Open Access Open Access  Restricted Access Subscription Access

A New Improved Approach for Feature Generation and Selection in Multi- Relational Statistical Modelling using ML


Affiliations
1 ABES Engineering College, Ghaziabad, Uttar Pradesh, India
2 Department of Computer Application, UIET, CSJM University, Kanpur, India
3 GIS Cell, MNNIT Prayagraj, Allahabad, India
 

Multi-relational classification is highly challengeable task in data mining, because so much data in our world is organised in multiple relations. The challenge comes from the huge collection of search spaces and high calculation cost arises in the selection of feature due to excessive complexity in the various relations. The state-of-the-art approach is based on clusters and inductive logical programming to retrieve important features and derived hypothesis. However, those techniques are very slow and unable to create enough data and information to produce efficient classifiers. In the given paper, we proposed a fast and effective method for the feature selection using multi-relational classification. Moreover we introduced the natural join and SVM based feature selection in multi-relation statistical learning. The performance of our model on various datasets indicates that our model is efficient, reliable and highly accurate.

Keywords

Feature Selection, Inductive Logical Programming, Natural Join, SVM, Statistical Learning.
User
Notifications
Font Size

  • Burges C J, A Tutorial on support vector machines for pattern recognition, datamining knowledge discovery, 2(2) (1998) 121–167.
  • Rahul M, Kohli N, Agarwal R, Mishra S, Facial expression recognition using geometric features and modified hidden markov model, Int J Grid Util Comput, 10(5) (2019) 488–496.
  • Rahul M, Kohli N, Agarwal R, Layered recognition scheme for robust facial expression recognition using modified hidden markov model, J Multimed Process Technol, 10(1) (2019) 18–26.
  • Rahul M, Kohli N, Agarwal R, Facial expression recognition using moment’s invariants and modified hidden markov model, Int J Appl Eng Res, 13(8) (2018) 6081–6088.
  • Rahul M, Kohli N, Agarwal R, Facial expression recognition using multistage hidden markov model, J Theor Appl Inf Technol, 95(23) (2017) 6379–6388.
  • Rahul M, Shukla R, Yadav D K, Yadav V, Zernike momentbased facial expression recognition using two-staged hidden markov model, Adv Comp Comm Comput Sci, 924 (2019) 661–670.
  • Rahul M, Kohli N, Agarwal R, Facial expression recognition using local binary pattern and modified hidden markov model, Int J Adv Intell Paradig, 17(3-4) (2020) 367–378.
  • Rahul M, Kohli N, Agarwal R, Partition based feature extraction technique for facial expression recognition using multi-stage hidden Markov model, J Appl Eng Sci 13(9) (2018) 2651–2658.
  • Rahul M, Kohli N, Agarwal R, Facial expression recognition using local multidirectional score pattern (LMSP) descriptor and modified hidden Markov model, Int J Adv Intell Paradig, (In Press).
  • Lavrac N, Dzeroski S, Inductive logic programming: Techniques and applications (Ellis Horwood, New York) 1994.
  • Muggleton S, Inductive logic programming, New Generat Comput, 8(4) (1991) 295–318.
  • Muggleton S, Raedt L, Inductive logic programming: Theory and methods, J Log Program, 19 (1994) 629–679.
  • Lloyd J W, Foundations of Logic Programming, (Springer, New York) 1987.
  • Quinlan J R, Cameron-Jones R M Foil, A Midterm Report, in ECML 1993, edited by Brazdil P B, LNCS, 667 (Springer, Heidelberg) 1993, 3–20,.
  • Muggleton S, Inverse entailment and progol, New Generat Comput, 13 (1995) 245–286.
  • Blockeel H, Raedt L D, Top-down induction of first-order logical decision trees, Artif Intell, 101(1-2), (1998) 285–297.
  • Quinlan J R, C4.5 Programs for Machine Learning (Morgan Kaufmann, California) 1993.
  • Yin X X, Han J W, Yang J, Yu P S, Crossmine: Efficient Classification across Multiple Database Relations, in ICDE, 2004, 399–411.
  • Kramer S, Relational learning VS Propositionalization: Investigations in Inductive Logic Programming and Propositional machine learning, Technical report, Vienna University of Technology, 1999.
  • Quinlan J R, Induction of Decision Trees, Mach Learn, 1 (1986) 81–106.
  • Lavrac N, Principles of Knowledge Acquisition in Expert Systems. PhD thesis, Facultyof Technical Sciences, University of Maribor, 1990.
  • Srinivasan A, King R D, Feature construction with inductive logic programming: A study of quantitative predictions of biological activity aided by structural attributes, Data Min Knowl Discov, 3(1) (1999), 37–57.
  • Krogel M A, On Propositionalization for knowledge discovery in relational databases, PhD thesis, Fakultat fur Informatik, Germany, 2005.
  • Molina L C, Belanche L and A Nebot, Feature selection algorithms: a survey and experimental evaluation, 2002 Proc IEEE Int Conf on Data Mining (Maebashi City, Japan) 2002, 306–313.
  • Yin X X, Han J W & Yu P S, Cross-Relational Clustering with User’s Guidance, in KDD 2005, 2005.
  • http://www.cs.waikato.ac.nz/ml/proper/datasets.html.
  • Zou M, Wang T, Li H & Yang D, A general multi-relational classification approach using feature generation and selection, ADMA 2010, Part II, LNCS 6441, 2010, 21–33.

Abstract Views: 8

PDF Views: 2




  • A New Improved Approach for Feature Generation and Selection in Multi- Relational Statistical Modelling using ML

Abstract Views: 8  |  PDF Views: 2

Authors

Vikash Yadav
ABES Engineering College, Ghaziabad, Uttar Pradesh, India
Mayur Rahul
Department of Computer Application, UIET, CSJM University, Kanpur, India
Rati Shukla
GIS Cell, MNNIT Prayagraj, Allahabad, India

Abstract


Multi-relational classification is highly challengeable task in data mining, because so much data in our world is organised in multiple relations. The challenge comes from the huge collection of search spaces and high calculation cost arises in the selection of feature due to excessive complexity in the various relations. The state-of-the-art approach is based on clusters and inductive logical programming to retrieve important features and derived hypothesis. However, those techniques are very slow and unable to create enough data and information to produce efficient classifiers. In the given paper, we proposed a fast and effective method for the feature selection using multi-relational classification. Moreover we introduced the natural join and SVM based feature selection in multi-relation statistical learning. The performance of our model on various datasets indicates that our model is efficient, reliable and highly accurate.

Keywords


Feature Selection, Inductive Logical Programming, Natural Join, SVM, Statistical Learning.

References