Ao Applied Time Series Analysis and Innovative Computing

1. Auflage 2010
ISBN: 978-90-481-8768-3
Verlag: Springer Netherlands
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 59, 112 Seiten

Reihe: Lecture Notes in Electrical Engineering

Applied Time Series Analysis and Innovative Computing contains the applied time series analysis and innovative computing paradigms, with frontier application studies for the time series problems based on the recent works at the Oxford University Computing Laboratory, University of Oxford, the University of Hong Kong, and the Chinese University of Hong Kong. The monograph was drafted when the author was a post-doctoral fellow in Harvard School of Engineering and Applied Sciences, Harvard University. It provides a systematic introduction to the use of innovative computing paradigms as an investigative tool for applications in time series analysis. Applied Time Series Analysis and Innovative Computing offers the state of art of tremendous advances in applied time series analysis and innovative computing paradigms and also serves as an excellent reference work for researchers and graduate students working on applied time series analysis and innovative computing paradigms.

Autoren/Hrsg.

Ao, Sio-Iong

Inhaltsverzeichnis

1;Applied Time Series Analysis and Innovative Computing;2
2;Chapter 1;14
2.1;Introduction;14
2.1.1;1.1 Applied Time Series Analysis;15
2.1.1.1;1.1.1 Basic Definitions;15
2.1.1.2;1.1.2 Basic Applied Time Series Models;15
2.1.1.3;1.1.3 Frequency Domain Models;15
2.1.2;1.2 Advances in Innovative Computing Paradigms;16
2.1.2.1;1.2.1 Computing Algorithms and Databases;16
2.1.2.2;1.2.2 Integration of Hardware, Systems and Networks;16
2.1.2.3;1.2.3 Internet, Web and Grid Computing;17
2.1.2.4;1.2.4 Visualization, Design and Communication;17
2.1.3;1.3 Real-World Applications: Innovative Computing Paradigms for Time Series Problems;18
2.1.3.1;1.3.1 Developing Innovative Computing Algorithms for Business Time Series;18
2.1.3.2;1.3.2 Developing Innovative Computing Algorithms for Biological Time Series;19
2.1.3.3;1.3.3 Developing Innovative Computing Algorithms for Astronomical Time Series;19
3;Chapter 2;21
3.1;Applied Time Series Analysis;21
3.1.1;2.1 Basic Characteristics of Time Series;22
3.1.1.1;2.1.1 Estimation of Correlation;22
3.1.1.1.1;2.1.1.1 Auto-Correlation Analysis;22
3.1.1.1.2;2.1.1.2 Cross-Correlation Analysis;22
3.1.1.1.3;2.1.1.3 Autocorrelation Functions;23
3.1.1.2;2.1.2 Stationary Time Series;24
3.1.1.3;2.1.3 Smoothing of the Time Series;24
3.1.1.4;2.1.4 Periodogram Analysis;25
3.1.2;2.2 Autoregression and ARIMA Models;26
3.1.2.1;2.2.1 Time Series Regression;26
3.1.2.2;2.2.2 Autoregressive Moving Average Models;26
3.1.2.3;2.2.3 Building ARIMA Models;27
3.1.2.4;2.2.4 Forecasting and Evaluation;28
3.1.2.5;2.2.5 Causality of the Time Series;28
3.1.3;2.3 Mathematical Models in the Frequency Domain;29
3.1.3.1;2.3.1 Introduction;29
3.1.3.2;2.3.2 Discrimination Analysis;30
3.1.3.3;2.3.3 Clustering Analysis;31
3.1.3.4;2.3.4 Principal Components and Factor Analysis;33
3.1.3.5;2.3.5 Dynamic Fourier Analysis;34
3.1.3.6;2.3.6 Random Coefficient Regression;35
3.1.3.7;2.3.7 Discrete Fourier Transform;36
4;Chapter 3;37
