Data Mining. Concepts and Techniques, 3rd Edition

HAN

22-ind-673-708-9780123814791

2011/6/1

3:27

Page 682

#10

682

Index

data characterization, 15, 166

attribute-oriented induction, 167–172

data mining query, 167–168

example, 16

methods, 16

output, 16

data classification. See classification

data cleaning, 6, 85, 88–93, 120

in back-end tools/utilities, 134

binning, 89–90

discrepancy detection, 91–93

by information network analysis, 592–593

missing values, 88–89

noisy data, 89

outlier analysis, 90

pattern mining for, 318

as process, 91–93

regression, 90

See also data preprocessing

data constraints, 294

antimonotonic, 300

pruning data space with, 300–301

succinct, 300

See also constraints

data cube aggregation, 110–111

data cube computation, 156–160, 214–215

aggregation and, 193

average()

, 215

BUC, 200–204, 235

cube

operator, 157–159

cube shells, 211

full, 189–190, 195–199

general strategies for, 192–194

iceberg, 160, 193–194

memory allocation, 199

methods, 194–218, 235

multiway array aggregation, 195–199

one-pass, 198

preliminary concepts, 188–194

shell fragments, 210–218, 235

Star-Cubing, 204–210, 235

data cubes, 10, 136, 178, 188

3-D, 138

4-D, 138, 139

apex cuboid, 111, 138, 158

base cuboid, 111, 137–138, 158

closed, 192

cube shell, 192

cuboids, 137

curse of dimensionality, 158

discovery-driven exploration, 231–234

example, 11–13

full, 189–190, 196–197

gradient analysis, 321

iceberg, 160, 190–191, 201, 235

lattice of cuboids, 157, 234, 290

materialization, 159–160, 179, 234

measures, 145

multidimensional, 12, 136–139

multidimensional data mining and, 26

multifeature, 227, 230–231, 235

multimedia, 596

prediction, 227–230, 235

qualitative association mining, 289–290

queries, 230

query processing, 218–227

ranking, 225–227, 235

sampling, 218–220, 235

shell, 160, 211

shell fragments, 192, 210–218, 235

sparse, 190

spatial, 595

technology, 187–242

data discretization. See discretization

data dispersion, 44, 48–51

boxplots, 49–50

five-number summary, 49

quartiles, 48–49

standard deviation, 50–51

variance, 50–51

data extraction, in back-end tools/utilities, 134

data focusing, 168

data generalization, 179–180

by attribute-oriented induction, 166–178

data integration, 6, 85–86, 93–99, 120

correlation analysis, 94–98

detection/resolution of data value conflicts,

99

entity identification problem, 94

by information network analysis, 592–593

object matching, 94

redundancy and, 94–98

schema, 94

tuple duplication, 98–99

See also data preprocessing

data marts, 132, 142

data warehouses versus, 142

dependent, 132

distributed, 134

implementation, 132

independent, 132

data matrix, 67–68

dissimilarity matrix versus, 67–68

relational table, 67–68

---

HAN

22-ind-673-708-9780123814791

2011/6/1

3:27

Page 683

#11

Index

683

rows and columns, 68

as two-mode matrix, 68

data migration tools, 93

data mining, 5–8, 33, 598, 623

ad hoc, 31

applications, 607–618

biological data, 624

complex data types, 585–598, 625

cyber-physical system data, 596

data streams, 598

data types for, 8

data warehouses for, 154

database types and, 32

descriptive, 15

distributed, 615, 624

efficiency, 31

foundations, views on, 600–601

functionalities, 15–23, 34

graphs and networks, 591–594

incremental, 31

as information technology evolution, 2–5

integration, 623

interactive, 30

as interdisciplinary effort, 29–30

invisible, 33, 618–620, 625

issues in, 29–33, 34

in knowledge discovery, 7

as knowledge search through data, 6

machine learning similarities, 26

methodologies, 29–30, 585–607

motivation for, 1–5

multidimensional, 11–13, 26, 33–34, 155–156,

179, 227–230

multimedia data, 596

OLAP and, 154

as pattern/knowledge discovery process, 8

predictive, 15

presentation/visualization of results, 31

privacy-preserving, 32, 621–622, 624–625, 626

query languages, 31

relational databases, 10

scalability, 31

sequence data, 586

social impacts, 32

society and, 618–622

spatial data, 595

spatiotemporal data and moving objects,

595–596, 623–624

statistical, 598

text data, 596–597, 624

trends, 622–625, 626

ubiquitous, 618–620, 625

user interaction and, 30–31

visual and audio, 602–607, 624, 625

Web data, 597–598, 624

data mining systems, 10

data models

entity-relationship (ER), 9, 139

multidimensional, 135–146

data objects, 40, 79

similarity, 40

terminology for, 40

data preprocessing, 83–124

cleaning, 88–93

forms illustration, 87

integration, 93–99

overview, 84–87

quality, 84–85

reduction, 99–111

in science applications, 612

summary, 87

tasks in, 85–87

transformation, 111–119

data quality, 84, 120

accuracy, 84

believability, 85

completeness, 84–85

consistency, 85

interpretability, 85

timeliness, 85

data reduction, 86, 99–111, 120

attribute subset selection, 103–105

clustering, 108

compression, 100, 120

data cube aggregation, 110–111

dimensionality, 86, 99–100, 120

histograms, 106–108

numerosity, 86, 100, 120

parametric, 105–106

principle components analysis, 102–103

sampling, 108

strategies, 99–100

theory, 601

wavelet transforms, 100–102

See also data preprocessing

data rich but information poor, 5

data scrubbing tools, 92

data security-enhancing techniques, 621

data segmentation, 445

data selection, 8

data source view, 151

data streams, 14, 598, 624

data transformation, 8, 87, 111–119, 120

aggregation, 112

---