Trends and Applications in Knowledge Discovery and Data Mining: PAKDD 2015 Workshops: BigPMA, VLSP, QIMIE, DAEBH, Ho Chi Minh City, Vietnam, May 19-21 [Paperback]

This book constitutes the refereed proceedings at PAKDD Workshops 2015, held in conjunction with PAKDD, the 19th Pacific-Asia Conference on Knowledge Discovery and Data Mining in Ho Chi Minh City, Vietnam, in May 2015. The 23 revised papers presented were carefully reviewed and selected from 57 submissions. The workshops affiliated with PAKDD 2015 include: Pattern Mining and Application of Big Data (BigPMA), Quality Issues, Measures of Interestingness and Evaluation of data mining models (QIMIE), Data Analytics for Evidence-based Healthcare (DAEBH), Vietnamese Language and Speech Processing (VLSP).

ProbitUCB: A Novel Method for ReviewRanking. From Cluster-based Outlier Detection to Time Series Discord Discovery.-Web site audience segmentation using hybrid alignment techniques.- MiningMassive-Scale Spatiotemporal Trajectories in Parallel: A Survey.- ManifoldRegularized Symmetric Joint Link Model for Overlapping Community Detection.- HighDimensional Explicit Feature Biased Matrix Factorization Recommendation.- ASimhash-based Generalized Framework for Citation Matching in MapReduce.- ACloud Based Diabetes Lifestyle Management System.- Construction of a predictionmodel for nephropathy among obese patients using genetic and clinical features.-A Research of Applying Association Rules and Decision Tree to Endometriosis.- ADynamic Feature Selection Based LDA Approach to Baseball Pitch Prediction.- AStudy of Interestingness Measures for Associative Classification on ImbalancedData.- Evaluation of Community Mining Algorithms in the Presence of Attributes.-Leveraging the Common Cause of Errors for Constraint-based Data Cleansing AnalyzingUser Behaviors Based on Temporal Patterns of Sequential Pattern EvaluationIndices on Twitter.- Model Selection of Symbolic Regression to Improve theAccuracy of PM 2.5 Concentration Prediction.- Internal Clustering Evaluation ofData Streams.- Feature maximization based clustering quality evaluation: apromising approaclSÞ