|
|
|
|
|
|
|
|
|
1. |
Record Nr. |
UNISA996465973703316 |
|
|
Titolo |
AI 2011: Advances in Artificial Intelligence [[electronic resource] ] : 24th Australasian Joint Conference, Perth, Australia, December 5-8, 2011, Proceedings / / edited by Dianhui Wang, Mark Reynolds |
|
|
|
|
|
|
|
Pubbl/distr/stampa |
|
|
Berlin, Heidelberg : , : Springer Berlin Heidelberg : , : Imprint : Springer, , 2011 |
|
|
|
|
|
|
|
|
|
ISBN |
|
|
|
|
|
|
Edizione |
[1st ed. 2011.] |
|
|
|
|
|
Descrizione fisica |
|
1 online resource (XVII, 821 p.) |
|
|
|
|
|
|
Collana |
|
Lecture Notes in Artificial Intelligence ; ; 7106 |
|
|
|
|
|
|
Classificazione |
|
|
|
|
|
|
|
|
Disciplina |
|
|
|
|
|
|
Soggetti |
|
Artificial intelligence |
Algorithms |
Application software |
Computers |
Information storage and retrieval |
Data mining |
Artificial Intelligence |
Algorithm Analysis and Problem Complexity |
Information Systems Applications (incl. Internet) |
Computation by Abstract Devices |
Information Storage and Retrieval |
Data Mining and Knowledge Discovery |
Kongress2011.Perth (Westaustralien) |
Conference papers and proceedings. |
|
|
|
|
|
|
|
|
Lingua di pubblicazione |
|
|
|
|
|
|
Formato |
Materiale a stampa |
|
|
|
|
|
Livello bibliografico |
Monografia |
|
|
|
|
|
Note generali |
|
Bibliographic Level Mode of Issuance: Monograph |
|
|
|
|
|
|
Nota di contenuto |
|
Intro -- Title page -- Preface -- Organization -- Table of Contents -- Session 1: Data Mining and Knowledge Discovery -- Guided Rule Discovery in XCS for High-Dimensional Classification Problems -- Introduction -- Background -- XCS Overview -- Related Work -- Model -- Experiments -- Data Sets -- Parameters -- Results -- Conclusions |
|
|
|
|
|
|
|
|
|
-- References -- Motif-Based Method for Initialization the K-Means Clustering for Time Series Data -- Introduction -- Background -- Dimensionality Reduction -- Clustering for Time Series Data -- locations are often termed the seeds for the k-Means algorithm.2.3 Time Series Motifs and the Brute-Force Algorithm for Finding Motifs -- The Proposed Clustering Method for Time Series Data -- How to Speed Up the Brute-Force Algorithm for Finding 1-Motifs -- How to Derive Initial Centers from Results of K-Means Clustering on 1-Motifs -- Experimental Evaluation -- Conclusions -- References -- Semi-Supervised Classification Using Tree-Based Self-Organizing Maps -- Introduction -- The Tree-Based Topology Oriented SOM -- The TTOSOM-Based Classifier -- Experimental Setup -- Results -- Conclusions -- References -- The Discovery and Use of Ordinal Information on Attribute Values in Classifier Learning -- Introduction -- Value of Ordinal Information -- Testing -- Results -- Discovering Orders -- Developing Methods -- Testing Order Discovery -- Random Orders for Ensemble Classifiers -- Conclusions and Further Work -- References -- Beyond Trees: Adopting MITI to Learn Rules and Ensemble Classifiers for Multi-Instance Data -- Introduction -- The MITI Algorithm -- Experimental Results -- MIRI: Using MITI to Learn Rule Sets -- Experimental Results -- Building Ensemble Classifiers -- Experimental Results -- Conclusions -- References -- Automatically Measuring the Quality of User Generated Content in Forums -- Introduction. |
