A Machine Learning Strategy Based on Kittler’s Taxonomy to Detect Anomalies and Recognize Contexts Applied to Monitor Water Bodies in Environments
Environmental monitoring, such as analyses of water bodies to detect anomalies, is recognized worldwide as a task necessary to reduce the impacts arising from pollution. However, the large number of data available to be analyzed in different contexts, such as in an image time series acquired by sate...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/9/2222 |
| _version_ | 1797502961047306240 |
|---|---|
| author | Maurício Araújo Dias Giovanna Carreira Marinho Rogério Galante Negri Wallace Casaca Ignácio Bravo Muñoz Danilo Medeiros Eler |
| author_facet | Maurício Araújo Dias Giovanna Carreira Marinho Rogério Galante Negri Wallace Casaca Ignácio Bravo Muñoz Danilo Medeiros Eler |
| author_sort | Maurício Araújo Dias |
| collection | DOAJ |
| description | Environmental monitoring, such as analyses of water bodies to detect anomalies, is recognized worldwide as a task necessary to reduce the impacts arising from pollution. However, the large number of data available to be analyzed in different contexts, such as in an image time series acquired by satellites, still pose challenges for the detection of anomalies, even when using computers. This study describes a machine learning strategy based on Kittler’s taxonomy to detect anomalies related to water pollution in an image time series. We propose this strategy to monitor environments, detecting unexpected conditions that may occur (i.e., detecting outliers), and identifying those outliers in accordance with Kittler’s taxonomy (i.e., detecting anomalies). According to our strategy, contextual and non-contextual image classifications were semi-automatically compared to find any divergence that indicates the presence of one type of anomaly defined by the taxonomy. In our strategy, models built to classify a single image were used to classify an image time series due to domain adaptation. The results 99.07%, 99.99%, 99.07%, and 99.53% were achieved by our strategy, respectively, for accuracy, precision, recall, and F-measure. These results suggest that our strategy allows computers to recognize contexts and enhances their capabilities to solve contextualized problems. Therefore, our strategy can be used to guide computational systems to make different decisions to solve a problem in response to each context. The proposed strategy is relevant for improving machine learning, as its use allows computers to have a more organized learning process. Our strategy is presented with respect to its applicability to help monitor environmental disasters. A minor limitation was found in the results caused by the use of domain adaptation. This type of limitation is fairly common when using domain adaptation, and therefore has no significance. Even so, future work should investigate other techniques for transfer learning. |
| first_indexed | 2024-03-10T03:43:39Z |
| format | Article |
| id | doaj.art-230a0de6c02b42d8990619680155be94 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:43:39Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-230a0de6c02b42d8990619680155be942023-11-23T09:12:24ZengMDPI AGRemote Sensing2072-42922022-05-01149222210.3390/rs14092222A Machine Learning Strategy Based on Kittler’s Taxonomy to Detect Anomalies and Recognize Contexts Applied to Monitor Water Bodies in EnvironmentsMaurício Araújo Dias0Giovanna Carreira Marinho1Rogério Galante Negri2Wallace Casaca3Ignácio Bravo Muñoz4Danilo Medeiros Eler5Department of Mathematics and Computer Science, Faculty of Sciences and Technology, Campus Presidente Prudente, São Paulo State University (UNESP), Sao Paulo 19060-900, BrazilDepartment of Mathematics and Computer Science, Faculty of Sciences and Technology, Campus Presidente Prudente, São Paulo State University (UNESP), Sao Paulo 19060-900, BrazilDepartment of Environmental Engineering, Sciences and Technology Institute, Campus São José dos Campos, São Paulo State University (UNESP), Sao Paulo 12247-004, BrazilDepartment of Energy Engineering, Campus Rosana, São Paulo State University (UNESP), Sao Paulo 19274-000, BrazilPolytechnic School, University of Alcalá (UAH), 28805 Alcalá de Henares, SpainDepartment of Mathematics and Computer Science, Faculty of Sciences and Technology, Campus Presidente Prudente, São Paulo State University (UNESP), Sao Paulo 19060-900, BrazilEnvironmental monitoring, such as analyses of water bodies to detect anomalies, is recognized worldwide as a task necessary to reduce the impacts arising from pollution. However, the