Iñigo Bilbao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Iñigo Bilbao has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Eneko Iradier
Department of Communications Engineering, University of the Basque Country, Bilbao, Spain
12 shared publications - Pablo Angueira
Department of Communications Engineering, University of the Basque Country (UPV/EHU), Bilbao, Spain
11 shared publications - Jon Montalban
Department of Communications Engineering, University of the Basque Country (UPV/EHU), Bilbao, Spain
10 shared publications - Lorenzo Fanari
Department of Communications Engineering, University of the Basque Country, Bilbao, Spain
4 shared publications - Rufino Cabrera
Department of Communications Engineering, University of the Basque Country (UPV/EHU), Bilbao, Spain
3 shared publications Jon Montalban
Univ Basque Country UPV EHU, Bilbao, Spain
2 shared publications
Latest Publications
- Open Access
Tiny Neural Receiver: Enabling On-Device Learning for Scalable and Adaptive 6G Devices
The evolution toward 6G communications requires integrating Tiny Machine Learning (TinyML) principles to enable intelligent, energy-efficient, and adaptable signal processing at the network edge. However, current receiver architectures face a fundamental trade-off: classical model-driven designs, while naturally efficient due to their basis in communication theory, lack the flexibility to adapt to varying channel conditions. Meanwhile, fully data-driven deep-learning-based approaches break the stringent resource constraints of TinyML. This paper introduces the tiny neural receiver (TNR), a pioneering architecture that bridges these paradigms by integrating model-based signal processing with lightweight neural optimization to overcome this challenge. The TNR’s primary contribution is its unique hybrid design, which combines the efficiency and interpretability of traditional theory-based receivers with the ability to adapt to different contexts using trainable neural components. This integration occurs within resource budgets that align with TinyML specifications. Experimental results show that the TNR achieves a 5 dB SNR reduction at a target block error rate of . The reported 5 dB SNR gain is a direct result of our resource-aware design framework, which selectively applies lightweight neural optimization to only the most impactful receiver blocks (channel estimation and decoding) to maximize gain without exceeding TinyML complexity limits. This achievement is further supported by an end-to-end training protocol that uses 15,000 iterations of over-the-air data to fine-tune these parameters for the specific static 3.5 GHz propagation channel and OFDM configuration evaluated. Furthermore, the TNR’s modular design enables flexible deployment across a range of 6G scenarios, from mobile broadband to mission-critical IoT. This establishes the TNR as a promising framework for AI-native 6G receivers.Open AccessTiny Neural Receiver: Enabling On-Device Learning for Scalable and Adaptive 6G Devices
The evolution toward 6G communications requires integrating Tiny Machine Learning (TinyML) principles to enable intelligent, energy-efficient, and adaptable signal processing at the network edge. However, current receiver architectures face a fundamental trade-off: classical model-driven designs, while naturally efficient due to their basis in communication theory, lack the flexibility to adapt to varying channel conditions. Meanwhile, fully data-driven deep-learning-based approaches break the stringent resource constraints of TinyML. This paper introduces the tiny neural receiver (TNR), a pioneering architecture that bridges these paradigms by integrating model-based signal processing with lightweight neural optimization to overcome this challenge. The TNR’s primary contribution is its unique hybrid design, which combines the efficiency and interpretability of traditional theory-based receivers with the ability to adapt to different contexts using trainable neural components. This integration occurs within resource budgets that align with TinyML specifications. Experimental results show that the TNR achieves a 5 dB SNR reduction at a target block error rate of . The reported 5 dB SNR gain is a direct result of our resource-aware design framework, which selectively applies lightweight neural optimization to only the most impactful receiver blocks (channel estimation and decoding) to maximize gain without exceeding TinyML complexity limits. This achievement is further supported by an end-to-end training protocol that uses 15,000 iterations of over-the-air data to fine-tune these parameters for the specific static 3.5 GHz propagation channel and OFDM configuration evaluated. Furthermore, the TNR’s modular design enables flexible deployment across a range of 6G scenarios, from mobile broadband to mission-critical IoT. This establishes the TNR as a promising framework for AI-native 6G receivers. - Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 7, 2761-2772
A Non-Coherent Distributed Massive Multi Antenna System Under Rician Propagation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 7, 2761-2772
Open AccessA Non-Coherent Distributed Massive Multi Antenna System Under Rician Propagation
- Open Access
- 21 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 11 (6) , 3913-3925
CNN-Aided Self-Interference Estimation for In-Band Full-Duplex Systems
Modern radio access technologies approach Shannon’s limit, necessitating innovative methods for enhanced spectral efficiency. In-band full-duplex (IBFD) can double the spectral efficiency, enabling simultaneous transmission and reception over the same time-frequency resource. IBFD faces the challenge of self-interference, which has to be canceled by up to 100 dB. This paper estimates the loopback channel through convolutional neural networks (CNNs), which leverage the natural signal structure of wireless channels, effectively mapping time-frequency features. We test the method via simulations in two measured channels, showing cancellations of up to 52 dB.