4.1;Advances in Innovative Computing Paradigms;37
4.1.1;3.1 Research Advances in Computing Algorithms and Databases;37
4.1.1.1;3.1.1 Knowledge Extraction Methods;37
4.1.1.2;3.1.2 Exploiting Large Complex Databases;38
4.1.1.3;3.1.3 Neural Computing Algorithms;38
4.1.1.4;3.1.4 Fuzzy Computing Algorithms;39
4.1.1.5;3.1.5 Evolutionary Computing Algorithms;39
4.1.1.6;3.1.6 Quantum Computing Algorithms;40
4.1.1.7;3.1.7 Swarm-Based Computing Algorithms;40
4.1.1.8;3.1.8 DNA Computing Algorithms;41
4.1.1.9;3.1.9 Theoretical Modeling and Simulations;41
4.1.2;3.2 Research Advances in Integration of Hardware, Systems and Networks;41
4.1.2.1;3.2.1 Innovative Experimental Hardware System;41
4.1.2.2;3.2.2 Data-Acquisition Devices;42
4.1.2.3;3.2.3 Interaction Devices for Visual Exploration;42
4.1.2.4;3.2.4 Graphics Processing Units and Co-Processors for Innovative Computing;43
4.1.2.5;3.2.5 Networking and Interoperability;43
4.1.2.6;3.2.6 Code Optimization and Integration;44
4.1.3;3.3 Research Advances in Internet, Web and Grid Computing;44
4.1.3.1;3.3.1 Distributed Computation and Data Sharing;44
4.1.3.2;3.3.2 Large-Scale Collaborations over the Internet;44
4.1.3.3;3.3.3 Grid Computing;45
4.1.3.4;3.3.4 Pooling of Remote Computer Resources;45
4.1.3.5;3.3.5 Integration of Knowledge Metadata Systems;45
4.1.4;3.4 Research Advances in Visualization, Design and Communication;46
4.1.4.1;3.4.1 Novel Solutions to Visualization and Communication Challenges;46
4.1.4.2;3.4.2 Displaying of Complex Information;46
4.1.4.3;3.4.3 Escaping Flatland;47
4.1.4.4;3.4.4 Systems Integration for High Performance Image Processing;47
4.1.4.5;3.4.5 Representation of Uncertainties;48
4.1.4.6;3.4.6 Informative Graphics for Scientific Communication;48
4.1.5;3.5 Advances and Applications for Time Series Problems;49
4.1.5.1;3.5.1 Efficient Retrieval of Similar Time Series;49
4.1.5.2;3.5.2 Automatic Classification of Time Series Sequences;49
4.1.5.3;3.5.3 Time Warping Algorithms;50
4.1.5.4;3.5.4 Time Frequency Clustering of Time Series Datasets;52
4.1.5.5;3.5.5 Enhanced Representation for Complex Time Series;52
4.1.5.6;3.5.6 Automatic Monitoring of Large and Complex Time Series;53
4.1.6;3.6 An Illustrative Example of Building an Innovative Computing Algorithm for Simulated Time Series;53
4.1.6.1;3.6.1 Description of the Simulated Time Series Problem;53
4.1.6.2;3.6.2 Background of the Methodology;54
4.1.6.3;3.6.3 Building the Innovative Regression Model;56
4.1.6.3.1;3.6.3.1 Neural Network Regression Models;56
4.1.6.3.2;3.6.3.2 Fuzzy Clustering;58
4.1.6.3.3;3.6.3.3 Hybrid Neural Network and Fuzzy Clustering (NN-FC);59
4.1.6.4;3.6.4 Experimental Results with the Simulated Time Series;60
4.1.6.5;3.6.5 Discussions and Further Works;62
5;Chapter 4;63
5.1;Real-Word Application I: Developing Innovative Computing Algorithms for Business Time Series;63
5.1.1;4.1 Business Time Series;63
5.1.2;4.2 Advances in Business Forecasting;64
5.1.2.1;4.2.1 Basic Econometrics Models;64
5.1.2.2;4.2.2 Neural Computing Models;64
5.1.2.3;4.2.3 Evolutionary Computing Models;65
5.1.2.4;4.2.4 Hybrid Intelligent Models;65
5.1.3;4.3 Developing a Hybrid Intelligent Econometrics Model for Business Forecasting;66
5.1.3.1;4.3.1 Vector Autoregression;66
5.1.3.2;4.3.2 Neural Network;67
