Data Set Information:

Vina conducted a comparison test of her rule-based system, BEAGLE, the nearest-neighbor algorithm, and discriminant analysis.  BEAGLE is a product available through VRS Consulting, Inc.; 4676 Admiralty Way, Suite 206; Marina Del Ray, CA 90292 (213) 827-7890 and FAX: -3189. In determining whether the glass was a type of "float" glass or not, the following results were obtained (# incorrect answers):

Type of Sample  -- Beagle -- NN -- DA
Windows that were float processed (87)  -- 10 -- 12 -- 21
Windows that were not:            (76) -- 19 -- 16 -- 22

The study of classification of types of glass was motivated by criminological investigation.  At the scene of the crime, the glass left can be used as evidence...if it is correctly identified!

Attribute Information:

1. Id number: 1 to 214
2. RI: refractive index
3. Na: Sodium (unit measurement: weight percent in corresponding oxide, as are attributes 4-10)
4. Mg: Magnesium
5. Al: Aluminum
6. Si: Silicon
7. K: Potassium
8. Ca: Calcium
9. Ba: Barium
10. Fe: Iron
11. Type of glass: (class attribute)
    -- 1 building_windows_float_processed
    -- 2 building_windows_non_float_processed
    -- 3 vehicle_windows_float_processed
    -- 4 vehicle_windows_non_float_processed (none in this database)
    -- 5 containers
    -- 6 tableware
    -- 7 headlamps

Relevant Papers:

Ian W. Evett and Ernest J. Spiehler. Rule Induction in Forensic Science. Central Research Establishment. Home Office Forensic Science Service. Aldermaston, Reading, Berkshire RG7 4PN
[Web link]

Papers That Cite This Data Set¹:

Ping Zhong and Masao Fukushima. A Regularized Nonsmooth Newton Method for Multi-class Support Vector Machines. 2005.  [View Context].

Yuan Jiang and Zhi-Hua Zhou. Editing Training Data for kNN Classifiers with Neural Network Ensemble. ISNN (1). 2004.  [View Context].

S. Augustine Su and Jennifer G. Dy. Automated hierarchical mixtures of probabilistic principal component analyzers. ICML. 2004.  [View Context].

Xiaoli Z. Fern and Carla Brodley. Solving cluster ensemble problems by bipartite graph partitioning. ICML. 2004.  [View Context].

Vassilis Athitsos and Stan Sclaroff. Boosting Nearest Neighbor Classifiers for Multiclass Recognition. Boston University Computer Science Tech. Report No, 2004-006. 2004.  [View Context].

Francesco Masulli. An experimental analysis of the dependence among codeword bit errors in ECOC learning machines. and Giorgio Valentini b,c. 2003.  [View Context].

Krzysztof Krawiec. Genetic Programming-based Construction of Features for Machine Learning and Knowledge Discovery Tasks. Institute of Computing Science, Poznan University of Technology. 2002.  [View Context].

Michail Vlachos and Carlotta Domeniconi and Dimitrios Gunopulos and George Kollios and Nick Koudas. Non-linear dimensionality reduction techniques for classification and visualization. KDD. 2002.  [View Context].

Giorgio Valentini and Francesco Masulli. NEURObjects: an object-oriented library for neural network development. Neurocomputing, 48. 2002.  [View Context].

D. I. S I and Francesco Masulli and Giorgio Valentini and D. I. S. Universit#a di Genova. Dipartimento di Informatica e Scienze dell' Informazione. 2001.  [View Context].

Petri Kontkanen and Petri Myllym and Tomi Silander and Henry Tirri and Peter Gr. On predictive distributions and Bayesian networks. Department of Computer Science, Stanford University. 2000.  [View Context].

Thierry Denoeux. A neural network classifier based on Dempster-Shafer theory. IEEE Transactions on Systems, Man, and Cybernetics, Part A, 30. 2000.  [View Context].

Francesco Masulli and Giorgio Valentini. Effectiveness of Error Correcting Output Codes in Multiclass Learning Problems. Multiple Classifier Systems. 2000.  [View Context].

Nir Friedman and Iftach Nachman. Gaussian Process Networks. UAI. 2000.  [View Context].

Carlotta Domeniconi and Jing Peng and Dimitrios Gunopulos. An Adaptive Metric Machine for Pattern Classification. NIPS. 2000.  [View Context].

Mark A. Hall. Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning. ICML. 2000.  [View Context].

Kai Ming Ting and Ian H. Witten. Issues in Stacked Generalization. J. Artif. Intell. Res. (JAIR, 10. 1999.  [View Context].

Christopher J. Merz. Using Correspondence Analysis to Combine Classifiers. Machine Learning, 36. 1999.  [<a href="../support/Glass+Identification#ae82a44ada49c66439b67eae7

Creator:

B. German
Central Research Establishment
Home Office Forensic Science Service
Aldermaston, Reading, Berkshire RG7 4PN

Donor:

Vina Spiehler, Ph.D., DABFT
Diagnostic Products Corporation
(213) 776-0180 (ext 3014)