Search

In this paper, simple methodologies of deep learning application to conventional multiple-input multiple-output (MIMO) communication systems are presented. The deep learning technologies with deep neural network (DNN) structure, emerging technologies in various engineering areas, have been actively investigated in the field of communication engineering as well. In the physical layer of conventional communication systems, there are practical challenges of application of DNN: calculating complex number in DNN and designing proper DNN structure for a specific communication system model. This paper proposes and verifies simple solutions for the difficulty. First, we apply a basic DNN structure for signal detection of one-tap MIMO channel. Second, convolutional neural network (CNN) and recurrent neural network (RNN) structures are presented for MIMO system with multipath fading channel. Our DNN structure for one-tap MIMO channel can achieve the optimal maximum likelihood detection performance, and furthermore, our CNN and RNN structures for multipath fading channel can detect the transmitted signal properly. [ABSTRACT FROM AUTHOR]

The detection of metal particles in oil is of great significance to the fault diagnosis of mechanical equipment. Real domain detection methods cannot simultaneously identify the sizes and materials of particles. Because a metal particle in an alternating magnetic field induces a complex domain signal whose strength relates to the particle properties, this article introduces a double lock-in amplifier circuit (DLAC) into a triple-coil inductive particle sensor to detect the complex domain signal under noise interference conditions. Furthermore, various sizes of red copper, brass, aluminum, iron, and type 403 steel particles are chosen as the experimental materials. For the first time, the complex domain signals induced by the five kinds of particles are detected. Hence, in the complex plane, a method is proposed to identify the size and material of a particle based on the amplitude and phase of these signals. With the high sensitivity and strong antinoise ability of the DLAC, this system can detect 25- $\mu \text{m}$ iron particles and 70- $\mu \text{m}$ copper particles. This study presents a new strategy for the online detection of particles in oil. [ABSTRACT FROM AUTHOR]

To solve practical challenges for implementing deep learning-based algorithm in MIMO signal detector such as handling complex number or designing proper neural network for a specific communication system, (Baek et al., 2019) has proposed candidate implementation methodologies with simple verification experiments. According to (Baek et al., 2019), it was shown that the proposed algorithms can achieve the optimal ML performance. However, due to the lack of explanation on the experimental environment, it is difficult for readers to reproduce the presented experiments and obtain the same results. This document precisely explains on the experimental environments of (Baek et al., 2019) including the exact channel profiles. [ABSTRACT FROM AUTHOR]

This article proposes a new probe for suppressing the vibration component from the detection signal in eddy current testing. The work is motivated by the desire to develop a new inspection method that can suppress the effects of vibration generated in the manufacturing process of metal parts such as tubes, rods, and wires in order to make the current manufacturing process faster. The novelty of the probe lies in its simultaneous use of self and mutual inductions. The proposed probe uses the different effects of the self and mutual inductions to suppress the vibration component. This article simplifies the discussion by limiting the dynamic vibration of the test specimen to static displacement. The coil distance between the excitation and detection coils should be adjusted for each test specimen for the most effective suppression of the displacement signal. The simulation and measurement results show that the coil distance in the mutual induction probe can control the phase of the displacement signal. It was confirmed that the amplitude of displacement signals measured by the proposed probe was under 6% of the amplitude measured by the self-induction probe when the optimal coil distance was used. The results obtained suggest that the proposed probe can suppress the vibration component. [ABSTRACT FROM AUTHOR]

Algorithm unfolding, which provides a systematic connection between conventional model-based algorithms and modern data-based deep learning, has exhibited great empirical success for efficiently balancing the performance and complexity of multiple-input and multiple-output (MIMO) detectors. However, existing unfolding-based MIMO detectors have difficulties adapting to the high discrepancy in channel and noise conditions. In this study, we present a novel unfolding-based framework for MIMO detectors, which can automatically determine internal parameters of an unfolding-based MIMO detector to adapt to the varying conditions. A key part of our approach is to develop a hypernetwork that can effectively learn to generate the internal parameters in the sophisticated expectation propagation-based MIMO detector. In particular, we design long short-term memory-based hypernetwork to ensure the flexibility of the layers of the unfolded algorithm. The proposed framework is also extended to a coded MIMO turbo receiver to adapt to the different feedback beliefs from the decoder. Numerical results demonstrate that the proposed MIMO detectors have excellent adaptation capability to different channel environments and noise levels. Compared with the existing unfolded algorithm that is an optimal reference, the proposed framework avoids frequent retraining and presents the nearly optimal performance in uncoded and coded MIMO systems. An over-the-air platform is presented as well to demonstrate the significant robustness of the proposed receivers in practical deployment. [ABSTRACT FROM AUTHOR]

