Industrial IoT (IIoT) deployments demand intelligent transmission schemes that balance monitoring fidelity with limited energy and bandwidth. This paper presents a lightweight adaptive framework that predicts a utility–cost slope via machine learning and refines it through Bayesian fusion with historical priors for anomaly-aware rate adjustment. Signal utility is derived from spectral and statistical features such as entropy and the Hurst exponent, while cost reflects link quality, anomaly likelihood, and SIM data usage. Deployed on a 342-day water-purification testbed, the method achieves up to 60% data reduction with negligible loss in reconstruction accuracy, demonstrating its practicality for resource-constrained IIoT edge devices.

A novel form of inference attack in vertical federated learning (VFL) is proposed, where two parties collaborate in training a machine learning (ML) model. Logistic regression is considered for the VFL model. One party, referred to as the active party, possesses the ground truth labels of the samples in the training phase, while the other, referred to as the passive party, only shares a separate set of features corresponding to these samples. It is shown that the active party can carry out inference attacks on both training and prediction phase samples by acquiring an ML model independently trained on the training samples available to them. This type of inference attack does not require the active party to be aware of the score of a specific sample, hence it is referred to as an agnostic inference attack. It is shown that utilizing the observed confidence scores during the prediction phase, before the time of the attack, can improve the performance of the active party’s autonomous ML model, and thus improve the quality of the agnostic inference attack. As a countermeasure, privacy-preserving schemes (PPSs) are proposed. While the proposed schemes preserve the utility of the VFL model, they systematically distort the VFL parameters corresponding to the passive party’s features. The level of the distortion imposed on the passive party’s parameters is adjustable, giving rise to a tradeoff between privacy of the passive party and interpretability of the VFL outcomes by the active party. The distortion level of the passive party’s parameters could be chosen carefully according to the privacy and interpretability concerns of the passive and active parties, respectively, with the hope of keeping both parties (partially) satisfied. Finally, experimental results demonstrate the effectiveness of the proposed attack and the PPSs.

The measurement of breath rate (BR) is essential for comprehensive human health monitoring across a wide range of scenarios. Several studies in the literature have explored the estimation of BR using millimeter wave (mmWave) technology. However, these approaches typically focus on a single subject at a time. To enable multi-person estimation, researchers have often relied on data fusion with camera systems or employed specialized hardware configurations. On the contrary, this paper proposes a methodology that employs only one Frequency Modulated Continuous Wave (FMCW) radar to estimate the BR of multiple subjects stationary in the environment. The proposed methodology includes a pre-processing pipeline to refine the radar-captured signals, followed by frequency-domain analysis to distinguish between subjects. Finally, phase variations in the reflected signals caused by chest movements are analyzed to estimate the BR. Advantages and limitations of the approach are discussed on the basis of an experimental campaign.

The explosion of the number of low-power devices in the next decades calls for a re-thinking of wireless network design, namely, unifying wireless transmission of information and power so as to make the best use of the RF spectrum, radiation, and infrastructure for the dual purpose of communicating and energizing. This article provides a novel learning-based approach towards such wireless network design. To that end, a parametric model of a practical energy harvester, accounting for various sources of nonlinearities, is proposed using a nonlinear regression algorithm applied over collected real data. Relying on the proposed model, the learning problem of modulation design for Simultaneous Wireless Information-Power Transmission (SWIPT) over a point-to-point link is studied. Joint optimization of the transmitter and the receiver is implemented using Neural Network (NN)-based autoencoders. The results reveal that by increasing the receiver power demand, the baseband transmit modulation constellation converges to an On-Off keying signalling. Utilizing the observations obtained via learning, an algorithmic SWIPT modulation design is proposed. It is observed via numerical results that the performance loss of the proposed modulations are negligible compared to the ones obtained from learning. Extension of the studied problem to learning modulation design for multi-user SWIPT scenarios and coded modulation design for point-to-point SWIPT are considered. The major conclusion of this work is to utilize learning-based results to design non learning-based algorithms, which perform as well. In particular, inspired by the results obtained via learning, an algorithmic approach for coded modulation design is proposed, which performs very close to its learning counterparts, and is significantly superior due to its high real-time adaptability to new system design parameters.