Problem Definition -- UGCQ Assessment Model -- Experiment -- Datasets -- Feature Selection -- Performance Evaluation -- Post Quality Classification -- Results -- Friedman Test -- Nemenyi Test -- Discussion -- Related Work -- Conclusion -- References -- Genetically Enhanced Feature Selection of Discriminative Planetary Crater Image Features -- Introduction -- Related Work -- Genetically Enhanced Feature Selection -- Genetic Representation -- Wrapped Classifier Fitness Function -- Random Crossover -- Mutation -- Highest Fitness (Greedy) Selection -- Weighted Random Selection -- Weighted Random Selection with Simulated Annealing -- Complexity -- Experimental Results -- Conclusion -- References -- Penalized Least Squares for Smoothing Financial Time Series -- Introduction -- Current Methods -- Our Proposed Method -- Experiment Description -- Data -- Smoothness (Noise) Function -- Lag Function -- Cross Validation -- Results -- Conclusions -- References -- Logistic Regression with the Nonnegative Garrote -- Introduction -- Nonnegative Garrote -- Simulation -- Simulated Data -- Path Consistency -- Initial Estimates for the NNG -- Real Data -- Discussion and Recommendations -- References -- Identification of Breast Cancer Subtypes Using Multiple Gene Expression Microarray Datasets -- Introduction -- The Consensus Clustering Problem -- Objective Function -- The Genetic Algorithm -- The Breast Cancer Datasets -- Results -- Comparison with Existing Subtypes -- Conclusion -- References -- Combining Instantaneous and Time-Delayed Interactions between Genes - A Two Phase Algorithm Based on Information Theory -- Introduction -- Background -- Bayesian Network (BN) -- Dynamic Bayesian Network (DBN) -- Information Theoretic Quantities -- The Method -- The Framework for Representation -- Finding the Appropriate Search Strategy -- Finding the Intra-slice Arc Directions. |
Simulation and Results -- Synthetic Network -- Real-Life Biological Data -- Conclusion -- References -- A Sparse-Grid-Based Out-of-Sample Extension for Dimensionality Reduction and Clustering with Laplacian Eigenmaps -- Introduction -- Laplacian Eigenmaps and Spectral Clustering -- Sparse Grids -- Sparse-Grid-Based Out-of- |
|
|
|
|
|
|
|
Sample Extension -- Experiments -- Conclusion -- References -- Distribution Based Data Filtering for Financial Time Series Forecasting -- Introduction -- Related Work -- Distribution Based Samples Removing Algorithm -- Distance Value - Threshold Based Decision -- Distance Value - Percentage Based Decision -- Datasets -- Experiments -- Conclusion -- References -- Sequential Feature Selection for Classification -- Introduction -- Framework -- General Idea -- Sequential Classification -- Action Selection without Replacement -- Solving the POMDP -- Experiments and Discussion -- Handwritten MNIST Digit Classification -- Diabetes Dataset with Naive Bayes Classification -- Discussion -- Conclusion -- References -- Long-Tail Recommendation Based on Reflective Indexing -- Introduction -- Novelty as an Important Value of Long-Tail Recommendations -- Methodological Assumptions -- Contribution of the Paper -- Algebraic Model for PRI -- Modeling User-Item Dependencies as a Probability Space -- Reflective Data Processing -- The PRI Algorithm -- Evaluation -- Data Sets -- Recommendation Quality Evaluation -- Conclusions -- References -- Author Name Disambiguation for Ranking and Clustering PubMed Data Using NetClus -- Introduction -- Related Work -- The Challenges of Author Name Disambiguation on PubMed -- Related Work on Disambiguation of PubMed Authors -- A Multi-evidence Author Disambiguation System -- Disambiguation Using Organisation Names and Addresses -- Disambiguation Using Co-author Network -- Evaluation of the Disambiguation Technique. |
Accuracy of the Proposed Disambiguation Technique -- Evaluation of NetClus Results -- Conclusion and Future Work -- References -- Self-Organizing Maps for Translating Health Care Knowledge: A Case Study in Diabetes Management -- Introduction -- Background: Mining Diabetic Patient Data -- Application -- Chronic Disease Management (CDM) -- Chronic Disease Management Network (cdmNet) -- Chronic Disease Management Network - Business Intelligence (cdmNet-BI) Module -- The Self-Organizing Map (SOM) -- The Growing Self-Organizing Map (GSOM) -- Patterns in Diabetes Management -- Analysis of Features Common to