Spiking Neural P Systems for Time Series Analysis
Description
An up-to-date and accurate discussion of spiking neural P systems in time series analysis
In Spiking Neural P Systems for Time Series Analysis, the authors explore the fundamentals and the current states of both spiking neural P systems and time series analysis and examine the application models of time series analysis. You'll also find walkthroughs of recurrent-like, echo-like, and reservoir computing models for time series prediction.
The book covers applications in time series analysis such as financial time series analysis, power load forecasting, photovoltaic power forecasting, and medical signal processing, and contains illustrative photographs and tables designed to improve reader understanding.
Readers will also find:
- A thorough introduction to the theoretical and application research relevant to membrane computing and spiking P neural systems
- Comprehensive explorations of a variety of recurrent-like models for time series forecasting, including LSTM-SNP and GSNP models
- Practical discussions of common problems in reservoir computing models, including classification problems
- Complete evaluations of models used in financial time series analysis, power load forecasting, and other techniques
Perfect for scientists, researchers, postgraduates, lecturers, and teachers, Spiking Neural P Systems for Time Series Analysis will also benefit undergraduate students interested in advanced techniques for time series analysis.
More details
Other editions
Additional editions
Persons
Jun Wang, PhD, is a Professor in the School of Electrical Engineering and Electronic Information at Xihua University in Chengdu, China. Her research is focused on membrane computing, artificial intelligence, intelligence control. She has published over 90 scientific papers in international journals and conferences with an H-index of 35.
Hong Peng, PhD, is a Professor in the School of Computer and Software Engineering at Xihua University in Chengdu, China. His research interests include membrane computing, machine learning, pattern recognition. He has published over 230 scientific papers in international journals and conferences with an H-index of 42.
Content
About the Authors ix
Preface xi
Acknowledgments xiii
Acronyms xv
1 Introduction 1
1.1 Background 1
1.2 Membrane Computing 2
1.3 Spiking Neural P Systems 4
1.4 Time Series Analysis 7
1.5 Organization of Chapters 10
2 Spiking Neural P Systems 17
2.1 Introduction 17
2.2 Preliminaries 18
2.3 Spiking Neural P Systems 19
2.4 Spiking Neural P Systems with Extended Rules 22
2.5 Spiking Neural P Systems with Autapses 25
2.6 Nonlinear Spiking Neural P Systems 28
3 Recurrent-like Models for Time-series Forecasting 33
3.1 Introduction 33
3.2 Recurrent Neural Networks 34
3.3 LSTM-SNP Model 37
3.4 GSNP Model 44
3.5 NSNP-AU Model 51
4 Echo-like Models for Time Series Forecasting 65
4.1 Introduction 65
4.2 Echo State Networks 66
4.3 Echo-like Spiking Neural P Model 67
4.4 Echo-like Feedback Spiking Neural P Model 76
4.5 Deep Echo-like Spiking Neural P Model 83
5 Reservoir Computing Models for Time Series Classification 97
5.1 Introduction 97
5.2 Preliminaries 98
5.3 Basic Models 100
5.4 Improved Models 105
5.5 Model Evaluation 109
6 Financial Time Series Analysis 115
6.1 Stock Market Index Prediction 115
6.2 Exchange Rate Price Prediction 126
6.3 Crude Oil Price Prediction 137
7 Power Load Forecasting and Photovoltaic Power Forecasting 155
7.1 Power Load Forecasting 155
7.2 Photovoltaic Power Forecasting 167
8 Medical Signal Processing 195
8.1 Introduction 195
8.2 Methodology 196
8.3 Model Evaluation 204
Index 211