The capacity of a complex and discrete-time memoryless additive white Gaussian noise (AWGN) channel under three constraints, namely, input average power, input amplitude and output delivered power is studied. The output delivered power constraint is modelled as the average of linear combination of even moments of the channel input being larger than a threshold. It is shown that the capacity of an AWGN channel under transmit average power and receiver delivered power constraints is the same as the capacity of an AWGN channel under an average power constraint. However, depending on the two constraints, the capacity can be either achieved by a Gaussian distribution or arbitrarily approached by using time-sharing between a Gaussian distribution and On-Off Keying. As an application, a simultaneous wireless information and power transfer (SWIPT) problem is studied, where an experimentally-validated nonlinear model of the harvester is used. It is shown that the delivered power depends on higher order moments of the channel input. Two inner bounds, one based on complex Gaussian inputs and the other based on further restricting the delivered power are obtained for the Rate-Power (RP) region. For Gaussian inputs, the optimal inputs are zero mean and a tradeoff between transmitted information and delivered power is recognized by considering asymmetric power allocations between inphase and quadrature subchannels. Through numerical algorithms, it is observed that input distributions (obtained by restricting the delivered power) attain larger RP region compared to Gaussian input counterparts. The benefits of the newly developed and optimized input distributions are also confirmed and validated through realistic circuit simulations. The results reveal the crucial role played by the energy harvester (EH) nonlinearity on SWIPT and provide new engineering guidelines on how to exploit this nonlinearity in the design of SWIPT modulation, signal and architecture.

The end-to-end learning of Simultaneous Wireless Information and Power Transfer (SWIPT) over a noisy channel is studied. Adopting a nonlinear model for the Energy Harvester (EH) at the receiver, a joint optimization of the transmitter and the receiver is implemented using Neural Network (NN)-based autoencoders. Modulation constellations for different levels of "power" and "information rate" demands at the receiver are obtained. The numerically optimized signal constellations are inline with the previous theoretical results. In particular, it is observed that as the receiver power demand increases, all but one of the modulation symbols are concentrated around the origin and the other symbol is shot away from the origin.

Simultaneous wireless information and power transmission (SWIPT) over a point-to-point frequency-selective channel is studied. Leveraging a small-signal model for a nonlinear energy harvester, a general form of the delivered power in terms of system baseband parameters is derived, which demonstrates the dependency of the delivered power on higher moments of the baseband channel input. The optimization problem of maximizing rate-power (RP) region is studied. Assuming that the channel state information (CSI) is available at both the receiver and the transmitter, and constraining to the non-zero mean Gaussian input distributions, an optimization algorithm for power allocation among different subchannels is studied. As a special case, optimality conditions for zero mean Gaussian inputs are derived. Results obtained from the numerical optimization demonstrate the superiority of the non-zero mean Gaussian inputs (with asymmetric power allocation in each complex subchannel) in yielding a larger RP region compared to their zero mean and non-zero mean (with symmetric power allocation in each complex subchannel) counterparts. The results motivate the design of new modulation for SWIPT and contrast with the SWIPT design under linear energy harvesting, for which the circularly symmetric Gaussian inputs with water-filling power allocation are optimal.

Simultaneous Wireless Information and Power Transfer (SWIPT) is subject to nonlinearity at the energy harvester that leads to significant changes to transmit signal designs compared to conventional wireless communications. In this paper, the capacity of a discrete time, memoryless and complex Additive White Gaussian Noise (AWGN) channel in the presence of a nonlinear energy harvester at the receiver is studied. Considering the two common nonlinear energy harvester models introduced in the literature, two sets of constraints are considered. First the capacity is studied under average power (AP), peak amplitude (PA) and receiver delivery power (RDP) constraints. The RDP constraint is modelled as a linear combination of even-moment statistics of the channel input being larger than a threshold. It is shown that the capacity of an AWGN channel under AP and RDP constraints is the same as the capacity of an AWGN channel under an AP constraint, however, depending on the two constraints, it can be either achieved or arbitrarily approached. It is also shown that under AP, PA and RDP constraints, the amplitude of the optimal inputs is discrete with a finite number of mass points. Next, the capacity is studied under AP, PA and output outage probability (OOP) constraints. OOP is modelled as satisfying a certain probability inequality for the amplitude of the received signal being outside of a given interval. Similarly, it is shown that the amplitude of the optimal input is discrete with a finite number of mass points.