Visible light communication (VLC) enables access to huge unlicensed bandwidth, a higher security level, and no radio frequency interference. With these advantages, VLC emerges as a complementary solution to radio frequency communications. VLC systems have primarily been designed for indoor scenarios with typical transmission distances between 2 and 5 m. Different designs would be required for larger distances. This article proposes for the first time, the use of a liquid crystal (LC)-based re-configurable intelligent surface (RIS) for improving the VLC signal detection and transmission range. An LC-based RIS presents multiple advantages, including the tunability of its photo-refractive parameters. Another advantage is its light amplification capabilities when under the influence of an externally applied field. In this article, we analyze an LC-based RIS structure to amplify the detected light and improve the VLC signal detection and transmission range. Results show that mixing LC with 4 to 8 wt% concentration of a dye such as the terthiophene (3T-2 MB) improves the VLC transmission range of about 0.20 to 1.08 m. This improvement can reach 6.56 m if we combine 8 wt% concentration of 3T-2 MB and 0.1 wt% concentration of trinitrofluorenone. [ABSTRACT FROM AUTHOR]

Underwater wireless optical communication (UWOC) has been recently proposed for high-rate data services. In underwater scenarios, the channel conditions are complicated due to various effects of the water waves, such as absorption, scattering and turbulence, which exhibit different statistical properties with diverse water types. Such capricious phenomena make channel estimation (CE) and signal detection (SD) become challenging issues for high-rate and reliable transmissions. To address these challenges, we devise a deep learning (DL) based joint channel classification (CC), CE and SD scheme for UWOC systems. Different from existing systems, where CE is typically an independent and fundamental module, we combine CE with SD by utilizing a new deep neural network (DNN). Furthermore, the proposed scheme exploits the channel characteristics extracted through an offline training powered by a new robust DNN channel classifier (CC), which can identify and classify the water types online to produce optimized estimated combinational weights (ECW) for improving the CE/SD performances under time-varying UWOC channels. Simulation and experimental results demonstrate the superiority of the proposed system in terms of link performances in various UWOC channel environments. [ABSTRACT FROM AUTHOR]

Deep neural networks (NNs) have exhibited considerable potential for efficiently balancing the performance and complexity of multiple-input and multiple-output (MIMO) detectors. However, existing NN-based MIMO detectors are difficult to be deployed in practical systems because of their slow convergence speed and low robustness in new environments. To address these issues systematically, we propose a receiver framework that enables efficient online training by leveraging the following simple observation: although NN parameters should adapt to channels, not all of them are channel-sensitive. In particular, we use a deep unfolded NN structure that represents iterative algorithms in signal detection and channel decoding modules as multi layer deep feed forward networks. An expectation propagation (EP) module, called EPNet, is established for signal detection by unfolding the EP algorithm and rendering the damping factors trainable. An unfolded turbo decoding module, called TurboNet, is used for channel decoding. This component decodes the turbo code, where trainable NN units are integrated into the traditional max-log-maximum a posteriori decoding procedure. We demonstrate that TurboNet is robust for channels and requires only one off-line training. Therefore, only a few damping factors in EPNet must be re-optimized online. An online training mechanism based on meta learning is then developed. Here, the optimizer, which is implemented by long short-term memory NNs, is trained to update damping factors efficiently by using a small training set such that they can quickly adapt to new environments. Simulation results indicate that the proposed receiver significantly outperforms traditional receivers and that the online learning mechanism can quickly adapt to new environments. Furthermore, an over-the-air platform is presented to demonstrate the significant robustness of the proposed receiver in practical deployment. [ABSTRACT FROM AUTHOR]

This work shows that a massive multiple-input multiple-output (MIMO) system with low-resolution analog-to-digital converters (ADCs) forms a natural extreme learning machine (ELM). The receive antennas at the base station serve as the hidden nodes of the ELM, and the low-resolution ADCs act as the ELM activation function. By adding random biases to the received signals and optimizing the ELM output weights, the system can effectively tackle hardware impairments, such as the nonlinearity of power amplifiers and the low-resolution ADCs. Moreover, the fast adaptive capability of ELM allows the design of an adaptive receiver to address time-varying effects of MIMO channels. Simulations demonstrate the promising performance of the ELM-based receiver compared to conventional receivers in dealing with hardware impairments. [ABSTRACT FROM AUTHOR]

