| Grant number: | 25/16322-4 |
| Support Opportunities: | Scholarships in Brazil - Scientific Initiation |
| Start date: | October 01, 2025 |
| End date: | September 30, 2026 |
| Field of knowledge: | Engineering - Electrical Engineering - Telecommunications |
| Principal Investigator: | Cintya Wink de Oliveira Benedito |
| Grantee: | Paulo Cesar Negreiros Domenciano |
| Host Institution: | Faculdade de Engenharia. Universidade Estadual Paulista (UNESP). Campus São João da Boa Vista. São João da Boa Vista , SP, Brazil |
Abstract The continuous evolution of mobile networks, currently in 5G and moving towards 5G-Advanced and, in the future, 6G, imposes increasingly strict requirements, especially related to reliability and latency. Polar codes and LDPC (Low-Density Parity-Check) codes are block-type error-correcting codes, with encoding and decoding algorithms that leverage various algebraic and computational concepts. These channel coding strategies are specified in current 5G standards, and possibly in future advancements, but they face an ongoing trade-off between achieving performance metrics and reducing computational complexity in their decoding algorithms. Machine Learning (ML) approaches emerge as a powerful tool to overcome such limitations. In this project, we propose the development and analysis of ML architectures to optimize the encoding and decoding processes of polar and LDPC codes in 5G-Advanced scenarios. In this undergraduate research project, we aim to design and evaluate code construction strategies using Reinforcement Learning (RL), as well as decoders based on Recurrent Neural Networks (RNN), with the goal of obtaining models that are more efficient and adaptable than those traditionally used without associated ML techniques. (AU) | |
| News published in Agência FAPESP Newsletter about the scholarship: | |
| More itemsLess items | |
| TITULO | |
| Articles published in other media outlets ( ): | |
| More itemsLess items | |
| VEICULO: TITULO (DATA) | |
| VEICULO: TITULO (DATA) | |