Motivated by the practical constraints arising in emerging sensor network and Internet-of-Things (IoT) applications, the zero-delay transmission of a Gaussian measurement over a real single-input multiple-output (SIMO) additive white Gaussian noise (AWGN) channel is studied with a low-resolution analog-to-digital converter (ADC) front end. Joint optimization of the encoder and the decoder mapping is tackled under both the mean squared error (MSE) distortion and the distortion outage probability (DOP) criteria, with an average power constraint on the channel input. Optimal encoder and decoder mappings are identified for a one-bit ADC front end under both criteria. For the MSE distortion, the optimal encoder mapping is shown to be non-linear in general, while it tends to a linear encoder in the low signal-to-noise ratio (SNR) regime, and to an antipodal digital encoder in the high SNR regime. This is in contrast to the optimality of linear encoding at all SNR values in the presence of a full-precision front end. For the DOP criterion, it is shown that the optimal encoder mapping is piecewise constant and can take only two opposite values when it is non-zero. For both the MSE distortion and the DOP criteria, necessary optimality conditions are then derived for $K$ -level ADC front ends as well as front ends with multiple one-bit ADCs. These conditions are used to obtain numerically optimized solutions. Extensive numerical results are also provided in order to gain insights into the structure of the optimal encoding and decoding mappings.

The capacity region of a two-transmitter Gaussian multiple access channel (MAC) under average input power constraints is studied, when the receiver employs a zero-threshold one-bit analog-to-digital converter (ADC). It is proved that the input distributions that achieve the boundary points of the capacity region are discrete. Based on the position of a boundary point, upper bounds on the number of the mass points of the corresponding distributions are derived. Finally, a conjecture on the sufficiency of K mass points in a point-to-point real AWGN with a K-bin ADC front end (symmetric or asymmetric) is settled1.

Simultaneous transmission of information and power over a point-to-point flat-fading complex Additive White Gaussian Noise (AWGN) channel is studied. In contrast with the literature that relies on an inaccurate linear model of the energy harvester, an experimentally-validated nonlinear model is considered. A general form of the delivered Direct Current (DC) power in terms of system baseband parameters is derived, which demonstrates the dependency of the delivered DC power on higher order statistics of the channel input distribution. The optimization problem of maximizing Rate-Power (R-P) region is studied. Assuming that the Channel gain is available at both the receiver and the transmitter, and constraining to independent and identically distributed (i.i.d.) channel inputs determined only by their first and second moment statistics, an inner bound for the general problem is obtained. Notably, as a consequence of the harvester nonlinearity, the studied inner bound exhibits a tradeoff between the delivered power and the rate of received information. It is shown that the tradeoff-characterizing input distribution is with mean zero and with asymmetric power allocations to the real and imaginary dimensions.

Zero-delay transmission of a Gaussian source over an additive white Gaussian noise (AWGN) channel is considered with a 1-bit analog-to-digital converter (ADC) front end and correlated side information at the receiver. The design of the optimal encoder and decoder is studied for two different performance criteria, namely the mean squared error (MSE) distortion and the distortion outage probability (DOP), under an average power constraint on the channel input. For both criteria, necessary optimality conditions for the encoder and the decoder are derived, which are then used to numerically obtain encoder and decoder mappings that satisfy these conditions. Using these conditions, it is observed that the numerically optimized encoder (NOE) under the MSE distortion criterion is periodic, and its period increases with the correlation between the source and the receiver side information. For the DOP, it is instead seen that the NOE mappings periodically acquire positive and negative values, which decay to zero with increasing source magnitude, and the interval over which the mapping takes non-zero values becomes wider with the correlation between the source and the side information. Finally, inspired by the mentioned properties of the NOE mappings, parameterized encoder mappings with a small number of degrees of freedom are proposed for both distortion criteria, and their performance is compared with that of the NOE mappings.

This paper considers the zero-delay transmission of a Gaussian source over an additive white Gaussian noise (AWGN) channel with a one-bit analog-to-digital converter (ADC) front end. The optimization of the encoder and decoder is tackled under both the mean squared error (MSE) distortion and the outage distortion criteria with an average power constraint. For MSE distortion, the optimal transceiver is identified over the space of symmetric encoders. This result demonstrates that the linear encoder, which is optimal with a full-precision front end, approaches optimality only in the low signal-to-noise ratio (SNR) regime; while, digital transmission is optimal in the high SNR regime. For the outage distortion criterion, the structure of the optimal encoder and decoder are obtained. In particular, it is shown that the encoder mapping is piecewise constant and can take only two opposite values when it is non-zero.

Zero-delay transmission of a Gaussian source over an additive white Gaussian noise (AWGN) channel with a 1-bit analog-to-digital converter (ADC) front end is investigated in the presence of correlated side information at the receiver. The design of the optimal encoder is considered for the mean squared error (MSE) distortion criterion under an average power constraint on the channel input. A necessary condition for the optimality of the encoder is derived. A numerically optimized encoder (NOE) is then obtained that aims that enforcing the necessary condition. It is observed that, due to the availability of receiver side information, the optimal encoder mapping is periodic, with its period depending on the correlation coefficient between the source and the side information. We then propose two parameterized encoder mappings, referred to as periodic linear transmission (PLT) and periodic BPSK transmission (PBT), which trade-off optimality for reduced complexity as compared to the NOE solution. We observe via numerical results that PBT performs close to the NOE in the high signal-to-noise ratio (SNR) regime, while PLT approaches the NOE performance in the low SNR regime.