large number of data available to be analyzed in different contexts, such as in an image time series acquired by satellites, still pose challenges for the detection of anomalies, even when using computers. This study describes a machine learning strategy based on Kittler’s taxonomy to detect anomalies related to water pollution in an image time series. We propose this strategy to monitor environments, detecting unexpected conditions that may occur (i.e., detecting outliers), and identifying those outliers in accordance with Kittler’s taxonomy (i.e., detecting anomalies). According to our strategy, contextual and non-contextual image classifications were semi-automatically compared to find any divergence that indicates the presence of one type of anomaly defined by the taxonomy. In our strategy, models built to classify a single image were used to classify an image time series due to domain adaptation. The results 99.07%, 99.99%, 99.07%, and 99.53% were achieved by our strategy, respectively, for accuracy, precision, recall, and F-measure. These results suggest that our strategy allows computers to recognize contexts and enhances their capabilities to solve contextualized problems. Therefore, our strategy can be used to guide computational systems to make different decisions to solve a problem in response to each context. The proposed strategy is relevant for improving machine learning, as its use allows computers to have a more organized learning process. Our strategy is presented with respect to its applicability to help monitor environmental disasters. A minor limitation was found in the results caused by the use of domain adaptation. This type of limitation is fairly common when using domain adaptation, and therefore has no significance. Even so, future work should investigate other techniques for transfer learning.https://www.mdpi.com/2072-4292/14/9/2222remote sensingKittler’s taxonomyanomaly detectionmachine learningtime seriespattern recognition |
| spellingShingle | Maurício Araújo Dias Giovanna Carreira Marinho Rogério Galante Negri Wallace Casaca Ignácio Bravo Muñoz Danilo Medeiros Eler A Machine Learning Strategy Based on Kittler’s Taxonomy to Detect Anomalies and Recognize Contexts Applied to Monitor Water Bodies in Environments Remote Sensing remote sensing Kittler’s taxonomy anomaly detection machine learning time series pattern recognition |
| title | A Machine Learning Strategy Based on Kittler’s Taxonomy to Detect Anomalies and Recognize Contexts Applied to Monitor Water Bodies in Environments |
| title_full | A Machine Learning Strategy Based on Kittler’s Taxonomy to Detect Anomalies and Recognize Contexts Applied to Monitor Water Bodies in Environments |
| title_fullStr | A Machine Learning Strategy Based on Kittler’s Taxonomy to Detect Anomalies and Recognize Contexts Applied to Monitor Water Bodies in Environments |
| title_full_unstemmed | A Machine Learning Strategy Based on Kittler’s Taxonomy to Detect Anomalies and Recognize Contexts Applied to Monitor Water Bodies in Environments |
| title_short | A Machine Learning Strategy Based on Kittler’s Taxonomy to Detect Anomalies and Recognize Contexts Applied to Monitor Water Bodies in Environments |
| title_sort | machine learning strategy based on kittler s taxonomy to detect anomalies and recognize contexts applied to monitor water bodies in environments |
| topic | remote sensing Kittler’s taxonomy anomaly detection machine learning time series pattern recognition |
| url | https://www.mdpi.com/2072-4292/14/9/2222 |
| work_keys_str_mv | AT mauricioaraujodias amachinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT giovannacarreiramarinho amachinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT rogeriogalantenegri amachinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT wallacecasaca amachinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT ignaciobravomunoz amachinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT danilomedeiroseler amachinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT mauricioaraujodias machinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT giovannacarreiramarinho machinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT rogeriogalantenegri machinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT wallacecasaca machinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT ignaciobravomunoz machinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments AT danilomedeiroseler machinelearningstrategybasedonkittlerstaxonomytodetectanomaliesandrecognizecontextsappliedtomonitorwaterbodiesinenvironments |