Guido Montorsi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Guido Montorsi has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Sergio Benedetto
IEEE-USA
4 shared publications - Farbod Kayhan
Interdisciplinary Centre for Security, Reliability and Trust (SnT) University of Luxembourg
3 shared publications - Alexandre Graelli Amat
Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden
2 shared publications - Andrea Modenini
Università di Parma, Dipartimento di Ingegneria dell'Informazione, Parco Area delle Scienze 181/A, ITALY
2 shared publications - Barbara Ripani
Politecnico di Torino, Department of Electronics and Telecommunications (DET), Torino, Italy
2 shared publications - Farbod Kayhan
Politecnico di Torino Dipartimento di Elettronica e Telecomunicazioni 10129 Torino Italy
2 shared publications
Latest Publications
- Open Access
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 9561-9574
The Trainable BCJR and Its Applications
We propose a trainable version of the Additive Bahl-Cocke-Jelinek-Raviv (A-BCJR) algorithm by interpreting it as a Recurrent Neural Network (RNN). By leveraging the smoothness and differentiability of the max* operator, the core component of the A-BCJR forward and backward recursions, we derive a backpropagation algorithm that enables end-to-end training from the network’s output. The resulting model, referred to as T-BCJR, comprises a linear layer that computes edge metrics from state and input metrics, followed by a nonlinear max* layer that marginalizes these metrics back to the state and output domains. We further derive the corresponding delta backpropagation recursions, which exhibit a structural symmetry with the original forward-backward predictive steps. Unlike prior approaches that only replaced memoryless metric units in BCJR or Viterbi algorithms with Neural Networks (NNs), T-BCJR enables full trainability of the entire recursive structure. We derive a trainable detector, termed T-Detector, by connecting the T-BCJR to the channel output via an additional convolutional linear layer that emulates a channel shortening filter. The T-Detector can be trained to operate as a modulation- and channel-agnostic detector, capable of performing channel shortening, Maximum Likelihood (ML) sequence detection, and the computation of symbol-level or bit-level Log-Likelihoods (LLs) for soft-input decoding. Moreover, it is compatible with iterative receiver schemes involving outer channel decoders. The predictive step of the T-Detector maintains the same Digital Signal Processing (DSP) complexity as a conventional model-based detector, with the added benefit of being trainable from a cost function defined on the generated LLs. Experimental results demonstrate that the T-Detector can be trained to match the performance of the corresponding model-based detector for static and slow-time varying channels with appropriate pilot densities.
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 9561-9574
Open AccessThe Trainable BCJR and Its Applications
We propose a trainable version of the Additive Bahl-Cocke-Jelinek-Raviv (A-BCJR) algorithm by interpreting it as a Recurrent Neural Network (RNN). By leveraging the smoothness and differentiability of the max* operator, the core component of the A-BCJR forward and backward recursions, we derive a backpropagation algorithm that enables end-to-end training from the network’s output. The resulting model, referred to as T-BCJR, comprises a linear layer that computes edge metrics from state and input metrics, followed by a nonlinear max* layer that marginalizes these metrics back to the state and output domains. We further derive the corresponding delta backpropagation recursions, which exhibit a structural symmetry with the original forward-backward predictive steps. Unlike prior approaches that only replaced memoryless metric units in BCJR or Viterbi algorithms with Neural Networks (NNs), T-BCJR enables full trainability of the entire recursive structure. We derive a trainable detector, termed T-Detector, by connecting the T-BCJR to the channel output via an additional convolutional linear layer that emulates a channel shortening filter. The T-Detector can be trained to operate as a modulation- and channel-agnostic detector, capable of performing channel shortening, Maximum Likelihood (ML) sequence detection, and the computation of symbol-level or bit-level Log-Likelihoods (LLs) for soft-input decoding. Moreover, it is compatible with iterative receiver schemes involving outer channel decoders. The predictive step of the T-Detector maintains the same Digital Signal Processing (DSP) complexity as a conventional model-based detector, with the added benefit of being trainable from a cost function defined on the generated LLs. Experimental results demonstrate that the T-Detector can be trained to match the performance of the corresponding model-based detector for static and slow-time varying channels with appropriate pilot densities.
