Applied Intelligence for Industry 4.0

We are all aware that artificial intelligence (AI) has brought a change in our lives, driven by a new form of interaction between man and machine. We are in the era of the fourth Industrial Revolution (IR) where AI plays vital roles in human development by enabling extraordinary technological advances making fundamental changes to the way we live, work and relate to one another. It is an opportunity to help everyone, including leaders, policymakers and people from all income groups and nations, to harness converging technologies in order to create an inclusive, human-centered future. We need to prepare our graduates as well as researchers to conduct their research with 4.0 IR-related technologies. We need to develop policies and implement those policies to focus onthe components of 4.0 IR for sustainable developments.Applied Intelligence for Industry 4.0 will cover cutting edge topics in the fields of AI and industry 4.0.The textwill appeal to beginners and advanced researchers in computer science, information sciences, engineering and robotics. Features Discusses advance data mining, feature extraction and classification algorithms for disease detection, cyber security detection and prevention, soil quality assessment and other industrial applications Includes the parameter optimization and explanation of intelligent approaches for business applications Presents context-aware smart insights and energy efficient and smart computing for the next-generation ofsmart industry

1. Multi-labelled Bengali Public Comments Sentiment Analysis with Bidirectional Recurrent Neural Networks (Bi-RNN) Promila Ghosh, M. Raihan, Nishat Tasnim Tonni, Himadri Sikder Badhon, Sayed Asaduzzaman, and Hasin Rehana INTRODUCTION RELATED WORK METHODOLOGY Data Preprocessing Bidirectional RNN Implementation: OUTCOMES CONCLUSION Bibliography 2. Machine Learning and Blockchain Based Privacy-Aware: Cognitive Radio Internet of ThingsMd Shamim Hossain, Kazi Mowdud Ahmed, Md Khairul Islam, Md MahbuburRahman, and Md Sipon Miah INTRODUCTION SYSTEM MODEL Blockchain based CR-IoT Network The Protocol Structure SENSING-CLUSTERING-BIDING-MINING POLICY Sensing-Mining Energy Efficiency SIMULATION RESULTS AND DISCUSSIONCONCLUSION Bibliography 3. Machine Learning Based Models for Predicting Autism Spectrum Disorders S. M. Mahedy Hasan, Md. Fazle Rabbi, Arifa Islam Champa, Md. Rifat Hossain, and Md. Asif Zaman INTRODUCTION MATERIALS AND METHODS Dataset Description Methods Classification Techniques Evaluation Measures and Experimental Setup EXPERIMENTAL RESULTS ANALYSIS Analysis of Toddlers Dataset Analysis of Adults Datasets Discussion CONCLUSION Bibliography 4. Implementing Machine Learning Through the Neural Network for the Time Delay SIR Epidemic Model for the Future ForecastSayed Allamah Iqbal, Md. Golam Hafez, and A.N.M. Rezaul Karim INTRODUCTION TIME DELAY SIR EPEDIMIC MODEL Neural Networks for time-delay SIR model DISCUSSION SUMMARY Bibliography 5. Prediction of PCOS Using Machine Learning and Deep Learning Algorithms Syed Mohd. Farhan, Maimuna Manita Hoque, and Mohammed Nazim Uddin INTRODUCTION RELATED WORK METHODOLOGY Dataset Collection Data Preprocessing Data Cleaning Feature Engineering Feature Selection Feature Scaling Dataset Split Handling Imbalanced Data Modelling Process Hyperparameter Optimization Logistic Regression Classifier Random Forest Classifier AdaBoost Classifier Nal?ve Bayes Classifier Artificial Neural Network Voting Classifier Performance Evaluation Selecting Best Model