- 21 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 11 (6) , 3913-3925
Open AccessCNN-Aided Self-Interference Estimation for In-Band Full-Duplex Systems
Modern radio access technologies approach Shannon’s limit, necessitating innovative methods for enhanced spectral efficiency. In-band full-duplex (IBFD) can double the spectral efficiency, enabling simultaneous transmission and reception over the same time-frequency resource. IBFD faces the challenge of self-interference, which has to be canceled by up to 100 dB. This paper estimates the loopback channel through convolutional neural networks (CNNs), which leverage the natural signal structure of wireless channels, effectively mapping time-frequency features. We test the method via simulations in two measured channels, showing cancellations of up to 52 dB.
- 19 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Broadcasting
- Vol. 70 (4) , 1181-1191
Enhancing Channel Estimation in Terrestrial Broadcast Communications Using Machine Learning
Artificial Intelligence (AI) and Machine Learning (ML) approaches have emerged as viable alternatives to conventional Physical Layer (PHY) signal processing methods. Specifically, in any wireless point-to-multipoint communication, accurate channel estimation plays a pivotal role in exploiting spectrum efficiency with functionalities such as higher-order modulation or full-duplex communication. This research paper proposes leveraging ML solutions, including Convolutional Neural Networks (CNNs) and Multilayer Perceptrons (MLPs), to enhance channel estimation within broadcast environments. Each architecture is instantiated using distinct procedures, focusing on two fundamental approaches: channel estimation denoising and ML-assisted pilot interpolation. Rigorous evaluations are conducted across diverse configurations and conditions, spanning rural areas and co-channel interference scenarios. The results demonstrate that MLP and CNN architectures consistently outperform classical methods, yielding 10 and 20 dB performance improvements, respectively. These results underscore the efficacy of ML-driven approaches in advancing channel estimation capabilities for broadcast communication systems.
- 19 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Broadcasting
- Vol. 70 (4) , 1181-1191
Enhancing Channel Estimation in Terrestrial Broadcast Communications Using Machine Learning
Artificial Intelligence (AI) and Machine Learning (ML) approaches have emerged as viable alternatives to conventional Physical Layer (PHY) signal processing methods. Specifically, in any wireless point-to-multipoint communication, accurate channel estimation plays a pivotal role in exploiting spectrum efficiency with functionalities such as higher-order modulation or full-duplex communication. This research paper proposes leveraging ML solutions, including Convolutional Neural Networks (CNNs) and Multilayer Perceptrons (MLPs), to enhance channel estimation within broadcast environments. Each architecture is instantiated using distinct procedures, focusing on two fundamental approaches: channel estimation denoising and ML-assisted pilot interpolation. Rigorous evaluations are conducted across diverse configurations and conditions, spanning rural areas and co-channel interference scenarios. The results demonstrate that MLP and CNN architectures consistently outperform classical methods, yielding 10 and 20 dB performance improvements, respectively. These results underscore the efficacy of ML-driven approaches in advancing channel estimation capabilities for broadcast communication systems.
- Open Access
- 21 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 5, 3753-3761
Deep Unfolding-Powered Analog Beamforming for In-Band Full-Duplex
In-band full-duplex (IBFD) can double the spectral efficiency of wireless communications systems. However, its major drawback is the self-interference, which interferes with the desired signal at the terminal. Self-interference cancellation can be operated in antenna, analog, and digital domains. In the antenna domain, beamformers are designed to minimize the leaked signal entering the system. This paper proposes an efficient analog beamforming design to maximize the channel achievable rate of massive multiple-input multiple-output (MIMO) IBFD systems. Specifically, we propose a low-complexity deep unfolding technique that provides a significantly better achievable rate than the state-of-the-art to deal with the non-convex design objective and constraints. More concretely, a complexity reduction of 75% is achieved for some scenarios, and of 50% is reached for the rest.