Any Individual -- Analysis of Common Features with Diabetes Specific Medical Features -- Patterns Recognised from Diabetes Data: Outcomes -- Conclusions and Future Work -- References -- Distance-Based Feature Selection on Classification of Uncertain Objects -- Introduction -- Related Work -- Problem Definition -- UK-Means -- Supervised UK-Means -- Algorithms -- Averaging Approach -- Distribution-Based Approach -- Experimental Results -- Data Sets -- Performance Evaluation -- Conclusion -- References -- Session 2: Machine Learning -- Closure Spaces of Isotone Galois Connections and Their Morphisms -- Introduction -- Preliminaries: Matrices, Decompositions, Concept Lattices -- Closure Spaces Induced by (^,V) -- Morphisms of c-Closure Spaces -- Isomorphic c-Closure Spaces -- Conclusions -- References -- Ensemble Learning and Pruning in Multi-Objective Genetic Programming for Classification with Unbalanced Data -- Introduction -- Related Work: Ensemble Learning for Class Imbalance -- Multi-Objective GP (MOGP) for Evolving Ensembles -- GP Framework for Classification -- MOGP Fitness -- MOGP Search -- MOGP Ensemble Performance -- Evolutionary Parameters and Unbalanced Data Sets -- MOGP Ensemble Results -- Ensemble Pruning -- Fitness-Based Pruning. |
GP for Evolving Composite Voting Trees -- Performance of Ensembles Using Puning Methods -- Conclusions -- References -- Compiling Bayesian Networks for Parameter Learning Based on Shared BDDs -- |
|
|
|
|
|
|
|
|
|
Introduction -- Preliminary -- Bayesian Networks -- Parameter Learning Problem for BNs -- Proposed Method -- Encoding and Compiling -- Learning -- Experiments -- Conclusion and Related Work -- References -- An Empirical Study of Bagging Predictors for Imbalanced Data with Different Levels of Class Distribution -- Introduction -- Designed Framework -- Evaluation Metrics -- Experimental Setting -- Selection of Base Learners -- Data-Sets -- Experimental Results Analysis -- Statistical Test -- Comparison between Bagging and Single Learners -- Comparison between Bagging Predictors -- Conclusion -- References -- A Simple Bayesian Algorithm for Feature Ranking in High Dimensional Regression Problems -- Introduction -- Bayesian Feature Ranking (BFR) Algorithm -- Discussion and Results -- Simulated Data -- Real Data -- Conclusion -- References -- Semi-random Model Tree Ensembles: An Effective and Scalable Regression Method -- Introduction -- Random Model Trees -- Experiments -- Linear Regression -- Gaussian Process Regression -- Additive Groves -- Random Model Trees -- Results -- Relative Mean Absolute Error -- Conclusions -- References -- Supervised Subspace Learning with Multi-class Lagrangian SVM on the Grassmann Manifold -- Introduction -- Proposed Method -- Multi-class Lagrangian SVM -- Learning the Projection -- Experiments -- Conclusion -- References -- Bagging Ensemble Selection -- Introduction -- Bagging Ensemble Selection -- Experimental Results -- Comparison of Bagging Ensemble Selection Algorithms to the Forward Ensemble Selection Algorithms -- Comparison of Bagging Ensemble Selection Algorithms to Other Ensemble Learning Algorithms -- Conclusions. |
References. |
|
|
|
|
|
|
Sommario/riassunto |
|
This book constitutes the refereed proceedings of the 24th Australasian Joint Conference on Artificial Intelligence, AI 2011, held in Perth, Australia, in December 2011. The 82 revised full papers presented were carefully reviewed and selected from 193 submissions. The papers are organized in topical sections on data mining and knowledge discovery, machine learning, evolutionary computation and optimization, intelligent agent systems, logic and reasoning, vision and graphics, image processing, natural language processing, cognitive modeling and simulation technology, and AI applications. |
|
|
|
|
|
|
|
| |