Data analysis in artificial intelligence
Download as PPTX, PDF2 likes188 views
The document analyzes different machine learning algorithms for classifying objects in two datasets: a ZOO dataset with 18 features and 7 classes, and a Glass Identification dataset with 10 features and 6 classes. For each dataset and algorithm, it provides the classification accuracy, confusion matrix, and compares the performance of Naive Bayes, KNN, Logistic Regression, Decision Tree, and ANN classifiers. The best performing algorithm for the ZOO dataset was ANN with 95.098% accuracy, while Decision Tree worked best for the Glass Identification dataset with 97.66% accuracy.
Data analysis in artificial intelligence
- 1. Performance Analysis on Glass Identification & ZOO dataset Group Members : Nazmul Hyder Md. Ariful Islam United International University. Dhaka Bangladesh
- 2. Problem descriptor. Preprocess visualization. Used algorithms. Results. Data analysis graph. Discussion.
- 3. Dataset Name: Glass Identification. ZOO. ZOO dataset : Data Number of features Level ZOO 18 7
- 4. Data source : Dataset Creator Donor ZOO Richard Forsyth Richard S. Forsyth 8 Grosvenor Avenue Mapperley Park Nottingham NG3 5DX 0602-621676
- 5. 1.Animal name.(unique for each ins.) 2.Hair.(boolean) 3.Feathers.(boolean) 4.Eggs.(boolean) 5.Milk.(boolean) 6.Airbone.(boolean) 7.Aquatic.(boolean) 8.predator.(boolean) 9.Toothed.(boolean) 10.Backbone.(boolean) 11.Breathes.(boolean) 12.Venomous.(boolean) 13.Fins.(boolean) 14.Legs.(numeric) 15.Tails.(boolean) 16.Domestic.(boolean) 17.Catsize.(boolean) 18.Type.(numeric)
- 7. Naive Bayes Classifier. K Nearest Neighbor. Logistic Regression. Decision Tree. Artificial Neural Network.
- 8. algorithm Correctly classified Instance Incorrectly classified Instance Cross-validation NBC 94.1176% 5.8824% 100 Confusion Matrix: : Classified as a=String b=mammal c=fish d=bird e=invertebrate f=insect g=amphibian h=reptile a b c d e f g h 1 0 0 0 0 0 0 0 0 41 0 0 0 0 0 0 0 0 13 0 0 0 0 0 0 0 0 20 0 0 0 0 0 0 0 0 7 2 0 1 0 0 0 0 0 8 0 0 0 0 0 0 0 0 3 1 0 0 1 1 0 0 0 3
- 9. algorithm Correctly classified Instance Incorrectly classified Instance Cross- validation K KNN 92.1516% 7.8431% 100 5 KNN 88.2353% 11.7647% 100 7 Confusion Matrix: Classified as a=String b=mammal c=fish d=bird e=invertebrate f=insect g=amphibian h=reptile a b c d e f g h 0 1 0 0 0 0 0 0 0 41 0 0 0 0 0 0 0 0 13 0 0 0 0 0 0 0 0 20 0 0 0 0 0 0 0 0 8 2 0 1 0 0 0 0 0 8 0 0 0 0 0 0 1 0 3 0 0 0 2 1 0 0 1 1
- 10. algorithm Correctly classified Instance Incorrectly classified Instance Cross-validation Logistic Regression 94.1176% 5.8824% 100 Confusion Matrix: Classified as a=String b=mammal c=fish d=bird e=invertebrate f=insect g=amphibian h=reptile a b c d e f g h 0 0 0 1 0 0 0 0 0 41 0 0 0 0 0 0 0 0 12 0 0 0 0 1 0 0 0 20 0 0 0 0 0 0 0 0 10 1 0 0 0 0 0 0 0 8 0 0 0 0 0 0 0 1 2 1 0 0 1 1 0 0 0 3
- 11. algorithm Correctly classified Instance Incorrectly classified Instance Cross-validation Decision Tree 91.1765% 8.8234% 100 Confusion Matrix: Classified as a=String b=mammal c=fish d=bird e=invertebrate f=insect g=amphibian h=reptile a b c d e f g h 0 1 0 0 0 0 0 0 0 41 0 0 0 0 0 0 0 0 13 0 0 0 0 0 0 0 0 20 0 0 0 0 0 0 0 0 8 2 0 0 0 0 0 0 3 5 0 0 0 0 0 0 0 0 3 1 0 0 1 0 1 0 0 3
- 12. algorithm Correctly classified Instance Incorrectly classified Instance Cross-validation ANN 95.098% 4.902% 10 Confusion Matrix: Classified as a=String b=mammal c=fish d=bird e=invertebrate f=insect g=amphibian h=reptile a b c d e f g h 0 1 0 1 0 0 0 0 0 41 0 0 0 0 0 0 0 0 13 0 0 0 0 0 0 0 0 20 0 0 0 0 0 0 0 0 9 0 0 1 0 0 0 0 3 8 0 0 0 0 0 0 0 0 3 1 0 0 1 1 0 0 0 3
- 13. Algorithms Correctly classified instance Incorrectly classified instance NBC 94.1176% 5.8824% KNN 92.1516% 7.8431% Logistic Regression 94.1176% 5.8824% Decision Tree 91.1765% 8.8234% ANN 95.098% 4.902%
- 15. (based on results) ANN>NBC>Logistic Regression>KNN>Decision Tree. ANN is the best correctly classified algorithm for this dataset. On the other hand rest of the algorithms also provides a good result. And we know that in maximum case Artificial Neural Network works well for any kind of dataset which have lots of attributes .That’s why it is more correctly classified data than the others.
