Energy Flux Prediction Using an Ordinal Soft Labelling Strategy

Áreas de investigación:

• Sin categoría

Año:

2024

Tipo de publicación:

Artículo en conferencia

Palabras clave:

Energy flux, renewable energy, ordinal classification, unimodal distributions

Autores:

• Gómez-Orellana, Antonio Manuel
• Vargas, Víctor Manuel
• Gutiérrez, Pedro Antonio
• Pérez-Aracil, Jorge
• Salcedo-Sanz, Sancho
• Hervás-Martínez, César
• Guijo-Rubio, David

Volumen:

14675

Título del libro:

Bioinspired Systems for Translational Applications: From Robotics to Social Engineering

Páginas:

283–292

Organización:

IWINAC

Mes:

Mayo

ISSN:

1611-3349

BibTex:

@conference{EnergyFlux_iwinac_2024, author = "Antonio Manuel G{\'o}mez-Orellana and V{\'i}ctor Manuel Vargas and Pedro Antonio Guti{\'e}rrez and Jorge P{\'e}rez-Aracil and Sancho Salcedo-Sanz and C{\'e}sar Herv{\'a}s-Mart{\'i}nez and David Guijo-Rubio", abstract = "This paper addresses the problem of short-term energy flux prediction. For this purpose, we propose the use of an ordinal classification neural network model optimised using the triangular regularised categorical cross-entropy loss, termed MLP-T. This model is based on a soft labelling strategy, that replaces the crisp 0/1 labels on the loss computation with soft versions encoding the ordinal information. This soft label encoding leverages the inherent ordering between categories to reduce the cost of ordinal classification errors and improve model generalisation performance. Specifically, the soft labels for each target class are derived from triangular probability distributions. To assess the performance of MLP-T, six datasets built from buoy measurements and reanalysis data have been used. MLP-T has been compared to nominal and ordinal classification techniques in terms of four performance metrics. MLP-T achieved an outstanding performance across all datasets and performance metrics, securing the best mean results. Despite the imbalanced nature of the problem, which makes the ordinal classification task notably difficult, MLP-T achieved good results in all classes across all datasets, including the underrepresented classes. Remarkably, MLP-T was the only approach that correctly classified at least one instance of the minority class in all datasets. Furthermore, MLP-T secured the top rank in all cases, confirming its suitability for the problem addressed.", booktitle = "Bioinspired Systems for Translational Applications: From Robotics to Social Engineering", doi = "https://link.springer.com/chapter/10.1007/978-3-031-61137-7_26", issn = "1611-3349", keywords = "Energy flux, renewable energy, ordinal classification, unimodal distributions", month = "Mayo", organization = "IWINAC", pages = "283–292", title = "{E}nergy {F}lux {P}rediction {U}sing an {O}rdinal {S}oft {L}abelling {S}trategy", url = "doi.org/10.1007/978-3-031-61137-7_26", volume = "14675", year = "2024", }

Abstract:

This paper addresses the problem of short-term energy flux prediction. For this purpose, we propose the use of an ordinal classification neural network model optimised using the triangular regularised categorical cross-entropy loss, termed MLP-T. This model is based on a soft labelling strategy, that replaces the crisp 0/1 labels on the loss computation with soft versions encoding the ordinal information. This soft label encoding leverages the inherent ordering between categories to reduce the cost of ordinal classification errors and improve model generalisation performance. Specifically, the soft labels for each target class are derived from triangular probability distributions. To assess the performance of MLP-T, six datasets built from buoy measurements and reanalysis data have been used. MLP-T has been compared to nominal and ordinal classification techniques in terms of four performance metrics. MLP-T achieved an outstanding performance across all datasets and performance metrics, securing the best mean results. Despite the imbalanced nature of the problem, which makes the ordinal classification task notably difficult, MLP-T achieved good results in all classes across all datasets, including the underrepresented classes. Remarkably, MLP-T was the only approach that correctly classified at least one instance of the minority class in all datasets. Furthermore, MLP-T secured the top rank in all cases, confirming its suitability for the problem addressed.