Data Science and Emerging Technologies

The book presents selected papers from International Conference on Data Science and Emerging Technologies (DaSET 2022), held online at UNITAR International University, Malaysia, during December 20-21, 2022. This book aims to present current research and applications of data science and emerging technologies. The deployment of data science and emerging technology contributes to the achievement of the Sustainable Development Goals for social inclusion, environmental sustainability, and economic prosperity. Data science and emerging technologies such as artificial intelligence and blockchain are useful for various domains such as marketing, health care, finance, banking, environmental, and agriculture.  An important grand challenge in data science is to determine how developments in computational and social-behavioral sciences can be combined to improve well-being, emergency response, sustainability, and civic engagement in a well-informed, data-driven society.  The topics ofthis book include, but not limited to: artificial intelligence, big data technology, machine and deep learning, data mining, optimization algorithms, blockchain, Internet of Things (IoT), cloud computing, computer vision, cybersecurity, augmented and virtual reality, cryptography, and statistical learning.

Part I: Artificial Intelligence.- Extractive Text Summarization Using Syntactic Sub- Graph Models.- Analysis of Big Five Personality Factors to determine the Appropriate Type of Career using the C4.5 Algorithm.- Predicting Disaster Type from Social Media Imagery via Deep Neural Networks Directed by Visual Attention.- Dissemination Management for Official Statistics Using Artificial Intelligence-Based Media Monitoring.- Part II: Computational Vision.- A Naive but Effective Post-Processing Approach for Dark Channel Prior (DCP).- COVID-19 Face Mask Classification Using Deep Learning.- Gender Classification Using Transfer Learning and Fine-Tuning.- Multi-Language Recognition Translator by Using the Convolutional Neural Network (CNN) Algorithm and Optical Character Recognition (OCR).- Autonomous Driving Through Road Segmentation Based on Computer Vision Techniques.- Part III: Cybersecurity.- Phishing Attack Types and Mitigation: A Survey.- A Review of Privacy Protection Methods for Smart Homes Against Wireless Snooping Attack.- Development of Graph-Based Knowledge on Ransom-Ware Attacks Using Twitter Data.- Part IV: Big Data Analytics.- BigMDHealth: Supporting Multidimensional Big Data Management and Analytics over Big Healthcare Data via Effective and Efficient Multidimensional Aggregate Queries over Key-Value Stores (Prof Alredo's paper).- Design and Implementation of Data Warehouse Solution at Kumpulan Wang Persaraan (KWAP).- Consumer Behavior Prediction During Covid-19 Pandemic Conditions Using Sentiment Analytics.- Big Data Application on Prediction of HDD Manufacturing Process Performance.- Visualising Economic Situation Through Malaysia Economic Recovery Dashboard (MERD).- Part V: Machine/Deep Learning.- Lung Nodules Classification Using Convolutional Neural Network with Transfer Learning.- Plant Growth Phase Classification Using Deep Neural Network.- The Implementation of Genetic Algorithm-Ensemble Learning on QSAR Study of Diacylglycerol Acyltransferase-1(DGAT1)Inhibitors as Anti-Diabetes.- Classification of Exercise Game Data for Rehabilitation Using Machine Learning Algorithms.- SDDLA: A New Architecture for Secured Decentralized Distributed Learning.- Gated Memory Unit: A Novel Recurrent Neural Network Architecture for Sequential Analysis.- Multi-Class Classification for Breast Cancer with High Dimensional Microarray Data Using Machine Learning Classifier.- Predicting Risks of Late Delivery to Online Shopping Customers Using Machine Learning Techniques.- Quora Insincere Questions Classification Using Attention Based Model.- Suicide Ideation Detection: A Comparative Study of Sequential and Transformer Hybrid Algorithms.- Well Log Data Preparation and Effective Utilization of Drilling Parameters Using Data Science Based Approaches.- Deep Learning-Based Approach for Classifying the Severity of Metal Corrosion Using SEM Images.- Insurance Risk Prediction Using Machine Learning.- Loan Default Forecasting Using StackNet.- Part VI: Statistical Learning.- Neural Network Autoregressive Model for Forecasting Malaysia Under-5 Mortality.- Robustness of Support Vector Regression and Random Forest Models: A Simulation Study.- The Impact of Restrictions Community Activities on COVID-19 Transmission: A Case Study in Sumatra Island, Indonesia.- Predicting Internet Usage for Digital Finance Services: Multitarget Classification Using Vector Generalized Additive Model with SMOTE-NC.- Part VII: Text Mining and Classification.- Identifying Topic Modeling Technique in Evaluating Textual Datasets.- Y-X-Y Encoding for Identifying Types of Sentence Similarity.- Evaluation of Extractive and Abstract Methods in Text Summarization