D. Maldonado, R. Araguillin, Felipe Grijalva, D. Benítez, Noel Pérez
{"title":"COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping","authors":"D. Maldonado, R. Araguillin, Felipe Grijalva, D. Benítez, Noel Pérez","doi":"10.1109/ColCACI59285.2023.10225933","DOIUrl":"https://doi.org/10.1109/ColCACI59285.2023.10225933","url":null,"abstract":"This paper proposes the development of a deep learning model for diagnosing COVID-19 through the analysis of chest X-ray images. First, data augmentation is implemented to avoid overfitting and improve model generalization. Then, instead of conventional image segmentation techniques, Gradient-weighted Class Activation Mapping (Grad-CAM) is used to highlight the important regions directly related to COVID-19. Subsequently, transfer learning is implemented to transform the data of the X-ray images to a reduced set of features using the Xception convolutional neural network. Finally, a classification neural network is designed, parameterized and trained, which is capable of recognizing healthy patients with 97% accuracy, while the detection rate for patients infected with COVID-19 was 92%.","PeriodicalId":206196,"journal":{"name":"2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115429597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Herrera, D. Benítez, Noel Pérez, A. Di Teodoro, Oscar Camacho
{"title":"A Novel Hybrid Control Approach with PSO Optimization for Processes with Long Time-Delay","authors":"M. Herrera, D. Benítez, Noel Pérez, A. Di Teodoro, Oscar Camacho","doi":"10.1109/ColCACI59285.2023.10226150","DOIUrl":"https://doi.org/10.1109/ColCACI59285.2023.10226150","url":null,"abstract":"This paper proposes a hybrid controller that mixes the Smith Predictor scheme along the sliding-mode method and uses particle swarm optimization to fine-tune the parameters for the controller. The proposed controller is based on the first-order plus dead-time model to put together a dead-time term as the non-invertible part and a gain for the invertible part; in this way, the controller synthesis is too easy. The performance of the designed controller is measured using the ISE, IAE, and TVu indices. The results show that the proposed controller can significantly increase the efficiency of designing robust controllers for high-order and inverse response linear systems.","PeriodicalId":206196,"journal":{"name":"2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128708002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Spatial Shrinkage Prior: A Probabilistic Approach to Model for Categorical Variables with Many Levels","authors":"D. Cruz-Reyes","doi":"10.1109/ColCACI59285.2023.10226106","DOIUrl":"https://doi.org/10.1109/ColCACI59285.2023.10226106","url":null,"abstract":"One of the most commonly used methods to prevent overfitting and select relevant variables in regression models with many predictors is the penalized regression technique. Under such approaches, variable selection is performed in a non-probabilistic way, using some optimization criterion. A Bayesian approach to penalized regression has been proposed by assuming a prior distribution for the regression coefficients that plays a similar role as the penalty term in classical statistics: to shrink non-significant coefficients toward zero and assign a significant probability mass to non-negligible coefficients. These prior distributions, called shrinkage priors, usually assume independence among the covariates, which may not be an appropriate assumption in many cases. We propose two shrinkage priors to model the uncertainty about coefficients that are spatially correlated. The proposed priors are considered as an alternative approach to model the uncertainty about the coefficients of categorical variables with many levels. To illustrate their use, we consider the linear regression model. We evaluate the proposed method through several simulation studies.","PeriodicalId":206196,"journal":{"name":"2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130860223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Diego Martínez, David Zabala-Blanco, Roberto Ahumada-García, I. Soto, A. D. Firoozabadi, Pablo Palacios Játiva