Zero-delay transmission of a Gaussian source over an additive white Gaussian noise (AWGN) channel is considered in the presence of an independent additive Gaussian interference signal. The mean squared error (MSE) distortion is minimized under an average power constraint assuming that the interference signal is known at the transmitter. Optimality of simple linear transmission does not hold in this setting due to the presence of the known interference signal. While the optimal encoder-decoder pair remains an open problem, various non-linear transmission schemes are proposed in this paper. In particular, interference concentration (ICO) and one-dimensional lattice (1DL) strategies, using both uniform and non-uniform quantization of the interference signal, are studied. It is shown that, in contrast to typical scalar quantization of Gaussian sources, a non-uniform quantizer, whose quantization intervals become smaller as we go further from zero, improves the performance. Given that the optimal decoder is the minimum MSE (MMSE) estimator, a necessary condition for the optimality of the encoder is derived, and the numerically optimized encoder (NOE) satisfying this condition is obtained. Based on the numerical results, it is shown that 1DL with non-uniform quantization performs closer (compared with the other schemes) to the NOE while requiring significantly lower complexity.

Zero-delay transmission of a Gaussian source is considered over an additive white Gaussian noise (AWGN) channel in the presence of an additive Gaussian interference signal. The mean squared error (MSE) distortion is minimized under an average power constraint assuming that the interference signal is known causally at the transmitter. Optimality of simple uncoded transmission does not hold in this setting due to the presence of the known interference signal, and various non-linear transmission schemes are proposed. In particular, interference concentration (ICO) and one-dimensional lattice (1DL) strategies are studied. It is shown that non-uniform quantization of the interference signal for ICO improves the performance.

Delay limited transmission of a uniform source over an additive white Gaussian noise (AWGN) channel under an average power constraint is considered. Assuming that the channel can be used only once, mean squared error (MSE) distortion is studied for both the bandwidth matched, and the 2∶1 bandwidth compression cases. In the bandwidth matched scenario, simply scaling the source sample, i.e., analog transmission, performs better than transmitting the scalar quantized source samples. For the bandwidth compression scenario, a hybrid digital analog transmission scheme that quantizes the first source sample and superimposes the quantized sample with the scaled version of the second sample is studied. It is shown that, in this scheme, as opposed to the bandwidth matched case, a finite number of quantization indices minimizes the achievable distortion. The performance of this hybrid scheme is then compared with a numerically optimized encoder using the steepest decent algorithm iteratively. It is observed that the performance of the hybrid scheme is reasonably close to the numerically optimized scheme, while having a significantly lower computational complexity. The theoretical Ziv-Zakai (ZZ) bound on the average distortion is also considered to better understand the gap between the optimal performance and the proposed scheme.

In this paper, we propose a modified joint source-channel coding (JSCC) scheme on the transmission of an analog Gaussian source over an additive white Gaussian noise (AWGN) channel in the presence of an interference, correlated with the source. This setting naturally generalizes the problem of sending a single Gaussian source over an AWGN channel, in the case of bandwidth-matched, and with uncorrelated interference in which separation-based scheme with Costa coding is optimal. We analyze the modifeied scheme to obtain achievable (mean-squared error) distortion-power tradeoff. For comparison, we also obtain a new outer bound for the achievable distortion-power tradeoff. Using numerical simulations, we demonstrate that, a two layered coding scheme consisting of analog and digital Costa coding layers, performs well compared to other provided JSCC schemes in the literature [1], [2].

In this paper, we consider transmission of a Gaussian source over a Gaussian channel under bandwidth compression in the presence of interference known only to the transmitter. We study hybrid digital-analog (HDA) joint source-channel coding schemes and propose two novel coding schemes that achieve the optimal mean-squared error (MSE) distortion. This can be viewed as the extension of results by Wilson et al. [1], originally proposed for sending a Gaussian source over a Gaussian channel in two cases: 1) Matched bandwidth with known interference only at the transmitter, 2) bandwidth compression where there is no interference in the channel. The proposed HDA codes can cancel the interference of the channel and obtain the “optimum performance theoretically attainable” (OPTA) of the AWGN channel with no interference in the case of bandwidth compression. We also provide performance analysis in the presence of signal-to-noise ratio (SNR) mismatch where we expect that HDA schemes perform better than strictly digital schemes.