Validating Final Model Deploying Final Model into PCOS Predictor EXPERIMENTAL RESULTS Statistical Results Model Visualization CONCLUSION AND FUTURE WORKS Bibliography 6. Malware Detection: Performance Evaluation of ML Algorithms Based on Feature Selection and ANOVA Nazma Akther, Md. Neamul Haque, and Khaleque Md. Aashiq Kamal INTRODUCTION RELATED WORK PROBLEM STATEMENT RESEARCH METHODOLOGY Data set Weka Tool Feature Selection Technique RESULT ANALYSIS STATISTICAL ANALYSIS Statistical Analysis of Feature Selection Technique Statistical Analysis of Machine Learning Algorithm CONCLUSION Bibliography 7. An Efficient Approach to Assess the Soil Quality of Sundarbans Utilizing Hierarchical Clustering Diti Roy, Md. Ashiq Mahmood, and Tamal Joyti Roy INTRODUCTION RELATED WORK PROPOSED METHODOLOGY RESULTS AND DISCUSSION CONCLUSION Bibliography 8. A Machine Learning Approach to Clinically Diagnose Human Pyrexia Cases Dipon Talukder and Md. Mokammel Haque INTRODUCTION RELATED HEALTHCARE RESEARCH DATASET DESCRIPTION Dataset Collection Data Analysis and Deductions FEATURE SELECTION Primary Feature Selection Final Feature Selection MODEL EVALUATION RESULT ANALYSIS CONCLUSION AND FUTURE WORKS Bibliography 9. Prediction of the Dengue Incidence in Bangladesh Using Machine Learning Md. Al Mamun, Abu Zahid Bin Aziz, Md. Palash Uddin, and Md Rahat Hossain INTRODUCTION LITERATURE REVIEW METHODOLOGY Dataset Collection Data Preprocessing Machine Learning Algorithms Method Evaluation Metrics RESULT AND DISCUSSION \Parameter Tuning Result Analysis ACKNOWLEDGEMENT CONCLUSION Bibliography 10. Detecting DNS over HTTPS Traffic Using Ensemble Feature Based Machine Learning Sajal Saha, Moinul Islam Sayed, and Rejwana Islam INTRODUCTION LITERATURE REVIEW METHODOLOGY Dataset Data Preprocessing Feature Engineering Machine Learning Models Proposed DOH Detection Model Ensemble Feature Selection Software and Hardware Preliminaries Evaluation Metrics RESULTS AND DISCUSSION CONCLUSION Bibliography 11. Development of Risk-Free COVID-19 Screening Algorithm from Routine Blood Test Using Ensemble Machine LearningMd. Mohsin Sarker Raihan, Md. Mohi Uddin Khan, Laboni Akte, and Abdullah Bin Shams INTRODUCTION RELATED WORKS METHODOLOGY Dataset Collection Data Pre-processing Missing Data Handling SMOTE Analysis Data Splitting Feature Scaling Stacked Ensemble Machine Learning Machine Learning Algorithms K-Nearest Neighbors (KNN) Support Vector Machine (SVM) Random Forest (RF) XG-Boost (XGB) AdaBoost (ADB) Compute Statistical Metrics OUTCOMES CONCLUSION SUPPLEMENTARY WEBLINK Bibliography 12. A Transfer Learning Approach to Recognize Pedestrian AttributesSaadman Sakib, Anik Sen, and Kaushik Deb INTRODUCTION RELATED WORKS METHODOLOGY Overview Mask RCNN Object Detector Preprocessing Spatial Feature Extraction Transfer Learning Approach Classifier OUTCOMES Dataset Description Experiments on the Proposed CNN Architecture Results and Discussion CONCLUSION Bibliography 13. TF-IDF Feature-Based Spam Filtering of Mobile SMS Using Machine Learning Approach Syed Md. Minhaz Hossain, Khaleque Md. Aashiq Kamal, Anik Sen, and Iqbal H. Sarker INTRODUCTION RELATED WORK MATERIALS AND METHODS Preprocessing Redundant character removal Removal of stop words Tokenization Lemmatization Feature Extraction Classifiers Support Vector Machine Multinomial Nal?ve Bayes: RESULT AND OBSERVATIONS Dataset Classification using SVM and Multinomial Nal?ve Bayes Performance Measure Performance Evaluation for Different Feature ExtractionMethods using Various Classifiers Performance