The sequential analysis of data and information gathered from past to present is called time series analysis. Time series data are of high dimension, large size and updated continuously. A time series depends on various factors like trend, seasonality, cycle and irregular data set, and is basically a series of data points well-organized in time. Time series forecasting is a significant area of machine learning. There are various prediction problems that are time-dependent and these problems can be handled through time series analysis. Computational intelligence (CI) is a developing computing approach for the forthcoming several years. CI gives the litheness to model the problem according to given requirements. It helps to find swift solutions to the problems arising in numerous disciplines. These methods mimic human behavior. The main objective of CI is to develop intelligent machines to provide solutions to real world problems, which are not modelled or are too difficult to model mathematically. This book aims to cover the recent advances in time series and applications of CI for time series analysis.
Author(s): Dinesh C. S. Bisht, Mangey Ram
Series: River Publishers Series in Automation, Control, and Robotics
Publisher: River Publishers
Year: 2022
Language: English
Pages: 190
City: Gistrup
Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
List of Figures
List of Tables
List of Contributors
List of Abbreviations
Chapter 1: On Dimensionless Dissimilarity Measures for Time Series
1.1: Introduction
1.2: Classical Dissimilarity Measures
1.3: Classical Entropy-type Dissimilarity Measures
1.4: Dissimilarity Measures for Time Series Data
1.4.1: Standard Dissimilarity Measures
1.4.2: Advanced Dissimilarity Measures
1.5: Conclusions
Chapter 2: The Classification Analysis of Variability of Time Series of Different Origin
2.1: Introduction
2.2: Used Datasets and Methods of Analysis
2.3: Results and Discussions
2.4: Summary
Chapter 3: A Comparative Study of CNN Architectures for Remaining Useful Life Estimation
3.1: Introduction
3.2: CNN Architectures and Hyperparameters
3.3: Numerical Experiments
3.3.1: Dataset
3.3.2: Pre-processing
3.3.2.1: Labelling
3.3.2.2: Scaling of data
3.3.2.3: Splitting of data
3.3.2.4: Time series to recurrence plots
3.4: Results
3.5: Conclusion
Chapter 4: The Analysis of Dynamical Changes and Local Seismic Activity of the Enguri Arch Dam
4.1: Introduction
4.2: Main Text
4.2.1: Methods and Results
4.3: Conclusion
Chapter 5: Analysis and Prediction of Daily Closing Price of Commodity Index Using Auto Regressive Integrated Moving Averages
5.1: Introduction
5.2: Literature Review
5.3: Objectives and Study
5.4: Data and Methodology
5.5: Data Decomposition
5.5.1: Seasonality
5.5.2: Trend
5.5.3: Cyclicity
5.6: Augmented Dicky Fuller (ADF) Test
5.6.1: Auto-correlation function (ACF)
5.6.2: Partial Autocorrelation Function (PACF)
5.6.3: ARIMA Model
5.7: Results and Analysis
5.8: Conclusion and Future Work
Chapter 6: Neural Networks Analysis of Suspended Sediment Transport Time Series Modeling in a River System
6.1: Introduction
6.2: Artificial Neural Networks
6.3: Hydrological Study Area
6.4: Methodology
6.4.1: Mathematics of SRC
6.5: Results
6.6: Hysteresis of Sediment Transport Process
6.7: Conclusions
6.8: Acknowledgements
Chapter 7: Ranking Forecasting Algorithms Using MCDM Methods: A Python Based Application
7.1: Introduction
7.2: Review of Literature
7.2.1: Analytic Hierarchy Process (AHP)
7.2.2: Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS)
7.2.3: VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR)
7.2.4: Time Series Analysis
7.3: Error Measurements and Forecasting
7.3.1: Holt-Winter
7.3.2: Autoregressive Integrated Moving Average (ARIMA)
7.3.3: SARIMA
7.3.4: ARIMA integrating Single Judgement Adjustment
7.3.5: ARIMA integrating Collaborative Judgement Adjustment
7.4: Multi Criteria Decision Making
7.4.1: Multiple Attribute Decision Making (MADM)
7.4.2: Multiple Objective Decision Making (MODM)
7.5: MCDM Methods
7.5.1: The AHP Method
7.5.2: The TOPSIS Method
7.5.3: The VIKOR Method
7.6: Framework of the Problem
7.7: Implementation Using Python Programming Language
7.7.1: Determining the criteria weights using AHP
7.7.2: Ranking Alternatives using TOPSIS method
7.7.3: Ranking Alternatives using VIKOR method
7.8: Result Analysis
7.9: Conclusion
7.10: Appendix
Chapter 8: Rainfall Prediction Using Artificial Neural Network
8.1: Introduction
8.2: Materials and Method
8.2.1: Input and Output Data Selection
8.2.2: Input Data Training
8.2.3: Validation and Testing
8.2.4: Artificial Neural Network Architecture
8.3: Result
8.4: Discussion
8.5: Comparision of ANN Model with Regresion
8.6: Conclusion
Chapter 9: Statistical Downscaling and Time Series Analysis for Future Scenarios of Temperature in Haridwar District, Uttarakhand
9.1: Introduction
9.2: Study Area
9.3: Data Used and Methodology
9.3.1: Data Used
9.3.2: Methodology
9.4: Results and Discussion
9.4.1: Regression Method
9.4.2: Predictor Variables Selection
9.4.3: Calibration and Validation Results
9.4.4: Future Emission Scenarios
9.5: Conclusion
Index
About the Editors