- 21 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 5, 3753-3761
Open AccessDeep Unfolding-Powered Analog Beamforming for In-Band Full-Duplex
In-band full-duplex (IBFD) can double the spectral efficiency of wireless communications systems. However, its major drawback is the self-interference, which interferes with the desired signal at the terminal. Self-interference cancellation can be operated in antenna, analog, and digital domains. In the antenna domain, beamformers are designed to minimize the leaked signal entering the system. This paper proposes an efficient analog beamforming design to maximize the channel achievable rate of massive multiple-input multiple-output (MIMO) IBFD systems. Specifically, we propose a low-complexity deep unfolding technique that provides a significantly better achievable rate than the state-of-the-art to deal with the non-convex design objective and constraints. More concretely, a complexity reduction of 75% is achieved for some scenarios, and of 50% is reached for the rest.
- Open Access
- 28 April 2024
- Published by Elsevier in Measurement
- Vol. 234
Characterizing in-band full-duplex in broadcast communications: From field trials to a loopback channel model
- 28 April 2024
- Published by Elsevier in Measurement
- Vol. 234
Open AccessCharacterizing in-band full-duplex in broadcast communications: From field trials to a loopback channel model
- Open Access
- 13 February 2024
- Published by Elsevier in Ad Hoc Networks
- Vol. 158
Optimized IEEE 802.11ax for smart warehouses
- 13 February 2024
- Published by Elsevier in Ad Hoc Networks
- Vol. 158
Open AccessOptimized IEEE 802.11ax for smart warehouses
- 22 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Broadcasting
- Vol. 69 (2) , 569-578
Signal Isolation Characterization of ITCN In-Band Full-Duplex Communications
Future digital terrestrial television (DTT) systems are introducing revolutionary changes to their architectures and operation modes. One of the best examples is ATSC 3.0, which is pushing to incorporate the Internet Protocol (IP) into the protocol stack. This way, implementing new applications (e.g., target advertisement, connected cars, 4k/8k video content) is closer than ever. Indeed, recent works have suggested designing and implementing an Inter-Tower Communications Network (ITCN) and wireless In-band Distribution Link (IDL) inside the ATSC 3.0 forums. ITCN will interconnect all broadcast towers to form a communication network for control, monitoring, data communication, and localized datacast and broadcast services. Nevertheless, this application has a significant challenge: the self-interference (SI) or loopback signal that is generated and added to the received signal. To reduce the impact of the SI, the transmission centers combine different signal isolation and cancellation techniques. This paper focuses on characterizing the signal power isolation between the transmitted and the received signals under different conditions. In particular, this paper shows the signal isolation values measured during various field trials in real broadcast transmission centers. The results show that the total signal isolation varies depending on the transmission/reception configuration between 70-90 dB. Moreover, due to the measurements, we have demonstrated that the antenna distance is a more relevant parameter for signal isolation than the center frequency. Finally, the possible antenna pattern discrimination has been calculated and discussed.
- 22 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Broadcasting
- Vol. 69 (2) , 569-578
Signal Isolation Characterization of ITCN In-Band Full-Duplex Communications
Future digital terrestrial television (DTT) systems are introducing revolutionary changes to their architectures and operation modes. One of the best examples is ATSC 3.0, which is pushing to incorporate the Internet Protocol (IP) into the protocol stack. This way, implementing new applications (e.g., target advertisement, connected cars, 4k/8k video content) is closer than ever. Indeed, recent works have suggested designing and implementing an Inter-Tower Communications Network (ITCN) and wireless In-band Distribution Link (IDL) inside the ATSC 3.0 forums. ITCN will interconnect all broadcast towers to form a communication network for control, monitoring, data communication, and localized datacast and broadcast services. Nevertheless, this application has a significant challenge: the self-interference (SI) or loopback signal that is generated and added to the received signal. To reduce the impact of the SI, the transmission centers combine different signal isolation and cancellation techniques. This paper focuses on characterizing the signal power isolation between the transmitted and the received signals under different conditions. In particular, this paper shows the signal isolation values measured during various field trials in real broadcast transmission centers. The results show that the total signal isolation varies depending on the transmission/reception configuration between 70-90 dB. Moreover, due to the measurements, we have demonstrated that the antenna distance is a more relevant parameter for signal isolation than the center frequency. Finally, the possible antenna pattern discrimination has been calculated and discussed.
