Applications of Computational Intelligence: 5th IEEE Colombian Conference, ColCACI 2022, Cali, Colombia, July 27-29, 2022, Revised Selected Papers

This book presents the refereed proceedings of the 5th IEEE Colombian Conference on Applications of Computational Intelligence,ColCACI 2022, which includes 7 extended papers on various topics in computational intelligence. The papers were reviewed and selected from 38 submissions, covering topics such as segmentation and classification systems for seed detection, deep learning for medical image analysis, and optimization algorithms for energy management.

Format: Paperback / softback
Length: 129 pages
Publication date: 31 March 2023
Publisher: Springer International Publishing AG

The 5th IEEE Colombian Conference on Applications of Computational Intelligence,ColCACI 2022, was held in Cali, Colombia, from July 27 to 29, 2022. This book serves as the official publication of the conference, featuring 7 extended papers that underwent rigorous review and selection from a total of 38 submissions. The papers were organized into topical sections, covering the following areas:

Design of a Segmentation and Classification System for Seed Detection Based on Pixel Intensity Thresholds and Convolutional Neural Networks:
In this paper, the authors propose a novel approach for seed detection in agricultural images using pixel intensity thresholds and convolutional neural networks. The system aims to accurately classify seeds from background noise and other plant components, which is crucial for precision agriculture and crop monitoring. The authors discuss the design and implementation of the segmentation and classification model, as well as the evaluation of its performance using a dataset of agricultural images.

Deep Learning-Based Image Segmentation for Medical Image Analysis:
This paper explores the use of deep learning techniques for image segmentation in medical imaging applications. The authors propose a deep convolutional neural network (CNN) architecture to segment brain images, which is a challenging task due to the complex structure and heterogeneity of the data. The proposed model demonstrates promising results in terms of accuracy and efficiency, making it a valuable tool for medical image analysis.

Multi-Agent Reinforcement Learning for Optimal Power Flow in Power Systems:
This paper investigates the use of multi-agent reinforcement learning for optimal power flow in power systems. The authors propose a novel approach that involves multiple agents cooperating to optimize the power flow in a power grid. The agents are modeled as decision-makers who interact with each other based on their preferences and objectives, and the goal is to find the optimal power flow solution that satisfies the system's constraints.

Neural Network-Based Prediction of Soil Moisture Using Satellite Images:
This paper presents a neural network-based approach for predicting soil moisture using satellite images. The authors propose a convolutional neural network (CNN) architecture that is trained on a dataset of satellite images and soil moisture data. The model demonstrates excellent performance in terms of accuracy and reliability, making it a valuable tool for monitoring soil moisture and predicting drought conditions.

Robust Deep Learning for Face Recognition in Real-Time:
This paper explores the use of robust deep learning techniques for face recognition in real-time. The authors propose a deep convolutional neural network (CNN) architecture that is designed to handle various challenges such as illumination changes, facial expressions, and pose variations. The model demonstrates impressive performance in terms of accuracy and speed, making it a suitable solution for real-time face recognition applications.

Multi-Scale Feature Fusion for Image Segmentation:
This paper investigates the use of multi-scale feature fusion for image segmentation. The authors propose a novel approach that combines multiple features from different scales of an image to improve the accuracy and robustness of the segmentation process. The proposed model demonstrates promising results in terms of segmentation accuracy and efficiency, making it a valuable tool for medical image analysis and other applications.

Overall, the 5th IEEE Colombian Conference on Applications of Computational Intelligence,ColCACI 2022, showcased a wide range of innovative research and applications in the field of computational intelligence. The papers included in this book provide valuable insights into the latest developments and advancements in the field, and they are expected to have a significant impact on the future of computational intelligence.
The 5th IEEE Colombian Conference on Applications of Computational Intelligence,ColCACI 2022, was held in Cali, Colombia, from July 27 to 29, 2022. This book serves as the official publication of the conference, featuring 7 extended papers that underwent rigorous review and selection from a total of 38 submissions. The papers were organized into topical sections, covering the following areas:

Design of a Segmentation and Classification System for Seed Detection Based on Pixel Intensity Thresholds and Convolutional Neural Networks:
In this paper, the authors propose a novel approach for seed detection in agricultural images using pixel intensity thresholds and convolutional neural networks. The system aims to accurately classify seeds from background noise and other plant components, which is crucial for precision agriculture and crop monitoring. The authors discuss the design and implementation of the segmentation and classification model, as well as the evaluation of its performance using a dataset of agricultural images.

Deep Learning-Based Image Segmentation for Medical Image Analysis:
This paper explores the use of deep learning techniques for image segmentation in medical imaging applications. The authors propose a deep convolutional neural network (CNN) architecture to segment brain images, which is a challenging task due to the complex structure and heterogeneity of the data. The proposed model demonstrates promising results in terms of accuracy and efficiency, making it a valuable tool for medical image analysis.

Multi-Agent Reinforcement Learning for Optimal Power Flow in Power Systems:
This paper investigates the use of multi-agent reinforcement learning for optimal power flow in power systems. The authors propose a novel approach that involves multiple agents cooperating to optimize the power flow in a power grid. The agents are modeled as decision-makers who interact with each other based on their preferences and objectives, and the goal is to find the optimal power flow solution that satisfies the system's constraints.

Neural Network-Based Prediction of Soil Moisture Using Satellite Images:
This paper presents a neural network-based approach for predicting soil moisture using satellite images. The authors propose a convolutional neural network (CNN) architecture that is trained on a dataset of satellite images and soil moisture data. The model demonstrates excellent performance in terms of accuracy and reliability, making it a valuable tool for monitoring soil moisture and predicting drought conditions.

Robust Deep Learning for Face Recognition in Real-Time:
This paper explores the use of robust deep learning techniques for face recognition in real-time. The authors propose a deep convolutional neural network (CNN) architecture that is designed to handle various challenges such as illumination changes, facial expressions, and pose variations. The model demonstrates impressive performance in terms of accuracy and speed, making it a suitable solution for real-time face recognition applications.

Multi-Scale Feature Fusion for Image Segmentation:
This paper investigates the use of multi-scale feature fusion for image segmentation. The authors propose a novel approach that combines multiple features from different scales of an image to improve the accuracy and robustness of the segmentation process. The proposed model demonstrates promising results in terms of segmentation accuracy and efficiency, making it a valuable tool for medical image analysis and other applications.

Overall, the 5th IEEE Colombian Conference on Applications of Computational Intelligence,ColCACI 2022, showcased a wide range of innovative research and applications in the field of computational intelligence. The papers included in this book provide valuable insights into the latest developments and advancements in the field, and they are expected to have a significant impact on the future of computational intelligence.

Weight: 232g
Dimension: 235 x 155 (mm)
ISBN-13: 9783031297823
Edition number: 1st ed. 2023