Trends and Applications in Knowledge Discovery and Data Mining PAKDD 2017 Workshops, MLSDA, BDM, DM-BPM Jeju, South Korea, May 23, 2017, Revised Selected Papers

This book constitutes the thoroughly refereed post-workshop proceedings at PAKDD Workshops 2017, held in conjunction with PAKDD, the 21st Pacific-Asia Conference on Knowledge Discovery and Data Mining in May 2017 in Jeju, South Korea. The 17 revised papers presented were carefully reviewed and selected from 38 submissions. The workshops affiliated with PAKDD 2017 include: Workshop on Machine Learning for Sensory Data Analysis (MLSDA), Workshop on Biologically Inspired Data Mining Techniques (BDM), Pacific Asia Workshop on Intelligence and Security Informatics (PAISI), and Workshop on Data Mining in Business Process Management (DM-BPM).

Early Classification of Multivariate Time Series on Distributed and In-Memory Platforms.- Behavior Classification of Dairy Cows fitted with GPS collars.- Dynamic Real-time Segmentation and Recongnition of Activities using a Multi-feature Windowing Approach.- Feature Extraction from EEG data for a P300 Based Brain-computer Interface.- Thermal Stratification Prediction at Lake Trevallyn.- Development of a Software Vulnerability Prediction Web Service based on Artificial Neural Networks .- Diversification Heuristics in Bees Swarm Optimization for Association Rules Mining.- Improved CFDP Algorithms Based on Shared Nearest Neighbors and Transitive Closure.- CNN-based Sequence Labeling for Fine-grained Opinion Mining of Microblogs.- A Genetic Algorithm for Interpretable Model Extraction from Decision Tree Ensembles.- Self-Adaptive Weighted Extreme Learning Machine for Imbalanced Classification Problems.- Estimating Word Probabilities with Neural Networks in Latent Dirichlet Allocation.- GA-Apriori: Combining Apriori Heuristic and Genetic Algorithms for Solving the Frequent Itemsets Mining Problem.- Shelf Time Analysis in CTP Insurance Claims Processing.- Automated Product-Attribute Mapping.- A Novel Extreme Learning Machine-based Classification Algorithm for Uncertain Data.- SPGLAD: A Self-Paced Learning-based Crowdsourcing Classification Model.