Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Design and development of self-organised neural network schemes as a data mining tool
Autore:
Sumathi, S; Sivanandam, SN; Balachandar;
Indirizzi:
PSG Coll Technol, Dept Elect & Elect Engn, Coimbatore 641004, Tamil Nadu, India PSG Coll Technol Coimbatore Tamil Nadu India 641004 04, Tamil Nadu, India
Titolo Testata:
ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING AND COMMUNICATIONS
fascicolo: 2, volume: 9, anno: 2001,
pagine: 109 - 125
SICI:
1472-8915(200106)9:2<109:DADOSN>2.0.ZU;2-K
Fonte:
ISI
Lingua:
ENG
Soggetto:
ARTMAP; CLASSIFICATION;
Keywords:
Adaptive Resonance Theory1 (ART1); ART2; fuzzy ART; pruning; rule extraction; rule validation;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
--discip_EC--
Citazioni:
65
Recensione:
Indirizzi per estratti:
Indirizzo: Sumathi, S PSG Coll Technol, Dept Elect & Elect Engn, Coimbatore 641004, Tamil Nadu, India PSG Coll Technol Coimbatore Tamil Nadu India 641004 adu, India
Citazione:
S. Sumathi et al., "Design and development of self-organised neural network schemes as a data mining tool", ENG INTEL S, 9(2), 2001, pp. 109-125

Abstract

Information and energy are at the core of everything around us. Our entireexistence is a process of gathering, analyzing, understanding and acting on the information. For many applications dealing with large amount of data,Pattern classification is a key element in arriving at the solution. Engineering applications like SONAR, RADAR, SEISMIC and medical diagnosis require the ability to accurately classify the recorded data for controlling, tracking and decision making respectively. Although modern technologies enablestorage of large streams of data, we do not yet have a technology to help us to understand, analyze, or even visualize the hidden information in the data. Data Mining is now the emerging field attracting all research communities. Pattern classification is one particular category of Data Mining, which enables the Discovery of Knowledge from Very Large Databases (VLDB). Modern developments in hardware and software technologies have paved way for developing the software for analyzing and visualizing the data. This development is based on the application of data mining concept. Artificial Neural Networks are used to mine the data base which has better noise immunity andlesser training time. The paper aims mainly at classification accuracy with reduction in learning time using self-organizing neural networks. The newness in the concept of Adaptive Resonance Theory (ART) makes this as the best and efficient approach for classification. In the first phase, the ART1 network was constructed. The pruning phase aims at removing redundant linksand units without increasing the classification error rate of the network. The final phase extracts the classification rules from the final weights of the pruned network in the form of IF-THEN rules. Finally the extracted rules have been validated for its correctness. The rule extraction process ofART network is simple compared to BPN rule extraction process. Moreover the rules extracted from this network is also very simple compared tp BPN approach. This approach is most widely used in the Medical industry for correct prediction of patients when the database is so large. The performance evaluation all the networks namely, ART1, ART2 and Fuzzy ART have been done and compared with conventional methods. Simulation is carried out using the medical data bases taken from the UCI repository of machine learning data bases.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 04/04/20 alle ore 12:05:21