15th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2020)

 
 
Springer (Verlag)
  • erschienen am 28. August 2020
  • |
  • XXVII, 876 Seiten
 
E-Book | PDF mit Wasserzeichen-DRM | Systemvoraussetzungen
978-3-030-57802-2 (ISBN)
 

This book contains accepted papers presented at SOCO 2020 conference held in the beautiful and historic city of Burgos (Spain), in September 2020.

Soft computing represents a collection or set of computational techniques in machine learning, computer science and some engineering disciplines, which investigate, simulate, and analyze very complex issues and phenomena.

After a through peer-review process, the SOCO 2020 International Program Committee selected 83 papers which are published in these conference proceedings and represents an acceptance rate of 35%. Due to the COVID-19 outbreak, the SOCO 2020 edition was blended, combining on-site and on-line participation. In this relevant edition a special emphasis was put on the organization of special sessions. Eleven special session were organized related to relevant topics such as: Soft Computing Applications in Precision Agriculture, Manufacturing and Management Systems, Management of Industrial and Environmental Enterprises, Logistics and Transportation Systems, Robotics and Autonomous Vehicles, Computer Vision, Laser-Based Sensing and Measurement and other topics such as Forecasting Industrial Time Series, IoT, Big Data and Cyber Physical Systems, Non-linear Dynamical Systems and Fluid Dynamics, Modeling and Control systems

The selection of papers was extremely rigorous in order to maintain the high quality of SOCO conference editions and we would like to thank the members of the Program Committees for their hard work in the reviewing process. This is a crucial process to the creation of a high standard conference and the SOCO conference would not exist without their help.