- 22 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 2040-2044
Digital PLLs for Phase Noise Channels: A Concept Based on the Tikhonov Distribution
We explore the concept of a digital phase-locked loop (PLL) of the first type, derived as an alternative solution to Kalman's estimation problem by employing the Tikhonov distribution rather than the traditional Gaussian model. The resulting Tikhonov PLL is a complex-valued nonlinear filter that is simple to implement and demonstrates interesting features in channels affected by strong phase noise. We present a comparative analysis including the classical PLL and Kalman filter to highlight the strengths of the Tikhonov PLL in such contexts.
- 22 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 2040-2044
Digital PLLs for Phase Noise Channels: A Concept Based on the Tikhonov Distribution
We explore the concept of a digital phase-locked loop (PLL) of the first type, derived as an alternative solution to Kalman's estimation problem by employing the Tikhonov distribution rather than the traditional Gaussian model. The resulting Tikhonov PLL is a complex-valued nonlinear filter that is simple to implement and demonstrates interesting features in channels affected by strong phase noise. We present a comparative analysis including the classical PLL and Kalman filter to highlight the strengths of the Tikhonov PLL in such contexts.
- Open Access
- 29 September 2022
- Published by MDPI AG in Electronics
- Vol. 11 (19) , 3130
Single-Frequency Network Terrestrial Broadcasting with 5GNR Numerology Using Recurrent Neural Network
We explore the feasibility of Terrestrial Broadcasting in a Single-Frequency Network (SFN) with standard 5G New Radio (5GNR) numerology designed for uni-cast transmission. Instead of the classical OFDM symbol-by-symbol detector scheme or a more complex equalization technique, we designed a Recurrent-Neural-Network (RNN)-based detector that replaces the channel estimation and equalization blocks. The RNN is a bidirectional Long Short-Term Memory (bi-LSTM) that computes the log-likelihood ratios delivered to the LDPC decoder starting from the received symbols affected by strong intersymbol/intercarrier interference (ISI/ICI) on time-varying channels. To simplify the RNN receiver and reduce the system overhead, pilot and data signals in our proposed scheme are superimposed instead of interspersed. We describe the parameter optimization of the RNN and provide end-to-end simulation results, comparing them with those of a classical system, where the OFDM waveform is specifically designed for Terrestrial Broadcasting. We show that the system outperforms classical receivers, especially in challenging scenarios associated with large intersite distance and large mobility. We also provide evidence of the robustness of the designed RNN receiver, showing that an RNN receiver trained on a single signal-to-noise ratio and user velocity performs efficiently also in a large range of scenarios with different signal-to-noise ratios and velocities.
- 29 September 2022
- Published by MDPI AG in Electronics
- Vol. 11 (19) , 3130
Open AccessSingle-Frequency Network Terrestrial Broadcasting with 5GNR Numerology Using Recurrent Neural Network
We explore the feasibility of Terrestrial Broadcasting in a Single-Frequency Network (SFN) with standard 5G New Radio (5GNR) numerology designed for uni-cast transmission. Instead of the classical OFDM symbol-by-symbol detector scheme or a more complex equalization technique, we designed a Recurrent-Neural-Network (RNN)-based detector that replaces the channel estimation and equalization blocks. The RNN is a bidirectional Long Short-Term Memory (bi-LSTM) that computes the log-likelihood ratios delivered to the LDPC decoder starting from the received symbols affected by strong intersymbol/intercarrier interference (ISI/ICI) on time-varying channels. To simplify the RNN receiver and reduce the system overhead, pilot and data signals in our proposed scheme are superimposed instead of interspersed. We describe the parameter optimization of the RNN and provide end-to-end simulation results, comparing them with those of a classical system, where the OFDM waveform is specifically designed for Terrestrial Broadcasting. We show that the system outperforms classical receivers, especially in challenging scenarios associated with large intersite distance and large mobility. We also provide evidence of the robustness of the designed RNN receiver, showing that an RNN receiver trained on a single signal-to-noise ratio and user velocity performs efficiently also in a large range of scenarios with different signal-to-noise ratios and velocities.
