Experimental analysis of the performance of machine learning algorithms in the classification of navigation accident records
This paper aims to evaluate the use of machine learning techniques in a database of marine accidents. We analyzed and evaluated the main causes and types of marine accidents in the Northern Fluminense region. For this, machine learning techniques were used. The study showed that the modeling can be...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculdade Salesiana Maria Auxiliadora
2017-06-01
|
| Series: | Sistemas de Informação |
| Subjects: | |
| Online Access: | http://www.fsma.edu.br/si/edicao19/Download_FSMA_SI_2017_1_Principal_4_en.html |
| _version_ | 1818426415326953472 |
|---|---|
| author | REIS, M V. S. de A. WEITZEL, L. |
| author_facet | REIS, M V. S. de A. WEITZEL, L. |
| author_sort | REIS, M V. S. de A. |
| collection | DOAJ |
| description | This paper aims to evaluate the use of machine learning techniques in a database of marine accidents. We analyzed and evaluated the main causes and types of marine accidents in the Northern Fluminense region. For this, machine learning techniques were used. The study showed that the modeling can be done in a satisfactory manner using different configurations of classification algorithms, varying the activation functions and training parameters. The SMO (Sequential Minimal Optimization) algorithm showed the best performance result. |
| first_indexed | 2024-12-14T14:29:28Z |
| format | Article |
| id | doaj.art-139fc40554134641b874c5854cf7edad |
| institution | Directory Open Access Journal |
| issn | 1983-5604 1983-5604 |
| language | English |
| last_indexed | 2024-12-14T14:29:28Z |
| publishDate | 2017-06-01 |
| publisher | Faculdade Salesiana Maria Auxiliadora |
| record_format | Article |
| series | Sistemas de Informação |
| spelling | doaj.art-139fc40554134641b874c5854cf7edad2022-12-21T22:57:50ZengFaculdade Salesiana Maria AuxiliadoraSistemas de Informação1983-56041983-56042017-06-011194252Experimental analysis of the performance of machine learning algorithms in the classification of navigation accident recordsREIS, M V. S. de A.0WEITZEL, L.1UFF - Rio das OstrasUFF - Rio das OstrasThis paper aims to evaluate the use of machine learning techniques in a database of marine accidents. We analyzed and evaluated the main causes and types of marine accidents in the Northern Fluminense region. For this, machine learning techniques were used. The study showed that the modeling can be done in a satisfactory manner using different configurations of classification algorithms, varying the activation functions and training parameters. The SMO (Sequential Minimal Optimization) algorithm showed the best performance result.http://www.fsma.edu.br/si/edicao19/Download_FSMA_SI_2017_1_Principal_4_en.htmlMachine LearningBrazilian NavyData MiningK-Nearest NeighborMultilayer PerceptronBayesian NetworksSequential Minimal Optimization |
| spellingShingle | REIS, M V. S. de A. WEITZEL, L. Experimental analysis of the performance of machine learning algorithms in the classification of navigation accident records Sistemas de Informação Machine Learning Brazilian Navy Data Mining K-Nearest Neighbor Multilayer Perceptron Bayesian Networks Sequential Minimal Optimization |
| title | Experimental analysis of the performance of machine learning algorithms in the classification of navigation accident records |
| title_full | Experimental analysis of the performance of machine learning algorithms in the classification of navigation accident records |
| title_fullStr | Experimental analysis of the performance of machine learning algorithms in the classification of navigation accident records |
| title_full_unstemmed | Experimental analysis of the performance of machine learning algorithms in the classification of navigation accident records |
| title_short | Experimental analysis of the performance of machine learning algorithms in the classification of navigation accident records |
| title_sort | experimental analysis of the performance of machine learning algorithms in the classification of navigation accident records |
| topic | Machine Learning Brazilian Navy Data Mining K-Nearest Neighbor Multilayer Perceptron Bayesian Networks Sequential Minimal Optimization |
| url | http://www.fsma.edu.br/si/edicao19/Download_FSMA_SI_2017_1_Principal_4_en.html |
| work_keys_str_mv | AT reismvsdea experimentalanalysisoftheperformanceofmachinelearningalgorithmsintheclassificationofnavigationaccidentrecords AT weitzell experimentalanalysisoftheperformanceofmachinelearningalgorithmsintheclassificationofnavigationaccidentrecords |