Advanced Meteorological Hazard Defense Capability Assessment: Addressing Sample Imbalance with Deep Learning Approaches
With the rise in meteorological disasters, improving evaluation strategies for disaster response agencies is critical. This shift from expert scoring to data-driven approaches is challenged by sample imbalance in the data, affecting accurate capability assessments. This study proposes a solution int...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/23/12561 |
| _version_ | 1797400485857067008 |
|---|---|
| author | Jiansong Tang Ryosuke Saga Qiangsheng Dai Yingchi Mao |
| author_facet | Jiansong Tang Ryosuke Saga Qiangsheng Dai Yingchi Mao |
| author_sort | Jiansong Tang |
| collection | DOAJ |
| description | With the rise in meteorological disasters, improving evaluation strategies for disaster response agencies is critical. This shift from expert scoring to data-driven approaches is challenged by sample imbalance in the data, affecting accurate capability assessments. This study proposes a solution integrating adaptive focal loss into the cross-entropy loss function to address sample distribution imbalances, facilitating nuanced evaluations. A key aspect of this solution is the Encoder-Adaptive-Focal deep learning model coupled with a custom training algorithm, adept at handling the data complexities of meteorological disaster response agencies. The model proficiently extracts and optimizes capability features from time series data, directing the evaluative focus toward more complex samples, thus mitigating sample imbalance issues. Comparative analysis with existing methods like UAE-NaiveBayes, UAE-SVM, and UAE-RandomForest illustrates the superior performance of our model in ability evaluation, positioning it as a robust tool for dynamic capability evaluation. This work aims to enhance disaster management strategies, contributing to mitigating the impacts of meteorological disasters. |
| first_indexed | 2024-03-09T01:56:12Z |
| format | Article |
| id | doaj.art-df3b6f239e744ce7a5109134763cd01d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T01:56:12Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-df3b6f239e744ce7a5109134763cd01d2023-12-08T15:10:59ZengMDPI AGApplied Sciences2076-34172023-11-0113231256110.3390/app132312561Advanced Meteorological Hazard Defense Capability Assessment: Addressing Sample Imbalance with Deep Learning ApproachesJiansong Tang0Ryosuke Saga1Qiangsheng Dai2Yingchi Mao3Graduate School of Informatics, Osaka Metropolitan University, Osaka 559-8531, JapanGraduate School of Informatics, Osaka Metropolitan University, Osaka 559-8531, JapanResearch Institute, State Grid Jiangsu Electric Power Company Ltd., Nanjing 211100, ChinaCollege of Computer and Information, Hohai University, Nanjing 211100, ChinaWith the rise in meteorological disasters, improving evaluation strategies for disaster response agencies is critical. This shift from expert scoring to data-driven approaches is challenged by sample imbalance in the data, affecting accurate capability assessments. This study proposes a solution integrating adaptive focal loss into the cross-entropy loss function to address sample distribution imbalances, facilitating nuanced evaluations. A key aspect of this solution is the Encoder-Adaptive-Focal deep learning model coupled with a custom training algorithm, adept at handling the data complexities of meteorological disaster response agencies. The model proficiently extracts and optimizes capability features from time series data, directing the evaluative focus toward more complex samples, thus mitigating sample imbalance issues. Comparative analysis with existing methods like UAE-NaiveBayes, UAE-SVM, and UAE-RandomForest illustrates the superior performance of our model in ability evaluation, positioning it as a robust tool for dynamic capability evaluation. This work aims to enhance disaster management strategies, contributing to mitigating the impacts of meteorological disasters.https://www.mdpi.com/2076-3417/13/23/12561meteorological hazard defensesample imbalanceloss functionclassification |
| spellingShingle | Jiansong Tang Ryosuke Saga Qiangsheng Dai Yingchi Mao Advanced Meteorological Hazard Defense Capability Assessment: Addressing Sample Imbalance with Deep Learning Approaches Applied Sciences meteorological hazard defense sample imbalance loss function classification |
| title | Advanced Meteorological Hazard Defense Capability Assessment: Addressing Sample Imbalance with Deep Learning Approaches |
| title_full | Advanced Meteorological Hazard Defense Capability Assessment: Addressing Sample Imbalance with Deep Learning Approaches |
| title_fullStr | Advanced Meteorological Hazard Defense Capability Assessment: Addressing Sample Imbalance with Deep Learning Approaches |
| title_full_unstemmed | Advanced Meteorological Hazard Defense Capability Assessment: Addressing Sample Imbalance with Deep Learning Approaches |
| title_short | Advanced Meteorological Hazard Defense Capability Assessment: Addressing Sample Imbalance with Deep Learning Approaches |
| title_sort | advanced meteorological hazard defense capability assessment addressing sample imbalance with deep learning approaches |
| topic | meteorological hazard defense sample imbalance loss function classification |
| url | https://www.mdpi.com/2076-3417/13/23/12561 |
| work_keys_str_mv | AT jiansongtang advancedmeteorologicalhazarddefensecapabilityassessmentaddressingsampleimbalancewithdeeplearningapproaches AT ryosukesaga advancedmeteorologicalhazarddefensecapabilityassessmentaddressingsampleimbalancewithdeeplearningapproaches AT qiangshengdai advancedmeteorologicalhazarddefensecapabilityassessmentaddressingsampleimbalancewithdeeplearningapproaches AT yingchimao advancedmeteorologicalhazarddefensecapabilityassessmentaddressingsampleimbalancewithdeeplearningapproaches |