This book gives a detailed information of various real-life applications from various fields using nature inspired optimization techniques. These techniques are proven to be efficient and robust in many difficult problems in literature. The authors provide detailed information about real-life problems and how various nature inspired optimizations are applied to solve these problems. The authors discuss techniques such as Biogeography Based Optimization, Glow Swarm Optimization, Elephant herd Optimization Algorithm, Cuckoo Search Algorithm, Ant Colony Optimization, and Grey Wolf Optimization etc. These algorithms are applied to a wide range of problems from the field of engineering, finance, medicinal etc. As an important part of the Women in Science and Engineering book series, the work highlights the contribution of women leaders in nature inspired optimization, inspiring women and men, girls and boys to enter and apply themselves to the field.
Author(s): Dipti Singh, Vanita Garg, Kusum Deep
Series: Women in Engineering and Science
Publisher: Springer
Year: 2023
Language: English
Pages: 210
City: Cham
Preface
Contents
Contributors
Chapter 1: An Overview of Swarm Intelligence-Based Algorithms
1 Introduction
2 Characteristics of SI-Based Algorithms
3 Particle Swarm Optimization Algorithm
Pseudocode of PSO
Minimizing Rosenbrock Function Using PSO
4 Artificial Bee Colony Algorithm
Minimizing Schwefel´s Function Using Artificial Bee Colony Algorithm
5 Comparative Analysis Using Fixed Iteration Test
6 Conclusion
References
Chapter 2: Particle Swarm Optimization and Its Applications in the Manufacturing Industry
1 Introduction to Optimization
Local and Global Optimal Solution
Nature-Inspired Algorithms
2 Particle Swarm Optimization
How PSO Works
Understanding PSO Parameters
Binary Particle Swarm Optimization
Research Developments in PSO
3 Application of PSO Manufacturing Industry
4 Conclusion
References
Chapter 3: Role of Machine Learning in Bioprocess Engineering: Current Perspectives and Future Directions
1 Introduction
2 Approaches of Machine Learning in Bioprocess Engineering
3 Why Machine Learning Strategies Are Needed in Bioprocess Engineering
4 Applications of Machine Learning in Bioprocess Engineering (Case Studies)
Approaches of Machine Learning in Biorefinery: A Case Study
Approaches of Machine Learning in Monoclonal Antibody Production: A Case Study
Approaches of Machine Learning for Antibiotic Production: A Case Study
Machine Learning in Protein Engineering: A Case Study
5 Current Challenges and Future Prospects
6 Conclusion
Glossary
References
Chapter 4: Advanced Selection Operation for Differential Evolution Algorithm
1 Introduction
2 Basic Differential Evolution (DE)
3 Proposed Modification
Advance Selection Strategy
Proposed DERLaS and MRLDEaS
4 Experimental Settings
Test Functions
Performance Criteria
Parameter Setting
5 Result and Discussion
Result on Benchmark Problems
Result on Real-Life Application
Convergence Graphs
6 Conclusions
References
Chapter 5: Profit Optimization of Two-Unit Briquetting System Using Grey Wolf Optimization Algorithm
1 Introduction
2 Introduction
3 State Transition Diagram
4 Transition Probabilities and Mean Sojourn Periods
5 System Effectiveness Measures
Mean Time to System Failure
System Availability
Busy Period
Expected Visits by Repairmen
Profit
6 Grey Wolf Optimizer
7 Graphical Results and Discussion
8 Conclusions
References
Chapter 6: Solving Portfolio Optimization Using Sine-Cosine Algorithm Embedded Mutation Operations
1 Introduction
2 Markowitz Model Based on Historical Stock Price Data
Markowitz Mean-Variance Model
Rate of Return
Expected Return
Variance
Portfolio Formulation
Statement of the Problem
3 Problem Description
Problem 1
Problem 2
4 Sine-Cosine Algorithm
Mutation
Power Mutation
Polynomial Mutation
Random Mutation
Gaussian Mutation
Cauchy Mutation
5 Numerical Analysis of Results Obtained by the Proposed Version of SCA
Problem 1
Problem 2
6 Result Analysis
7 Conclusion
References
Chapter 7: Detecting Group Shilling Profiles in Recommender Systems: A Hybrid Clustering and Grey Wolf Optimizer Technique
1 Introduction
2 Related Work and Motivation
3 Shilling Attacks
4 Grey Wolf Optimizer (GWO)
Motivation
Description and Algorithm
5 GWODS
Motivation
Proposed Approach
6 Experiments and Results
Dataset and Experimental Setup
Parameter Setting
Evaluation Metrics
Experiments and Results
Comparison of Binary Operators
Result Analysis
Comparison of GWODS with State-of-the-Art Approaches
7 Conclusion and Future Work
References
Chapter 8: Single Image Reflection Removal Using Deep Learning
1 Introduction
2 Literature Survey
Multi-image Methods
Single Input Methods
Traditional Approaches
Learning-Based Approaches
3 Proposed Method
Training Dataset
Model Description (Table 8.1)
Loss Function
4 Experiment and Results
Training Details
Experimental Set-Up
Performance Evaluation Metrics
Testing Dataset
5 Conclusion and Future Work
References
Chapter 9: Social Media Analysis: A Tool for Popularity Prediction Using Machine Learning Classifiers
1 Introduction
2 Related Works
3 Proposed Methodology
Problem Identification
Data Gathering
Data Filtering
Fetching Features
Classification Using ML Classifier
Comparative Study of Different Models
Implementing Tools
Python
Jupyter Notebook
Statistical NLP, Machine Learning, and Deep Learning
Application of NLP
4 Result and Discussion
Real-Time Applications
Experimental Validation and Accuracy
5 Conclusion and Future Scope
6 Challenges and Limitations
References
Appendix
Benchmark Problems
Real-Life Applications
RF1: Parameter Estimation for Frequency-Modulated (FM) Sound Waves
RF2: Optimal Thermohydraulic Performance of an Artificially Roughened Air Heater
RF3: Spread-Spectrum Radar Polyphase Code Design
References
Index
