Fábio D. L. Coutinho
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fábio D. L. Coutinho has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Arnaldo Silva Rodrigues Oliveira
Instituto de Telecomunicaes, Universidade de Aveiro, Aveiro, Portugal
6 shared publications - Hugerles Sales Silva
University of Brasilia (UnB)
4 shared publications - Petia Georgieva
Department of Electronics Telecommunications and Informatics, Institute of Electronics and Informatics Engineering of Aveiro (IEETA), University of Aveiro, 3800-193 Aveiro, Portugal
4 shared publications - Samuel Santos Pereira
Instituto de Telecomunicaes, Universidade de Aveiro, Campus Universitrio de Santiago, Aveiro, Portugal
2 shared publications - Thalles M. Moreira
Instituto de Telecomunicações
2 shared publications - Bruno M. S. Teixeira
Instituto de Telecomunicações
1 shared publication
Latest Publications
- Open Access
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 46-50
Transfer Learning-Based Channel Estimation Supported by FPGA Dynamic Reconfiguration
This letter presents a novel framework for deploying transfer learning (TL) at the network edge using field-programmable gate array (FPGA) partial reconfiguration. While deep learning (DL) algorithms can already be implemented, the flexible and dynamic modification of their architectures has been a constraint for TL fulfillment in the network edge. The proposed framework enables updates of DL architectures while ensuring uninterrupted operation of the core system. To demonstrate the efficacy of the approach, a case study focusing on TL in channel estimation is conducted. The study involves modifying the convolutional neural network (CNN) architecture to accommodate a scenario change. The proposed framework optimizes resource utilization by 20%, approximately, and achieves a reconfiguration process time of 28 ms, approximately. The results highlight the robustness and versatility of the TL-oriented implementation approach in handling dynamic DL architecture modifications.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 46-50
Open AccessTransfer Learning-Based Channel Estimation Supported by FPGA Dynamic Reconfiguration
This letter presents a novel framework for deploying transfer learning (TL) at the network edge using field-programmable gate array (FPGA) partial reconfiguration. While deep learning (DL) algorithms can already be implemented, the flexible and dynamic modification of their architectures has been a constraint for TL fulfillment in the network edge. The proposed framework enables updates of DL architectures while ensuring uninterrupted operation of the core system. To demonstrate the efficacy of the approach, a case study focusing on TL in channel estimation is conducted. The study involves modifying the convolutional neural network (CNN) architecture to accommodate a scenario change. The proposed framework optimizes resource utilization by 20%, approximately, and achieves a reconfiguration process time of 28 ms, approximately. The results highlight the robustness and versatility of the TL-oriented implementation approach in handling dynamic DL architecture modifications.
- Open Access
- 29 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
A Quantization-Aware DL-based Channel Estimation Algorithm for OFDM Systems
This paper proposes a quantization-aware deep learning (DL)-based channel estimation algorithm for orthogonal frequency-division multiplexing (OFDM) systems under varying effective number of bits (ENOB) configurations. The algorithm addresses two key aspects: generalization in both channel conditions and analog-to-digital converter (ADC) resolutions, and mitigation of quantization noise. Generalization is achieved during the training phase by utilizing a dataset that includes multiple channel realizations across different ADC resolutions. Regarding quantization noise mitigation, the algorithm uses medium- to high- resolution data as target labels during offline training to learn the corresponding ENOBs indirect mapping. This approach enables improved channel estimation accuracy and enhances end-to-end system performance in terms of mean square error (MSE) and bit error rate (BER). Test results demonstrate consistent improvements both locally and globally across ENOBs configurations, with validation conducted in an indoor over-the-air (OTA) scenario to confirm real-world applicability. To the best of the authors’ knowledge, this is the first work to address the mitigation of ADC quantization noise in the channel estimation process without relying on medium- to high- resolution data during inference, while ensuring algorithm generalization across multiple channel realizations and varying ENOB configurations.
