1
|
Holguin-Garcia SA, Guevara-Navarro E, Daza-Chica AE, Patiño-Claro MA, Arteaga-Arteaga HB, Ruz GA, Tabares-Soto R, Bravo-Ortiz MA. A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure. BMC Med Inform Decis Mak 2024; 24:60. [PMID: 38429718 PMCID: PMC10908140 DOI: 10.1186/s12911-024-02460-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2023] [Accepted: 02/13/2024] [Indexed: 03/03/2024] Open
Abstract
INTRODUCTION Epilepsy is a disease characterized by an excessive discharge in neurons generally provoked without any external stimulus, known as convulsions. About 2 million people are diagnosed each year in the world. This process is carried out by a neurological doctor using an electroencephalogram (EEG), which is lengthy. METHOD To optimize these processes and make them more efficient, we have resorted to innovative artificial intelligence methods essential in classifying EEG signals. For this, comparing traditional models, such as machine learning or deep learning, with cutting-edge models, in this case, using Capsule-Net architectures and Transformer Encoder, has a crucial role in finding the most accurate model and helping the doctor to have a faster diagnosis. RESULT In this paper, a comparison was made between different models for binary and multiclass classification of the epileptic seizure detection database, achieving a binary accuracy of 99.92% with the Capsule-Net model and a multiclass accuracy with the Transformer Encoder model of 87.30%. CONCLUSION Artificial intelligence is essential in diagnosing pathology. The comparison between models is helpful as it helps to discard those that are not efficient. State-of-the-art models overshadow conventional models, but data processing also plays an essential role in evaluating the higher accuracy of the models.
Collapse
Affiliation(s)
| | - Ernesto Guevara-Navarro
- Departamento de Electrónica y Automatización, Universidad Autónoma de Manizales, Manizales, 170001, Caldas, Colombia
| | - Alvaro Eduardo Daza-Chica
- Departamento de Electrónica y Automatización, Universidad Autónoma de Manizales, Manizales, 170001, Caldas, Colombia
| | - Maria Alejandra Patiño-Claro
- Departamento de Electrónica y Automatización, Universidad Autónoma de Manizales, Manizales, 170001, Caldas, Colombia
| | - Harold Brayan Arteaga-Arteaga
- Departamento de Electrónica y Automatización, Universidad Autónoma de Manizales, Manizales, 170001, Caldas, Colombia
| | - Gonzalo A Ruz
- Facultad de Ingeniería y Ciencias, Universidad Adolfo Ibáñez, Santiago, 7941169, Chile
- Center of Applied Ecology and Sustainability (CAPES), Santiago, 8331150, Chile
- Data Observatory Foundation, Santiago, 7510277, Chile
| | - Reinel Tabares-Soto
- Departamento de Electrónica y Automatización, Universidad Autónoma de Manizales, Manizales, 170001, Caldas, Colombia
- Departamento de Sistemas e Informática, Universidad de Caldas, Manizales, 170004, Caldas, Colombia
- Facultad de Ingeniería y Ciencias, Universidad Adolfo Ibáñez, Santiago, 7941169, Chile
| | - Mario Alejandro Bravo-Ortiz
- Departamento de Electrónica y Automatización, Universidad Autónoma de Manizales, Manizales, 170001, Caldas, Colombia.
- Centro de Bioinformática y Biología Computacional (BIOS), Manizales, 170001, Colombia.
| |
Collapse
|
2
|
Arteaga-Arteaga HB, Candamil-Cortés MS, Breaux B, Guillen-Rondon P, Orozco-Arias S, Tabares-Soto R. Machine learning applications on intratumoral heterogeneity in glioblastoma using single-cell RNA sequencing data. Brief Funct Genomics 2023; 22:428-441. [PMID: 37119295 DOI: 10.1093/bfgp/elad002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2022] [Revised: 01/17/2023] [Indexed: 05/01/2023] Open
Abstract
Artificial intelligence is revolutionizing all fields that affect people's lives and health. One of the most critical applications is in the study of tumors. It is the case of glioblastoma (GBM) that has behaviors that need to be understood to develop effective therapies. Due to advances in single-cell RNA sequencing (scRNA-seq), it is possible to understand the cellular and molecular heterogeneity in the GBM. Given that there are different cell groups in these tumors, there is a need to apply Machine Learning (ML) algorithms. It will allow extracting information to understand how cancer changes and broaden the search for effective treatments. We proposed multiple comparisons of ML algorithms to classify cell groups based on the GBM scRNA-seq data. This broad comparison spectrum can show the scientific-medical community which models can achieve the best performance in this task. In this work are classified the following cell groups: Tumor Core (TC), Tumor Periphery (TP) and Normal Periphery (NP), in binary and multi-class scenarios. This work presents the biomarker candidates found for the models with the best results. The analyses presented here allow us to verify the biomarker candidates to understand the genetic characteristics of GBM, which may be affected by a suitable identification of GBM heterogeneity. This work obtained for the four scenarios covered cross-validation results of $93.03\% \pm 5.37\%$, $97.42\% \pm 3.94\%$, $98.27\% \pm 1.81\%$ and $93.04\% \pm 6.88\%$ for the classification of TP versus TC, TP versus NP, NP versus TP and TC (TPC) and NP versus TP versus TC, respectively.
