New Frontiers in Mining Complex Patterns : Third International Workshop, NFMCP 2014, Held in Conjunction with ECML-PKDD 2014, Nancy, France, September 19, 2014, Revised Selected Papers / / edited by Annalisa Appice, Michelangelo Ceci, Corrado Loglisci, Giuseppe Manco, Elio Masciari, Zbigniew W. Ras

• Pubblicazione: Cham : , : Springer International Publishing : , : Imprint : Springer, , 2015
• Edizione: 1st ed. 2015.
• Descrizione fisica: 1 online resource (XII, 211 p. 61 illus.)
• Disciplina: 006.3
• Soggetto topico: Data mining; Database management; Information storage and retrieval systems; Artificial intelligence; Data Mining and Knowledge Discovery; Database Management; Information Storage and Retrieval; Artificial Intelligence
• Persona (resp. second.): AppiceAnnalisa; CeciMichelangelo; LoglisciCorrado; MancoGiuseppe; MasciariElio; RasZbigniew W
• Note generali: Includes index.
• Nota di contenuto: Intro -- Preface -- Organization -- Sampling and Presenting Patterns from Structured Data -- Contents -- Classification and Regression -- Semi-supervised Learning for Multi-target Regression -- 1 Introduction -- 2 MTR with Ensembles of Predictive Clustering Trees -- 2.1 Predictive Clustering Trees for MTR -- 2.2 Ensembles of PCTs -- 3 Self-training for MTR with Ensembles of PCTs -- 4 Experimental Design -- 4.1 Data Description -- 4.2 Experimental Setup and Evaluation Procedure -- 5 Results and Discussion -- 6 Conclusions -- References -- Evaluation of Different Data-Derived Label Hierarchies in Multi-label Classification -- 1 Introduction -- 2 Background -- 2.1 The Task of Multi-label Classification (MLC) -- 2.2 The Task of Hierarchical Multi-label Classification (HMC) -- 3 The Use of Data Derived Label Hierarchies in Multi-Label Classification -- 3.1 Generating a Label Hierarchy on a Multi-label Output Space -- 3.2 Solving MLC Problems by Using Classification Approaches for HMC -- 3.3 Classification Approaches for HMC -- 4 Experimental Design -- 4.1 Datasets and Evaluation Measures -- 4.2 Experimental Setup -- 4.3 Statistical Evaluation -- 5 Results and Discussion -- 6 Conclusions and Further Work -- A Evaluation Measures -- A.1 Example Based Measures -- A.2 Label Based Measures -- A.3 Ranking Based Measures -- B Complete Results from the Experimental Evaluation -- References -- Clustering -- Predicting Negative Side Effects of Surgeries Through Clustering -- 1 Introduction -- 2 Background -- 2.1 Multi-valued Information System -- 2.2 Atomic Action Terms and Action Terms -- 2.3 Meta-Actions for Multi-valued Information System -- 3 Negative Side Effects -- 4 Clustering Based on Negative Side Effects -- 5 New Approach for Predicting Negative Side Effects -- 5.1 Distance Between Two Patients -- 5.2 Distance Between a Patient and a Cluster. ; 6 Dataset and Experiments -- 6.1 HCUP Dataset Description -- 6.2 Experiments -- 7 Summary and Conclusions -- References -- Parallel Multicut Segmentation via Dual Decomposition -- 1 Introduction -- 2 Related Work -- 3 Segmentations and Multicuts -- 4 Outer Relaxation of the Cycle Polytope -- 5 Lagrangian Decomposition -- 5.1 Constrained Reparameterization -- 6 Bound Maximization Along Subgradients -- 7 Rounding Heuristic and Interpretation -- 7.1 Decoding Heuristic: Iterative Construction -- 8 Experiments -- 8.1 Berkeley Segmentation Data Set -- 8.2 Correlation Clustering in Non-planar Graphs -- 9 Discussion -- References -- Learning from Imbalanced Data Using Ensemble Methods and Cluster-Based Undersampling -- 1 Introduction -- 2 Related Work -- 3 Proposed Algorithms -- 3.1 Undersampling Based on Clustering and K-Nearest Neighbour -- 3.2 Undersampling Based on Clustering and Ensemble Learning -- 4 Experiments and Results -- 4.1 Evaluation Criteria -- 4.2 Datasets and Experimental Settings -- 4.3 Results and Analyses -- 5 