In this letter, we propose a novel deep learning based approach for joint channel estimation and signal detection in orthogonal frequency division multiplexing (OFDM) systems by exploring the time and frequency correlation of wireless fading channels. Specifically, a Channel Estimation Network (CENet) is designed to replace the conventional interpolation procedure in pilot-aided estimation scheme. Then, based on the outcome of the CENet, a Channel Conditioned Recovery Network (CCRNet) is designed to recover the transmit signal. Experimental results demonstrate that CENet and CCRNet achieve superior performance compared with conventional estimation and detection methods. In addition, both networks are shown to be robust to the variation of parameter chances, which makes them appealing for practical implementation. [ABSTRACT FROM AUTHOR]

The matrix-based differential encoding invoked by Differential Space-Time Modulation (DSTM) typically results in an infinite-cardinality of arbitrary signals, despite the fact that the transmit antennas (TAs) can only radiate a limited number of patterns. As a remedy, the recently developed differential spatial modulation (DSM) is capable of avoiding this problem by conceiving a beneficial sparse signal matrix design, which also facilitates low-complexity single-RF signal transmission. Inspired by this development, the differential space-time block code using index shift keying (DSTBC-ISK) further introduces a beneficial diversity gain without compromising the DSM’s appealingly low transceiver complexity. However, the DSTBC-ISK’s performance advantage tends to diminish as the throughput increases, especially when an increased number of Receive Antennas (RAs) is used. By contrast, the classic Differential Group Code (DGC) that actively maximizes its diversity gain for different multiple-input-multiple-output (MIMO) system setups is capable of achieving a superior performance, but its detection complexity grows exponentially with the throughput. Against this background, we propose the differential space-time shift keying using Diagonal Algebraic Space-Time scheme, which is the first DSTM that is capable of achieving the DGC’s superior diversity gain at high throughputs without compromising the DSM’s low transceiver complexity. As a further advance, we also conceive a new differential space-time shift keying using Threaded Algebraic Space-Time arrangement, which is capable of achieving an even further improved diversity gain at a substantially reduced signal detection complexity compared to the best DGCs. Furthermore, in order to strike a practical tradeoff, we develop a generic multi-element and multi-level-ring Amplitude Phase Shift Keying design, and we also arrange for multiple reduced-size DSTM sub-blocks to be transmitted in a permuted manner, which exhibits an improved diversity-throughput tradeoff. [ABSTRACT FROM AUTHOR]

For colocated multiple-input multiple-output (MIMO) radar, we investigate the target detection problem in Gaussian clutter with unknown covariance matrix with known inverse complex Wishart distribution as its prior probability density function. We propose three detectors in the Bayesian framework according to the criteria of the generalized likelihood ratio test, Rao test, and Wald test. The two main advantages of the proposed Bayesian detectors are as follows: first, no training data are required; and second, a priori knowledge about the clutter is incorporated in the decision rules to achieve detection performance gains. Numerical simulations show that the proposed Bayesian detectors outperform their non-Bayesian counterparts, especially when the sample number of the transmitted waveform is small. In addition, the proposed Bayesian Wald test is the most robust against the mismatch in the receive steering vector, and the proposed Bayesian Rao test exhibits the strongest rejection capability of mismatched signals. [ABSTRACT FROM AUTHOR]

The problem of target detection in colocated multiple-input multiple-output radar with unknown disturbance covariance matrix is considered. According to the generalized likelihood ratio test, we design an adaptive detector by exploiting the persymmetric structure of the covariance matrix. In particular, training data are not required in the proposed adaptive detector. Analytical expressions for the probability of false alarm and detection probability are derived, which are confirmed by Monte Carlo simulations. The expression for the probability of false alarm shows that the proposed detector exhibits a constant false alarm rate property against the disturbance covariance matrix. Numerical examples based on both simulated and experimental data confirm that the proposed detector has better detection performance than its counterparts. [ABSTRACT FROM AUTHOR]

This paper deals with the problem of detecting a subspace signal in the presence of spatially and temporally colored disturbance. A new subspace parametric signal model that takes into account a multi-rank subspace structure for the target signal and employs a multi-channel auto-regressive process for the disturbance signal is proposed. Following this model, a new subspace parametric Rao detector (SP-Rao) is developed for training-limited scenarios. Unlike conventional parametric detectors that are designed for only rank-one signal detection, the SP-Rao has a new multi-rank structure with a pairwise successive spatio-temporal whitening and cross-correlation process between the observed signal and each subspace basis vector. Additionally, a non-parametric subspace detector (NSD) is derived based upon a frequency-domain representation of the SP-Rao test statistic. The NSD is distinctively different from conventional subspace detectors, in which the former involves pairwise whitening and cross-correlation between the test signal and each subspace basis vector but the latter employs the whole subspace matrix. Numerical results are presented to illustrate the performance of the proposed subspace detectors in comparison with several leading existing methods, especially in the case of limited data. [ABSTRACT FROM AUTHOR]