5.1.3.3;4.3.3 Genetic Algorithm;70
5.1.3.4;4.3.4 A Cybernetic Framework of Hybrid Vector Autoregression, Neural Network and Genetic Algorithm;72
5.1.4;4.4 Application for Tourism Demand Forecasting;73
5.1.4.1;4.4.1 Quantifying Cross-Market Dynamics;74
5.1.4.2;4.4.2 Experimental Results;74
5.1.5;4.5 Application for Cross-Market Financial Forecasting;75
5.1.5.1;4.5.1 Quantifying the Cybernetic Lead–Lag Dynamics across Different Markets;76
5.1.5.2;4.5.2 Benchmark Stand-Alone Neural Network;76
5.1.5.3;4.5.3 Hybrid Innovative System and Results Comparison;77
5.1.6;4.6 Discussions and Further Works;78
6;Chapter 5;79
6.1;Real-Word Application II: Developing Innovative Computing Algorithms for Biological Time Series;79
6.1.1;5.1 Biological Time Series;79
6.1.2;5.2 Advances in Experimental Designs for Microarray Time Series;80
6.1.2.1;5.2.1 Microarray Experiments;80
6.1.2.2;5.2.2 Microarray Time Series and Applications;81
6.1.3;5.3 Reverse Engineering of Biological Networks;82
6.1.3.1;5.3.1 Introduction;82
6.1.3.2;5.3.2 Materials and Methods;83
6.1.3.2.1;5.3.2.1 Elman Neural Networks;83
6.1.3.2.2;5.3.2.2 Support Vector Machines;85
6.1.3.2.3;5.3.2.3 Ensemble of Innovative Models;87
6.1.3.2.4;5.3.2.4 Pedagogical Rule Extraction for Biological Network Inference;88
6.1.4;5.4 Models for Biological Network Inference;90
6.1.4.1;5.4.1 Biological Time Series Datasets;90
6.1.4.2;5.4.2 Analysis with Simulated Non-stationary Datasets;91
6.1.4.3;5.4.3 Analysis with Real Biological Datasets;91
6.1.4.4;5.4.4 Rule Extraction for Reverse Engineering of Biological Networks;92
6.1.5;5.5 Discussions and Further Works;93
7;Chapter 6;95
7.1;Real-Word Application III: Developing Innovative Computing Algorithms for Astronomical Time Series;95
7.1.1;6.1 Astronomical Time Series;95
7.1.2;6.2 Advances and Applications of Innovative Computing Paradigms;96
7.1.2.1;6.2.1 Classification of Astronomical Time Series;96
7.1.2.2;6.2.2 Clustering of Astronomical Time Series;96
7.1.2.3;6.2.3 Semi-Supervised Learning for Astronomical Time Series;97
7.1.2.4;6.2.4 Anomaly Detection of Astronomical Time Series;98
7.1.3;6.3 Motivations for Investigating the Quasar Time Series with Innovative Approaches;98
7.1.4;6.4 Advances in Emerging Methods for Quasar Studies;99
7.1.4.1;6.4.1 Variability Properties of the Quasar Light Curves;99
7.1.4.2;6.4.2 Algorithms Based on Variability and Proper Motion for Quasar Classification;101
7.1.4.2.1;6.4.2.1 Data: Deviation from a Constant Brightness Lightcurve;102
7.1.4.2.2;6.4.2.2 First Criterion: Selection on Photometry: Magnitude and Colour;103
7.1.4.2.3;6.4.2.3 Second Criterion: The Slope of Variograms;103
7.1.4.2.4;6.4.2.4 Third Criterion: QSO and Be Star Colors;104
7.1.4.2.5;6.4.2.5 Fourth Criterion: Manual Selection;104
7.1.4.2.6;6.4.2.6 Follow-Up Spectroscopy Experiments and Works;104
7.1.4.3;6.4.3 Bayesian Classification for Efficient Photometric Selection of Quasars;105
7.1.4.3.1;6.4.3.1 Follow-Up Works to This Automatic Photometric Selection of Quasars;106
7.1.4.3.2;6.4.3.2 Nonparametric Bayesian Classification (NBC);107
7.1.4.3.3;6.4.3.3 Fast Algorithms for Computing the Kernel Density Estimate;107
7.1.4.4;6.4.4 Machine Learning Paradigms for Quasar Selection;109
8;Bibliography;110

