Bipartite Graph Representation of Multiple Decision Table Classifiers

In this paper, we consider the two-class classification problem, a significant issue in machine learning. From a given set of positive and negative samples, the problem asks to construct a classifier that predicts the classes of future samples with high accuracy. For this problem, we have studied a new visual classifier in our previous works, which is constructed as follows: We first create several decision tables and extract a bipartite graph structure (called an SE-graph) between the given set of samples and the set of created decision tables.We then draw the bipartite graph as a two-layered drawing by using an edge crossing minimization technique, and the resulting drawing acts as a visual classifier. We first describe our background and philosophy on such a visual classifier, and then consider improving its classification accuracy. We demonstrate the effectiveness of our methodology by computational studies using benchmark data sets, where the new classifier outperforms our older version, and is competitive even with such standard classifiers as C4.5 or LibSVM.

[1]  David S. Johnson,et al.  Crossing Number is NP-Complete , 1983 .

[2]  Stephen Chen,et al.  Towards the automated design of phased array ultrasonic transducers: Using particle swarms to find "smart" start points , 2007 .

[3]  A. Asuncion,et al.  UCI Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences , 2007 .

[4]  David L. Waltz,et al.  Toward memory-based reasoning , 1986, CACM.

[5]  Jon R. Kettenring,et al.  The Practice of Cluster Analysis , 2006, J. Classif..

[6]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[7]  Peter Eades,et al.  Edge crossings in drawings of bipartite graphs , 1994, Algorithmica.

[8]  Hiroshi Nagamochi,et al.  An Improved Bound on the One-Sided Minimum Crossing Number in Two-Layered Drawings , 2005, Discret. Comput. Geom..

[9]  Ron Kohavi,et al.  The Power of Decision Tables , 1995, ECML.

[10]  Weidong Huang,et al.  Layout Effects on Sociogram Perception , 2005, GD.

[11]  Colin Ware.  Designing with a 2 1/2-D Attitude , 2001 .

[12]  Stefan Wrobel,et al.  Machine Learning: ECML-95 , 1995, Lecture Notes in Computer Science.

[13]  Helen C. Purchase,et al.  Which Aesthetic has the Greatest Effect on Human Understanding? , 1997, GD.

[14]  Mitsuhiko Toda,et al.  Methods for Visual Understanding of Hierarchical System Structures , 1981, IEEE Transactions on Systems, Man, and Cybernetics.

[15]  Jerome H. Friedman,et al.  Recent Advances in Predictive (Machine) Learning , 2006, J. Classif..

[16]  Norbert Jankowski,et al.  Transformations of Symbolic Data for Continuous Data Oriented Models , 2003, ICANN.

[17]  Michael Jünger,et al.  Journal of Graph Algorithms and Applications 2-layer Straightline Crossing Minimization: Performance of Exact and Heuristic Algorithms , 2022 .

[18]  Xiaotie Deng,et al.  Crossings and Permutations , 2005, Graph Drawing.

[19]  Erkki Oja,et al.  Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003 , 2003, Lecture Notes in Computer Science.

[20]  Ian Witten,et al.  Data Mining , 2000 .

[21]  Casimir A. Kulikowski,et al.  Computer Systems That Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning and Expert Systems , 1990 .

[22]  Moni Naor,et al.  Rank aggregation methods for the Web , 2001, WWW '01.

[24]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[25]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[26]  Hiroshi Nagamochi,et al.  Extension of ICF Classifiers to Real World Data Sets , 2007, IEA/AIE.