- 29 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 58 (6) , 5373-5381
On the Use of PN Ranging With High-Rate Spectrally-Efficient Modulations in Satellite Payload Telemetry Links
Pseudo Noise (PN) ranging is a ranging technique that has been recently introduced in near-Earth space research (SR) missions. For these, at the state-of-the-art, the PN ranging signal is combined with a high-rate telemetry stream binary modulated in phase. The coupling of the two, together with the 10 MHz bandwidth constraint imposed for this class of missions, translates into a data rate bound of approximately 10 Mbps. The purpose of this article is to prove the feasibility of overcoming the current data rate limitation by defining a communication architecture that foresees the coupling of the PN ranging signal with a high-order modulated telemetry stream. To achieve the goal, we study the feasibility of pairing the PN ranging with filtered high-order modulations in satellite payload telemetry links and investigate the simultaneous demodulation of the telemetry stream while tracking the ranging sequence. Accordingly, we design a receiver scheme that is able to perform a closed-loop parallel cancellation of the ranging and the telemetry signal, reciprocally. From our analysis, we find that the non-constant envelope property, characterizing the considered modulation set, causes an additional jitter on the PN ranging timing estimation that, on the other hand, can be controlled and reduced by properly sizing the receiver loop bandwidth, without limiting the timing synchronization dynamic. Our study proves that the use of filtered high-order modulations combined with PN ranging outperforms the state-of-the-art in terms of spectral efficiency and achievable data rate while having comparable ranging performance.
- 29 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 58 (6) , 5373-5381
On the Use of PN Ranging With High-Rate Spectrally-Efficient Modulations in Satellite Payload Telemetry Links
Pseudo Noise (PN) ranging is a ranging technique that has been recently introduced in near-Earth space research (SR) missions. For these, at the state-of-the-art, the PN ranging signal is combined with a high-rate telemetry stream binary modulated in phase. The coupling of the two, together with the 10 MHz bandwidth constraint imposed for this class of missions, translates into a data rate bound of approximately 10 Mbps. The purpose of this article is to prove the feasibility of overcoming the current data rate limitation by defining a communication architecture that foresees the coupling of the PN ranging signal with a high-order modulated telemetry stream. To achieve the goal, we study the feasibility of pairing the PN ranging with filtered high-order modulations in satellite payload telemetry links and investigate the simultaneous demodulation of the telemetry stream while tracking the ranging sequence. Accordingly, we design a receiver scheme that is able to perform a closed-loop parallel cancellation of the ranging and the telemetry signal, reciprocally. From our analysis, we find that the non-constant envelope property, characterizing the considered modulation set, causes an additional jitter on the PN ranging timing estimation that, on the other hand, can be controlled and reduced by properly sizing the receiver loop bandwidth, without limiting the timing synchronization dynamic. Our study proves that the use of filtered high-order modulations combined with PN ranging outperforms the state-of-the-art in terms of spectral efficiency and achievable data rate while having comparable ranging performance.
