Muutke küpsiste eelistusi

Data Mining and Machine Learning in Building Energy Analysis [Kõva köide]

5.00/5 (2 hinnangut Goodreads-ist)
,
  • Formaat: Hardback, 186 pages, kõrgus x laius x paksus: 241x163x15 mm, kaal: 431 g
  • Ilmumisaeg: 08-Jan-2016
  • Kirjastus: ISTE Ltd and John Wiley & Sons Inc
  • ISBN-10: 1848214227
  • ISBN-13: 9781848214224
Teised raamatud teemal:
Data Mining and Machine Learning in Building Energy AnalysisSuurem pilt
  • Formaat: Hardback, 186 pages, kõrgus x laius x paksus: 241x163x15 mm, kaal: 431 g
  • Ilmumisaeg: 08-Jan-2016
  • Kirjastus: ISTE Ltd and John Wiley & Sons Inc
  • ISBN-10: 1848214227
  • ISBN-13: 9781848214224
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781848214224.html
Märksõnad:
The energy consumption of a building has, in recent years, become a determining factor during its design and construction. With carbon footprints being a growing issue, it is important that buildings be optimized for energy conservation and CO2 reduction. This book therefore presents AI models and optimization techniques related to this application.

The authors start with a review of recent models for the prediction of building energy consumption: engineering methods, statistical methods, artificial intelligence methods, ANNs and SVMs in particular. The book then focuses on SVMs, by first applying them to building energy consumption, then presenting the principles and various extensions, and SVR. The authors then move on to RDP, which they use to determine building energy faults through simulation experiments before presenting SVR model reduction methods and the benefits of parallel computing. The book then closes by presenting some of the current research and advancements in the field.
Preface ix
Introduction xi
Chapter 1 Overview of Building Energy Analysis
1(16)
1.1 Introduction
1(2)
1.2 Physical models
3(3)
1.3 Gray models
6(1)
1.4 Statistical models
6(2)
1.5 Artificial intelligence models
8(6)
1.5.1 Neural networks
8(5)
1.5.2 Support vector machines
13(1)
1.6 Comparison of existing models
14(2)
1.7 Concluding remarks
16(1)
Chapter 2 Data Acquisition for Building Energy Analysis
17(22)
2.1 Introduction
17(1)
2.2 Surveys or questionnaires
18(3)
2.3 Measurements
21(4)
2.4 Simulation
25(9)
2.4.1 Simulation software
26(2)
2.4.2 Simulation process
28(6)
2.5 Data uncertainty
34(1)
2.6 Calibration
35(2)
2.7 Concluding remarks
37(2)
Chapter 3 Artificial Intelligence Models
39(40)
3.1 Introduction
39(1)
3.2 Artificial neural networks
40(13)
3.2.1 Single-layer perceptron
41(2)
3.2.2 Feed forward neural network
43(1)
3.2.3 Radial basis functions network
44(3)
3.2.4 Recurrent neural network
47(2)
3.2.5 Recursive deterministic perceptron
49(2)
3.2.6 Applications of neural networks
51(2)
3.3 Support vector machines
53(23)
3.3.1 Support vector classification
54(5)
3.3.2 ε-support vector regression
59(3)
3.3.3 One-class support vector machines
62(1)
3.3.4 Multiclass support vector machines
63(1)
3.3.5 υ-support vector machines
64(1)
3.3.6 Transductive support vector machines
65(2)
3.3.7 Quadratic problem solvers
67(8)
3.3.8 Applications of support vector machines
75(1)
3.4 Concluding remarks
76(3)
Chapter 4 Artificial Intelligence for Building Energy Analysis
79(24)
4.1 Introduction
79(1)
4.2 Support vector machines for building energy prediction
80(11)
4.2.1 Energy prediction definition
80(1)
4.2.2 Practical issues
81(4)
4.2.3 Support vector machines for prediction
85(6)
4.3 Neural networks for fault detection and diagnosis
91(11)
4.3.1 Description of faults
94(1)
4.3.2 RDP in fault detection
95(5)
4.3.3 RDP in fault diagnosis
100(2)
4.4 Concluding remarks
102(1)
Chapter 5 Model Reduction for Support Vector Machines
103(18)
5.1 Introduction
103(1)
5.2 Overview of model reduction
104(4)
5.2.1 Wrapper methods
105(1)
5.2.2 Filter methods
106(1)
5.2.3 Embedded methods
107(1)
5.3 Model reduction for energy consumption
108(4)
5.3.1 Introduction
108(1)
5.3.2 Algorithm
109(2)
5.3.3 Feature set description
111(1)
5.4 Model reduction for single building energy
112(4)
5.4.1 Feature set selection
112(2)
5.4.2 Evaluation in experiments
114(2)
5.5 Model reduction for multiple buildings energy
116(3)
5.6 Concluding remarks
119(2)
Chapter 6 Parallel Computing for Support Vector Machines
121(24)
6.1 Introduction
121(1)
6.2 Overview of parallel support vector machines
122(1)
6.3 Parallel quadratic problem solver
123(4)
6.4 MPI-based parallel support vector machines
127(3)
6.4.1 Message passing interface programming model
127(2)
6.4.2 Pisvm
129(1)
6.4.3 Psvm
130(1)
6.5 MapReduce-based parallel support vector machines
130(8)
6.5.1 MapReduce programming model
131(2)
6.5.2 Caching technique
133(1)
6.5.3 Sparse data representation
133(1)
6.5.4 Comparison of MRPsvm with Pisvm
134(4)
6.6 MapReduce-based parallel ε-support vector regression
138(4)
6.6.1 Implementation aspects
138(1)
6.6.2 Energy consumption datasets
139(1)
6.6.3 Evaluation for building energy prediction
140(2)
6.7 Concluding remarks
142(3)
Summary and Future of Building Energy Analysis 145(4)
Bibliography 149(14)
Index 163
Frédéric Magoulès is Professor at the Ecole Centrale Paris in France and Honorary Professor at the University of Pècs in Hungary. His research focuses on parallel computing, numerical linear algebra and machine learning.



Hai-Xiang Zhao is Senior Researcher at Amadeus in France. His research focuses on parallel computing, data mining and machine learning.