Metaheuristics for Big Data.

Cover -- Title Page -- Copyright -- Contents -- Acknowledgments -- Introduction -- 1. Optimization and Big Data -- 1.1. Context of Big Data -- 1.1.1. Examples of situations -- 1.1.2. Definitions -- 1.1.3. Big Data challenges -- 1.1.4. Metaheuristics and Big Data -- 1.2. Knowledge discovery in Big Data -- 1.2.1. Data mining versus knowledge discovery -- 1.2.2. Main data mining tasks -- 1.2.3. Data mining tasks as optimization problems -- 1.3. Performance analysis of data mining algorithms -- 1.3.1. Context -- 1.3.2. Evaluation among one or several dataset(s) -- 1.3.3. Repositories and datasets -- 1.4. Conclusion -- 2. Metaheuristics - A Short Introduction -- 2.1. Introduction -- 2.1.1. Combinatorial optimization problems -- 2.1.2. Solving a combinatorial optimization problem -- 2.1.3. Main types of optimization methods -- 2.2. Common concepts of metaheuristics -- 2.2.1. Representation/encoding -- 2.2.2. Constraint satisfaction -- 2.2.3. Optimization criterion/objective function -- 2.2.4. Performance analysis -- 2.3. Single solution-based/local search methods -- 2.3.1. Neighborhood of a solution -- 2.3.2. Hill climbing algorithm -- 2.3.3. Tabu Search -- 2.3.4. Simulated annealing and threshold acceptance approach -- 2.3.5. Combining local search approaches -- 2.4. Population-based metaheuristics -- 2.4.1. Evolutionary computation -- 2.4.2. Swarm intelligence -- 2.5. Multi-objective metaheuristics -- 2.5.1. Basic notions in multi-objective optimization -- 2.5.2. Multi-objective optimization using metaheuristics -- 2.5.3. Performance assessment in multi-objective optimization -- 2.6. Conclusion -- 3. Metaheuristics and Parallel Optimization -- 3.1. Parallelism -- 3.1.1. Bit-level -- 3.1.2. Instruction-level parallelism -- 3.1.3. Task and data parallelism -- 3.2. Parallel metaheuristics -- 3.2.1. General concepts.

3.2.2. Parallel single solution-based metaheuristics -- 3.2.3. Parallel population-based metaheuristics -- 3.3. Infrastructure and technologies for parallel metaheuristics -- 3.3.1. Distributed model -- 3.3.2. Hardware model -- 3.4. Quality measures -- 3.4.1. Speedup -- 3.4.2. Efficiency -- 3.4.3. Serial fraction -- 3.5. Conclusion -- 4. Metaheuristics and Clustering -- 4.1. Task description -- 4.1.1. Partitioning methods -- 4.1.2. Hierarchical methods -- 4.1.3. Grid-based methods -- 4.1.4. Density-based methods -- 4.2. Big Data and clustering -- 4.3. Optimization model -- 4.3.1. A combinatorial problem -- 4.3.2. Quality measures -- 4.3.3. Representation -- 4.4. Overview of methods -- 4.5. Validation -- 4.5.1. Internal validation -- 4.5.2. External validation -- 4.6. Conclusion -- 5. Metaheuristics and Association Rules -- 5.1. Task description and classical approaches -- 5.1.1. Initial problem -- 5.1.2. A priori algorithm -- 5.2. Optimization model -- 5.2.1. A combinatorial problem -- 5.2.2. Quality measures -- 5.2.3. A monoor a multi-objective problem? -- 5.3. Overview of metaheuristics for the association rules mining problem -- 5.3.1. Generalities -- 5.3.2. Metaheuristics for categorical association rules -- 5.3.3. Evolutionary algorithms for quantitative association rules -- 5.3.4. Metaheuristics for fuzzy association rules -- 5.4. General table -- 5.5. Conclusion -- 6. Metaheuristics and (Supervised) Classification -- 6.1. Task description and standard approaches -- 6.1.1. Problem description -- 6.1.2. K-nearest neighbor -- 6.1.3. Decision trees -- 6.1.4. Naive Bayes -- 6.1.5. Artificial neural networks -- 6.1.6. Support vector machines -- 6.2. Optimization model -- 6.2.1. A combinatorial problem -- 6.2.2. Quality measures -- 6.2.3. Methodology of performance evaluation in supervised classification.

6.3. Metaheuristics to build standard classifiers -- 6.3.1. Optimization of K-NN -- 6.3.2. Decision tree -- 6.3.3. Optimization of ANN -- 6.3.4. Optimization of SVM -- 6.4. Metaheuristics for classification rules -- 6.4.1. Modeling -- 6.4.2. Objective function(s) -- 6.4.3. Operators -- 6.4.4. Algorithms -- 6.5. Conclusion -- 7. On the Use of Metaheuristics for Feature Selection in Classification -- 7.1. Task description -- 7.1.1. Filter models -- 7.1.2. Wrapper models -- 7.1.3. Embedded models -- 7.2. Optimization model -- 7.2.1. A combinatorial optimization problem -- 7.2.2. Representation -- 7.2.3. Operators -- 7.2.4. Quality measures -- 7.2.5. Validation -- 7.3. Overview of methods -- 7.4. Conclusion -- 8. Frameworks -- 8.1. Frameworks for designing metaheuristics -- 8.1.1. Easylocal++ -- 8.1.2. HeuristicLab -- 8.1.3. jMetal -- 8.1.4. Mallba -- 8.1.5. ParadisEO -- 8.1.6. ECJ -- 8.1.7. OpenBeagle -- 8.1.8. JCLEC -- 8.2. Framework for data mining -- 8.2.1. Orange -- 8.2.2. R and Rattle GUI -- 8.3. Framework for data mining with metaheuristics -- 8.3.1. RapidMiner -- 8.3.2. WEKA -- 8.3.3. KEEL -- 8.3.4. MO-Mine -- 8.4. Conclusion -- Conclusion -- Bibliography -- Index -- Other titles from iSTE in Computer Engineering -- EULA.

Description based on publisher supplied metadata and other sources.

Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2024. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.