Collapse
Affiliation(s)
| | - Mariana S Candamil-Cortés
- Departamento de Ciencias Computacionales, Universidad Autónoma de Manizales, Manizales, Caldas, Colombia
- Centro de Investigaciones en Medio Ambiente y Desarrollo - CIMAD, Universidad de Manizales, Manizales, Caldas, Colombia
| | - Brian Breaux
- Department of Computer Science, University of Houston Downtown, Houston, Texas, United States of America
| | - Pablo Guillen-Rondon
- Department of Computer Science, University of Houston Downtown, Houston, Texas, United States of America
- Biomedical and Energy Solutions LLC, Houston, Texas, United States of America
| | - Simon Orozco-Arias
- Departamento de Ciencias Computacionales, Universidad Autónoma de Manizales, Manizales, Caldas, Colombia
- Departamento de Sistemas e Informática, Universidad de Caldas, Manizales, Caldas, Colombia
| | - Reinel Tabares-Soto
- Departamento de Electrónica y Automatización, Universidad Autónoma de Manizales, Manizales, Caldas, Colombia
- Departamento de Sistemas e Informática, Universidad de Caldas, Manizales, Caldas, Colombia
| |
Collapse
|
3
|
Arias-Barahona MX, Arteaga-Arteaga HB, Orozco-Arias S, Flórez-Ruíz JC, Valencia-Díaz MA, Tabares-Soto R. Requests classification in the customer service area for software companies using machine learning and natural language processing. PeerJ Comput Sci 2023; 9:e1016. [PMID: 37346599 PMCID: PMC10280277 DOI: 10.7717/peerj-cs.1016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2022] [Accepted: 06/03/2022] [Indexed: 06/23/2023]
Abstract
Artificial intelligence (AI) is one of the components recognized for its potential to transform the way we live today radically. It makes it possible for machines to learn from experience, adjust to new contributions and perform tasks like human beings. The business field is the focus of this research. This article proposes implementing an incident classification model using machine learning (ML) and natural language processing (NLP). The application is for the technical support area in a software development company that currently resolves customer requests manually. Through ML and NLP techniques applied to company data, it is possible to know the category of a request given by the client. It increases customer satisfaction by reviewing historical records to analyze their behavior and correctly provide the expected solution to the incidents presented. Also, this practice would reduce the cost and time spent on relationship management with the potential consumer. This work evaluates different Machine Learning models, such as support vector machine (SVM), Extra Trees, and Random Forest. The SVM algorithm demonstrates the highest accuracy of 98.97% with class balance, hyper-parameter optimization, and pre-processing techniques.
Collapse
Affiliation(s)
| | | | - Simón Orozco-Arias
- Department of Computer Science, Universidad Autónoma de Manizales, Manizales, Caldas, Colombia
- Departamento de Sistemas e Informática, Universidad de Caldas, Manizales, Caldas, Colombia
| | - Juan Camilo Flórez-Ruíz
- Department of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, Colombia
| | | | - Reinel Tabares-Soto
- Department of Electronics and Automation, Universidad Autónoma de Manizales, Manizales, Caldas, Colombia
- Departamento de Sistemas e Informática, Universidad de Caldas, Manizales, Caldas, Colombia
| |
Collapse
|
4
|
Comparative Performance of Machine-Learning and Deep-Learning Algorithms in Predicting Gas–Liquid Flow Regimes. Processes (Basel) 2023. [DOI: 10.3390/pr11010177] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/09/2023] Open
Abstract
Gas–liquid flow is a significant phenomenon in various engineering applications, such as in nuclear reactors, power plants, chemical industries, and petroleum industries. The prediction of the flow patterns is of great importance for designing and analyzing the operations of two-phase pipeline systems. The traditional numerical and empirical methods that have been used for the prediction are known to result in a high inaccuracy for scale-up processes. That is why various artificial intelligence-based (AI-based) methodologies are being applied, at present, to predict the gas–liquid flow regimes. We focused in the current study on a thorough comparative analysis of machine learning (ML) and deep learning (DL) in predicting the flow regimes with the application of a diverse set of ML and DL frameworks to a database comprising 11,837 data points, which were collected from thirteen independent experiments. During the pre-processing, the big data analysis was performed to analyze the correlations among the parameters and extract important features. The comparative analysis of the AI-based models’ performances was conducted using precision, recall, F1-score, accuracy, Cohen’s kappa, and receiver operating characteristics curves. The extreme gradient boosting method was identified as the optimum model for predicting the two-phase flow regimes in inclined or horizontal pipelines.
Collapse
|