{"title":"Evaluation of Extreme Learning Machines for Detecting Heart Diseases","authors":"Diego Martínez, David Zabala-Blanco, Roberto Ahumada-García, I. Soto, A. D. Firoozabadi, Pablo Palacios Játiva","doi":"10.1109/ColCACI59285.2023.10226128","DOIUrl":"https://doi.org/10.1109/ColCACI59285.2023.10226128","url":null,"abstract":"Currently, cardiovascular diseases are the leading cause of human death according to the World Health Organization. Their prediction allows doctors to indicate preventive measures to their patients and perform procedures on time. In this research, the performance of different Extreme Learning Machine (ELM)-based algorithms applied to the binary classification problem of the heart's state (healthy or sick) was evaluated. The following ELMs were used: the basic model, regularized, weighted, and multi-layer. The experiments were carried out in a MATLAB programming environment and a mid-range laptop. To evaluate the models' performance, the accuracy (Acc), the geometric mean (G-mean), and the execution time of the algorithms were used, comparing the results with other classifiers reported in the literature. In this research, it is proposed to use a Weighted ELM (W1-ELM) due to its acceptable accuracy of 0.81 and its low training complexity compared to deeper models such as Convolutional Neural Networks.","PeriodicalId":206196,"journal":{"name":"2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134158201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Analysis of Economic Indicators Through News and Twitter Using Text Mining, Machine Learning and Multiagent Systems","authors":"Cristhian Johnathan Izquierdo Ortiz","doi":"10.1109/ColCACI59285.2023.10225755","DOIUrl":"https://doi.org/10.1109/ColCACI59285.2023.10225755","url":null,"abstract":"This research proposes a new analysis approach for economic phenomena, including data from news and social networks as external information to predict commodity values (LBMA GOLD and Brent oil) and the USD/COP currency, clas-sify the sources of information and model multi-agent systems. Information was collected from 166 news sources through RSS and Twitter for 8 months (from October 2020 to May 2021). Linear regressions and assembly machine learning techniques such as XGBoost and Random Forest are used to predict daily changes. The analysis is complemented with the construction of a socio-inspired multi-agent system that evolves using external information, at the end presents patterns typical of complex systems.","PeriodicalId":206196,"journal":{"name":"2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124554504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Michael Stiven Ramirez Campos, Diana C. Rodríguez, A. Orjuela-Cañón
{"title":"Molecular Compounds Proposal for Drug-Resistant Tuberculosis in the Drug Discovery Process","authors":"Michael Stiven Ramirez Campos, Diana C. Rodríguez, A. Orjuela-Cañón","doi":"10.1109/ColCACI59285.2023.10225875","DOIUrl":"https://doi.org/10.1109/ColCACI59285.2023.10225875","url":null,"abstract":"Tuberculosis is a contagious disease considered as world emergency by the World Health Organization. One of the common prevalent problems are associated to drug-resistant TB, because of unsuccessful treatments of using antibiotics. The use of artificial intelligence algorithms, mainly machine learning (ML) models have allowed to provided more tools for the drug discovery field. For this study, the methodology used was driven to identify new components that may contribute to the inhibition of the inhA protein. Leveraging ML models that learn from data, six regression models were implemented. Best model obtained R2 value of 0.99 and a MSE value of 1.8 e-5.","PeriodicalId":206196,"journal":{"name":"2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126726013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Walter Fuertes, Karen Hunter, D. Benítez, Noel Pérez, Felipe Grijalva, Maria Baldeon-Calisto
{"title":"Application of Convolutional Neural Networks to Emotion Recognition for Robotic Arm Manipulation","authors":"Walter Fuertes, Karen Hunter, D. Benítez, Noel Pérez, Felipe Grijalva, Maria Baldeon-Calisto","doi":"10.1109/ColCACI59285.2023.10225880","DOIUrl":"https://doi.org/10.1109/ColCACI59285.2023.10225880","url":null,"abstract":"This paper presents the development of a system that operates a robotic arm to deliver an object based on the facial expression of a human standing in front of the robot, demonstrating real-time emotion recognition for physical Human-Robot Interaction. To achieve this, a convolutional neural network-based model was developed to identify emotions in real time. The robotic arm operation was implemented using an embedded NVidia Jetson Nano computer, a web camera, and OpenCV, ROS, and TensorFlow libraries. Using a 26.6k face photos data set from the emotion detection database, the built emotion detection model demonstrated an accuracy of 93.5% and an error of 6.5% during training and validation. The final real-time prototype had a testing accuracy of 94% with an error of 6%. This proof-of-concept shows that in the near future more advanced applications that harness user emotions may also be built.","PeriodicalId":206196,"journal":{"name":"2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)","volume":"66 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139354862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
