Automation and Computational Intelligence for Road Maintenance and Management

Advances and Applications

AvHamzeh Zakeri,Fereidoon Moghadas Nejad

Inbunden, Engelska, 2022

1 531 kr

Beställningsvara. Skickas inom 5-8 vardagar. Fri frakt över 249 kr.

Beskrivning

Automation and Computational Intelligence for Road Maintenance and Management A comprehensive computational intelligence toolbox for solving problems in infrastructure management In Automation and Computational Intelligence for Road Maintenance and Management, a team of accomplished researchers delivers an incisive reference that covers the latest developments in computer technology infrastructure management. The book contains an overview of foundational and emerging technologies and methods in both automation and computational intelligence, as well as detailed presentations of specific methodologies. The distinguished authors emphasize the most recent advances in the maintenance and management of infrastructure robotics, automated inspection, remote sensing, and the applications of new and emerging computing technologies, including artificial intelligence, evolutionary computing, fuzzy logic, genetic algorithms, knowledge discovery and engineering, and more. Automation and Computational Intelligence for Road Maintenance and Management explores a universal synthesis of the cutting edge in parameters and indices to evaluate models. It also includes: Thorough introductions to management science and the latest methods of automation and the structure and framework of automation and computing intelligenceComprehensive explorations of advanced image processing techniques, recent advances in fuzzy, and diagnosis automationPractical discussions of segmentation and fragmentation and different types of features and feature extraction methodsIn-depth examinations of methods of classification along with various developed methodologies and models of quantification, evaluation, and indexing in automationPerfect for postgraduate students in road and transportation engineering, evaluation, and assessment, Automation and Computational Intelligence for Road Maintenance and Management will also earn a place in the libraries of researchers interested in or working with the evaluation and assessment of infrastructure.

Produktinformation

Utgivningsdatum:2022-07-13
Mått:10 x 10 x 10 mm
Vikt:454 g
Format:Inbunden
Språk:Engelska
Antal sidor:544
Förlag:John Wiley & Sons Inc
ISBN:9781119800644

Utforska kategorier

Elektronik och kommunikationer inom Naturvetenskap och teknik

Mer om författaren

Hamzeh Zakeri, PhD, is Adjunct Research Professor for the Department of Civil and Environment Engineering, Amirkabir University of Technology. His research interests include Automation, and Fuzzy type 2, Image Processing, Remote sensing, Machine Learning, Knowledge extraction, Hybrid Meta-heuristic Application in the field of pavement engineering.Fereidoon Moghadas Nejad, PhD, is Professor and Head of Transportation Group at Amirkabir University of Technology. His research interests include Materials, and Testing, Image Processing, Automation, Fuzzy and Numerical Methods in Pavement and Railway Engineering. Amir H. Gandomi, PhD, is Professor of Data Science and an ARC DECRA Fellow for the Faculty of Engineering and Information Technology at the University of Technology, Sydney. His research interests include Global Optimisation and (Big) Data Analytics using Machine Learning and Evolutionary Computations in particular.