- Open Access
- 19 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Industrial Electronics Society
- Vol. 4, 1-13
Sparse Vector Coding for Short-Packet Transmission on Industrial Communications: Reference Architecture and Design Challenges
Reliable, fast, and deterministic communications are fundamental for future industrial wireless systems. This goal requires multiple cooperating technologies that pertain to different areas of the communication arena. The weight of the waveform and coding technique choices are critical to match industrial use cases' reliability and latency requirements. Specifically, this paper contributes to the field of channel coding in wireless fieldbus links. Classical block coding schemes were designed to maximize information bitrates without stringent latency requirements. Their performance in applications that use short messages degrades significantly. Recently, Sparse Vector Coding (SVC) has been proposed as a coding approach suitable for short packet communications with moderate complexity and low processing latency. This paper presents a comprehensive analysis of sparse vector coding and a reference communications framework for its implementation on a wireless system. A set of simulations is also designed to establish the cross-correlation between the different parameters involved in the code design. As a result, the coding matrix has been identified as a critical parameter that can improve coding performance. In addition, this work includes two new procedures for determining the matrix that could lead to a gain of up to 2dB with respect to the current state of the art.
- 19 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Industrial Electronics Society
- Vol. 4, 1-13
Open AccessSparse Vector Coding for Short-Packet Transmission on Industrial Communications: Reference Architecture and Design Challenges
Reliable, fast, and deterministic communications are fundamental for future industrial wireless systems. This goal requires multiple cooperating technologies that pertain to different areas of the communication arena. The weight of the waveform and coding technique choices are critical to match industrial use cases' reliability and latency requirements. Specifically, this paper contributes to the field of channel coding in wireless fieldbus links. Classical block coding schemes were designed to maximize information bitrates without stringent latency requirements. Their performance in applications that use short messages degrades significantly. Recently, Sparse Vector Coding (SVC) has been proposed as a coding approach suitable for short packet communications with moderate complexity and low processing latency. This paper presents a comprehensive analysis of sparse vector coding and a reference communications framework for its implementation on a wireless system. A set of simulations is also designed to establish the cross-correlation between the different parameters involved in the code design. As a result, the coding matrix has been identified as a critical parameter that can improve coding performance. In addition, this work includes two new procedures for determining the matrix that could lead to a gain of up to 2dB with respect to the current state of the art.
- Open Access
- 4 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Industrial Electronics Society
- Vol. 3, 674-699
A Survey on FEC Techniques for Industrial Wireless Communications
Industry 4.0 aims to digitize industrial processes entirely, and wireless technologies represent one of the enablers for scalable and flexible communications. However, the current standards and proprietary solutions do not meet the industry's tight requirements in fundamental use cases such as Factory Automation (FA). One of the key research challenges towards replacing wired fieldbuses with wireless links is the design of techniques that enable real-time and deterministic behavior when transmitting short packets. Forward Error Correction (FEC) techniques are critical to this objective, and coding/decoding algorithms must comply with reliability and low latency specifications. This paper surveys existing FEC techniques for short packet transmissions. Compared to other survey papers in the field, we propose several FEC candidate techniques specifically suitable for FA wireless systems. We explore four of these techniques, also examining hardware architecture proposals. The paper proposes a methodology to evaluate their latency and reliability performance. We finally discuss the lessons learned and challenges for future research.
- 4 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Industrial Electronics Society
- Vol. 3, 674-699
Open AccessA Survey on FEC Techniques for Industrial Wireless Communications
Industry 4.0 aims to digitize industrial processes entirely, and wireless technologies represent one of the enablers for scalable and flexible communications. However, the current standards and proprietary solutions do not meet the industry's tight requirements in fundamental use cases such as Factory Automation (FA). One of the key research challenges towards replacing wired fieldbuses with wireless links is the design of techniques that enable real-time and deterministic behavior when transmitting short packets. Forward Error Correction (FEC) techniques are critical to this objective, and coding/decoding algorithms must comply with reliability and low latency specifications. This paper surveys existing FEC techniques for short packet transmissions. Compared to other survey papers in the field, we propose several FEC candidate techniques specifically suitable for FA wireless systems. We explore four of these techniques, also examining hardware architecture proposals. The paper proposes a methodology to evaluate their latency and reliability performance. We finally discuss the lessons learned and challenges for future research.