María-José Zurita, Daniel Riofrío, Noel Pérez, David Romo, D. Benítez, Ricardo Flores Moyano, Felipe Grijalva, Maria Baldeon-Calisto
{"title":"Towards Automatic Animal Classification in Wildlife Environments for Native Species Monitoring in the Amazon","authors":"María-José Zurita, Daniel Riofrío, Noel Pérez, David Romo, D. Benítez, Ricardo Flores Moyano, Felipe Grijalva, Maria Baldeon-Calisto","doi":"10.1109/ColCACI59285.2023.10226093","DOIUrl":"https://doi.org/10.1109/ColCACI59285.2023.10226093","url":null,"abstract":"Although critical for habitat and species conservation, camera trap image analysis is often manual, time-consuming, and expensive. Thus, automating this process would allow large-scale research on biodiversity hotspots of large conspicuous mammals and bird species. This paper explores the use of deep learning species-level object detection and classification models for this task, using two state-of-the-art architectures, YOLOv5 and Faster R-CNN, for two species: white-lipped peccary and collared peccary. The dataset contains 7,733 images obtained after data augmentation from the Tiputini Biodiversity Station. The models were trained in 70% of the dataset, validated in 20%, and tested in 10% of the available data. The YOLOv5 model proved to be more robust, having lower losses and a higher overall mAP (Mean Average Precision) value than Faster-RCNN. This is one of the first steps towards developing an automated camera trap analysis tool, allowing a large-scale analysis of population and habitat trends to benefit their conservation. The results suggest that hyperparameter fine-tuning would improve our models and allow us to extend this tool to other native species.","PeriodicalId":206196,"journal":{"name":"2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132136814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Camilo Andrés Pérez Ospino, Jorman Arbey Castro Rivera, A. Orjuela-Cañón
{"title":"Machine Learning Clustering for Cancer Analysis Employing Gene Expression Data","authors":"Camilo Andrés Pérez Ospino, Jorman Arbey Castro Rivera, A. Orjuela-Cañón","doi":"10.1109/ColCACI59285.2023.10226026","DOIUrl":"https://doi.org/10.1109/ColCACI59285.2023.10226026","url":null,"abstract":"The idea that cancer types vary in their molecular structure (DNA, RNA, proteins, and epigenetics) depending on the origin and location of the cancer, has been worked on. The Cancer Genome Atlas (TCGA) has generated an initiative to carefully create a database to ensure quality data in the profiling of different tumors to promote research, a part of this large database was called Pan-Cancer, which has the genomic, epigenetic, transcriptional and proteomic profiling of 12 different types of cancer. In this research we took one of the profiling, RNA profiling, in 5 cancer types, in order to determine the possibility of segmenting in an unsupervised manner and to evaluate the difference of them by their origin. The results indicate that the number of clusters can vary from 5 to 7, with 5 clusters being established by the database labels, however, the division of 6 or 7 clusters is due to the clustering of breast cancer (BRCA) which has several origins.","PeriodicalId":206196,"journal":{"name":"2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127994545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Daniel Bonilla Blanco, Yoiner Picón González, Oscar Manuel Duque Suaréz, J. Vargas, Jorge Luis Diaz Rodriguez, Aldo Pardo García
{"title":"GUI for fuzzy logic self-tuning PID control and FPD+I control in a temperature plant","authors":"Daniel Bonilla Blanco, Yoiner Picón González, Oscar Manuel Duque Suaréz, J. Vargas, Jorge Luis Diaz Rodriguez, Aldo Pardo García","doi":"10.1109/ColCACI59285.2023.10225874","DOIUrl":"https://doi.org/10.1109/ColCACI59285.2023.10225874","url":null,"abstract":"This work deals with the development of a Graphical User Interface (GUI) for fuzzy logic self-tuning PID adjustment and FPD+I (Proportional-derivative fuzzy+integral) control. To appreciate the advantages and disadvantages of these controllers, the GUI also has classic control options, simulation graphs, comparative graphs, and control options for the temperature plant that consists of a flat heating resistance, an infrared sensor, a fan, and an Arduino micro in slave mode. Once the identification of the plant is carried out, the tuning of the different controllers is carried out, even with experimental improvements in some cases. After obtaining the Matlab GUI and drivers, it is verified that it works properly.","PeriodicalId":206196,"journal":{"name":"2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114418012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}