Intelligent Computing and Optimization: Proceedings of the 6th International Conference on Intelligent Computing and Optimization 2023 (ICO2023), Volume 1 (Lecture Notes in Networks and Systems, 729)

✍ Scribed by Pandian Vasant (editor), Mohammad Shamsul Arefin (editor), Vladimir Panchenko (editor), J. Joshua Thomas (editor), Elias Munapo (editor), Gerhard-Wilhelm Weber (editor), Roman Rodriguez-Aguilar (editor)

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 364
• Category: Library

✦ Synopsis

This book of Springer Nature is another proof of Springer’s outstanding greatness on the lively interface of Holistic Computational Optimization, Green IoTs, Smart Modeling, and Deep Learning! It is a masterpiece of what our community of academics and experts can provide when an interconnected approach of joint, mutual, and meta-learning is supported by advanced operational research and experience of the World-Leader Springer Nature!

The 6th edition of International Conference on Intelligent Computing and Optimization took place at G Hua Hin Resort Mall on April 27–28, 2023, with tremendous support from the global research scholars across the planet. Objective is to celebrate “Research Novelty with Compassion and Wisdom” with researchers, scholars, experts, and investigators in Intelligent Computing and Optimization across the globe, to share knowledge, experience, and innovation―a marvelous opportunity for discourse and mutuality by novel research, invention, and creativity. This proceedings book of the 6th ICO’2023 is published by Springer Nature―Quality Label of Enlightenment.