- 29 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
Open AccessA Quantization-Aware DL-based Channel Estimation Algorithm for OFDM Systems
This paper proposes a quantization-aware deep learning (DL)-based channel estimation algorithm for orthogonal frequency-division multiplexing (OFDM) systems under varying effective number of bits (ENOB) configurations. The algorithm addresses two key aspects: generalization in both channel conditions and analog-to-digital converter (ADC) resolutions, and mitigation of quantization noise. Generalization is achieved during the training phase by utilizing a dataset that includes multiple channel realizations across different ADC resolutions. Regarding quantization noise mitigation, the algorithm uses medium- to high- resolution data as target labels during offline training to learn the corresponding ENOBs indirect mapping. This approach enables improved channel estimation accuracy and enhances end-to-end system performance in terms of mean square error (MSE) and bit error rate (BER). Test results demonstrate consistent improvements both locally and globally across ENOBs configurations, with validation conducted in an indoor over-the-air (OTA) scenario to confirm real-world applicability. To the best of the authors’ knowledge, this is the first work to address the mitigation of ADC quantization noise in the channel estimation process without relying on medium- to high- resolution data during inference, while ensuring algorithm generalization across multiple channel realizations and varying ENOB configurations.
- 28 June 2025
- Published by Springer Nature
- p. 124-136
Understanding Signal Feature Impact in CNN-Based Modulation Classification with Realistic Datasets
- 28 June 2025
- Published by Springer Nature
- p. 124-136
Understanding Signal Feature Impact in CNN-Based Modulation Classification with Realistic Datasets
- Open Access
- 25 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 147-155
AI Frameworks and DL Processing Units Performance Evaluation for CNN-Based Real-Time RF Modulation Classification
- 25 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 147-155
Open AccessAI Frameworks and DL Processing Units Performance Evaluation for CNN-Based Real-Time RF Modulation Classification
- 17 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 13 (1) , 193-197
A Novel CNN-Based Channel Estimation Algorithm in the Presence of Phase Noise and CFO
In this work, we propose a convolutional neural network (CNN)-based algorithm for channel estimation in the presence of phase noise and carrier frequency offset (CFO) in fifth-generation (5G) and beyond systems. The migration of these networks to high-frequency bands, such as millimeter waves, presents significant challenges due to the unsatisfactory performance of local oscillators, resulting in hardware impairments like phase noise and CFO. Additionally, in these scenarios, the presence of intercarrier interference (ICI) imposed by these issues becomes more pronounced, posing limitations on channel estimation. To address this issue, we propose a new algorithm that simultaneously considers the imposed ICI regarding phase noise and CFO when estimating the channel gain based on received pilot subcarriers. The quality of the CNN’s predictions for channel estimation is assessed using mean square error, which showed a considerable improvement in end-to-end system performance, measured by bit error rate. Our proposed approach is compared to the least squares method, the optimum least minimum mean-square error estimator, and the typical deep learning (DL) algorithm with two state-of-the-art CNN architectures. To the best of our knowledge, this is the first work that addresses channel estimation in the presence of phase noise and CFO using a CNN-based algorithm.
- 17 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 13 (1) , 193-197
A Novel CNN-Based Channel Estimation Algorithm in the Presence of Phase Noise and CFO
In this work, we propose a convolutional neural network (CNN)-based algorithm for channel estimation in the presence of phase noise and carrier frequency offset (CFO) in fifth-generation (5G) and beyond systems. The migration of these networks to high-frequency bands, such as millimeter waves, presents significant challenges due to the unsatisfactory performance of local oscillators, resulting in hardware impairments like phase noise and CFO. Additionally, in these scenarios, the presence of intercarrier interference (ICI) imposed by these issues becomes more pronounced, posing limitations on channel estimation. To address this issue, we propose a new algorithm that simultaneously considers the imposed ICI regarding phase noise and CFO when estimating the channel gain based on received pilot subcarriers. The quality of the CNN’s predictions for channel estimation is assessed using mean square error, which showed a considerable improvement in end-to-end system performance, measured by bit error rate. Our proposed approach is compared to the least squares method, the optimum least minimum mean-square error estimator, and the typical deep learning (DL) algorithm with two state-of-the-art CNN architectures. To the best of our knowledge, this is the first work that addresses channel estimation in the presence of phase noise and CFO using a CNN-based algorithm.
- 18 February 2022
- Published by Elsevier in Digital Signal Processing
- Vol. 126
5G cascaded channel estimation using convolutional neural networks
- 18 February 2022
- Published by Elsevier in Digital Signal Processing
- Vol. 126
5G cascaded channel estimation using convolutional neural networks