Open Access
Time Series Forecasting with Transformer Architectures
Maria Santos
1
,
Ahmed Hassan
2
,
Jan Kowalski
3
,
Anna Lindqvist
4
,
Ahmed Hassan
2
,
Jan Kowalski
3
,
Anna Lindqvist
4
1
University of São Paulo, Brazil
2
Cairo University, Egypt
3
Warsaw University of Technology, Poland
4
KTH Royal Institute of Technology, Sweden
Abstract
This research explores advanced techniques for this research area. We introduce a hybrid model combining advanced algorithms with modern techniques to improve accuracy. Our experiments on diverse datasets demonstrate superior performance compared to existing baseline methods. The proposed framework achieves 36% accuracy on standard benchmark datasets.
Keywords
natural language processing,text mining,sentiment analysis,NLP,transformers
How to Cite
Santos, M., Hassan, A., Kowalski, J., & Lindqvist, A. (2019). Time Series Forecasting with Transformer Architectures. Nivo Light - International Journal of Research & Innovation, 1(3), 6–11. https://doi.org/10.28051/ojstest-12
References
Smith, J., & Brown, A. (2018). Deep learning applications in urban computing. Journal of Smart Cities, 15(3), 234-251.
Wang, L., Chen, H., & Liu, X. (2017). Energy optimization algorithms for intelligent buildings. Energy and Buildings, 142, 45-58.
García, M., Rodriguez, P., & Martinez, S. (2018). Sustainable urban development: A comprehensive review. Sustainability Science, 13(2), 189-205.
Tanaka, K., & Yamamoto, H. (2016). Smart grid technologies and renewable energy integration. IEEE Transactions on Smart Grid, 7(4), 1892-1901.
Anderson, R., Williams, T., & Davis, M. (2017). Machine learning for demand response systems. Applied Energy, 201, 112-125.