Advances in Intelligent Data Analysis XVIII : 18th International Symposium on Intelligent Data Analysis, IDA 2020, Konstanz, Germany, April 27–29, 2020, Proceedings / / edited by Michael R. Berthold, Ad Feelders, Georg Krempl.

• Superior document: Information Systems and Applications, incl. Internet/Web, and HCI ; 12080
• HerausgeberIn: Berthold, Michael R.; Feelders, Ad.; Krempl, Georg.
• Place / Publishing House: Cham : : Springer International Publishing :, Imprint: Springer,, 2020.
• Year of Publication: 2020
• Edition: 1st ed. 2020.
• Language: English
• Series: Information Systems and Applications, incl. Internet/Web, and HCI ; 12080
• Physical Description: 1 online resource (XIV, 588 p. 210 illus., 132 illus. in color.)

This open access book constitutes the proceedings of the 18th International Conference on Intelligent Data Analysis, IDA 2020, held in Konstanz, Germany, in April 2020. The 45 full papers presented in this volume were carefully reviewed and selected from 114 submissions. Advancing Intelligent Data Analysis requires novel, potentially game-changing ideas. IDA’s mission is to promote ideas over performance: a solid motivation can be as convincing as exhaustive empirical evaluation.

Table of Contents

Multivariate Time Series as Images: Imputation Using Convolutional Denoising Autoencoder -- Dual Sequential Variational Autoencoders for Fraud Detection -- A Principled Approach to Analyze Expressiveness and Accuracy of Graph Neural Networks -- Efficient Batch-Incremental Classification Using UMAP for Evolving Data Streams -- GraphMDL: Graph Pattern Selection Based on Minimum Description Length -- Towards Content Sensitivity Analysis -- Gibbs Sampling Subjectively Interesting Tiles -- Even Faster Exact k-Means Clustering -- Ising-Based Consensus Clustering on Special Purpose Hardware -- Transfer Learning by Learning Projections from Target to Source -- Computing Vertex-Vertex Dissimilarities Using Random Trees: Application to Clustering in Graphs -- Towards Evaluation of CNN Performance in Semantically Meaningful Latent Spaces -- Vouw: Geometric Pattern Mining Using the MDL Principle -- A Consensus Approach to Improve NMF Document Clustering -- Discriminative Bias for Learning Probabilistic Sentential Decision Diagrams -- Widening for MDL-Based Retail Signature Discovery -- Addressing the Resolution Limit and the Field of View Limit in Community Mining -- Estimating Uncertainty in Deep Learning for Reporting Confidence: An Application on Cell Type Prediction in Testes Based on Proteomics -- Adversarial Attacks Hidden in Plain Sight -- Enriched Weisfeiler-Lehman Kernel for Improved Graph Clustering of Source Code -- Overlapping Hierarchical Clustering (OHC) -- Digital Footprints of International Migration on Twitter -- Percolation-Based Detection of Anomalous Subgraphs in Complex Networks -- A Late-Fusion Approach to Community Detection in Attributed Networks -- Reconciling Predictions in the Regression Setting: an Application to Bus Travel Time Prediction -- A Distribution Dependent and Independent Complexity Analysis of Manifold Regularization -- Actionable Subgroup Discovery and Urban Farm Optimization -- AVATAR - Machine Learning Pipeline Evaluation Using Surrogate Model -- Detection of Derivative Discontinuities in Observational Data -- Improving Prediction with Causal Probabilistic Variables -- DO-U-Net for Segmentation and Counting -- Enhanced Word Embeddings for Anorexia Nervosa Detection on Social Media -- Event Recognition Based on Classification of Generated Image Captions -- Human-to-AI Coach: Improving Human Inputs to AI Systems -- Aleatoric and Epistemic Uncertainty with Random Forests -- Master your Metrics with Calibration -- Supervised Phrase-Boundary Embeddings -- Predicting Remaining Useful Life with Similarity-Based Priors -- Orometric Methods in Bounded Metric Data -- Interpretable Neuron Structuring with Graph Spectral Regularization -- Comparing the Preservation of Network Properties by Graph Embeddings -- Making Learners (More) Monotone -- Combining Machine Learning and Simulation to a Hybrid Modelling Approach -- LiBRe: Label-Wise Selection of Base Learners in Binary Relevance for Multi-Label Classification -- Angle-Based Crowding Degree Estimation for Many-Objective Optimization.