Intro
Organization
Preface
Contents
Editors and Contributors
Artificial Intelligence for Detection and Prediction
ColorNet: A Deep Learning-Based Approach to Colorize the Historical Documentaries of Bangladesh
1 Introduction
2 Literature Review
2.1 User-Guided Colorization with Image Processing
2.2 Traditional Machine Learning-Based Colorization
2.3 Deep Learning-Based Colorization
3 Proposed Approach
3.1 Model Architecture
3.2 Strength of Our Model Architecture
4 Implementation
4.1 Dataset Creation
4.2 Dataset
4.3 Parameter Settings

4.4 Environment Settings
5 Experiment Results and Analysis
5.1 Performance Metrics
5.2 Training Results
5.3 Evaluation
6 Conclusion and Future Work
References
A Methodology for Recommending In-Vehicle Coupons Incorporating Machine Learning Algorithms for Efficient Financial Schemes
1 Introduction
2 Literature Review
3 Work Flow Layout of the Proposed System
4 Algorithms
4.1 Artificial Neural Networks
4.2 CNN LSTM
4.3 Random Forest
4.4 Extreme Gradient Boosting
4.5 Stacking
5 Dataset and Data Pre-processing
5.1 Dataset Description

5.2 Dataset Pre-processing
6 Comparative Analysis and Result Discussions
7 Proposed Coupon Recommendation Framework
8 Conclusion and Future Works
References
A Deep Convolutional Neural Network Based Approach to Classify and Detect Crack in Concrete Surface Using Xception
1 Introduction
2 Methodology
2.1 Data Acquisition and Cleaning
2.2 Data Distribution
2.3 Xception Architecture
3 Optimization and Loss Estimation
4 Result and Analysis
4.1 Training and Validation of Xception Model
4.2 Performance Evaluation
5 Conclusion
References

Machine-Learning Based Physical Exercise Identification with Heuristic Optimized Features Prioritization
1 Introduction
2 Methodology
2.1 Dataset Description
2.2 Feature Explanation
2.3 Classifier Model
2.4 Feature Selection
3 Result and Discussion
4 Conclusions
References
Modelling Lips State Detection Using CNN for Non-verbal Communications
1 Introduction
2 New Lips State Detection Models
2.1 Landmark Detection
2.2 Distance Calculation
2.3 Dataset Collection
2.4 Lips State Detection
2.5 Training Performance Evaluation

2.6 Time Slots and Commands
3 Results
4 Conclusion
References
Depression-Level Prediction During COVID-19 Pandemic Among the People of Bangladesh Using Ensemble Technique: MIRF Stacking and MIRF Voting
1 Introduction
2 Literature Review
3 Methodology
3.1 Dataset Description
3.2 Data Preprocessing
3.3 Features Selection
3.4 Model Implementation
3.5 Calculate Performance Metrics
4 Results and Discussions
5 Conclusion
References
HandFruitNet: A Deep Learning Based Model for Fruits Classification from Hand
1 Introduction
2 Related Works