&

✦ Table of Contents

Preface
Contents
About the Editors
Digital Transformation, Image Analysis and Sensor Technology
Digitally-Enabled Dynamic Capabilities for Digital Transformation
1 Introduction
2 Dynamic Capabilities for Digital Transformation
3 Methodology
4 Results and Analysis
5 Discussion and Conclusion
5.1 Implications for Theory
5.2 Implications for Practice
5.3 Limitations and Suggestions for Future Research
Appendix A: Robustness Test
Appendix B
References
Digitization of Feeding Processes in Pond Aquaculture Using a Cyber-Physical System for Analyzing Monitoring Data and Transmitting Information Using LoRaWAN Technology
1 Introduction
2 Data and Methods
3 Results and Discussion
4 Conclusion
References
Energy Efficient Routing Approaches in Wireless Sensor Networks: A Review
1 Introduction
2 Energy Consumption and Protocol Stacks
3 Related Work
3.1 Leach [5]
3.2 Leach-C [6]
3.3 Cluster Fuzzy-Based Algorithm [7]
3.4 Leach-Mac [8]
3.5 Energy-Aware Distributed Unequal Clustering [9]
3.6 Unequal Clustering Size Model [10]
3.7 Energy-Aware Distributed Clustering [11]
3.8 Fuzzy Based Balanced Cost CH Selection [12]
3.9 Distributed CH Scheduling [13]
3.10 K-means Based Clustering Algorithm [14]
3.11 Pareto Optimization Based Approach [15]
3.12 Energy Efficiency Semi Static Routing Algorithm [16]
3.13 Hybrid Energy Efficient Routing [17]
3.14 Improved ABC Algorithm [18]
3.15 Hierarchical Energy Balancing Multipath [19]
3.16 Novel Energy Aware Hierarchical Cluster Based Protocol [20]
3.17 Heuristic Algorithm for Clustering Hierarchy [21]
3.18 Multi-level Route Aware Clustering [22]
3.19 Double Phase Cluster Head Election Scheme [23]
4 Open Research Issues
5 Conclusion
References
Robust Vehicle Speed Estimation Based on Vision Sensor Using YOLOv5 and DeepSORT
1 Introduction
2 Related Works
2.1 Learning-Based
2.2 Three-Based Process
2.3 Speed Estimation
3 Proposed Method
3.1 Data Acquisition
3.2 Detection: YOLOv5
3.3 Tracking: DeepSORT
3.4 Speed Estimation
4 Conclusion
References
Automatic Alignment of Aerospace Images Based on the Search for Characteristic Points
1 Introduction
2 Materials and Methods
3 Conclusion
References
Method for Plant Leaves Square Area Estimation Based on Digital Image Analysis
1 Instruction
2 Methods and Materials
3 Results and Discussion
4 Conclusions
References
Digital Revolution Through Computational Intelligence: Innovative Applications and Trends
1 Introduction
2 The Five Main Principles of CI and Its Applications
2.1 Fuzzy Logic
2.2 Neural Networks
2.3 Evolutionary Computation
2.4 Learning Theory
2.5 Probabilistic Methods
2.6 Issues of Traditional Computing
3 Digital Revolution and Artificial Intelligence
4 Big Data
5 Artificial Intelligence (AI) and Computational Intelligence (CI)
6 Internet of Things (IoT) and Computational Intelligence (CI)
7 Computational Intelligence as a New Paradigm
8 Innovative Applications
9 Conclusion
References
Compressive Sensing and Orthogonal Matching Pursuit-Based Approach for Image Compression and Reconstruction
1 Introduction
2 Literature Review
3 Proposed Approach
4 Results
5 Conclusion
References
Capabilities for Digital Transformation and Sustainability in an Emerging Economy
1 Introduction
2 Capabilities for Digital Transformation and Sustainability
3 Research Methodology
4 Results and Analysis
5 Discussion and Conclusion
5.1 Implications for Theory and Practice
5.2 Limitations and Directions for Future Research
Appendix
References
Non-invasive Glucose Measurement with 940 nm Sensor Using Short Wave NIR Technique
1 Introduction
2 Proposed Methodology and Implementation
3 Mathematical Modelling for Prediction of Blood Glucose Concentration
4 Conclusion
References
Managing the Purchase-Sale Process of Digital Currencies Under Fuzzy Conditions
1 Introduction
2 Literature Review
3 The Purpose of the Study
4 Methods and Models
4.1 Model of Trading Operations with Cryptocurrencies in a Fuzzy Setting
4.2 The Solution of the Problem
5 Computational Experiment
6 Discussion of the Results of a Computational Experiment
7 Conclusions
References
A Comparative Analysis of the Impacts of Traditional and Digital Billing Methods
1 Introduction
2 Literature Review
3 Materials and Methods
3.1 Data Collection Methods
3.2 Participants
3.3 Data Analysis
3.4 Research Ethics
4 Results and Discussion
4.1 Experimental Result and Analysis
4.2 Discussion
4.3 Limitations and Future Works
5 Conclusion
References
Chest X-ray Image Classification Using Convolutional Neural Network to Identify Tuberculosis
1 Introduction
2 Related Work
3 System Architecture and Design
3.1 Dataset Description
3.2 Data Pre-processing
3.3 Model Architecture and Algorithms
4 Experimental Results
4.1 Experimental Setup
4.2 Experimental Result
4.3 Performance Evaluation
5 Conclusion
References
Digital Wireless Mini-transduce of Plant Thermoregulation
1 Introduction
2 Materials and Methods
3 Results and Discussion
4 Conclusion
References
Convolution Neural Network, Deep Learning, and Machine Learning
Effective Fault Prediction Techniques for the Green Cloud Computing Environment Applying Machine Learning to Enhance Network Management
1 Introduction
2 Literature Review
3 System Architecture and Design
3.1 Dataset Description
3.2 Pre-processing of Data Sources
4 Implementation and Experimental Result
4.1 Experimental Set-Up
4.2 Model Assessment
4.3 Performance Analysis
4.4 Result Analysis
5 Conclusion
References
Transforming the Financial Industry Through Machine and Deep Learning Innovations
1 Introduction
2 ML and DL Models
3 Literature Review