Leseproben

"Chapter 1 Introduction (p. 1-2)

Abstract This book is organized as follows. In first two sections of this chapter, it is the brief introduction to the applied time series analysis and the advances in innovative computing paradigms. In the third section, we describe briefly about the three real-world applications of innovative computing paradigms for time series problems. The contributions of these algorithms to the time series analysis are also described briefly in that section and in more details in their respective chapters. In Chap. 2, we describe about the applied time series analysis generally. Time series analysis models including time domain models and frequency domain models are covered. In Chap. 3, we describe about the recent advances in innovative computing paradigms.

Topics like computing algorithms and databases, integration of hardware, systems and networks, Internet and grid computing, and visualization, design and communication, will be covered. The advances of innovative computing for time series problems are also discussed, and an example of building of an innovative computing algorithm for some simulated time series is illustrated. In Chap. 4, we present the real-world application of innovative computing paradigms for time series problems.

The interdisciplinary innovative computing techniques are applied to understand, model and design systems for business forecasting. In Chap. 5, the second real-world application is for the analysis of the biological time series. Recurrent Elman neural networks and support vector machines have been outlined for temporal modeling of microarray continuous time series data sets. In Chap. 6, we present the last real-world application for the astronomical time series. It is to explore if some innovative computing algorithms can automatically classify the light curves of the quasars against the very similar light curves of the other stars.

1.1 Applied Time Series Analysis

1.1.1 Basic Definitions

A time series can be regarded as any series of measurements taken at different times. Different from other common data analysis problems, time series data have a natural temporal ordering. Examples of time series are the daily stock prices, daily temperature, temporal gene expression values, and temporal light intensity of astronomical objects etc. Applied time series analysis consists of empirical models for analyzing time series in order to extract meaningful statistics and other properties of the time series data. Time series models usually take advantage of the fact that observations close together in time are generally more closely related than observations further apart.

There are many reasons to analyze the time series data, for example, to understand the underlying generating mechanism better, to achieve optimal control of the system, or to obtain better forecasting of future values. Time series forecasting is about the employment of time series model to forecast future events based on past events. The forecasting methods have been applied in various domains, like for example, business forecasting (Ao 2003b–e, 2006, 2007b) and genomic analysis (Ao et al. 2004, Ao 2006, 2007a).

1.1.2 Basic Applied Time Series Models

Time series models have various forms and represent different stochastic processes. Different from a deterministic process, in a stochastic process, there is some indeterminacy in its future evolution described by probability distributions. Time series analysis model is usually classified as either time domain model or frequency domain model. Time domain models include the auto-correlation and cross-correlation analysis.

In a time domain model, mathematical functions are usually used to study the data with respect to time. The three broad classes for modeling the variations of time series process are the autoregressive (AR) models, the integrated (I) models, and the moving average (MA) models. They all depend linearly on previous time series data points (Box and Jenkins 1976). The autoregressive fractionally integrated moving average (ARFIMA) model is the generalization of these three classes."