Notice: Undefined index: linkPowrot in C:\wwwroot\wwwroot\publikacje\publikacje.php on line 1275
Publikacje
Pomoc (F2)
[27412] Rozdział:

Fuzzy rule-based modelling of the web server statistics

w książce:   Information Systems Architecture and Technology (L. Borzemski, A. Grzech, J. Świątek, Z. Wilimowska (Ed.) )
ISBN:  9788374934176
Wydawca:  Designing, Development and Implementation of Information Systems
Opublikowano: 2008
Seria wydawnicza:  Biblioteka Informatyki Szkół Wyższych, Politechnika Wrocławska
Liczba stron:  8
Liczba arkuszy wydawniczych:  0.50
 
  Autorzy / Redaktorzy / Twórcy
Imię i nazwisko Wydział Katedra Procent
udziału
Liczba
punktów
Adam Głuszek orcid logoWEAiIKatedra Elektroniki i Systemów Inteligentnych *****50.00  
Filip Rudziński orcid logoWEAiIKatedra Elektroniki i Systemów Inteligentnych *****50.00  

Grupa MNiSW:  Autorstwo rozdziału w monografii naukowej w językach: angielskim, niemieckim, francuskim, hiszpańskim, rosyjskim lub włoskim
Punkty MNiSW: 0



Słowa kluczowe:

sztuczna inteligencja  odkrywanie wiedzy  systemy rozmyte  algorytmy genetyczne 


Keywords:

artificial intelligence  knowledge discovery  fuzzy modelling  fuzzy systems  genetic algorithms 



Abstract:

The main aim of the paper is to present an approach to the construction of fuzzy rule-based model and its application to modelling of the web server statistics. First, the general problem synthesizing a rule-based model from data is shortly described. Then, the details of knowledge representation in the fuzzy rule base are discussed. Next section presents the results obtained applying proposed methodology to the modelling of the real-world web server statistics. The problem is to synthesize the knowledge base – in the form of fuzzy conditional rules – which enables to forecast the amount of the data sent by the server based on some other values taken from its statistics. This question can be considered also as the knowledge discovery in the real-world statistical data. The most important criterions of assessment of the model are its performance (the accuracy of modelling) and interpretability (the transparency and the ability to explain generated decisions; it also includes an analysis and reduction of obtained fuzzy rule base). Finally, the conclusions are provided.