E-raamat: Advances in Intelligent Data Analysis XIV: 14th International Symposium, IDA 2015, Saint Etienne. France, October 22 -24, 2015. Proceedings

This book constitutes the refereed conference proceedings of the 14th International Conference on Intelligent Data Analysis, which was held in October 2015 in Saint Étienne. France. The 29 revised full papers were carefully reviewed and selected from 65 submissions. The traditional focus of the IDA symposium series is on end-to-end intelligent support for data analysis. The symposium aims to provide a forum for inspiring research contributions that might be considered preliminary in other leading conferences and journals, but that have a potentially dramatic impact. To facilitate this, IDA 2015 will feature two tracks: a regular "Proceedings" track, as well as a "Horizon" track for early-stage research of potentially ground-breaking nature.

Dataanalytics and optimization for assessing a ride sharing system.- Constraint-BasedQuerying for Bayesian Network Exploration.- Efficient Model Selection forRegularized Classification by Exploiting Unlabeled Data.- Segregation Discoveryin a Social Network of Companies.- A first+-order-logic based model forgrounded language learning.- A parallel distributed processing algorithm forimage feature extraction.- Modeling concept drift: A probabilistic graphicalmodel based approach.- Diversity-driven Widening of Hierarchical AgglomerativeClustering.- Batch Steepest-Descent-Mildest-Ascent for Interactive MaximumMargin Clustering.- Time Series Classification with Representation Ensembles.- SimultaneousClustering and Model Selection for Multinomial Distribution: A ComparativeStudy.- On Binary Reduction of Large-scale Multiclass Classification Problems.-Probabilistic Active Learning in Data Streams.- Implicitly ConstrainedSemi-Supervised Least Squares Classification.- Diagonal

Co-clustering Algorithmfor Document-Word Partitioning.- I-Louvain: an attributed graph clusteringmethod.- Class-based outlier detection: staying zombies or awaiting forresurrection .- Using Metalearning for Prediction of Taxi Trip Duration UsingDifferent Granularity Levels.- Using entropy as a measure of acceptance formulti-label classification.- Investigation of Node Deletion Techniques forClustering Applications of Growing Self Organizing Maps.- Exploratory topicmodeling with distributional semantics.- Assigning Geo-Relevance of SentimentsMined from Location-Based Social Media Posts.- Continuous and Discrete DeepClassifiers for Data Integration.- A Bayesian Approach for IdentifyingMultivariate Differences Between Groups.- Automatically Discovering OffensivePatterns in Soccer Match Data.- Fast Algorithm Selection using LearningCurves.- Optimally Weighted Cluster Kriging for Big Data Regression.- Slowercan be faster: The iRetis incremental model tree learner.- VoQs: A

WebApplication for Visualization of Questionnaire Surveys.