Representation for the best classifier Using AUC and Confusion Matrix Computational Time Analysis for Classifying spam Comparison among the benchmark spam detection method Critical Evaluation CONCLUSION Bibliography 14. Content-Based Spam Email Detection Using N-gram Machine Learning Approach Nusrat Jahan Euna, Syed Md. Minhaz Hossain, Md. Musfique Anwar, and Iqbal H. Sarker INTRODUCTION RELATED WORKS METHODOLOGY Preprocessing Special character removal: Stop words removal: Tokenization: Lemmatization: Feature extraction N-gram: Word2vec: Training Support Vector Machine: Logistic Regression: Decision Tree: Multinomial nal?ve bayes: RESULT AND OBSERVATIONS CONCLUSION Bibliography 15. AI Poet: A Deep Learning Based Approach to Generate Artificial Poetry in Bangla Hasan Murad and Rashik Rahman INTRODUCTION BACKGROUND AND LITERATURE REVIEW Related Terminologies Existing Works Limitations of the Existing Works PROPOSED APPROACH Dataset Creation Data Pre-processing Model Architecture Design IMPLEMENTATION Development Tools Pre-processing Pipeline Model Architecture Implementation RESULTS Training Results Parameter Setting Environment Setting Evaluation Limitations of Our Work CONCLUSION Bibliography 16. Document Level Comparative Sentiment Analysis on Bangla News Using Long-Short Term Memory and Machine Learning Approaches Nuren Nafisa, Sabrina Jahan Maisha, and Abdul Kadar Muhammad Masum INTRODUCTION LITERATURE REVIEW SA in Bangla Language TASK DEFINITION ccxlixIdentifying Sentiment from Bangla news documents Positive News (PN): Negative News (NN): Corpora Development Data Collection Data Pre-processing Data Annotation METHODOLOGY Feature Extraction Supervised ML algorithms Deep learning approach LSTM EXPERIMENTS AND RESULT ANALYSIS Performance Measurement Tools Experimental Output Performance Statistics Error Analysis CONCLUSION Bibliography 17. Employee Turnover Prediction Using Machine Learning ApproachMd. Ali Akbar, kamruzzaman Chowdhury, and Mohammed Nazim Uddin INTRODUCTION RELATED WORK METHODOLOGY System Architecture. Dataset Collection Data Preprocessing Data Cleaning One Hot Encoding Feature Selection Dataset Split Class Imbalance Performance Matrix Selected Classification Methods Base Rate Model Logistic Regression Classifier Decision Tree Classifier Random Forest Classifier AdaBoost Classifier EXPERIMENTAL EVALUATION Exploratory Data Analysis Result Analysis ROC-AUC Graph F

Nazmul Siddique received the Dipl.-Ing. degree in Cybernetics and Automation from Dresden University of Technology, Dresden, Germany, MSc in Computer Science from Bangladesh University of Engineering and Technology, Dhaka, Bangladesh and the Ph.D in Intelligent Control from the University of Sheffield, England, U.K. He has been a Lecturer with the School of Computing, Engineering and Intelligent Systems, University of Ulster Magee Campus, Londonderry, U.K since 2001. He was previously with the Computer Science and Engineering Discipline, Khulna University, Khulna, Bangladesh. He has been a guest editor of seven special issues of several reputed journals. He has served as committee member and chair of a number of national and international conferences. He is a senior member of IEEE. He is on the Editorial Board of a number of International Journals. Dr. Siddique has published over 170 journal, refereed conference papers, book chapters, and five books (John Wiley, Springer, Taylor & Francis). His research interests are in the fields of intelligent systems, computational intelligence, stochastic systems, and Markov modeling.