Applications of Computational Intelligence: Third IEEE Colombian Conference, ColCACI 2020, Cali, Colombia, August 7-8, 2020, Revised Selected Papers ... in Computer and Information Science, 1346)

This book constitutes revised and extended selected papers of the Third IEEE Colombian Conference, ColCACI 2020, held in Cali, Colombia, August 2020. Due to the COVID-19 pandemic the conference was held online. The12 full papers presented were carefully reviewed and selected from 65 submissions. The papers are organized in topical sections on ​earth sciences applications; biomedical and power applications; alternative proposals and its applications. Preface Organizers Contents Earth Sciences Applications Understanding the Cotopaxi Volcano Activity with Clustering-Based Approaches 1 Introduction 2 Materials and Methods 2.1 Volcano Seismic Event Dataset 2.2 Clustering-Based Classifiers 2.3 Experimental Setup 3 Results and Discussion 3.1 Performance of Explored Models 3.2 State of Art-Based Comparison 4 Conclusions and Future Work References Seismic Event Classification Using Spectrograms and Deep Neural Nets 1 Introduction 2 Materials and Methods 2.1 Spectrogram Images Dataset 2.2 Deep-Learning Networks 2.3 Proposed Method 2.4 Experimental Setup 3 Results and Discussion 3.1 Performance Evaluation of the Proposed Method 3.2 State of the Art Based Comparison 4 Conclusions and Future Work References An Android App to Classify Culicoides Pusillus and Obsoletus Species 1 Introduction 2 Materials and Methods 2.1 Automatic Culicoides Species Classification 2.2 Development Environment 2.3 Proposed MosCla App 2.4 Experimental Setup 3 Results and Discussion 3.1 Classification Performance 3.2 MosCla App Feasibility 4 Conclusions and Future Work References Hammerhead Shark Species Monitoring with Deep Learning 1 Introduction 2 Materials and Methods 2.1 YOLOv3 Framework 2.2 Mask-RCNN Framework 2.3 Proposed Method 2.4 Shark Database 2.5 Experimental Setup 3 Results and Discussion 3.1 Performance of Proposed Method 3.2 Deep-Learning Models Comparison 4 Conclusions and Future Work References Towards Automatic Comparison of Online Campaign Versus Electoral Manifestos 1 Introduction 2 Materials and Methods 2.1 Architecture 2.2 Case Study 3 Results and Discussion 4 Conclusions and Future Work References Biomedical and Power Applications Time and Frequency Domain Features Extraction Comparison for Motor Imagery Detection 1 Introduction 2 Methodology 2.1 Database 2.2 Feature Extraction 2.3 Machine Learning Techniques 3 Results 4 Discussion 5 Conclusions References Automatic Classification of Diagnosis-Related Groups Using ANN and XGBoost Models 1 Introduction 2 Related Works 2.1 Diagnosis-Related Groups - DRG 2.2 Traditional Method of DRG Classification 2.3 Classification of Patients in DRG Using ML 3 Methods 4 Dataset 4.1 Cohort of Study 5 Experiments and Results 5.1 Experimental Setup 5.2 Results 6 Conclusions References Power Management Strategies for Hybrid Vehicles: A Comparative Study 1 Introduction 2 Vehicle Longitudinal Dynamic 2.1 Engine Model 2.2 Electric Motor Model 2.3 Battery Model 3 Power Management Strategy 3.1 PMS Rule-Based 3.2 PMS Based Fuzzy 4 Simulation Results 5 Conclusion References Alternative Proposals and Its Applications FCM Algorithm: Analysis of the Membership Function Influence and Its Consequences for Fuzzy Clustering 1 Introduction 2 Clustering and Fuzzy Clustering 3 Fuzzy C-Means Method 3.1 Fuzzy C-Means Algorithm 3.2 Analysis of FCM Algorithm 4 Proposal 5 Experiments and Results 5.1 Dataset and Parameter Setting 5.2 Experimental Results and Discussions 6 Conclusions References Echo State Network Performance Analysis Using Non-random Topologies 1 Introduction 2 Literature Review 3 Echo State Network Model 4 Experiments and Results 4.1 Problem Statement 4.2 Dataset Preparation 4.3 Implementation Setup 4.4 Methodology 5 Results 6 Conclusion References Deep Learning-Based Object Classification for Spectral Images 1 Introduction 2 Method 2.1 Data Acquisition 2.2 Pre-processing of the Data 2.3 CNN Architecture 3 Results 3.1 Simulation with 29 Spectral Bands 3.2 Dimensinality Reduction 3.3 Simulation Applying Different Levels of Gaussian Noise 4 Conclusions References Transfer Learning for Spectral Image Reconstruction from RGB Images 1 Introduction 2 RGB Acquisition 3 Transfer Learning Strategy 4 Simulations and Results 4.1 Datasets 4.2 Models 4.3 Metrics and Configurations 4.4 Results 5 Conclusions References Author Index