- Open Access
Code Design for Non-Coherent Detection of Frame Headers in Precoded Satellite Systems
In this paper we propose a simple method for generating short-length rate-compatible codes over $\mathbb{Z}_M$ that are robust to non-coherent detection for $M$-PSK constellations. First, a greedy algorithm is used to construct a family of rotationally invariant codes for a given constellation. Then, by properly modifying such codes we obtain codes that are robust to non-coherent detection. We briefly discuss the optimality of the constructed codes for special cases of BPSK and QPSK constellations. Our method provides an upper bound for the length of optimal codes with a given desired non-coherent distance. We also derive a simple asymptotic upper bound on the frame error rate (FER) of such codes and provide the simulation results for a selected set of proposed codes. Finally, we briefly discuss the problem of designing binary codes that are robust to non-coherent detection for QPSK constellation.Open AccessCode Design for Non-Coherent Detection of Frame Headers in Precoded Satellite Systems
In this paper we propose a simple method for generating short-length rate-compatible codes over $\mathbb{Z}_M$ that are robust to non-coherent detection for $M$-PSK constellations. First, a greedy algorithm is used to construct a family of rotationally invariant codes for a given constellation. Then, by properly modifying such codes we obtain codes that are robust to non-coherent detection. We briefly discuss the optimality of the constructed codes for special cases of BPSK and QPSK constellations. Our method provides an upper bound for the length of optimal codes with a given desired non-coherent distance. We also derive a simple asymptotic upper bound on the frame error rate (FER) of such codes and provide the simulation results for a selected set of proposed codes. Finally, we briefly discuss the problem of designing binary codes that are robust to non-coherent detection for QPSK constellation. - 8 February 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 36 (2) , 327-337
Next Generation High-Rate Telemetry
Recent investigations show that high-rate telemetry systems, based on the CCSDS 131.2-B-1 standard and employed in Earth observation missions, do not fully exploit the available capacity. We thus propose and discuss possible ways to improve the data return of these systems that can be considered for a revision of the current standard. Some of them are represented by a revision and/or an extension of the currently adopted modulation and coding formats. The remaining techniques are related to an enhancement of the transceiver architecture. Different bandwidth allocation strategies are also considered. The benefits of the proposed techniques are assessed by means of computer simulations with reference to a realistic scenario where a real nonlinear amplifier, real filters, and real impairments are considered.
- 8 February 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 36 (2) , 327-337
Next Generation High-Rate Telemetry
Recent investigations show that high-rate telemetry systems, based on the CCSDS 131.2-B-1 standard and employed in Earth observation missions, do not fully exploit the available capacity. We thus propose and discuss possible ways to improve the data return of these systems that can be considered for a revision of the current standard. Some of them are represented by a revision and/or an extension of the currently adopted modulation and coding formats. The remaining techniques are related to an enhancement of the transceiver architecture. Different bandwidth allocation strategies are also considered. The benefits of the proposed techniques are assessed by means of computer simulations with reference to a realistic scenario where a real nonlinear amplifier, real filters, and real impairments are considered.
- Open Access
Low Complexity Two-Stage Soft/Hard Decoders
Next generation wireless systems will need higher spectral efficiency as the expected traffic volumes per unit bandwidth and dimension will inevitably grow. As a consequence, it is necessary to design coding schemes with performances close to the theoretical limits, having high flexibility and low complexity requirements at transmitter and receiver. In this paper, we point out some of the limitations of the Bit Interleaved Code Modulation (BICM) technique which is the state of the art adopted in several standards and then propose some new lower complexity alternatives. These low complexity alternatives are obtained by applying the recently introduced Analog Digital Belief Propagation (ADBP) algorithm to a two stage encoding scheme embedding a hard decoding stage. First we show that for PAM$^2$ type constellations over the AWGN channel, the performance loss caused by using a hard decoded stage for all modulation bits except the two least protected is negligible. Next, we consider the application of two stage decoders to more challenging Rician channels, showing that in this case the number of bits needed to be soft decoded depends on the Rician factor and increases to a maximum of three bits per dimension for the Rayleigh channel. Finally, we apply the ADBP algorithm to further reduce the detection and decoding complexity.
Open AccessLow Complexity Two-Stage Soft/Hard Decoders
Next generation wireless systems will need higher spectral efficiency as the expected traffic volumes per unit bandwidth and dimension will inevitably grow. As a consequence, it is necessary to design coding schemes with performances close to the theoretical limits, having high flexibility and low complexity requirements at transmitter and receiver. In this paper, we point out some of the limitations of the Bit Interleaved Code Modulation (BICM) technique which is the state of the art adopted in several standards and then propose some new lower complexity alternatives. These low complexity alternatives are obtained by applying the recently introduced Analog Digital Belief Propagation (ADBP) algorithm to a two stage encoding scheme embedding a hard decoding stage. First we show that for PAM$^2$ type constellations over the AWGN channel, the performance loss caused by using a hard decoded stage for all modulation bits except the two least protected is negligible. Next, we consider the application of two stage decoders to more challenging Rician channels, showing that in this case the number of bits needed to be soft decoded depends on the Rician factor and increases to a maximum of three bits per dimension for the Rayleigh channel. Finally, we apply the ADBP algorithm to further reduce the detection and decoding complexity.