1st ed. 2021
  • Englisch
  • Cham
  • |
  • Schweiz
Springer International Publishing
  • 104
  • |
  • 267 farbige Abbildungen, 104 s/w Abbildungen
  • |
  • XXVII, 876 p. 371 illus., 267 illus. in color.
  • 92,14 MB
978-3-030-57802-2 (9783030578022)
10.1007/978-3-030-57802-2
weitere Ausgaben werden ermittelt
  • Intro
  • Preface
  • Soco 2020 Organization
  • General Chair
  • General Co-chair
  • International Advisory Committee
  • Program Committee Chairs
  • Program Committee
  • Special Sessions
  • Contributions of Soft Computing to Precision Agriculture
  • Special Session Organizers
  • Program Committee
  • Soft Computing Methods in Manufacturing and Management Systems
  • Special Session Organizers
  • Program Committee
  • Soft Computing Applications for the Management of Industrial and Environmental Enterprises
  • Special Session Organizers
  • Program Committee
  • Optimization, Modeling and Control by Soft Computing Techniques
  • Special Session Organizers
  • Program Committee
  • Soft Computing and Machine Learning in Nonlinear Dynamical Systems and Fluid Dynamics: New Methods and Applications
  • Special Session Organizers
  • Program Committee
  • Soft Computing Techniques and Applications in Logistics and Transportation Systems
  • Special Session Organizers
  • Program Committee
  • Soft Computing and Machine Learning in IoT, Big Data, and Cyberphysical Systems
  • Special Session Organizers
  • Program Committee
  • Soft Computing Applied to Robotics and Autonomous Vehicles
  • Special Session Organizers
  • Program Committee
  • Soft Computing for Forecasting Industrial Time Series
  • Special Session Organizers
  • Program Committee
  • Machine Learning in Computer Vision
  • Special Session Organizers
  • Program Committee
  • Computational Intelligence for Laser-Based Sensing and Measurement
  • Special Session Organizers
  • Program Committee
  • Organising Committee Chairs
  • Organising Committee
  • Contents
  • I Soft Computing Applications
  • Advanced Oversampling for Improved Detection of Software Anomalies in a Robot
  • 1 Introduction
  • 2 Data Oversampling Proposal
  • 3 Experiments and Results
  • 3.1 Dataset
  • 3.2 Obtained Results
  • 4 Conclusions and Future Work
  • References
  • A Preliminary Study for Automatic Activity Labelling on an Elder People ADL Dataset
  • 1 Introduction and Motivation
  • 2 The Proposal
  • 2.1 OLDDEVICES Dataset Clean and Pre-processing
  • 2.2 Automatic Segmentation of Activities of the OLDDEVICES Dataset
  • 3 Numerical Results
  • 3.1 Materials and Methods
  • 3.2 Dataset Clean and Pre-processing
  • 3.3 Automatic Segmentation of Activities
  • 4 Conclusion and Future Work
  • References
  • How Noisy and Missing Context Influences Predictions in a Practical Context-Aware Data Mining System
  • 1 Introduction
  • 1.1 CADM and Context Quality
  • 1.2 Related Work
  • 2 Experimental Methodology
  • 2.1 Data Sources
  • 2.2 Methods
  • 2.3 Machine Learning Algorithms and Measurements
  • 2.4 Tools and Setup Parameters
  • 3 Experimental Results
  • 3.1 Results of Dirty Context Impact for DT Algorithm
  • 3.2 Results of Dirty Context Impact for DL Algorithm
  • 3.3 Results of Dirty Context Impact for GBT Algorithm
  • 4 Conclusions
  • References
  • Small-Wind Turbine Power Generation Prediction from Atmospheric Variables Based on Intelligent Techniques
  • 1 Introduction
  • 2 Case of Study: Bioclimatic House of Sotavento
  • 2.1 Wind Turbine
  • 2.2 Dataset Description
  • 3 Atmospheric Variables Study
  • 3.1 Pre-process
  • 3.2 Feature Reduction
  • 4 Used Techniques
  • 5 Experiments and Results
  • 5.1 Quality Measures
  • 5.2 Baseline Tests
  • 5.3 Regression Tests
  • 6 Conclusions and Future Work
  • References
  • Supported Decision-Making by Explainable Predictions of Ship Trajectories
  • 1 Introduction
  • 2 Related Work
  • 2.1 Residual Neural Network for Ship Vessel Classification
  • 2.2 Explainability Approaches
  • 2.3 User Studies in the Field of Explainable Machine Learning
  • 3 Explainable Ship Trajectory Classifications
  • 4 First Experimental Results
  • 4.1 Methodology
  • 4.2 Experimental Design
  • 4.3 Task
  • 4.4 Results
  • 5 Conclusion
  • References
  • A Natural Language Processing Approach to Represent Maps from Their Description in Natural Language
  • 1 Introduction
  • 2 State of the Art
  • 3 Data Corpus
  • 4 Developed System
  • 5 Experiments
  • 6 Conclusions and Future Work
  • References
  • I Evolutionary Computation
  • A Novel Formulation for the Energy Storage Scheduling Problem in Solar Self-consumption Systems
  • 1 Introduction
  • 2 Problem Formulation
  • 3 Optimization Methods Under Consideration
  • 3.1 MINLP Heuristics
  • 3.2 Evolutionary Algorithms
  • 4 Experimental Setup, Results and Discussion
  • 5 Concluding Remarks and Future Research Lines
  • References
  • A Behavioural Study of the Crossover Operator in Diploid Genetic Algorithms
  • 1 Introduction
  • 2 The Diploid Genetic Algorithms
  • 3 Crossover Operators
  • 4 Experimental Study
  • 5 Experimental Results
  • 6 Conclusions and Future Work
  • References
  • Parallel Differential Evolution with Variable Population Size for Global Optimization
  • 1 Introduction
  • 2 Mutation Strategies in Differential Evolution
  • 3 Proposed gPVaDE for Global Optimization
  • 3.1 Aging Mechanism
  • 3.2 Adaptive Population Growth
  • 3.3 Design and Implementation of gPVaDE
  • 4 Experiments and Results
  • 4.1 Results
  • 5 Conclusion
  • References
  • A Preliminary Many Objective Approach for Extracting Fuzzy Emerging Patterns
  • 1 Introduction
  • 2 Emerging Pattern Mining
  • 3 Evolutionary Fuzzy Systems for Extracting Emerging Patterns
