Comparative analysis of the computational geometry and neural network classification methods for person identification purposes via the EEG : Part 1

2004 ◽  
Vol 7 (3) ◽  
pp. 319-347 ◽  
Author(s):  
Marios Poulos ◽  
Maria Rangoussi ◽  
Vasilios Chrissikopoulos ◽  
Agelos Evangelou ◽  
Fotis Georgiacodis
Keyword(s):  
Neural Network ◽  
Comparative Analysis ◽  
Computational Geometry ◽  
Classification Methods ◽  
Person Identification ◽  
Neural Network Classification

scholarly journals Klasifikasi Motif Batik Berbasis Kemiripan Ciri dengan Wavelet Transform dan Fuzzy Neural Network

2014 ◽  
Vol 5 (1) ◽  
pp. 361
Author(s):  
A Haris Rangkuti
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Fuzzy Neural Network ◽  
Classification Methods ◽  
Neural Network Classification ◽  
Fuzzy Input ◽  
Fuzzy Neural ◽  
Input Variables

 This paper introduces a classification of the image of the batik process, which is based on the similarity of the characteristics, by combining the method of wavelet transform Daubechies type 2 level 2, to process the characteristic texture consisting of standard deviation, mean and energy as input variables, using the method of Fuzzy Neural Network (FNN). Fuzzyfikasi process will be carried out all input values with five categories: Very Low (VL), Low (L), Medium (M), High (H) and Very High (VH). The result will be a fuzzy input in the process of neural network classification methods. The result will be a fuzzy input in the process of neural network classification methods. For the image to be processed seven types of batik motif is ceplok, kawung, lereng, parang, megamendung, tambal and nitik. The results of the classification process with FNN is rule generation, so for the new image of batik can be immediately known motif types after treatment with FNN classification.  For the degree of precision of this method is 86-92%.

scholarly journals Implementasi Metode Ekstraksi Fitur Gabor Filter dan Probablity Neural Network (PNN) untuk Identifikasi Kain Tapis Lampung

2020 ◽  
Vol 8 (2) ◽  
Author(s):  
admi syarif ◽  
AKBAR RISMAWAN TANJUNG ◽  
RICO ANDRIAN ◽  
FAVORISEN R. LUMBANRAJA
Keyword(s):  
Neural Network ◽  
Extraction Method ◽  
Gabor Filter ◽  
Research Report ◽  
Classification Methods ◽  
Filter Cloth ◽  
Feature Extraction Method ◽  
Neural Network Classification ◽  
The People ◽  
Orientation Parameters

Tapis Fabric is a traditional clothing of the people of Lampung in the form of a shawl cloth or a sarong made of woven cotton thread with various motifs and ornaments, silver thread or gold thread by embroidered or punched. The pattern of filter cloth is quite complex, unlike the pattern of fabric in general, with its own uniqueness that has become the culture of Lampung society until now. This filter cloth will be investigated by identifying the three types of filter cloth, namely Sasab, Bintang Perak and Gunung Beradu and see the results of its identification. The method used to identify is by combining the Gabor Filter feature extraction method which has frequency and orientation parameters and Probability Neural Network classification methods. Previously, the combination of these two methods was used to identify objects with simple patterns. The results are quite good, such as detecting faces, leaf patterns, and other simple patterns. This research is expected to get maximum identification results on the filter cloth even though it has a pattern that is not simple and will be used as a research report to determine the suitability of the method used for the filter object.

COMPARATIVE ANALYSIS OF CLASSIFICATION METHODS IN PROCESSING DATA ON THE ACTIVITIES OF CREDIT ORGANIZATIONS

2020 ◽  
pp. 29-39
Author(s):  
Yu. M. Beketnova
Keyword(s):  
Neural Network ◽  
Comparative Analysis ◽  
Money Laundering ◽  
Practical Importance ◽  
Support Vector ◽  
Classification Algorithms ◽  
Classification Methods ◽  
Processing Data ◽  
Decision Forest ◽  
Credit Institutions

The results of solving the classification problem of credit organizations from the point of view of possible involvement in the money laundering processes are presented. A comparative analysis of the results obtained using various modern classification algorithms is carried out. When analyzing credit institutions, Rosfinmonitoring analysts have to operate with large amounts of information. The actual need for the number of objects to be analyzed is in many times greater than the capabilities of analysts. This problematic situation requires prioritization of inspections. The heterogeneous nature of information resources and their significant volume exclude the possibility of their manual processing. It is necessary to move from successive expert examinations of individual objects to parallel mass automated checks, taking into account modern methodological and instrumental possibilities in the context of digital transformation of public administration. A comparative analysis of the results of processing data on the activities of credit organizations by classification methods – logistic regression, decision trees (algorithms of Two-Class Boosted Decision Forest, AdaBoost), the method of support vectors (algorithm of Two-Class Support Vector Machine), neural network methods (algorithm of Two-Class Neural Network), Bayesian networks (the algorithm of Two-Class Bayes Pointmachine) carried out. Of the classification algorithms considered, the most accurate results were shown by the algorithm of Two-Class Boosted Decision Forest (AdaBoost). The results obtained are of great practical importance and may allow Rosfinmonitoring analysts, as well as experts of the Bank of Russia, to identify deviant credit institutions potentially involved in money laundering processes.

Sign in / Sign up

Export Citation Format

Share Document