Advanced Spiking Neural P Systems Models and Applications

✍ Scribed by Hong Peng, Jun Wang

• Publisher: Springer
• Year: 2024
• Tongue: English
• Leaves: 304
• Category: Library

✦ Synopsis

Membrane computing is a class of distributed and parallel computing models inspired by living cells. Spiking neural P systems are neural-like membrane computing models, representing an interdisciplinary field between membrane computing and artificial neural networks, and are considered one of the third-generation neural networks. Models and applications constitute two major research topics in spiking neural P systems. The entire book comprises two parts: models and applications.
In the model part, several variants of spiking neural P systems and fuzzy spiking neural P systems are introduced. Subsequently, their computational completeness is discussed, encompassing digital generation/accepting devices, function computing devices, and language generation devices. This discussion is advantageous for researchers in the fields of membrane computing, biologically inspired computing, and theoretical computer science, aiding in understanding the distributed computing model of spiking neural P systems.
In the application part, the application of spiking neural P systems in time series prediction, image processing, sentiment analysis, and fault diagnosis is examined. This offers a novel method and model for researchers in artificial intelligence, data mining, image processing, natural language processing, and power systems. Simultaneously, it furnishes engineering and technical personnel in these fields with a powerful, efficient, reliable, and user-friendly set of tools and methods.