  • 4 ManyObjective-EFEP: ManyObjective Evolutionary Algorithm for Extracting Fuzzy Emerging Patterns
  • 5 Experimental Study
  • 5.1 Experimental Framework
  • 5.2 Analysis of the Results Obtained
  • 6 Conclusions
  • References
  • I Artificial Neural Networks
  • A Smart Crutch Tip for Monitoring the Activities of Daily Living Based on a Novel Neural-Network Intelligent Classifier
  • 1 Introduction
  • 2 Smart Tip
  • 3 Database Generation
  • 3.1 Experimental Test Definition
  • 3.2 Indicator Selection
  • 4 ADL Classifier
  • 4.1 Single Step ANN-Based Classifier
  • 4.2 Two Step Based Classifier
  • 5 Conclusions
  • References
  • Hourly Air Quality Index (AQI) Forecasting Using Machine Learning Methods
  • 1 Introduction
  • 1.1 State of the Art
  • 2 Datasets
  • 3 Methods and Experimental Design
  • 3.1 Air Pollution Index
  • 3.2 Methods
  • 3.3 Experimental Procedure
  • 4 Results and Discussion
  • 5 Conclusions
  • References
  • Interpretable Deep Learning with Hybrid Autoencoders to Predict Electric Energy Consumption
  • 1 Introduction
  • 2 Backgrounds
  • 2.1 Difficulties in Predicting Energy Consumption
  • 2.2 Related Works
  • 3 The Proposed Method
  • 3.1 Projector and Information Projector
  • 3.2 Consumption Predictor
  • 3.3 Latent Space of Auxiliary Information for Interpretability
  • 4 Experiments
  • 4.1 Dataset and Experimental Settings
  • 4.2 Results of Demand Prediction
  • 4.3 Analysis on Evidence of Predicted Results
  • 5 Conclusion
  • References
  • On the Performance of Deep Learning Models for Time Series Classification in Streaming
  • 1 Introduction
  • 2 Related Work
  • 3 Materials and Methods
  • 3.1 ADLStream Framework
  • 3.2 Datasets
  • 3.3 Experimental Study
  • 4 Experimental Results
  • 4.1 Prequential Kappa
  • 4.2 Computation Time Analysis
  • 4.3 Statistical Analysis
  • 5 Conclusions
  • References
  • An Approach to Forecasting and Filtering Noise in Dynamic Systems Using LSTM Architectures
  • 1 Introduction
  • 2 Problem Formulation
  • 3 Database
  • 3.1 Setting up Data for Training
  • 4 Data Standardization
  • 5 LSTM Neuro Position Estimator
  • 5.1 Setup Training Options
  • 6 Experiments
  • 6.1 LSTM Validation
  • 6.2 Loss Position Measurements Effect Simulation
  • 6.3 Filtering System Simulation with New Measurements in Feedback
  • 7 Conclusions and Future Works
  • References
  • Novel Approach for Person Detection Based on Image Segmentation Neural Network
  • 1 Introduction and Related Work
  • 2 Problem Formulation and Methodology
  • 2.1 Novel Approach for Person Detection
  • 2.2 YOLO Architectures
  • 3 Dataset Creation
  • 4 Experiment Procedure
  • 4.1 Tested Encoder-Decoder Topologies
  • 4.2 Tested YOLO Architectures
  • 5 Results and Discussion
  • 5.1 Metrics Definition
  • 5.2 Results
  • 5.3 Discussion
  • 6 Conclusion
  • References
  • An Adaptive Cognitive Model to Integrate Machine Learning and Visual Streaming Data
  • 1 Introduction
  • 2 Proposal of an Adaptive Cognitive Model for Knowledge Representation
  • 3 Integration of Machine Learning Tools
  • 3.1 Computer Vision
  • 3.2 Deep Neural Networks
  • 4 Design of the Experiments
  • 4.1 Results
  • 5 Conclusions
  • References
  • Smart Song Equalization Based on the Classification of Musical Genres
  • 1 Introduction
  • 2 Related Works
  • 3 Proposed Architecture
  • 4 Experimentation
  • 4.1 Datasets
  • 4.2 Training
  • 4.3 Smart Song Equalization
  • 5 Conclusions
  • References
  • I Special Session: Contributions of Soft Computing to Precision Agriculture
  • Machine Learning in Classification of the Wax Structure of Breathing Openings on Leaves Affected by Air Pollution
  • 1 Introduction
  • 2 Methods
  • 2.1 Real Data Description
  • 2.2 Feature Extraction
  • 2.3 Image Classification
  • 3 Results
  • 4 Conclusion
  • References
  • Software Sensors for the Monitoring of Bioprocesses
  • 1 Introduction
  • 2 Case 1: ANN-Based Software Sensor for Biomass Concentration Estimation in a Yeast Cultivation Process
  • 3 Case 2: Set of Two Software Sensors for the Monitoring of Biomass Growth in a Filamentous Bacterial Cultivation Process
  • 4 Conclusion
  • References
  • RGB Images Driven Recognition of Grapevine Varieties
  • 1 Introduction
  • 2 Materials and Methods
  • 2.1 Data Collection
  • 2.2 Dataset
  • 2.3 Densely Connected Convolutional Networks
  • 2.4 Variety Recognition System
  • 3 Results and Discussion
  • 4 Conclusion
  • References
  • Discovering Spatio-Temporal Patterns in Precision Agriculture Based on Triclustering
  • 1 Introduction
  • 2 Related Works
  • 3 Methodology
  • 3.1 Triclustering
  • 3.2 The TriGen Algorithm
  • 4 Results
  • 4.1 Dataset Description
  • 4.2 Behaviour Patterns Quality, the TRIQ Measure
  • 4.3 Discovery of Spatio-Temporal Patterns in Maize Crops
  • 5 Conclusions
  • References
  • Counting Livestock with Image Segmentation Neural Network
  • 1 Introduction
  • 2 Methodology
  • 2.1 Problem Formulation
  • 2.2 Proposed Solution
  • 3 Image Segmentation Neural Network
  • 3.1 Dataset for Training and Validation
  • 3.2 U-Net Training
  • 3.3 Results
  • 4 Conclusion
  • References
  • Smart, Precision or Digital Agriculture and Farming - Current State of Technology
  • 1 Introduction
  • 2 Worldwide, EU and Czech Republic View
  • 3 Terminology and Technology
  • 4 Soft Computing Techniques Application Areas
  • 5 Commercial PA and Smart Agriculture Solutions
  • 6 Conclusions
  • References
  • An Automated Platform for Microrobot Manipulation
  • 1 Introduction
  • 2 Microrobots Specification
  • 2.1 Composition
  • 2.2 Production
  • 2.3 Microrobots Response to Laser Beam Pulse
