You are here

Home » Content

ÇOKLU İLİŞKİSEL VERİ MADENCİLİĞİNDE GRAFİKLERİN KULLANIMI

USING GRAPHS IN MULTI RELATIONAL DATA MINING

Journal Name:

  • Journal of Naval Sciences And Engineering

Publication Year:

  • 2015

Key Words:

Keywords (Original Language):

Author NameUniversity of Author
Abstract (2. Language): 
Multi-relational concept discovery aims to find the relational rules that best describe the target concept. In this paper, we present a graph-based concept discovery method in Multi- Relational Data Mining. Concept rule discovery aims at finding the definition of a specific concept in terms of relations involving background knowledge. The proposed method is an improvement over a state-of-the-art concept discovery system that uses both ILP and conventional association rule mining techniques during concept discovery process. The proposed method generates graph structures with respect to data that is initially stored in a relational database and utilizes them to guide the concept induction process. A set of experiments is conducted on data sets that belong to different learning problems. The results show that the proposed method has promising results in comparison to state of the art methods.
Bookmark/Search this post with
Abstract (Original Language): 
Çok ilişkili konsept keşfinin amacı hedef konsepti en iyi şekilde anlatabilen ilşkisel kuralları bulmaktır. Bu çalışma ile çok ilişkili veri madenciliğinde diyagram tabanlı konsept keşif metodundan bahsediyoruz. Konsept kural keşfi, arkaplan bilgilerini içeren ilişkileri gözönünde bulundurarak özel bir konsetin tanımını bulmayı hedefler. Anlatılan metot C^2D konsept keşif sisteminin geliştirlmesi ile elde edilmiştir. C^2D konsept keşfi esnasında ILP ve geleneksel ortaklık kural madenciliği (APRIORI gibi) tekniklerini birlikte kullanır. Anlatılan sistem, isim olarak D-KKS(Diyagram tabanlı Konsept Keşif Sistemi), başlangıçta ilişkisel veritabanında tutulan verilere bağlı kalmak kaydı ile diyagram yapılarını oluşturur ve bu verileri kullanarak konsept çıkarsama sürecini yönlendirir.Farklı öğrenme problemleri ile alakalı veri setleri üzerinde testler yapılmıştır. Test sonuçları D-KKS'nin, bu alandaki diğer sistemler ve C^2D'ye nispeten umut verici olduğunu göstermektedir.
FULL TEXT (PDF): 
PDF icon arastirmax-coklu-iliskisel-veri-madenciliginde-grafiklerin-kullanimi.pdf
  • 1
19
33
  • Turkish

REFERENCES

References: 

[1] Dzeroski, S.: Multi-relational data mining: an introduction. SIGKDD
Explorations 5(1) (2003) 1-16
[2] Muggleton, S.: Inductive Logic Programming. In: The MIT Encyclopedia
of the Cognitive Sciences (MITECS). MIT Press (1999)
[3] Huchard, M., Hacene, M.R., Roume, C., Valtchev, P.: Relational concept
discovery in structured datasets. Ann. Math. Artif. Intell. 49(1-4) (2007) 39-76
[4] Quinlan, J.R.:Learning logical definitions from relations. Mach. Learn.
5(3) (1990) 239-266
[5] Dehaspe, L., Toivonen, H.: Discovery of relational association rules. In
Dzeroski S., Lavra c, N., eds.: Relational Data Mining. Springer-Verlag
(September 2001) 189-212
[6] Alphonse, E, Osmani, A.: On the connection between the phase transition of
the covering test and the learning success rate in ilp. Machine Learning 70(2-3)
(2008) 135-150
[7] Mutlu, A., Karagoz, P.: A hybrid graph-based method for concept rule
discovery. In: Data Warehousing and Knowledge Discovery - 15th International
Conference, DaWaK 2013, Prague, Czech Republic, August 26-29, 2013.
Proceedings. (2013) 327-338
[8] Gao, Z., Zhang, Z., Huang, Z.: Learning relations by path finding and
simultaneous covering. In: CSIE (5). (2009) 539-543
[9] Agrawal, R., Mannila, H., Srikant, R., Toivonen, H., Verkamo, A.I.: Fast
discovery of association rules. In: Advances in Knowledge Discovery and Data
Mining. AAAI/MIT Press (1996) 307-328
[10] Kavurucu, Y., Senkul, P., Toroslu, I.H.: Ilp-based concept discovery in
multirelational data mining. Expert Syst. Appl. 36(9) (November 2009) 11418-
11428
Using Graphs in Multi Relational Data Mining
33
[11] Kavurucu, Y., Senkul, P., Toroslu, I.H.: Concept discovery on relational
databases: New techniques for search space pruning and rule quality improvement.
Knowledge-Based Systems 23(8) (December 2010) 743-756
[12] Muggleton, S.: Inverse entailment and Progol. New Generation Computing,
Special issue on Inductive Logic Programming 13(3-4) (1995) 245-286
[13] Srinivasan, A.: The Aleph Manual (1999)
[14] Dehaspe, L., Raedt, L.D.: Mining association rules in multiple relations. In:
ILP'97:Proceedings of the 7th International Workshop on Inductive Logic
Programming, London,UK, Springer-Verlag(1997) 125-132
[15] Gonzalez, J.A., Holder, L.B., Cook, D.J.: Graph-based concept learning.
In:FLAIRS Conference. (2001) 377-381
[16] Yoshida, K., Motoda, H.: Clip: Concept learning from inference patterns.
Artif.Intell. 75(1) (1995) 63-92
[17] Richards, B.L., Mooney, R.J.: Learning relations by path finding.
In: AAAI. (1992) 50-55
[18] Michalski, R., Larson, J.: Inductive inference of vl decision rules. In:
Workshop on Pattern-Directed Inference Systems. Volume 63., Hawaii, SIGART
Newsletter, ACM (1997) 33-44
[19] Dolsak, B., Muggleton, S.: The application of inductive logic programming to
finite-element mesh design. In Muggleton, S., ed.: Inductive Logic Programming.
Academic Press (1992) 453-472
[20] Srinivasan, A., Muggleton, S., King, R.D., Sternberg, M.J.: Mutagenesis: Ilp
experiments in a non-determinate biological domain. In: Proceedings of the 4th
international workshop on inductive logic programming. Volume 237., Citeseer
(1994) 217-232

Thank you for copying data from http://www.arastirmax.com