4 Application in Finance and the Way Forward
References
MRI-Based Brain Tumor Classification Using Various Deep Learning Convolutional Networks and CNN
1 Introduction
2 Related Work
3 System Architecture and Design
3.1 Description
3.2 Data Preprocessing
3.3 Proposed Model
3.4 Architecture and Design Proposed Model
4 Model Evaluation Result
4.1 Hypothetical Setup
4.2 Hypothetical Result
4.3 Confusion Matrix
4.4 Performance Evaluation
5 Conclusion
References
Deciphering Handwritten Text: A Convolutional Neural Network Framework for Handwritten Character Recognition
1 Introduction
2 Literature Review
3 Methodology
3.1 Dataset Description
4 Implementation
4.1 Device Set-Up
4.2 Implementation
5 Experimental Result
6 Conclusion
References
Applying Machine Learning Techniques to Forecast Demand in a South African Fast-Moving Consumer Goods Company
1 Introduction
2 Literature Review
3 Methodology and Data
3.1 Exploratory Data Analysis
3.2 Modeling
3.3 Accuracy Measures
4 Empirical Results
4.1 Exploratory Data Analysis
4.2 Demand Modeling
4.3 Moving Averages
4.4 SARIMA Model Results
4.5 Forecasting Using ANN Model
4.6 Model Accuracy
5 Conclusions
References
A Review on Machine Learning Algorithms for Cost Estimation in Construction Projects
1 Introduction
1.1 Cost Estimation Modelling Techniques
1.2 Machine Learning for Cost Estimation
1.3 Main Contribution
1.4 Paper Organization
2 Related Work
3 Open Research Challenges
4 Conclusion
References
A Computer Assisted Detection Framework of Kidney Diseases Based on CNN Model
1 Introduction
2 Background
3 Related Work
4 Materials and Methods
4.1 Dataset
4.2 Methodological Approach and Proposed Models
4.3 Pseudo Code
5 Experimental Result
5.1 Result
5.2 Performance Evaluation
6 Conclusion
References
Rice Blast Disease Detection Using CNN Models and DCGAN
1 Introduction
2 Related Work
3 Methodology
3.1 Dataset Preparation
3.2 Data Pre-processing
3.3 Network Architecture
4 Experimental Result and Discussion
5 Conclusion
References
Evaluation of Performance of Different Machine Learning Techniques for Structural Models
1 Introduction
2 The Prediction Methodologies
2.1 Support Vector Regression (SVR)
2.2 K-Nearest Neighbor (k-NN)
2.3 Bagging
3 Numerical Examples
3.1 Structural Models
3.2 Investigation of Prediction Models
4 Results
4.1 Prediction Performance and Error Measurements for Training Models
4.2 Prediction Performance and Error Measurements for Test Models
5 Conclusion
References
Age Estimation from Human Facial Expression Using Deep Neural Network
1 Introduction
2 Related Research
3 Materials and Proposed Methodology
3.1 CNN Architecture
3.2 Attention Module
3.3 Model Design and Tuning
4 Result and Observation
4.1 Dataset and Preprocessing
4.2 Augmentation Techniques
4.3 Performance Evaluation and Hyperparameters Tuning
5 Conclusion and Future Work
References
Recognition and Classification of Crop Images by Convolutional Neural Network of Hybrid Architecture
1 Introduction
2 Materials and Methods
3 Results and Discussion
4 Conclusion
References
A Comparative Study of Deep Learning Algorithms and SARIMA Models for Forecasting Monthly Solar Radiation and UV Index: Case Study for Mauritius
1 Introduction
2 Deep Learning Algorithms
2.1 Training of an ANN
3 Simulation Results and Discussions
3.1 Solar Radiation and UV Index Data
3.2 Result Analysis for Monthly Mean Solar Radiation and UV Index
4 Conclusions
References
A Study on Fault Classification and Location Using Supervised Machine Learning
1 Introduction
2 Classification of Faults
2.1 Shunt Faults (Short Circuit Faults)
3 Machine Learning Techniques
3.1 Supervised Machine Learning (SML)
3.2 Unsupervised Machine Learning (UML)
4 Related Work
5 Methodology
5.1 Test System and Data Base Generation
5.2 Algorithm
5.3 The Flow Chart
5.4 Results and Discussions
6 Conclusion
References
Deep Learning-Based Time Series Forecasting for CO2 Emission
1 Introduction
2 Literature Review
3 The Dataset
4 Methodology
4.1 Data Normalization
4.2 Sliding Window
4.3 Deep Learning Model-1 - Long Term-Short Memory
4.4 Deep Learning Model-2 - Convolutional Neural Network – Long Short-Term Memory
4.5 Deep Learning Model-3 - Dynamic Mode Decomposition (DMD) Using PyDMD
4.6 Analysis of Models Using Performance Evaluation Metrics
5 Results and Discussions
6 Conclusion
References
Manila City House Prices: A Machine Learning Analysis of the Current Market Value for Improvements
1 Introduction
2 Review of Related Literature
3 Methodology
3.1 Data Collection
3.2 Data Preprocessing
3.3 Model Training
3.4 Optimization
3.5 Model Evaluation
4 Results and Discussion
5 Conclusion
References
An Analysis of the Relationship Between Temperature Rise and GDP Using Machine Learning Techniques
1 Introduction
2 Method
3 Results and Discussion
4 Conclusion
References
Machine Learning Techniques for Predicting Remaining Useful Life (RUL) of Machinery for Sustainable Manufacturing Lines
1 Introduction
2 Literature Review
2.1 Machine Learning
2.2 Gradient Boosting Regression
3 Decision of Algorithm and Justification
4 Implementation
4.1 Predictive Model
5 Result and Discussion
References
Machine Learning-Based Predictive Modelling of Spot-Welding Process Parameters
1 Introduction
2 Machine Learning Algorithms
2.1 Linear Regression
2.2 Random Forest Regression
2.3 Adaptive Boosting Regression
2.4 SVM Regression
3 Predictive Model Performance Evaluation Metrics
4 Results and Discussion
4.1 Case Study: Spot Welding
4.2 Effect of Process Parameters
4.3 ML Modelling of Nugget Diameter (ND)
4.4 ML Modelling of Nugget Height (NH)
5 Conclusions
References
Author Index