  • 3 Automated Platform Overview
  • 3.1 Software Overview
  • 3.2 Precision of the Positioning
  • 3.3 Camera Setting
  • 3.4 Disk Localisation Algorithm
  • 3.5 Automated Control of Microrobots Movement
  • 4 Conclusions and Further Work
  • 4.1 Further Works
  • References
  • Growth Models of Female Dairy Cattle
  • 1 Introduction
  • 1.1 Problem of Growth Modelling
  • 2 Growth Models
  • 2.1 Functions Overview
  • 3 Linearization of Nonlinear Model and Curvature of Nonlinear Model
  • 3.1 Nonlinear Model, Linearization and Estimates
  • 4 Numerical Study
  • 4.1 Data Processing
  • 5 Conclusion Remark
  • References
  • A Preliminary Study on Crop Classification with Unsupervised Algorithms for Time Series on Images with Olive Trees and Cereal Crops
  • 1 Introduction
  • 2 Clustering Algorithms
  • 3 Methodology, Experimentation and Results
  • 4 Conclusions
  • References
  • I Special Session: Soft Computing Methods in Manufacturing and Management Systems
  • Blocks of Jobs for Solving Two-Machine Flow Shop Problem with Normal Distributed Processing Times
  • 1 Introduction
  • 2 Two-Machine Problem with Due Dates
  • 3 Random Task Execution Times
  • 4 Blocks of Tasks
  • 4.1 Blocks of Early Tasks
  • 4.2 Blocks of Tardy Tasks
  • 5 Tabu Search Algorithm
  • 6 Random Tasks Execution Times
  • 7 Computational Experiments
  • 8 Conclusions
  • References
  • Soft Computing Analysis of Pressure Decay Leak Test Detection
  • 1 Introduction
  • 2 Literature Review
  • 3 Leak Test Data
  • 4 Data Analysis
  • 4.1 Test Setup
  • 4.2 Model Generation
  • 4.3 Impact of Measure Time
  • 5 Future Work
  • 6 Conclusion
  • References
  • Fuzzy FMEA Application to Risk Assessment of Quality Control Process
  • 1 Introduction
  • 2 Classical and Fuzzy Failure Mode and Effects Analysis (FMEA and Fuzzy FMEA)
  • 3 Research of FQC in Automotive Industry
  • 3.1 Final Quality Control (FQC)
  • 3.2 FMEA of FQC Process
  • 3.3 Fuzzy FMEA of Final Quality Control (FQC)
  • 4 Conclusion
  • References
  • Similarity of Parts Determined by Semantic Networks as the Basis for Manufacturing Cost Estimation
  • 1 Introduction
  • 1.1 Method for Determining the Similarity of Parts
  • 2 Description of Gear-Casing-Type Parts Using Semantic Networks and Estimating Similarity of Semantic Networks
  • 2.1 Description of Gear-Housing's Technological and Structural Features
  • 2.2 Description of Gear-Housing's Elementary Functional Surfaces
  • 2.3 Assessment of the Similarity of Semantic Networks
  • 3 An Application of Proposed Method
  • 3.1 Cost Similarity
  • 3.2 S&T Similarity and Cost Similarity Comparison Results
  • 4 Summary
  • References
  • A Simulated Annealing Based Method for Sequencing Problem in Mixed Model Assembly Lines
  • 1 Introduction
  • 2 Mixed-Model Assembly Line Sequencing Problem
  • 2.1 The Simulated Annealing Algorithm
  • 2.2 Modified SA Algorithm for MMALSP
  • 2.3 Objective Function
  • 3 An Illustrative Example
  • 4 Summary
  • References
  • The Concept of Genetic Algorithm Application for Scheduling Operations with Multi-resource Requirements
  • 1 Introduction
  • 2 Machines and Crews Scheduling Problem
  • 3 A Basic Schedule Generation Using the Genetic Algorithm
  • 3.1 Encoding and Decoding
  • 3.2 Initialization
  • 3.3 Chromosome Differentiation and Selection
  • 3.4 Ordering Selection Procedure and Terminal Condition
  • 4 Summary
  • References
  • I Special Session: Soft Computing Applications for the Management of Industrial and Environmental Enterprises
  • Comparative Analysis of Clustering Techniques for a Hybrid Model Implementation
  • 1 Introduction
  • 2 Case of Study
  • 2.1 Sotavento Bioclimatic House
  • 2.2 Model Approach
  • 3 Used Techniques
  • 3.1 Preprocessing
  • 3.2 LDA Projection
  • 3.3 Clustering
  • 3.4 Error Metrics
  • 3.5 Regression Method
  • 4 Experiments and Results
  • 4.1 Cluster
  • 4.2 Regression
  • 5 Conclusions and Future Works
  • References
  • Data Balancing to Improve Prediction of Project Success in the Telecom Sector
  • 1 Introduction and Previous Work
  • 2 Soft-Computing Techniques
  • 2.1 Data-Balancing
  • 2.2 Classifiers
  • 3 Experiments and Results
  • 3.1 Dataset
  • 3.2 Results by SVM
  • 3.3 Results by RF
  • 4 Conclusions and Future Work
  • References
  • Demand Control Ventilation Strategy by Tracing the Radon Concentration in Smart Buildings
  • 1 Introduction
  • 2 Indoor Air Quality Algorithm
  • 2.1 Mathematical Model
  • 2.2 Details of the Demand Control Ventilation Strategy
  • 3 Results and Discussion for the Operation of the Demand Control Ventilation Strategy
  • 3.1 Experimental Setup
  • 3.2 Indoor Radon Level
  • 4 Conclusion
  • References
  • Implementation of a Statistical Dialogue Manager for Commercial Conversational Systems
  • 1 Introduction
  • 2 The DialogFlow Platform
  • 3 Proposed Framework for Statistical Dialogue Management
  • 4 Use Case: Train Scheduling Domain
  • 5 Integration and Evaluation
  • 6 Conclusions and Future Work
  • References
  • I Special Session: Optimization, Modeling and Control by Soft Computing Techniques (OMCS)
  • Wind Turbine Pitch Control with an RBF Neural Network
  • 1 Introduction
  • 2 Wind Turbine Mathematical Description
  • 3 Description of the Neuro-Controller
  • 3.1 Control Architecture
  • 3.2 RBF Neural Network Calculation
  • 3.3 Learning Algorithm
  • 4 Simulation Results
  • 5 Conclusions and Future Works
  • References
  • MIMO Neural Models for a Twin-Rotor Platform: Comparison Between Mathematical Simulations and Real Experiments
  • 1 Introduction
  • 2 Twin-Rotor System Dynamics
  • 2.1 Mathematical Model
  • 2.2 Study of the Range of Non-linear Working Points
