RGANFormer: Relativistic Generative Adversarial Transformer for time-series signal forecasting on intelligent vehicles
| dc.contributor.author | Xing, Yang | |
| dc.contributor.author | Kong, Xiangqi | |
| dc.contributor.author | Tsourdos, Antonios | |
| dc.coverage.spatial | Jeju Island, Republic of Korea | |
| dc.date.accessioned | 2024-07-23T14:29:35Z | |
| dc.date.available | 2024-07-23T14:29:35Z | |
| dc.date.freetoread | 2024-07-23 | |
| dc.date.issued | 2024-07-15 | |
| dc.description.abstract | Time-series modelling (TSM) is a critical task for intelligent vehicles (IVs), covering areas like fault detection, health monitoring, and inference of road user intentions. In this study, we present a novel TSM approach for enhancing the accuracy of multi-variate signal forecasting in intelligent vehicles. Our method leverages advanced Transformer networks within a relativistic generative adversarial network (RGAN) training framework. The RGAN training framework efficiently improves the accuracy of vehicle states forecasting for IV, demonstrating effective learning of long-time dependencies for more accurate predictions over extended sequences. Additionally, we introduce a high-dimensional extension (HDE) built-in block for the time-series Transformer to explore the impact of higher-dimensional features on representing long-term sequences. The experimental data is collected from a real-world electric vehicle testing bed. We evaluate the proposed RGANFormer framework and the HDE block on two popular time-series models, namely, Autoformer and FiLM. The results demonstrate that the RGANFormer, along with the built-in HDE block, significantly enhances long-term sequential forecasting accuracy for both multivariate and univariate tasks. | |
| dc.format.extent | 3241-3247 | |
| dc.identifier.citation | Xing Y, Kong X, Tsourdos A. (2024) RGANFormer: Relativistic Generative Adversarial Transformer for time-series signal forecasting on intelligent vehicles. In: 2024 IEEE Intelligent Vehicles Symposium (IV), 2-5 June 2024, Jeju Island, Republic of Korea, pp. 3241-3247 | |
| dc.identifier.uri | https://doi.org/10.1109/IV55156.2024.10588746 | |
| dc.identifier.uri | https://dspace.lib.cranfield.ac.uk/handle/1826/22664 | |
| dc.language.iso | en | |
| dc.publisher | IEEE | |
| dc.publisher.uri | https://ieeexplore.ieee.org/document/10588746 | |
| dc.rights | Attribution 4.0 International | en |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | Time-series | |
| dc.subject | generative adversarial network | |
| dc.subject | Transformer | |
| dc.subject | multi-task learning | |
| dc.title | RGANFormer: Relativistic Generative Adversarial Transformer for time-series signal forecasting on intelligent vehicles | |
| dc.type | Conference paper | |
| dcterms.temporal.endDate | 05-Jun-2024 | |
| dcterms.temporal.startDate | 02-Jun-2024 |