Innehållsförteckning

Dedication xiiiPreface xvAuthor Biography xvii1 Concepts and Foundations Automation and Emerging Technologies 11.1 Introduction 11.2 Structure and Framework of Automation and Key Performance Indexes (KPIs) 31.3 Advanced Image Processing Techniques 41.4 Fuzzy and Its Recent Advances 61.5 Automatic Detection and Its Applications in Infrastructure 61.6 Feature Extraction and Fragmentation Methods 81.7 Feature Prioritization and Selection Methods 81.8 Classification Methods and Its Applications in Infrastructure Management 101.9 Models of Performance Measures and Quantification in Automation 111.10 Nature-Inspired Optimization Algorithms (NIOAS) 121.11 Summary and Conclusion 141.12 Questions and Exercise 142 The Structure and Framework of Automation and Key Performance Indices (KPIs) 152.1 Introduction 152.2 Macro Plan and Architecture of Automation 162.2.1 Infrastructure Automation 162.2.2 Importance of Infrastructure Automation Evaluation 162.3 A General Framework and Design of Automation 172.4 Infrastructure Condition Index and Its Relationship with Cracking 202.4.1 Road Condition Index 202.4.2 Bridge Condition Index 282.4.3 Tunnel Condition Index 312.5 Automation, Emerging Technologies, and Futures Studies 312.6 Summary and Conclusion 322.7 Questions 32Further Reading 323 Advanced Images Processing Techniques 35Introduction 353.1 Preprocessing (PPS) 363.1.1 Edge Preservation Index (EPI) 393.1.2 Edge-Strength Similarity-Based Image Quality Metric (ESSIM) 393.1.3 QILV Index 403.1.4 Structural Content Index (SCI) 403.1.5 Signal-To-Noise Ratio Index (PSNR) 413.1.6 Computational time index (CTI) 413.2 Preprocessing Using Single-Level Methods 413.2.1 Single-Level Methods 423.2.2 Linear Location Filter (LLF) 423.2.3 Median Filter 443.2.4 Wiener Filter 453.3 Preprocessing Using Multilevel (Multiresolution) Methods 493.3.1 Wavelet Method 493.3.2 Ridgelet Transform 573.3.3 Curvelet Transform 623.3.4 Decompaction and Reconstruction Images Using Shearlet Transform (SHT) 663.3.5 Discrete Shearlet Transform (DST) 673.3.6 Shearlet Decompaction and Reconstruction 693.3.7 Shearlet and Wavelet Comparison 713.3.8 Complex Shearlet Transform 743.3.9 Complex Shearlet Transform for Image Enhancement 783.3.10 Low and High frequencies of Complex Shearlet Transform for Image Denoising 793.4 General Comparison of Single/Multilevel Methods and Selection of Methods for Noise Removal and Image Enhancement 873.5 Application of Preprocessing 883.5.1 Pavement Surface Drainage Condition Assessment 883.6 Summary and Conclusion 933.7 Questions and Exercises 944 Fuzzy and Its Recent Advances 974.1 Introduction 974.1.1 Type-1 Fuzzy Set Theory 974.1.2 Type-2 Fuzzy Set Theory 984.1.3 α-Plane Representation of General Type-2 Fuzzy Sets 994.1.4 Type-Reduction 1014.1.5 Defuzzification 1034.1.6 Type-3 Fuzzy Logic Sets 1054.2 Ambiguity Modeling in the Fuzzy Methods 1064.2.1 Background of General Type-2 Fuzzy Sets 1064.3 Theory of Automatic Methods for MF Generation 1104.3.1 Automatic Procedure to Generate a 3D Membership Function 1104.4 Steps and Components of General 3D Type-2 Fuzzy Logic Systems (G3DT2 FL) 1114.4.1 General 3D Type-2 Fuzzy Logic Systems (G3DT2 FL) 1114.5 General 3D Type-2 Polar Fuzzy Method 1184.5.1 Automatic MF Generator 1184.5.2 A Measure of Ultrafuzziness 1194.5.3 Theoretic Operations of 3D Type-2 Fuzzy Sets in the Polar Frame 1224.5.4 Representation of Fuzzy 3D Polar Rules 1234.5.5 ϑ-Slice and α − Planes 1234.6 Computational Performance (CP) 1284.7 Application of G3DT2FLS in Pattern Recognition 1294.7.1 Examples of the Application of Fuzzy Methods in Infrastructure Management 1294.8 Summary and Conclusion 1364.9 Questions and Exercises 138Further Reading 1385 Automatic Detection and Its Applications in Infrastructure 1415.1 Introduction 1415.1.1 Photometric Hypotheses (PH) 1425.1.2 Geometric and Photometric Hypotheses (GPH) 1435.1.3 Geometric Hypotheses (GH) 1435.1.4 Transform Hypotheses (TH) 1435.2 The Framework for Automatic Detection of Abnormalities in Infrastructure Images 1445.2.1 Wavelet Method 1445.2.2 High Amplitude Wavelet Coefficient Percentage (HAWCP) 1445.2.3 High-Frequency Wavelet Energy Percentage (HFWEP) 1465.2.4 Wavelet Standard Deviation (WSTD) 1475.2.5 Moments of Wavelet 1485.2.6 High Amplitude Shearlet Coefficient Percentage (HASHCP) 1485.2.7 High-Frequency Shearlet Energy Percentage (HFSHEP) 1565.2.8 Fractal Index 1605.2.9 Moments of Complex Shearlet 1645.2.10 Central Moments q 1685.2.11 Hu Moments 1695.2.12 Bamieh Moments 1745.2.13 Zernike Moments 1775.2.14 Statistic of Complex Shearlet 1865.2.15 Contrast of Complex Shearlet 1865.2.16 Correlation of Complex Shearlet 1895.2.17 Uniformity of Complex Shearlet 1895.2.18 Homogeneity of Complex Shearlet 1895.2.19 Entropy of Complex Shearlet 1915.2.20 Local Standard Deviation of Complex Shearlet Index (F_Local_STD) 1935.3 Summary and Conclusion 1975.4 Questions and Exercises 202Further Reading 2036 Feature Extraction and Fragmentation Methods 2136.1 Introduction 2136.2 Low-Level Feature Extraction Methods 2136.3 Shape-Based Feature (SBF) 2166.3.1 Center of Gravity (COG) or Center of Area (COA) 2166.3.2 Axis of Least Inertia (ALI) 2176.3.3 Average Bending Energy 2186.3.4 Eccentricity Index (ECI) 2186.3.5 Circularity Ratio (CIR) 2206.3.6 Ellipse Variance Feature (EVF) 2206.3.7 Rectangularity Feature (REF) 2226.3.8 Convexity Feature (COF) 2236.3.9 Euler Number Feature (ENF) 2236.3.10 Profiles Feature (PRF) 2246.4 1D Function-Based Features for Shape Representation 2256.4.1 Complex Coordinates Feature (CCF) 2266.4.2 Extracting Edge Characteristics Using Complex Coordinates 2266.4.3 Edge Detection Using Even and Odd Shearlet Symmetric Generators 2286.4.4 Object Detection and Isolation Using the Shearlet Coefficient Feature (SCF) 2306.5 Polygonal-Based Features (PBF) 2316.6 Spatial Interrelation Feature (SIF) 2316.7 Moments Features (MFE) 2316.8 Scale Space Approaches for Feature Extraction (SSA) 2316.9 Shape Transform Features (STF) 2316.9.1 Radon Transform Features (RTF) 2316.9.2 Linear Radon Transform 2336.9.3 Translation of RT 2356.9.4 Scaling of RT 2356.9.5 Point and Line Transform Using RT 2356.9.6 RT in Sparse Objects 2386.9.7 Point and Line in RT 2386.10 Various Case-Based Examples in Infrastructures Management 2416.10.1 Case 1: Feature Extraction from Polypropylene Modified Bitumen Optical Microscopy Images 2416.10.2 Ratio of Number of Black Pixels to the Number of Total Pixels (RBT) 2456.10.3 Ratio of Number of Black Pixels to the Number of Total Pixels in Watershed Segmentation (RWS) 2466.10.4 Number and Average Area of the White Circular Objects in the Binary Image (The number of circular objects [NCO] & ACO) 2506.10.5 Entropy of the Image 2506.10.6 Radon Transform Maximum Value (RTMV) 2526.10.7 Entropy of Radon Transform (ERT) 2536.10.8 High Amplitude Radon Percentage (HARP) 2556.10.9 High-Energy Radon Percentage (HERP) 2576.10.10 Standard Deviation of Radon Transform (STDR) 2586.10.11 Q th -Moment of Radon Transform (QMRT) 2626.10.12 Case 2: Image-Based Feature Extraction for Pavement Skid Evaluation 2626.10.13 Case 3: Image-Based Feature Extraction for Pavement Texture Drainage Capability Evaluation 2696.10.14 Case 4: Image-Based Features Extraction in Pavement Cracking Evaluation 2796.10.15 Automatic Extraction of Crack Features 2816.10.16 Extraction of Crack Skeleton Using Shearlet Complex Method 2816.10.17 Calculate Crack Width Feature Using External Multiplication Method 2826.10.18 Detection of Crack Starting Feature (Crack Core) Using EPA Emperor Penguin Metaheuristic Algorithm 2846.10.19 Selection of Crack Root Feature Based on Geodetic Distance 2866.10.20 Determining Coordinates of the Crack Core as the Optimal Center at the Failure Level using EPA Method 2896.10.21 Development of New Features for Crack Evaluation Based on Graph Energy 2926.10.22 Crack Homogeneity Feature Based on Graph Energy