  • 3 Neural Network Structures
  • 3.1 Neural Network Model Structure Comparison
  • 3.2 Experimental Methodology
  • 4 Experiments and Results
  • 4.1 Simulation
  • 4.2 Structure Comparison and Prediction Degradation
  • 4.3 Simulation vs Real Platform
  • 5 Conclusions
  • References
  • Fuzzy-Logic Based Identification of Conventional Two-Lane Roads
  • 1 Introduction
  • 2 Road Classes and Geometric Characteristics
  • 2.1 Two-Lane Road Classes
  • 2.2 Geometric Characteristics of a Road
  • 3 Identification of Two-Lane Roads by a Fuzzy Mamdani System
  • 3.1 Variables of the Fuzzy Inference System
  • 3.2 Mamdani-Type Fuzzy Classification System
  • 3.3 Discussion of the Results with the Mamdani Fuzzy System
  • 4 Neuro-Fuzzy System
  • 5 Conclusions and Future Work
  • References
  • Swarm Modelling Considering Autonomous Vehicles for Traffic Jam Assist Simulation
  • 1 Introduction
  • 2 State of the Art
  • 3 Intelligent Driver Model (IDM)
  • 4 Traffic Jam Assistant
  • 4.1 Single Lane with Heterogeneous Vehicles
  • 4.2 Multiple Lanes with Heterogeneous Vehicles
  • 5 Conclusions and Future Work
  • References
  • I Special Session: Soft Computing and Machine Learning in Non-linear Dynamical Systems and Fluid Dynamics: New Methods and Applications
  • Exploring Datasets to Solve Partial Differential Equations with TensorFlow
  • 1 Introduction
  • 2 Data and Methods
  • 2.1 Our Deep Neural Network
  • 2.2 Our Training Datasets
  • 3 Example: The Heat Equation
  • 4 Results
  • 5 Summary and Conclusions
  • References
  • Modeling Double Concentric Jets Using Linear and Non-linear Approaches
  • 1 Introduction
  • 2 Test Problem: Double Concentric Jets
  • 3 Linear Global Stability Analysis
  • 4 Data Analysis Using Dynamic Mode Decomposition
  • 5 Creating a Simple Linear Model
  • 6 Creating a Complex Non-linear Model
  • 7 Conclusions
  • References
  • Unsupervised Data Analysis of Direct Numerical Simulation of a Turbulent Flame via Local Principal Component Analysis and Procustes Analysis
  • 1 Introduction
  • 2 Theory
  • 2.1 Variable Selection via Principal Component Analysis and Procustes Analysis
  • 2.2 Unsupervised Data Analysis via Local Principal Variables
  • 3 Case Description
  • 4 Results
  • 5 Conclusions
  • References
  • HODMD Analysis in a Forced Flow over a Backward-Facing Step by Harmonic Perturbations
  • 1 Introduction
  • 2 Problem Description
  • 3 Non-modal Stability Analysis
  • 4 Higher Order Dynamic Mode Decomposition
  • 5 Studying the System Response Using HODMD
  • 5.1 Initial Data Processing
  • 5.2 Creating a Matrix of Modes
  • 5.3 Prediction of Optimal Perturbation
  • 6 Results
  • 7 Conclusions
  • References
  • An Application of Variational Mode Decomposition in Simulated Flight Test Data
  • 1 Introduction
  • 2 Variational Mode Decomposition
  • 3 Simulated Signal Input Using NeoCASS
  • 3.1 NeoCASS Parameters
  • 3.2 Analysis of the Signals
  • 4 Application of VMD to Acceleration Output
  • 4.1 Frequencies Detection for Different Maneuvers
  • 5 Conclusions
  • References
  • Following Vortices in Turbulent Channel Flows
  • 1 Introduction
  • 2 Input Data
  • 3 Coherent Structure Reconstruction
  • 4 Temporal Tracking
  • 5 Preliminary Results
  • 6 Conclusions and Future Works
  • References
  • I Special Session: Soft Computing Techniques and Applications in Logistics and Transportation Systems
  • Stable Performance Under Sensor Failure of Local Positioning Systems
  • 1 Introduction
  • 2 Taylor-Based Positioning Algorithm in TDOA Systems
  • 3 CRLB Modeling in TDOA Systems
  • 4 GA Optimization
  • 5 Results
  • 6 Conclusions
  • References
  • Solving the Two-Stage Supply Chain Network Design Problem with Risk-Pooling and Lead Times by an Efficient Genetic Algorithm
  • 1 Introduction
  • 2 Definition of the Problem
  • 3 Description of the Proposed Genetic Algorithm
  • 4 Computational Results
  • 5 Conclusions
  • References
  • Genetic Algorithm Optimization of Lift Distribution in Subsonic Low-Range Designs
  • 1 Introduction
  • 2 Description of the Problem
  • 3 Genetic Algorithm
  • 4 Results
  • 5 Conclusion
  • References
  • Hybrid Genetic Algorithms and Tour Construction and Improvement Algorithms Used for Optimizing the Traveling Salesman Problem
  • 1 Introduction
  • 2 A Genetic Algorithm and Crossover Operators for TSP
  • 3 Other Heuristic Algorithms for TSP
  • 3.1 A Nearest Neighbor Algorithm
  • 3.2 A Nearest Insertion Algorithm
  • 3.3 A 2-OPT Algorithm
  • 4 The Variants of the Genetic Algorithm for TSP
  • 4.1 A Generic Genetic Algorithm for TSP
  • 4.2 A Genetic Algorithm with a 2-OPT Algorithm for TSP
  • 4.3 A Genetic Algorithm with a Nearest Neighbor Algorithm, a Nearest Insertion Algorithm and a 2-OPT Algorithm for TSP
  • 5 Computational Results and Discussion
  • 6 Conclusion and Future Work
  • References
  • Segmentation Optimization in Trajectory-Based Ship Classification
  • 1 Introduction
  • 2 State of the Art
  • 3 Ship-Type Determination Using Binary Classification
  • 4 Trajectories Segmentation
  • 5 Results Analysis
  • 6 Conclusions and Perspectives
  • References
  • Bio-Inspired System for MRP Production and Delivery Planning in Automotive Industry
  • 1 Introduction
  • 2 Related Work
  • 3 Modelling the Material Requirements Planning
  • 3.1 Mainframe of the Firefly Algorithm
  • 3.2 Collection of Input Data
  • 4 Experimental Results and Discussion
  • 5 Conclusion and Future Work
  • References
  • I Special Session: Soft Computing and Machine Learning in IoT, Big Data and Cyber Physical Systems
  • Time Series Data Augmentation and Dropout Roles in Deep Learning Applied to Fall Detection