- 16. Dataset Name: Glass Identification. Glass Identification dataset : Data Number of features Level Glass Identification 10 6
- 17. Data source : Dataset Creator Donor Glass Identification B. German Central Research Establishment Home Office Forensic Science Service Vina Spiehler, Ph.D.,DABFT Diagnostic Products Corporation
- 18. Id number.(numeric) Refractive index(RI) .(numeric) Sodium(Na) .(numeric) Magnesium (Mg) .(numeric) Aluminum(Al) .(numeric) Silicon (Si) .(numeric) Potassium (K) .(numeric) Calcium (Ca) .(numeric) Barium(Ba) .(numeric) Iron(Fe) .(numeric)
- 20. algorithm Correctly classified Instance Incorrectly classified Instance Cross-validation NBC 82.71% 17.29% 100 Confusion Matrix: Classified as a = building_windows_float_processed b=building_windows_non_float_processed c = vehicle_windows_float_processed d = containers e = tableware f = headlamps a b c d e f 68 2 0 0 0 0 19 50 6 1 0 0 0 2 15 0 0 0 0 4 0 8 0 1 0 0 0 0 8 1 0 1 0 0 0 28
- 21. algorithm Correctly classified Instance Incorrectly classified Instance Cross- validation K KNN 88.32 % 11.68 % 100 5 KNN 86.45% 13.55% 100 9 Confusion Matrix: Classified as a = building_windows_float_processed b=building_windows_non_float_processed c = vehicle_windows_float_processed d = containers e = tableware f = headlamps a b c d e f 68 2 0 0 0 0 3 71 0 2 0 0 0 5 12 0 0 0 0 2 0 7 1 3 0 0 0 2 7 0 0 1 1 1 2 24
- 22. algorithm Correctly classified Instance Incorrectly classified Instance Cross-validation Logistic Regression 94.86% 5.14% 100 Confusion Matrix: Classified as a = building_windows_float_processed b=building_windows_non_float_processed c = vehicle_windows_float_processed d = containers e = tableware f = headlamps a b c d e f 69 1 0 0 0 0 1 73 1 1 0 0 0 1 16 0 0 0 0 2 1 10 0 0 0 0 0 0 9 0 0 0 1 1 1 26
- 23. algorithm Correctly classified Instance Incorrectly classified Instance Cross-validation Decision Tree 97.66% 2.34% 100 Confusion Matrix: Classified as a = building_windows_float_processed b=building_windows_non_float_processed c = vehicle_windows_float_processed d = containers e = tableware f = headlamps a b c d e f 69 1 0 0 0 0 0 75 1 0 0 0 0 0 17 0 0 0 0 0 1 11 1 0 0 0 0 0 8 1 0 0 0 0 0 29
- 24. algorithm Correctly classified Instance Incorrectly classified Instance Cross-validation ANN 94.86% 5.14% 100 Confusion Matrix: Classified as a = building_windows_float_processed b=building_windows_non_float_processed c = vehicle_windows_float_processed d = containers e = tableware f = headlamps a b c d e f 70 0 0 0 0 0 1 74 0 0 0 1 0 2 15 0 0 0 0 0 1 10 1 1 0 0 0 1 8 0 0 0 0 1 2 26
- 25. Algorithms Correctly classified instance Incorrectly classified instance NBC 82.71% 17.29% KNN 88.32 % 11.68 % Logistic Regression 94.86% 5.14% Decision Tree 97.66% 2.34% ANN 94.86% 5.14%
- 27. Algorithms Correctly classified instance Incorrectly classified instance NBC 82.71% 17.29% KNN 88.32 % 11.68 % Logistic Regression 94.86% 5.14% Decision Tree 97.66% 2.34% ANN 94.86% 5.14%
- 28. That’s All