- 10 August 2015
- Published by Wiley in International Journal of Satellite Communications and Networking
- Vol. 34 (6) , 771-785
Code design for adaptive coding and modulation indicator in broadcast systems
- 10 August 2015
- Published by Wiley in International Journal of Satellite Communications and Networking
- Vol. 34 (6) , 771-785
Code design for adaptive coding and modulation indicator in broadcast systems
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 82-86
Analog Digital Belief Propagation and its application to multi stage decoding systems
Next generation wireless systems will need to have higher spectral efficiency as the expected traffic volumes per unit bandwidth and dimension will inevitably grow. As a consequence, it is necessary to design coding schemes with performances close to the theoretical limits, having at the same time high flexibility and low complexity requirements at the receiver. In this paper we start by pointing out some of the main drawbacks of the Bit Interleaved Code Modulation (BICM) technique which is the state of the art adopted in several standards and then propose some lower complexity alternatives. These low complexity alternatives are obtained by applying the recently introduced Analog Digital Belief Propagation (ADBP) algorithm to a two stage encoding scheme. First we show that the loss in performance can be kept quite small by using a hard decoder in all stages of a multistage decoder (MSD) except the two lowest levels with a reasonable flexibility of choosing the code rates. Then we apply the ADBP algorithm to further reduce the decoding complexity of the soft decoded stages.
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 82-86
Analog Digital Belief Propagation and its application to multi stage decoding systems
Next generation wireless systems will need to have higher spectral efficiency as the expected traffic volumes per unit bandwidth and dimension will inevitably grow. As a consequence, it is necessary to design coding schemes with performances close to the theoretical limits, having at the same time high flexibility and low complexity requirements at the receiver. In this paper we start by pointing out some of the main drawbacks of the Bit Interleaved Code Modulation (BICM) technique which is the state of the art adopted in several standards and then propose some lower complexity alternatives. These low complexity alternatives are obtained by applying the recently introduced Analog Digital Belief Propagation (ADBP) algorithm to a two stage encoding scheme. First we show that the loss in performance can be kept quite small by using a hard decoder in all stages of a multistage decoder (MSD) except the two lowest levels with a reasonable flexibility of choosing the code rates. Then we apply the ADBP algorithm to further reduce the decoding complexity of the soft decoded stages.
- Open Access
Constellation Design for Transmission over Nonlinear Satellite Channels
In this paper we use a variation of simulated annealing algorithm for optimizing two-dimensional constellations with 32 signals. The main objective is to maximize the symmetric pragmatic capacity under the peak-power constraint. The method allows the joint optimization of constellation and binary labeling. We also investigate the performance of the optimized constellation over nonlinear satellite channel under additive white Gaussian noise. We consider the performance over systems with and without pre-distorters. In both cases the optimized constellations perform considerably better than the conventional Amplitude Phase Shift Keying (APSK) modulations, used in the current digital video broadcasting standard (DVB-S2) on satellite channels. Based on our optimized constellations, we also propose a new labeling for the 4+12+16-APSK constellation of the DVB-S2 standard which is Gray over all rings.
Open AccessConstellation Design for Transmission over Nonlinear Satellite Channels
In this paper we use a variation of simulated annealing algorithm for optimizing two-dimensional constellations with 32 signals. The main objective is to maximize the symmetric pragmatic capacity under the peak-power constraint. The method allows the joint optimization of constellation and binary labeling. We also investigate the performance of the optimized constellation over nonlinear satellite channel under additive white Gaussian noise. We consider the performance over systems with and without pre-distorters. In both cases the optimized constellations perform considerably better than the conventional Amplitude Phase Shift Keying (APSK) modulations, used in the current digital video broadcasting standard (DVB-S2) on satellite channels. Based on our optimized constellations, we also propose a new labeling for the 4+12+16-APSK constellation of the DVB-S2 standard which is Gray over all rings.