Conclusion and Future Work -- References -- Data Streams and Sequences -- Prequential AUC for Classifier Evaluation and Drift Detection in Evolving Data Streams -- 1 Introduction -- 2 Evaluating Data Stream Classifiers -- 3 Prequential AUC -- 4 Drift Detection Using AUC -- 5 Experiments -- 5.1 Datasets -- 5.2 Results -- 6 Conclusions -- References -- Mining Positional Data Streams -- 1 Introduction -- 2 Related Work -- 3 Efficiently Finding Similar Movements -- 3.1 Representation -- 3.2 Approximate Dynamic Time Warping -- 3.3 An N-Best Algorithm -- 3.4 Distance-Based Hashing -- 4 Frequent Episode Mining for Positional Data -- 4.1 Counting Phase -- 4.2 Generation Phase -- 5 Empirical Evaluation -- 5.1 Positional Data -- 5.2 Near Neighbour Search -- 5.3 Episode Discovery -- 6 Conclusion -- References. ; Visualization for Streaming Telecommunications Networks -- 1 Motivation -- 2 Related Work -- 2.1 Visualization -- 2.2 top-k Itemsets -- 3 Streaming Simulation System -- 3.1 Components -- 3.2 Landmark Windows -- 3.3 Sliding Windows -- 3.4 top-k Networks -- 4 Case Study -- 4.1 Data Description -- 4.2 Sliding Windows Visualization -- 4.3 top-k Landmark Window -- 5 Conclusions -- References -- Temporal Dependency Detection Between Interval-Based Event Sequences -- 1 Introduction -- 2 Temporal Dependencies -- 2.1 Temporal Dependency Assessment -- 2.2 Significant Temporal Dependencies Selection -- 3 Discovery of Temporal Dependencies -- 4 Experimental Study -- 4.1 Quantitative Experiments -- 4.2 Case Study -- 5 Related Work -- 6 Conclusion -- References -- Applications -- Discovering Behavioural Patterns in Knowledge-Intensive Collaborative Processes -- 1 Introduction -- 1.1 Motivation -- 2 Related Work -- 3 Behavioural Pattern -- 4 Methodology -- 4.1 Case Study: Collaborative Research Activity -- 4.2 Log Building -- 4.3 Hierarchical Clustering -- 5 Experiments -- 5.1 Discussion -- 6 Conclusions and Future Work -- References -- Learning Complex Activity Preconditions in Process Mining -- 1 Introduction -- 2 Representation -- 3 Learning -- 4 Computational Complexity Issues -- 5 Exploitation -- 6 Evaluation -- 7 Conclusions -- References -- Location Prediction of Mobile Phone Users Using Apriori-Based Sequence Mining with Multiple Support Thresholds -- 1 Introduction -- 2 Previous Work -- 3 Proposed Technique -- 3.1 Preliminaries -- 3.2 Apriori-Based Sequence Mining Algorithm with Multiple Support Thresholds (ASMAMS) -- 4 Evaluation -- 5 Experimental Results -- 6 Conclusion -- References -- Pitch-Related Identification of Instruments in Classical Music Recordings -- 1 Introduction -- 2 Audio Data -- 2.1 Parametrization -- 3 Classification with Random Forests. ; 3.1 Instrument and Pitch Identification -- 3.2 Cleaning -- 3.3 Training of Random Forests -- 4 Results -- 5 Summary and Conclusions -- References -- Author Index.
• Sommario/riassunto: This book constitutes the thoroughly refereed post-conference proceedings of the Third International Workshop on New Frontiers in Mining Complex Patterns, NFMCP 2014, held in conjunction with ECML-PKDD 2014 in Nancy, France, in September 2014. The 13 revised full papers presented were carefully reviewed and selected from numerous submissions. They illustrate advanced data mining techniques which preserve the informative richness of complex data and allow for efficient and effective identification of complex information units present in such data. The papers are organized in the following sections: classification and regression; clustering; data streams and sequences; applications.
• Titolo autorizzato: New Frontiers in Mining Complex Patterns
• ISBN: 3-319-17876-8
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910483389103321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture Notes in Artificial Intelligence, . 2945-9141 ; ; 8983