Special Session on Data Generation and Data Pre-processing in Machine Learning -- A Preprocessing Approach for Class-imbalanced Data using SMOTE and Belief Function Theory -- Multi-Agent Based Manifold Denoising -- A Novel Evaluation Metric for Synthetic Data Generation -- Data Pre-processing and Data Generation in the Student Flow Case Study -- Enhanced Credit Prediction using Artificial Data -- Data Generation Using Gene Expression Generator -- Stabilisation of Dataset Matrix Form for Classification Dataset Generation and Algorithm Selection -- Special Session on Optimization and Machine Learning for Industry 4.0 -- Distributed Coordination of Heterogeneous Robotic Swarms using Stochastic Diffusion Search -- An Intelligent Procedure for the Methodology of Energy Consumption in Industrial Environments -- Unified Performance Measure for Binary Classification Problems -- Data Augmentation for Industrial Prognosis using Generative Adversarial Networks -- A Comparison of Evolutionary Multi-Objective Optimization Algorithms Applied to Antenna Design -- Special Session on Practical Applications of Deep Learning -- Cloud Type Identification Using Data Fusion and Ensemble Learning -- Deep Learning in Aeronautics: Air Traffic Trajectory Classification Based on Weather Reports -- Analysis of Hand-Crafted and Automatic-Learned Features for Glaucoma Detection Through Raw Circumpapillary OCT Images -- Video Semantics Quality Assessment using Deep Learning -- A Deep Learning Approach for Intelligent Cockpits: Learning Drivers Routines -- Predicting Recurring Telecommunications Customer Support Problems using Deep Learning -- Pre- and Post-processing on Generative Adversarial Networks for Old Photos Restoration: A Case Study -- On Analysing Similarity Knowledge Transfer by Ensembles -- Special Session on New trends and challenges on Social Networks Analysis -- Social Network Recommender System, a Neural Network Approach -- Exploring Multi-objective Cellular Genetic Algorithmsin Community Detection Problems -- Special Session on Machine Learning in Automatic Control -- Under-Actuation Modelling in Robotic Hands via Neural Networks for Sign Language Representation with End-User Validation -- Exploratory Data Analysis of Wind and Waves for Floating Wind Turbines in Santa María, California -- Wind Turbine Pitch Control First Approach based on Reinforcement Learning -- Intelligent Fuzzy Optimized Control for Energy Extraction in Large Wind Turbines -- Special Session on Emerging Trends in Machine Learning -- Autoencoder Latent Space Influence on IoT MQTT Attack Classification -- A Recommendation System of Nutrition and Physical Activity for Patients with Type 2 Diabetes Mellitus -- A Comparative Analysis between Crisp and Fuzzy Data Clustering Approaches for Traditional and Bioinspired Algorithms -- Bridging the Gap of Neuroscience, Philosophy, and Evolutionary Biology to Propose an Approach to Machine Learning of Human-like Ethics -- Anticipating Maintenance in Telecom Installation Processes -- Meta-Hyperband: Hyperparameter Optimization with Meta-Learning and Coarse-to-Fine -- Stateful Optimization in Federated Learning of Neural Networks -- Talking in Italian about AI with a Chatbot: a Prototype of a Question-Answering Agent -- Review of Trends in Automatic Human Activity Recognition in Vehicle based in Synthetic Data -- Special Session on Machine Learning, Law and Legal Industry -- Intellectual Properties of Artificial Creativity: Dismantling Originality in European's Legal Framework -- Network Analysis for Fraud Detection in Portuguese Public Procurement -- Biased Language Detection in Court Decisions -- Special Session on Machine Learning Algorithms for Hard Problems -- A One-by-One Method for Community Detection in Attributed Networks -- A Hybrid Approach to the Analysis of a Collection of Research Papers -- Sequential Self-tuning Clustering for Automatic Delimitation of Coastal Upwelling on SST Images -- Special Session on Automated learning for industrial applications -- Time Series Clustering for Knowledge Discovery on Metal Additive Manufacturing -- Quaternion Neural Networks: State-of-the-art and Research Challenges -- A Solar Thermal System Temperature Prediction of a Smart Building for Data Recovery and Security Purposes -- A Fault Detection System for Power Cells During Capacity Confirmation Test Through a Global One-Class Classifier -- A Deep Metric Neural Network with Disentangled Representation for Detecting Smartphone Glass Defects -- Improving Performance of Recommendation System Architecture -- Automated Learning of In-vehicle Noise Representation with Triplet-loss Embedded Convolutional Beamforming Network -- Sequence Mining for Automatic Generation of Software Tests from GUI Event Traces -- Deep Learning Based Algorithms for Welding Edge Points Detection -- Detecting Performance Anomalies in the Multi-Component Software a Collaborative Robot -- Prediction of Small-Wind Turbine Performance from TimeSeries Modelling using Intelligent Techniques -- Review of Trends in Automatic Human Activity Recognition using Synthetic Audio-Visual Data -- Atmospheric Tomography using Convolutional Neural Networks -- Workshop on Machine Learning in Smart Mobility -- Driver Monitoring System Based on CNN Models: An Approach for Attention Level Detection -- Road Patterns Identification and Risk Analysis based on Machine Learning framework: Powered Two-Wheelers Case -- Towards Predicting Pedestrian Paths: Identifying Surroundings from Monocular Video -- A Semi-automatic Object Identification Technique Combining Computer Vision and Deep Learning for the Crosswalk Detection Problem -- Using Deep Learning to Construct a Real-Time Road Safety Model; Modelling the Personal Attributes for Cyclist.

This two-volume set of LNCS 12489 and 12490 constitutes the thoroughly refereed conference proceedings of the 21th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2020, held in Guimaraes, Portugal, in November 2020.* The 93 papers presented were carefully reviewed and selected from 134 submissions. These papers provided a timely sample of the latest advances in data engineering and machine learning, from methodologies, frameworks, and algorithms to applications. The core themes of IDEAL 2020 include big data challenges, machine learning, data mining, information retrieval and management, bio-/neuro-informatics, bio-inspiredmodels, agents and hybrid intelligent systems, real-world applications of intelligent techniques and AI. * The conference was held virtually due to the COVID-19 pandemic.