Computational Intelligence Dating of the Iron Age Glass

1
Computational Intelligence Dating of the Iron
Age Glass

• Karol Grudzinski
• Bydgoszcz Academy, Poland
• Maciej Karwowski
• University of Rzeszów, Poland
• Wlodzislaw Duch
• Nanyang Institute of Technology, Singapore
• Nicolaus Copernicus University, Poland

2
Donors of the Data

• Interdisciplinary Project Celtic Glass
  Characterization Prof. G. Trnka (Institute of
  Prehistory, University of Vienna) Prof. P.
  Wobrauschek (Atomic Institute of the Austrian
  Universities in Vienna)

3
Celtic Glass samples
4
Data Description (Original Database)

• Measurements of chemical compound concentrations
  using Energy Dispersive X-ray Fluorescence
  Spectroscopy (26 compounds)
• Class chronological period of manufacturement
• LT C1 (La Tene C1, 260 170 B.C.)
• LT C2 (La Tene C2, 170 110 B.C.)
• LT D1 (La Tene D1, 110 50 B.C.)
• 555 glass measurements, usually in 4 points of a
  single glass object.

5
Questions to be answered using CI analysis

• System capable of automatic dating of glass
  artifacts given chemical compound concentrations
  is needed, because there are few experts that can
  do it.
• Exploration of the hidden patterns in the data,
  with possible implication in archeology through
  rule extraction analysis (expert archeologist are
  unable to formalize the knowledge required to
  predict date).
• Corrosion layer is on the surface, broken parts
  are less corroded. Influence of corrosion on
  measurements and prediction of the class unknown.

6
Data Preprocessing

• Challenge to classification methods several
  vectors for one object, small data. In this case
  for one glass artifact usually two measurements
  on each side on the surface and two on the broken
  parts are included.
• Database contains cases with missing class,
  belonging to other chronological periods,
  measurements on decorations were excluded.

7
Numerical Experiments

• Three different experiments
• 1st Both Surface and Broken Side Data
• 2nd Surface Data
• 3rd Broken Side Data
• Many algorithms implemented in WEKA, NETLAB, SBL
  and the GhostMiner packages were used for
  calculations.

8
Surface and Broken Side Data

• Experiment on the whole preprocessed dataset
  divided into training and test sets.
• Class Distribution (whole set)
• 1) LT C1, 29.68 (84 cases)
• 2) LT C2, 33.57 (95 cases)
• 3) LT D1, 36.75 (104 cases)
• 283 cases total, 143 training, 140 test 1
  surface and 1 side measurement (on average)
  belonging to the same glass object in both
  training and test sets !

9
Results of the First Experiment
10
Summary of the Results of the First Experiment

• LT C1 well separated.
• Naive Bayes works very well.
• SBM methods may be very misleading for such data
  measurements on the same artifact both in train
  and test uncontrolled bootstrap learning.

11
MDS visualization
12
Logical Rules Attribute Selection

• 1R Tree Rules predict correctly 100/143 training
  and 93/140 test samples
• 1. IF MnO lt 2185.205 THEN C1
• 2. IF MnO ? 2185.205,9317.315) THEN C2
• 3. IF MnO ?9317.315 THEN D1
• Important attributes MnO
• TiO2, Fe2O3, NiO, Sb2O3, ZnO (LT C1),
• Fe2O3, TiO2, NiO, PbO (LT C2)
• TiO2, Sb2O3, Fe2O3, PbO, ZnO (LT D1)

13
Surface data experiment

• Experiment on a surface measurement dataset
  divided into training and test sets.
• Class Distribution (whole set)
• 1) LT C1, 26.36 (34 cases)
• 2) LT C2, 37.98 (49 cases)
• 3) LT D1, 35.66 (46 cases)
• 129 cases total, 61 training, 68 test, cases
  belonging to the same artifact distributed into
  training and test partition.

14
Results - Second Experiment
15
Logical rules from 1R

• 1R rules predict correctly 42/61 (68.9) training
  and 43/68 (63.2) test samples.
• 1. IF MnO lt 187.34 THEN C1
• 2. IF MnO lt 3821.99,9489.09) THEN C2
• 3. IF MnO ? 187.34, 3821.99) or MnO ?
  9489.09 THEN D1

16
Logical Rules from C45

• C45 rules predict correctly 54/68 (79.4) test
  samples
• 1. IF ZrO2 gt 296.1 THEN C1
• 2. IF Na2O ? 36472.22 THEN C1
• 3. IF Sb2O3 gt2078.76 THEN C2
• 4. IF CdO 0 Na2O ? 27414.98 THEN C2
• 5. IF Na2O gt 27414.98 NiO ? 58.42 THEN D1
• 6. IF NiO gt 48.45 CdO 0 BaO 0 Br2O7 lt
  53.6 Fe2O3 ? 12003.35 ZnO ? 149.31 THEN D1
• 7. Default D1

17
Logical rules from SSV

• 1. IF MnO lt 1668.47 ZrO2 gt 303.34 THEN C1
• 2. IF MnO lt 1668.47 ZrO2 lt 303.34 TiO2 lt
  76.235, or MnO gt 1668.47 Sb2O3 gt 986.19, or
  MnO gt 1668.47 Sb2O3 lt 986.19 CaO lt 79370 THEN
  C2
• 3. IF MnO gt 1668.47 Sb2O3 lt 986.19 CaO gt
  79370, or MnO lt 1668.47 ZrO2 lt 303.34 TiO2 gt
  76.235 THEN D1

18
Broken Side Data

• Experiment on a broken side data divided into
  training and test partition
• Class Distribution (whole set)
• 1) LT C1, 32.47 (50 cases)
• 2) LT C2, 29.87 (46 cases)
• 3) LT D1, 37.66 (58 cases)
• 154 cases total, 78 training, 76 test, cases
  separated

19
Results of the third experiment
20
Logical rules from 1R

• 1R Rules predict correctly 58/78 (74.4) training
  and 57/76 (75.0) test samples.
• 1. IF MnO lt 2134.61 THEN C1
• 2. IF MnO ? 2134.61 9078.525) THEN C2
• 3. IF MnO ? 9078.525 THEN D1
• Similar Rules were found by the SSV tree with
  strong pruning.

21
Rules from C45

• 1. IF ZrO2 gt 199.38 CdO 0 THEN C1
• 2. IF NiO ? 62.23 CaO ? 114121.35 THEN C1
• 3. IF CuO ? 5105.37 MnO gt 2546.77 ZnO ?
  126.29 THEN C2
• 4. IF SnO2 gt 61.98 Br2O7 ? 64.08 THEN D1
• 5. IF Sb2O3 ? 8246.11 CuO ? 2042.19 Al2O3 gt
  11525.69 THEN D1
• 6. Default C2

22
Conclusions

• CI methods may help to assign samples of
  uncertain chronology to one of the chronological
  periods, providing rough logical rules to
  archeologists.
• Important chemical compounds useful for dating
  have been identified.
• Separate tests on the surface and broken side
  data lead to similar classification accuracies,
  confirming the hypothesis that corrosion on the
  surface has minor or no influence on results of
  the analysis.

23
Further Work

• Larger database is needed.
• Detailed predictions by the CI methods should be
  confronted with archeologists.
• There is a significant proportion of unlabeled
  samples in the original database, unsupervised
  methods should be applied using reduced feature
  space.

24
Acknowledgments

• The research on chemical analysis of the
  archeological glass was funded by the Austrian
  Science Foundation, project No. P12526-SPR.
• We are very grateful to our colleagues from the
  Atomic Institute in Vienna for making this data
  available to us.