S1 Data -
<div><p>Coal and gas outburst (CGO) is a complicated natural disaster in underground coal mine production. In constructing smart mines, predicting CGO risks efficiently and accurately is necessary. This paper proposes a CGO risk prediction method based on data augmentation and a neuroevo...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852022572397363200 |
|---|---|
| author | Wenbing Shi (5806160) |
| author2 | Ji Huang (295410) Gaoming Yang (7464977) Shuzhi Su (20760086) Shexiang Jiang (20760089) |
| author2_role | author author author author |
| author_facet | Wenbing Shi (5806160) Ji Huang (295410) Gaoming Yang (7464977) Shuzhi Su (20760086) Shexiang Jiang (20760089) |
| author_role | author |
| dc.creator.none.fl_str_mv | Wenbing Shi (5806160) Ji Huang (295410) Gaoming Yang (7464977) Shuzhi Su (20760086) Shexiang Jiang (20760089) |
| dc.date.none.fl_str_mv | 2025-02-20T18:27:44Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0317461.s001 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/S1_Data_-/28453154 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Genetics Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified transfer function using pointwise intensity transformation lightweight network architecture constructing smart mines complicated natural disaster initial genome code evolutionary neural network div >< p imbalanced data samples neuroevolution </ p neuroevolution algorithm genome mutation evolutionary generations augmented samples rmse </ mae </ evar </ test set species differentiation sample features results show precision mapping population initialization paper proposes outburst risk optimal phenotype multiple aspects method comparisons insufficient diversity gas outburst fitness evaluation feature parameters data augmentation |
| dc.title.none.fl_str_mv | S1 Data - |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <div><p>Coal and gas outburst (CGO) is a complicated natural disaster in underground coal mine production. In constructing smart mines, predicting CGO risks efficiently and accurately is necessary. This paper proposes a CGO risk prediction method based on data augmentation and a neuroevolution algorithm, denoted as ANEAT. First, sample features are applied to the transfer function using a pointwise intensity transformation to obtain new feature samples. It solves the problems of imbalanced data samples and insufficient diversity. Second, the feature importance score sorting and Sparse PCA dimensionality reduction are performed on the data-augmented samples. It provides the initial genome code for the evolutionary neural network. Finally, an evolutionary neural network for CGO prediction is constructed through population initialization, fitness evaluation, species differentiation, genome mutation, and recombination. The optimal phenotype is obtained in the evolutionary generations. In the experiment, we verify the effectiveness of ANEAT from multiple aspects such as data augmentation effectiveness analysis, deep learning model comparison, swarm intelligence optimization algorithm comparison, and other method comparisons. The results show that the <i>MAE</i>, <i>RMSE</i>, and <i>EVAR</i> indexes of ANEAT on the test set are 0.0816, 0.1322, and 0.8972, respectively. It has the optimal CGO prediction effect. ANEAT realizes the high-precision mapping of feature parameters and outburst risk with a lightweight network architecture, which can be well applied to CGO prediction.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_9fee5c4451d7be4da96ebfcb37fdedb8 |
| identifier_str_mv | 10.1371/journal.pone.0317461.s001 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28453154 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | S1 Data - Wenbing Shi (5806160)Ji Huang (295410)Gaoming Yang (7464977)Shuzhi Su (20760086)Shexiang Jiang (20760089)GeneticsBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedtransfer function usingpointwise intensity transformationlightweight network architectureconstructing smart minescomplicated natural disasterinitial genome codeevolutionary neural networkdiv >< pimbalanced data samplesneuroevolution </ pneuroevolution algorithmgenome mutationevolutionary generationsaugmented samplesrmse </mae </evar </test setspecies differentiationsample featuresresults showprecision mappingpopulation initializationpaper proposesoutburst riskoptimal phenotypemultiple aspectsmethod comparisonsinsufficient diversitygas outburstfitness evaluationfeature parametersdata augmentation<div><p>Coal and gas outburst (CGO) is a complicated natural disaster in underground coal mine production. In constructing smart mines, predicting CGO risks efficiently and accurately is necessary. This paper proposes a CGO risk prediction method based on data augmentation and a neuroevolution algorithm, denoted as ANEAT. First, sample features are applied to the transfer function using a pointwise intensity transformation to obtain new feature samples. It solves the problems of imbalanced data samples and insufficient diversity. Second, the feature importance score sorting and Sparse PCA dimensionality reduction are performed on the data-augmented samples. It provides the initial genome code for the evolutionary neural network. Finally, an evolutionary neural network for CGO prediction is constructed through population initialization, fitness evaluation, species differentiation, genome mutation, and recombination. The optimal phenotype is obtained in the evolutionary generations. In the experiment, we verify the effectiveness of ANEAT from multiple aspects such as data augmentation effectiveness analysis, deep learning model comparison, swarm intelligence optimization algorithm comparison, and other method comparisons. The results show that the <i>MAE</i>, <i>RMSE</i>, and <i>EVAR</i> indexes of ANEAT on the test set are 0.0816, 0.1322, and 0.8972, respectively. It has the optimal CGO prediction effect. ANEAT realizes the high-precision mapping of feature parameters and outburst risk with a lightweight network architecture, which can be well applied to CGO prediction.</p></div>2025-02-20T18:27:44ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0317461.s001https://figshare.com/articles/dataset/S1_Data_-/28453154CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/284531542025-02-20T18:27:44Z |
| spellingShingle | S1 Data - Wenbing Shi (5806160) Genetics Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified transfer function using pointwise intensity transformation lightweight network architecture constructing smart mines complicated natural disaster initial genome code evolutionary neural network div >< p imbalanced data samples neuroevolution </ p neuroevolution algorithm genome mutation evolutionary generations augmented samples rmse </ mae </ evar </ test set species differentiation sample features results show precision mapping population initialization paper proposes outburst risk optimal phenotype multiple aspects method comparisons insufficient diversity gas outburst fitness evaluation feature parameters data augmentation |
| status_str | publishedVersion |
| title | S1 Data - |
| title_full | S1 Data - |
| title_fullStr | S1 Data - |
| title_full_unstemmed | S1 Data - |
| title_short | S1 Data - |
| title_sort | S1 Data - |
| topic | Genetics Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified transfer function using pointwise intensity transformation lightweight network architecture constructing smart mines complicated natural disaster initial genome code evolutionary neural network div >< p imbalanced data samples neuroevolution </ p neuroevolution algorithm genome mutation evolutionary generations augmented samples rmse </ mae </ evar </ test set species differentiation sample features results show precision mapping population initialization paper proposes outburst risk optimal phenotype multiple aspects method comparisons insufficient diversity gas outburst fitness evaluation feature parameters data augmentation |