  • 1 Introduction and Related Work
  • 2 Materials and Methods
  • 2.1 Neural Network Models Used in This Study
  • 2.2 Enhancements in the Network Learning
  • 2.3 Data Set and Cross Validation
  • 3 Results and Discussion
  • 4 Conclusion
  • References
  • A Comparison of Multivariate Time Series Clustering Methods
  • 1 Introduction
  • 2 Materials and Methods
  • 2.1 MTS Clustering Methods
  • 2.2 Experimental Data Sets
  • 2.3 Assessment of the Methods
  • 3 Results and Discussion
  • 4 Conclusions
  • References
  • Synthesized A* Multi-robot Path Planning in an Indoor Smart Lab Using Distributed Cloud Computing
  • 1 Introduction
  • 2 Related Work on Multi-robot Path Planning
  • 2.1 A* Algorithms
  • 3 Solution Design Approach and Features
  • 3.1 Refinement and Synthesize Phases
  • 3.2 The Heuristic of the Meta-planner
  • 3.3 Solution Architecture of CNMA-A* PP
  • 4 Experiment and Results
  • 5 Conclusions
  • References
  • Towards Fog-Based HiTLCPS for Human Robot Interactions in Smart Lab: Use Cases and Architecture Overview
  • 1 Introduction
  • 2 Related Research Work
  • 3 Entities and Use Case Definitions
  • 3.1 Description of the Entities
  • 3.2 Focus of the Study
  • 3.3 Use Cases for Robot in Following Mode
  • 4 Architecture Overview
  • 5 Conclusions
  • References
  • Neural Models to Predict Irrigation Needs of a Potato Plantation
  • 1 Introduction
  • 2 Previous Work
  • 3 Applied Methods
  • 3.1 Interpolation
  • 3.2 Neural Models
  • 4 Agronomic Setup
  • 5 Experiments and Results
  • 5.1 Results by Cubic Interpolation
  • 5.2 Results by Makima Interpolation
  • 5.3 Results by Spline Interpolation
  • 6 Conclusions and Future Work
  • References
  • I Special Session: Soft Computing Applied to Robotics and Autonomous Vehicles
  • Mathematical Modelling for Performance Evaluation Using Velocity Control for Semi-autonomous Vehicle
  • 1 Introduction
  • 2 Vehicle Dynamics
  • 2.1 Constraints
  • 2.2 Mathematical Modeling
  • 2.3 Velocity Control
  • 3 Simulation Setup and Results
  • 3.1 Simulation Setup
  • 3.2 Results
  • 4 Conclusion
  • References
  • A Relative Positioning Development for an Autonomous Mobile Robot with a Linear Regression Technique
  • 1 Introduction
  • 2 LiDAR Odometry Development
  • 2.1 Linear Regression Development
  • 2.2 LiDAR Odometry Pseudocode
  • 3 LiDAR Odometry Test
  • 4 Conclusions
  • References
  • Generating 2.5D Photorealistic Synthetic Datasets for Training Machine Vision Algorithms
  • 1 Introduction
  • 2 Related Work
  • 3 Ensuring Photo-Realistic 3D Models
  • 4 Ensuring Photo-Realistic Lighting Conditions
  • 5 Dataset Generation Framework Description
  • 6 Dataset Acquisition
  • 6.1 Single Object Datasets for Training
  • 6.2 Multiple Object Datasets for Testing
  • 7 Discussion and Future Prospects
  • References
  • Control of Industrial AGV Based on Reinforcement Learning
  • 1 Introduction
  • 2 System Description
  • 2.1 AGV Model
  • 2.2 Workspace
  • 3 Reinforcement Learning Control Approach
  • 3.1 Space of States and Set of Actions
  • 3.2 Design of the Reward Strategy
  • 4 Simulation Results
  • 5 Conclusions and Future Works
  • References
  • Shared Control Framework and Application for European Research Projects
  • 1 Introduction
  • 2 Driver-Automation Framework for PRYSTINE and HADRIAN
  • 3 Shared Control System
  • 3.1 Lane-Keeping Controller
  • 3.2 The LoHA Controller
  • 3.3 The Arbitration System
  • 4 Use Case and Results
  • 5 Conclusions and Future Works
  • References
  • A First Approach to Path Planning Coverage with Multi-UAVs
  • 1 Introduction
  • 2 Coverage Area Decomposition and Navigation Strategy
  • 2.1 Area Decomposition Strategy
  • 2.2 Navigation Strategy
  • 3 Simulation Results
  • 3.1 Performance Measurements
  • 3.2 Scenarios
  • 4 Conclusions and Future Works
  • References
  • I Special Session: Soft Computing for Forecasting Industrial Time Series
  • Copper Price Time Series Forecasting by Means of Generalized Regression Neural Networks with Optimized Predictor Variables
  • 1 Introduction
  • 2 Materials
  • 3 Method
  • 3.1 Length of the Lagged Variables
  • 3.2 Figures of Merit
  • 4 Results and Discussion
  • 4.1 Best Model Selection
  • 4.2 Copper Prices Forecast
  • 5 Conclusions
  • References
  • A Multivariate Approach to Time Series Forecasting of Copper Prices with the Help of Multiple Imputation by Chained Equations and Multivariate Adaptive Regression Splines
  • 1 Introduction
  • 2 Materials and Methods
  • 2.1 The Database
  • 2.2 Multiple Imputation by Chained Equations
  • 2.3 Multivariate Adaptive Regression Splines
  • 2.4 The Algorithm
  • 3 Results
  • 3.1 Missing Data Imputation
  • 3.2 Training of a Copper Price MARS Model with All the Variables
  • 3.3 Training of MARS Models for Prediction from One to Twelve Months Ahead
  • 4 Discussion and Conclusions
  • References
  • Time Series Analysis for the COMEX Copper Spot Price by Using Support Vector Regression
  • 1 Introduction
  • 2 Materials and Methods
  • 2.1 Experimental Dataset
  • 2.2 Support Vector Regression (SVR) for Time Series Analysis
  • 2.3 Computational Procedure and Numerical Schemes
  • 3 Results and Discussion
  • 4 Conclusions
  • References
  • Uncertainty Propagation Using Hybrid Methods
  • 1 Introduction
  • 2 Hybrid Methodology
  • 3 Application of the Hybrid SGP4 Propagator to Galileo-Type Orbits
  • 3.1 SGP4 and AIDA Orbit Propagators
  • 3.2 Numerical Results
  • 4 Conclusions
  • References
  • I Special Session: Machine Learning in Computer Vision
  • Multidimensional Measurement of Virtual Human Bodies Acquired with Depth Sensors
  • 1 Introduction
  • 2 3D Body Acquisition and Modelling
