Muutke küpsiste eelistusi

Data-Driven Optimization and Knowledge Discovery for an Enterprise Information System 2015 ed. [Kõva köide]

, ,
  • Formaat: Hardback, 160 pages, kõrgus x laius: 235x155 mm, kaal: 482 g, 47 Illustrations, color; 29 Illustrations, black and white; XII, 160 p. 76 illus., 47 illus. in color., 1 Hardback
  • Ilmumisaeg: 29-Jun-2015
  • Kirjastus: Springer International Publishing AG
  • ISBN-10: 3319187376
  • ISBN-13: 9783319187372
Teised raamatud teemal:
  • Kõva köide
  • Hind: 95,02 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 111,79 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Data-Driven Optimization and Knowledge Discovery for an Enterprise Information System 2015 ed.Suurem pilt
  • Formaat: Hardback, 160 pages, kõrgus x laius: 235x155 mm, kaal: 482 g, 47 Illustrations, color; 29 Illustrations, black and white; XII, 160 p. 76 illus., 47 illus. in color., 1 Hardback
  • Ilmumisaeg: 29-Jun-2015
  • Kirjastus: Springer International Publishing AG
  • ISBN-10: 3319187376
  • ISBN-13: 9783319187372
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9783319187372.html
Märksõnad:
This book provides a comprehensive set of optimization and prediction techniques for an enterprise information system. Readers with a background in operations research, system engineering, statistics, or data analytics can use this book as a reference to derive insight from data and use this knowledge as guidance for production management. The authors identify the key challenges in enterprise information management and present results that have emerged from leading-edge research in this domain. Coverage includes topics ranging from task scheduling and resource allocation, to workflow optimization, process time and status prediction, order admission policies optimization, and enterprise service-level performance analysis and prediction. With its emphasis on the above topics, this book provides an in-depth look at enterprise information management solutions that are needed for greater automation and reconfigurabilty-based fault tolerance, as well as to obtain data-driven recommendat

ions for effective decision-making.