In this paper, we consider multiuser massive multiple-input multiple-output (MIMO) uplink systems in which there are multiple users with each having a single antenna and one base station (BS) with a large number of antennas. It is assumed that each user and BS have neither small-scale nor large-scale channel state information. For such a noncoherent system, we systematically design a series of absolutely additively uniquely decomposable constellation pairs using the phase-shift keying (PSK) constellations such that when any linear combination of two PSK constellation points with positive weight coefficients is received, each individual PSK signal can be uniquely decoded. With this, a novel noncoherent massive space-time block code with PSK modulation is developed for the system. In a noise-free case, we prove that when the number of the antenna at BS grows to infinity, the transmitted symbols and uplink channel can be uniquely determined if the channel coherence time is at least equal to the number of users. In a noisy case, a minimum Euclidean distance detector and a minimum Riemannian distance detector are developed for efficiently and effectively estimating both the channel coefficients and the transmitted signals. Furthermore, a successive two-symbol update receiver is derived for reducing the computational complexity. The benefits of the proposed scheme are illustrated through application examples in multipair two-way massive MIMO half-duplex relaying system and a two-cell massive MIMO uplink system. [ABSTRACT FROM AUTHOR]

Received signal strength based radio tomographic imaging is a popular device-free indoor localization method which reconstructs the spatial loss field of the environment using measurements from a dense wireless network. Existing methods achieve high accuracy localization using a complex system with many sophisticated components. In this work, we propose an alternative and simpler imaging system based on link level occupancy detection. First, we introduce a single-bounce reflection based received signal strength model, which allows relating received signal strength variations to a large region around the link-lines. Then, based on the model, we present methods for all system components including a classifier, a detector, a back-projection based reconstruction algorithm, and a localization method. The introduced system has the following advantages over the other imaging based methods: i) a simple image reconstruction method that is straightforward to implement; ii) significantly lower computational complexity such that no floating point multiplication is required; iii) each link's measured data are compressed to a single bit, providing improved scalability; and iv) physically significant and repeatable parameters. The proposed method is validated using measurement data. Results show that the proposed method achieves the above advantages without loss of accuracy compared to the other available methods. [ABSTRACT FROM PUBLISHER]

The adaptive classification of the interference covariance matrix structure for radar signal processing applications is addressed in this paper. This represents a key issue because many detection architectures are synthesized assuming a specific covariance structure which may not necessarily coincide with the actual one due to the joint action of the system and environment uncertainties. The considered classification problem is cast in terms of a multiple hypotheses test with some nested alternatives and the theory of model order selection (MOS) is exploited to devise suitable decision rules. Several MOS techniques, such as the Akaike, Takeuchi, and Bayesian information criteria, are adopted and the corresponding merits and drawbacks are discussed. At the analysis stage, illustrating examples for the probability of correct model selection are presented showing the effectiveness of the proposed rules. [ABSTRACT FROM PUBLISHER]

Our aim in this work is to analyze the detection performance of a constant false alarm rata matched filter (CFAR-MF) which was developed for the detection problem in white Gaussian noise with unknown noise power. An exact expression for the detection probability of the CFAR-MF is derived in the mismatched case where mismatch exists between the actual signal steering vector and the nominal one. This theoretical expression can be used to facilitate the performance evaluation of the CFAR-MF in real-world scenarios when signal mismatch cannot be neglected. [ABSTRACT FROM PUBLISHER]

In this letter, we propose new frequency-domain pilot-multiplexing techniques (FDPMTs) for the channel estimation and equalization in orthogonal frequency-division multiplexing (OFDM) systems. A robust and effective pilot insertion and detection scheme is devised thereby. These pilot positions are optimally selected to minimize the distortion of the transmitted time-domain signal caused by the subcarrier-removal at the corresponding pilot positions. Besides, three different blind pilot-detection techniques are designed at the receiver without any a priori knowledge of the pilot positions, and the distorted data symbols can thus be iteratively reconstructed. Rigorous theoretical analysis and Monte Carlo simulation results both demonstrate that our proposed new OFDM system using dynamical pilot positions is more robust than the conventional OFDM system using the fixed pilot positions over multipath fading channels. [ABSTRACT FROM AUTHOR]