Theory 2996.10.23 Spall Type 1 Feature: Crack Based on Graph Energy Theory in Crack Width Mode 2996.10.24 General Crack Index Based on Graph Energy Theory 3016.11 Summary and Conclusion 3066.12 Questions and Exercises 307Further Reading 3087 Feature Prioritization and Selection Methods 3137.1 Introduction 3137.2 A Variety of Features Selection Methods 3137.2.1 Filter Methods 3157.2.2 Correlation Criteria 3157.2.3 Mutual Information (MI) 3157.2.4 Wrapper Methods 3187.2.5 Sequential Feature Selection (SFS) Algorithm 3187.2.6 Heuristic Search Algorithm (HAS) 3207.2.7 Embedded Methods 3207.2.8 Hybrid Methods 3237.2.9 Feature Selection Using the Fuzzy Entropy Method 3267.2.10 Hybrid-Based Feature Selection Using the Hierarchical Fuzzy Entropy Method 3277.2.11 Step 1: Measure Similarity Index and Evaluate Features 3317.2.12 Step 2: Final Feature Vector 3377.3 Classification Algorithm Based on Modified Support Vectors for Feature Selection – CDFESVM 3377.3.1 Methods for Determining the Fuzzy Membership Function in Feature Selection 3417.4 Summary and Conclusion 3487.5 Questions and Exercises 349Further Reading 3508 Classification Methods and Its Applications in Infrastructure Management 3538.1 Introduction 3538.2 Classification Methods 3548.2.1 Naive Bayes Classification 3558.2.2 Decision Trees 3608.2.3 Logistic Regression 3658.2.4 k-Nearest Neighbors (kNN) 3678.2.5 Ensemble Techniques 3678.2.6 Adaptive Boosting (AdaBoost) 3708.2.7 Artificial Neural Network 3738.2.8 Support Vector Machine 3788.2.9 Fuzzy Support Vector Machine (FSVM) 3798.2.10 Twin Support Vector Machine (TSVM) 3808.2.11 Fuzzy Twin Support Vector Machine (FTSVM) 3818.2.12 Entropy and Its Application FSVM 3818.2.13 Development of Entropy Fuzzy Coordinate Descent Support Vector Machine (efcdsvm) 3838.2.14 Development of a New Support Vector Machine in Polar Frame (PSVM) 3848.2.15 Case Study: Pavement Crack Classification Based on PSVM 3888.3 Summary and Conclusion 3968.4 Questions and Exercises 399Further Reading 3999 Models of Performance Measures and Quantification in Automation 4059.1 Introduction 4059.2 Basic Definitions 4079.2.1 Confusion Matrix 4079.2.2 Main Metrics 4079.2.3 Accuracy Indexes 4089.2.4 Time (Speed) 4089.3 Database Modeling and Model Selection 4099.3.1 Different Parts of the Data 4099.3.2 Cross Validation 4109.3.3 Regularization Techniques and Overfitting 4109.4 Performance Evaluations and Main Metrics 4119.4.1 General Statistics 4119.4.2 Basic Rations 4119.4.3 Rations of Ratios 4129.4.4 Additional Statistics 4139.4.5 Operating Characteristic 4149.5 Case Studies 4159.5.1 Case 1: The Confusion Matrix for Evaluating Drainage of Pavement Surface 4169.5.2 Case 2: Metrics for Pavement Creak Detection Based on Deep Learning Using Transfer Learning 4179.5.3 Case 3: The Confusion Matrix for Evaluating Pavement Crack Classification 4209.5.4 Case 4: Quality Evaluation for Determining Bulk Density of Aggregates 4259.6 Summary and Conclusion 4299.7 Questions and Exercises 430Further Reading 43110 Nature-Inspired Optimization Algorithms (NIOAs) 43710.1 Introduction 43710.2 General Framework and Levels of Designing Nature-Inspired Optimization Algorithms (NIOAs) 43810.3 Basic Principles of Important Nature-Inspired Algorithms (NIOAs) 43910.3.1 Genetic Algorithm (GA) 44010.3.2 Particle Swarm Optimization (PSO) Algorithm 44110.3.3 Artificial Bee Colony (ABC) Algorithm 44410.3.4 Bat Algorithm (BA) 44610.3.5 Immune Algorithm (IA) 44810.3.6 Firefly Algorithm (FA) 45110.3.7 Cuckoo Search (CS) Algorithm 45210.3.8 Gray Wolf Optimizer (GWO) 45410.3.9 Krill Herd Algorithm (KHA) 45510.3.10 Emperor Penguin Algorithms (EPA) 45810.3.11 Hybrid Optimization Methods 46710.4 Summary and Conclusion 47010.5 Questions and Exercises 470Further Reading 471Appendix A Data Sets and Codes 475Appendix B The Glossary of Nature-Inspired Optimization Algorithms (NIOAS) 477Appendix C Sample Code for Feature Selection 483Index 521

Mer från samma författare