✦ Table of Contents

Foreword
Preface
Contents
Acronyms
Part I Models
1 Introduction
1.1 Background
1.2 Membrane Computing
1.3 Spiking Neural P Systems
1.3.1 Model and Computational Theory
1.3.2 Model Application
1.3.3 Simulation Systems
1.4 Organization of Chapters
References
2 Spiking Neural P Systems and Variants
2.1 Introduction
2.2 Preliminaries
2.3 Spiking Neural P Systems
2.3.1 Definition
2.3.2 Illustrative Example
2.4 Variants
2.4.1 Spiking Neural P Systems with Multiple Channels
2.4.1.1 Definition
2.4.1.2 Illustrative Example
2.4.2 Spiking Neural P Systems with Inhibitory Rules
2.4.2.1 Definition
2.4.2.2 Illustrative Example
2.4.3 Dynamic Threshold Neural P Systems
2.4.3.1 Definition
2.4.3.2 Illustrative Example
2.4.4 Coupled Neural P Systems
2.4.4.1 Definition
2.4.4.2 Illustrative Example
2.4.5 Dendrite P Systems
2.4.5.1 Definition
2.4.5.2 Illustrative Example
2.4.5.3 Compared with Other Variants
2.4.6 Nonlinear Spiking Neural P Systems
2.4.6.1 Definition
2.4.6.2 Illustrative Example
2.4.7 Spiking Neural P Systems with Autapses
2.4.7.1 Definition
2.4.7.2 Illustrative Example
2.4.8 Spiking Neural P Systems with Delay on Synapses
2.4.8.1 Definition
2.4.8.2 Illustrative Example
References
3 Computational Completeness
3.1 Introduction
3.2 Preliminaries
3.2.1 Grammar
3.2.2 Register Machines
3.3 Number Generating/Accepting Devices
3.3.1 Turing Universality as Number Generating Devices
3.3.2 Turing Universality as Number Accepting Devices
3.4 Function Computing Devices
3.5 Language Generating Devices
3.5.1 Relationships with Regular Languages
3.5.2 A Characterization of Recursively Enumerable Languages
3.6 Sequential Computing Devices
3.6.1 SDeP Systems
3.6.1.1 Definition
3.6.2 An Illustrative Example
3.6.3 Universality Results
3.6.3.1 Working in Max-Sequentiality Strategy
3.6.3.2 Working in Max-Pseudo-Sequentiality Strategy
3.6.4 Small Universal SDeP Systems for Computing Functions
3.7 Asynchronous Computing Devices
3.7.1 ASNP-MCS Systems
3.7.2 An Illustrative Example
3.7.3 Universality Results
3.7.3.1 ASNP-MCS Systems as Number Generating Devices
3.7.3.2 ASNP-MCS Systems as Number Accepting Devices
3.7.4 ASNP-MCS Systems as Small Universal Function Computing Devices
References
4 Fuzzy Spiking Neural P Systems
4.1 Introduction
4.2 Fuzzy Reasoning Spiking Neural P Systems
4.2.1 FRSNP Systems
4.2.2 Modeling Fuzzy Production Rules UsingFRSNP Systems
4.2.2.1 Fuzzy Production Rules
4.2.2.2 FRSNP System Model for Fuzzy Production Rules
4.2.3 Reasoning Algorithm Based on FRSNP Systems
4.3 Weighted Fuzzy Spiking Neural P Systems
4.3.1 WFSNP Systems
4.3.2 Weighted Fuzzy Knowledge Representation
4.3.2.1 Weighted Fuzzy Production Rules
4.3.2.2 Mapping Weighted Fuzzy Production Rules into WFSNP Systems
4.3.3 Weighted Fuzzy Reasoning Algorithm
4.4 Adaptive Fuzzy Spiking Neural P Systems
4.4.1 AFSNP Systems
4.4.2 Modeling Weighted Fuzzy Production Rules by AFSNP Systems
4.4.3 Fuzzy Reasoning Based on AFSNP Systems
4.4.4 Learning of AFSNP Systems
4.4.5 Simulation Example
4.5 Intuitionistic Fuzzy Spiking Neural P Systems
4.5.1 Definition
4.5.2 Modeling and Fuzzy Reasoning
4.6 Interval-Valued Fuzzy Spiking Neural P Systems
4.6.1 Interval-Valued Fuzzy Numbers
4.6.2 IVFSNP Systems
4.6.3 Modeling Fuzzy Production Rules
4.6.4 Fuzzy Reasoning Algorithm
References
Part II Applications
5 Time Series Forecasting
5.1 Introduction
5.2 Nonlinear Spiking Neural Systems with Global Weights
5.3 Univariate Time Series Forecasting Basedon NSNP-GW Systems
5.3.1 Overview of the Prediction Model
5.3.2 Learning of NSNP-GW Systems
5.3.3 Model Evaluation
5.3.3.1 Comparison of RW-NSNP Model with HFCM Model
5.3.3.2 Comparison of RW-NSNP Model with Other Models
5.4 Multivariate Time Series Forecasting Basedon NSNP-GW Systems
5.4.1 Prediction Framework for Multivariate Time Series
5.4.2 NSST Representation of Time Series
5.4.3 The Construction of NSNP-GW Systems
5.4.4 The Training of NSNP-GW Systems
5.4.5 The Prediction of NSNP-GW Systems
5.4.6 Model Evaluation
5.4.6.1 Gas Furnace Time Series
5.4.6.2 Sunspot Time Series
5.4.6.3 Beijing PM2.5 Time Series
5.4.6.4 Italian Air Quality Time Series
5.4.6.5 Nasdaq 100 Time Series
5.5 Echo Spiking Neural P Systems for Time Series Forecasting
5.5.1 A Specialized NSNP System and Its Extension
5.5.2 ESNP Systems
5.5.3 Model Evaluation
5.5.3.1 Comparison on Six Benchmark Time Series
5.5.3.2 Comparison on Three Larger Real-Life Time Series
5.5.3.3 Comparison on Two Synthetic Data Sets
5.5.3.4 Discussion
References
6 Image Processing
6.1 Introduction
6.2 Color Image Segmentation
6.2.1 DTNP Systems with Local Topology
6.2.2 Image Segmentation Method
6.2.2.1 Preprocessing
6.2.2.2 DTNP-LT-Based Segmentation
6.2.2.3 Determination of Local Weight
6.2.2.4 Post-processing
6.2.3 Model Evaluation
6.2.3.1 Qualitative Evaluation of Segmentation Performance
6.2.3.2 Quantitative Evaluation of Segmentation Accuracy
6.3 Multimodal Image Fusion
6.3.1 Coupled Neural P Systems with Local Topology
6.3.2 Image Fusion Framework for Infrared and Visible Images
6.3.2.1 Fusion Rules for Low-Frequency NSCT Coefficients
6.3.2.2 Fusion Rules for High-Frequency NSCT Coefficients
6.3.2.3 Implementation of the Fusion Method
6.3.3 Model Evaluation
6.3.3.1 Compared with Nine Fusion Methods
6.3.3.2 Compared with Five Fusion Methods Based on Deep Learning
6.3.3.3 Computational Efficiency
6.4 Edge Detection
6.4.1 NSNP-TO Systems
6.4.2 Edge Detector Based on NSNP-TO Systems
6.4.2.1 Input Module
6.4.2.2 ED-NSNP Detector
6.4.2.3 PSO-Based Optimization Module
6.4.2.4 Output Module
6.4.3 Model Evaluation
References
7 Sentiment Analysis
7.1 Introduction
7.2 Sentiment Classification Based on the LSTM-SNP Model
7.2.1 Attention-Aware LSTM-SNP Model
7.2.1.1 LSTM-SNP Model
7.2.1.2 Attention Mechanism
7.2.1.3 ALS Model
7.2.2 Sentiment Classification Method Based on ALS Model
7.2.2.1 Task Definition
7.2.2.2 Preprocessing
7.2.2.3 Word Embedding Layer
7.2.2.4 ALS Layer Processing
7.2.3 Model Evaluation
7.2.3.1 Data Sets
7.2.3.2 Hyperparameter Configuration
7.2.3.3 Performance Comparison and Analysis
7.3 Sentiment Classification Based on the GSNP Model
7.3.1 GSNP Model
7.3.2 AGSNP Model for Sentiment Classification
7.3.2.1 Word Embedding
7.3.2.2 Attention Mechanism
7.3.2.3 Attention-Enabled GSNP Model
7.3.3 Model Evaluation
7.3.3.1 Data Sets
7.3.3.2 Parameter Settings
7.3.3.3 Experimental Results
7.3.3.4 The Effects of Different Parameters on Performance
References
8 Fault Diagnosis
8.1 Introduction
8.2 Power Transformer Fault Diagnosis Based on FRSNP Systems
8.3 Fault Diagnosis of Power Systems Based on IFSNP Systems
8.3.1 Fault Diagnosis Model Based on IFSNP Systems
8.3.2 Example I
8.3.3 Example II
8.3.4 Comparison Analysis with Other Methods
8.4 Fault Diagnosis of Power Systems Based on IVFSNP Systems
8.4.1 Problem Description
8.4.2 Fault Diagnosis Model
8.4.3 Case Studies
8.4.3.1 Illustration Example: 345kV Transmission System
8.4.3.2 Comparison Analysis with Other Methods
References
Index