heuristic fuzzy method for the classification of numerical data, followed by the design and...
متن کاملمنابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ذخیره در منابع من قبلا به منابع من ذحیره شده{@ msg_add @}
عنوان ژورنال
دوره 4 شماره 3
صفحات 71- 78
تاریخ انتشار 2008-10
با دنبال کردن یک ژورنال هنگامی که شماره جدید این ژورنال منتشر می شود به شما از طریق ایمیل اطلاع داده می شود.
میزبانی شده توسط پلتفرم ابری doprax.com
copyright © 2015-2023