Introduction.- Production Simulation Platform.- Production Workflow Optimizations.- Predictions of Process-Execution Time and Process-Execution Status.- Optimization of Order-Admission Policies.- Conclusion.
1 Introduction
1(18)
1.1 Challenges and Opportunities for an Enterprise Information System
4(2)
1.1.1 Transient, Heterogeneous and Stochastic Nature
4(1)
1.1.2 Real-Time Decision Making
5(1)
1.1.3 Diverse and Multi-dimensional Big Data
5(1)
1.2 Introduction to Digital Print Production
6(4)
1.2.1 Manual and Automated Rule-Based Scheduling and Resource Allocation
7(1)
1.2.2 Off-line Solutions
8(1)
1.2.3 Manual and Template-Based Order Acquisition
8(1)
1.2.4 Lack of Service-Level Forecasting and Capacity Planning
9(1)
1.3 Review of State-of-the-Art
10(2)
1.3.1 Simulation
10(1)
1.3.2 Operation Optimization
10(2)
1.3.3 Knowledge Discovery
12(1)
1.4 Outline of Book
12(7)
1.4.1 Simulation
13(1)
1.4.2 Operation Optimization
13(1)
1.4.3 Knowledge Discovery
14(1)
References
14(5)
2 Production Simulation Platform
19(10)
2.1 Background and Motivation
19(1)
2.2 Introduction to Stochastic Discrete-Event Simulation
19(1)
2.2.1 Ptolemy
20(1)
2.3 Virtual Print Factory
20(9)
2.3.1 MySql Databases
23(1)
2.3.2 Order, Product, and Part Hierarchy
23(1)
2.3.3 Resource Set and Task Set
24(1)
2.3.4 Successive Order Acceptance
25(1)
2.3.5 Stochastic Product Reprocessing
25(1)
2.3.6 Simulation Validation
26(1)
References
26(3)
3 Production Workflow Optimization
29(32)
3.1 Background and Motivation
29(2)
3.2 Problem Description and Formulation
31(7)
3.2.1 Resources, Attributes, Parameters, and Task Sequencing Graph
31(2)
3.2.2 Risk-Aware Execution-Time Estimation
33(4)
3.2.3 Normalized Risk-Aware Slack
37(1)
3.3 Production Scheduler
38(1)
3.4 Problem Complexity Analysis
39(1)
3.5 Incremental Genetic Algorithm
40(1)
3.6 Dispatcher
41(3)
3.6.1 Scheduling Priority, Resource Allocation Policy, and Fitness Function in the Dispatching GA
42(2)
3.7 Scheduler
44(1)
3.7.1 Scheduling Priority, Resource Allocation Policy, and Fitness Function in the Scheduling GA
44(1)
3.8 Validation
45(13)
3.8.1 Evaluation Metrics
45(1)
3.8.2 Simulation Settings
45(1)
3.8.3 GA Configuration and Convergence Performance
46(4)
3.8.4 ILP Model for GA Performance Evaluation
50(3)
3.8.5 Production Scheduler Configuration
53(3)
3.8.6 Results and Discussions
56(2)
3.9 Conclusion
58(3)
References
58(3)
4 Predictions of Process-Execution Time and Process-Execution Status
61(24)
4.1 Introduction
62(3)
4.2 Problem Statement and Data Source
65(4)
4.2.1 Problem Statement
65(1)
4.2.2 Status-Prediction Problem Statement
66(1)
4.2.3 Production Event Log
67(1)
4.2.4 Data Source
67(2)
4.3 Process-Execution Time Prediction
69(7)
4.3.1 Baseline Time-Prediction Method
69(1)
4.3.2 Proposed Time-Prediction Method: Integration Based on Statistical Analysis and Machine Learning
69(5)
4.3.3 Comparison Results and Discussions
74(2)
4.4 Process Status Prediction
76(5)
4.4.1 Baseline Status-Prediction Methods
76(1)
4.4.2 Proposed Status-Prediction Method
77(2)
4.4.3 Comparison Results and Discussions
79(2)
4.5 Conclusion and Future Work
81(4)
References
81(4)
5 Optimization of Order-Admission Policies
85(30)
5.1 Background and Motivation
86(4)
5.1.1 Related Prior Solutions
87(1)
5.1.2 Costs for Service-Level Violation
88(2)
5.2 Due-Date Validation Engine
90(12)
5.2.1 Knowledge Base
92(1)
5.2.2 Inputs to the Decision Engine
92(1)
5.2.3 Outputs of the Decision Engine
93(1)
5.2.4 Classifier Evaluation Metrics
93(1)
5.2.5 Support Vector Machines
94(3)
5.2.6 Decision Tree
97(2)
5.2.7 Bayesian Probabilistic Model
99(2)
5.2.8 Comparison of Classifiers
101(1)
5.3 Decision Integration
102(5)
5.3.1 Dempster-Shafer Theory-Based Decision Integration Approach
102(1)
5.3.2 Decision Fusion Approach
103(2)
5.3.3 Voting Approach
105(1)
5.3.4 Exploring New Due Dates
106(1)
5.4 Results and Discussions
107(5)
5.4.1 Classifier Evaluation Strategy and Results
107(2)
5.4.2 Discussion
109(3)
5.5 Conclusion
112(3)
References
112(3)
6 Analysis and Prediction of Enterprise Service-Level Performance
115(24)
6.1 Problem Statement, Baseline Methods, and Data Source
119(3)
6.1.1 Problem Statement
119(1)
6.1.2 Baseline Univariate Method
120(1)
6.1.3 Baseline Multivariate Method
121(1)
6.1.4 Data Source
121(1)
6.2 Mid-Term Time-Series Analysis and Prediction
122(10)
6.2.1 Time-Series Decomposition and Modeling
123(4)
6.2.2 Support Vector Regression
127(1)
6.2.3 Implementation of Baseline Methods
128(1)
6.2.4 Proposed Univariate Mid-Term Time-Series Prediction Method
129(1)
6.2.5 Results and Discussions
130(2)
6.3 Multivariate Short-Term Time-Series Analysis and Prediction
132(3)
6.3.1 Time-Series Cross-Correlation Analysis
132(1)
6.3.2 Implementation of Baseline Methods
133(1)
6.3.3 The Proposed Multivariate Short-Term Time-Series Prediction Method
133(1)
6.3.4 Results and Discussions
134(1)
6.4 Conclusion
135(4)
References
136(3)
7 Conclusion
139(4)
7.1 Book Contributions
139(4)
A Derivation of Eq. (3.3)
143(4)
B Derivation of the PMF of Random Variable X
147(4)
C Derivation of Eq. (3.4)
151(4)
C.1 Approximate the Distribution of X by an Exponential Distribution
151(1)
C.2 The Expectation of the Maximum of Exponentials
151(4)
D Introduction to SVR
155
References
159
Qing Duan is a data scientist at Paypal, Inc. Krishnendu Chakrabarty is a Professor in the Department of Electrical and Computer Engineering at Duke University. Jun Zeng is a principal researcher at Hewlett-Packard Labs.