  • 3 3D Body Measuring Method
  • 3.1 Perimetral Measurements Method
  • 3.2 Selection of Body Parts to Be Measured
  • 3.3 Estimation of Area and Volume
  • 4 Quantifying the Accuracy of the Method for Measuring Scanned 3D Models
  • 4.1 Experimentation with Synthetic 3D Models
  • 4.2 Experimentation with Real 3D Models
  • 5 Conclusions
  • References
  • Event-Based Conceptual Architecture for the Management of Cyber-Physical Systems Tasks in Real Time
  • 1 Introduction
  • 2 Related Works
  • 2.1 Software Engineering for Component-Based CPS
  • 2.2 Software Engineering for Service-Based CPS
  • 2.3 Software Engineering for Agent-Based CPS
  • 3 Software Engineering for Event-Based CPS
  • 4 Components of the Conceptual Architecture
  • 5 Conclusions
  • References
  • A Preliminary Study on Deep Transfer Learning Applied to Image Classification for Small Datasets
  • 1 Introduction
  • 2 Related Works
  • 3 Methodology
  • 3.1 Image Preprocessing
  • 3.2 Creation of Source and Target Subsets
  • 3.3 Deep Neural Network Architecture
  • 3.4 Four Validation Schemes
  • 3.5 Source-Target Similarity Analysis
  • 3.6 Class Imbalance Analysis
  • 4 Experimentation and Results
  • 4.1 Image Dataset
  • 4.2 Evaluation Metrics
  • 4.3 Experimental Settings
  • 4.4 Results and Discussion
  • 5 Conclusions
  • References
  • Burr Detection Using Image Processing in Milling Workpieces
  • 1 Introduction
  • 2 Inspection Method
  • 2.1 Image Processing
  • 2.2 Section Image and Percentage of White Pixels
  • 2.3 Threshold of Points
  • 2.4 Linear Regression
  • 2.5 Criteria Selection
  • 3 Experimental Results
  • 4 Conclusions
  • References
  • A Deep Learning Architecture for Recognizing Abnormal Activities of Groups Using Context and Motion Information
  • 1 Introduction
  • 1.1 One-Class Classification (OCC)
  • 2 Deep Learning Architecture for Abnormal Classification
  • 2.1 Activity Description Vector
  • 2.2 D-ADV: Activity Descriptor for Deep Learning Purposes
  • 2.3 D-ADV-OC: Abnormal Sequence Classifier Based on Two-Stream Activity Recognition and Context Information
  • 3 Experiments
  • 4 Conclusions
  • References
  • Implementation of a Low-Cost Rain Gauge with Arduino and Thingspeak
  • 1 Introduction
  • 2 System Overview
  • 2.1 Thingspeak
  • 2.2 Arduino Nano
  • 2.3 TFA Rain Gauge
  • 2.4 DTH11 Temperature-Relative Humidity Sensor
  • 2.5 Sensor FC-28 Soil Moisture
  • 2.6 GPS Module for Arduino NEO-GM-0-001
  • 2.7 MCU Wi Fi Node ESP8266MOD for Arduino
  • 2.8 LCD Display
  • 2.9 Solar Panel
  • 3 Software Architecture
  • 4 Calibration and Monitoring of Variables
  • 5 Conclusions
  • References
  • Functional Networks for Image Segmentation of Cutaneous Lesions with Rational Curves
  • 1 Introduction
  • 2 The Problem
  • 3 Functional Networks
  • 4 Our Method
  • 5 Experimental Results
  • 6 Conclusions and Future Work
  • References
  • Manufacturing Description Language for Process Control in Industry 4.0
  • 1 Introduction
  • 2 Manufacturing Description Language
  • 2.1 Parameterization
  • 2.2 Assembly Actions
  • 3 Validation of the Proposal
  • 4 Conclusions
  • References
  • ToolSet: A Real-Synthetic Manufacturing Tools and Accessories Dataset
  • 1 Introduction
  • 2 Related Works
  • 2.1 Industry 4.0
  • 2.2 You Only Look Once
  • 2.3 Relevant Datasets
  • 3 Toolset Dataset
  • 3.1 Real Images
  • 3.2 Synthetic Images
  • 4 Experiments
  • 5 Conclusions
  • References
  • I Special Session: Computational Intelligence for Laser-Based Sensing and Measurement
  • Robust 3D Object Detection from LiDAR Point Cloud Data with Spatial Information Aggregation
  • 1 Introduction
  • 2 Related Work
  • 2.1 BEV Object Detection Methods
  • 2.2 Methods Learning from Raw Point Cloud
  • 3 Methodology
  • 3.1 Baseline Pipeline
  • 3.2 FeatExt Operation
  • 3.3 Fusion Design
  • 4 Implementation
  • 5 Experiments and Results
  • 6 Conclusions
  • References
  • A Comparison of Registration Methods for SLAM with the M8 Quanergy LiDAR
  • 1 Introduction
  • 2 Materials
  • 3 Point Cloud Registration Methods
  • 3.1 ICP
  • 3.2 CPD
  • 3.3 NDT ch79Bibersps2003spsNDT2D
  • 4 Registration and SLAM Algorithm
  • 5 Results
  • 6 Conclusion
  • References
  • An Application of Laser Measurement to On-Line Metal Strip Flatness Measurement
  • 1 Introduction
  • 2 Optical Flatness Measurement System
  • 2.1 3D Sheet Measurement
  • 3 Results
  • 4 Conclusions
  • References
  • Efficiency of Public Wireless Sensors Applied to Spatial Crowd Monitoring in Buildings
  • 1 Introduction
  • 2 Turning Bands Method
  • 3 Experiment Background
  • 4 Preliminary and Structural Analysis Data from Sensors
  • 5 Spatial Prediction Models of PWR-WiFi Network Efficiency Simulated by TBM
  • 6 Conclusions
  • References
  • Machine-Learning Techniques Applied to Biomass Estimation Using LiDAR Data
  • 1 Introduction
  • 2 Materials and Methods
  • 2.1 Study Area
  • 2.2 Ground Truth Data
  • 2.3 LiDAR Data
  • 2.4 Orthophotos
  • 2.5 Methods
  • 3 Results
  • 4 Discussion
  • 5 Conclusions
  • References
  • Active Learning for Road Lane Landmark Inventory with Random Forest in Highly Uncontrolled LiDAR Intensity Based Image
  • 1 Introduction
  • 1.1 Problem Definition and Motivation
  • 1.2 Active Learning
  • 1.3 Proposed Approach
  • 1.4 Paper Contribution and Content
  • 2 Methods
  • 2.1 Random Forest Classifiers
  • 2.2 Active Learning for Image Segmentation
  • 2.3 Active Learning and Class Imbalance
  • 2.4 Gabor Texture Features
  • 3 Experimental Setup
  • 3.1 Dataset
  • 3.2 Model Parameter Exploration
  • 3.3 Validation
  • 4 Experimental Results
  • 5 Conclusion and Future Works
  • References
  • Author Index

Dateiformat: PDF
Kopierschutz: Wasserzeichen-DRM (Digital Rights Management)

Systemvoraussetzungen:

Computer (Windows; MacOS X; Linux): Verwenden Sie zum Lesen die kostenlose Software Adobe Reader, Adobe Digital Editions oder einen anderen PDF-Viewer Ihrer Wahl (siehe E-Book Hilfe).

Tablet/Smartphone (Android; iOS): Installieren Sie die kostenlose App Adobe Digital Editions oder eine andere Lese-App für E-Books, z.B. PocketBook (siehe E-Book Hilfe).

E-Book-Reader: Bookeen, Kobo, Pocketbook, Sony, Tolino u.v.a.m. (nur bedingt: Kindle)

Das Dateiformat PDF zeigt auf jeder Hardware eine Buchseite stets identisch an. Daher ist eine PDF auch für ein komplexes Layout geeignet, wie es bei Lehr- und Fachbüchern verwendet wird (Bilder, Tabellen, Spalten, Fußnoten). Bei kleinen Displays von E-Readern oder Smartphones sind PDF leider eher nervig, weil zu viel Scrollen notwendig ist. Mit Wasserzeichen-DRM wird hier ein "weicher" Kopierschutz verwendet. Daher ist technisch zwar alles möglich - sogar eine unzulässige Weitergabe. Aber an sichtbaren und unsichtbaren Stellen wird der Käufer des E-Books als Wasserzeichen hinterlegt, sodass im Falle eines Missbrauchs die Spur zurückverfolgt werden kann.

Weitere Informationen finden Sie in unserer E-Book Hilfe.


Als Download verfügbar

234,33 €
inkl. 7% MwSt.
E-Book Einzellizenz
PDF mit Wasserzeichen-DRM
siehe Systemvoraussetzungen
E-Book bestellen