Fig 4 - uploaded by Jie Chen
Content may be subject to copyright.
Theoretical and simulation performance comparison with different overhead of dedicated symbols when both FDT and ET adopt QPSK: h 0 = 1, c 0 = 1, P 1 = 10 dB and N = 128.
Source publication
In conventional full-duplex communications, dedicated symbols are transmitted to estimate both the self-interference channel and the desired signal channel in order to perform self-interference cancellation (SIC) and to coherently detect the desired signal. However, inaccurate channel estimation will produce residual self-interference and degrade t...
Context in source publication
Context 1
... are taken expectation over the AWGN channels by 10 6 Monte Carlo simulations. We can observe that the theoretical BER performances of ML-LS and ML-Perfect match the simulated BER performances well. Besides, the simulated BER performance of the designed FDT is well bounded by the theoretical lower BER bound and the theoretical upper BER bound. Fig. 4 plots the impact of the number of training symbols on the BER performance of the FDT with ML-LS over the AWGN channels when both FDT and ET adopt QPSK. It can be observed that the theoretical BER performances of ML-LS and ML-Perfect match the simulated BER performances well. Furthermore, we observe that when L ≤ 8, the BER performance ...
Similar publications
In this paper, a machine learning based deployment framework of unmanned aerial vehicles (UAVs) is studied. In the considered model, UAVs are deployed as flying base stations (BS) to offload heavy traffic from ground BSs. Due to time-varying traffic distribution, a long short-term memory (LSTM) based prediction algorithm is introduced to predict th...
Citations
... Then, the BS transmits the beamformed ISAC signals to all users for individual information transmission and concurrently receives echo signals from targets to re-estimate the radar CSI of selected targets. Note that re-estimating communication CSI incurs time consumption for pilot transmission and re-estimating radar CSI causes energy and computation costs due to successive interference cancellation (SIC) [34]- [36] in the full-duplex module. On the other hand, predicting CSI does not cause additional training costs due to without involving pilot transmission or SIC. ...
... To perform radar CSI re-estimation, the BS will receive the echo signals from the target and the self-transmitted ISAC signals defined in (4). With the full-duplex operation, we follow a similar assumption in [34]- [36] that the selfinterference is canceled by applying SIC, and the remaining signals at the BS for tracking are ...
... where F (W, µ, α, β, η) Here, η ∈ C |Q|×1 is the vector consisting of η q for q ∈ Q, and η q is the non-negative Lagrangian dual variable due to constraint (36), which is updated by sub-gradient method [47]. Let W old , µ old , α old , β old , and η old be the updated solutions in the last iteration. ...
Due to the distinct objectives and multipath utilization mechanisms between the communication module and radar module, the system design of integrated sensing and communication (ISAC) necessitates two types of channel state information (CSI), i.e., communication CSI representing the whole channel gain and phase shifts, and radar CSI exclusively focused on target mobility and position information. However, current ISAC systems apply an identical mechanism to estimate both types of CSI at the same predetermined estimation interval, leading to significant overhead and compromised performances. Therefore, this paper proposes an intermittent communication and radar CSI estimation scheme with adaptive intervals for individual users/targets, where both types of CSI can be predicted using channel temporal correlations for cost reduction or re-estimated via training signal transmission for improved estimation accuracy. Specifically, we jointly optimize the binary CSI re-estimation/prediction decisions and transmit beamforming matrices for individual users/targets to maximize communication transmission rates and minimize radar tracking errors and costs in a multiple-input single-output (MISO) ISAC system. Unfortunately, this problem has causality issues because it requires comparing system performances under re-estimated CSI and predicted CSI during the optimization. Additionally, the binary decision makes the joint design a mixed integer nonlinear programming (MINLP) problem, resulting in high complexity when using conventional optimization algorithms. Therefore, we propose a deep reinforcement online learning (DROL) framework that first implements an online deep neural network (DNN) to learn the binary CSI updating decisions from the experiences. Given the learned decisions, we propose an efficient algorithm to solve the remaining beamforming design problem efficiently.
... Further, advanced ML techniques, such as tensor completion (TC), TensorFlow graphs, and so forth, have also been investigated for learning the SI in FD transceivers [109], [110], [112]. Other ML techniques, such as Gaussian mixture models (GMMs), deep unfolding (DU), lazy learning (LL), and so forth, have additionally been explored for FD SIC [119], [120], [122], [125], [126]. Integrating ML with FD communications has achieved considerable success in terms of performance and/or complexity when compared to the model-driven approaches. ...
... 2) Gaussian Mixture Models (GMMs): In [120], an ML approach based on GMMs clustering is introduced to design an FD transceiver, which can detect the desired signal (i.e., SoI) directly without using digital-domain cancellation or even channel estimation. As the name implies, GMMs clustering uses a mixture, i.e., a superposition, of Gaussian distributions to fit the training data and assign the data points to a certain cluster based on their conditional probabilities [121]. ...
... As the name implies, GMMs clustering uses a mixture, i.e., a superposition, of Gaussian distributions to fit the training data and assign the data points to a certain cluster based on their conditional probabilities [121]. In more detail, in [120], the received signal is firstly clustered, and a one-to-one mapping of the symbols, based on a GMMs clustering and an expectation-maximization (EM) algorithm, is utilized to perform the signal detection in each cluster. Simulation results reveal that an FD transceiver, utilizing the GMMs clustering, could achieve a comparable bit error rate with that of FD transceivers employing maximum likelihood detectors when perfect channel knowledge is considered and a better one when the LS/LMS channel estimation is used [120]. ...
In contrast to the long-held belief that wireless systems can only work in half-duplex mode, full-duplex (FD) systems are able to concurrently transmit and receive information over the same frequency bands to theoretically enable a twofold increase in spectral efficiency. Despite their significant potential, FD systems suffer from an inherent self-interference (SI) due to a coupling of the transmit signal to its own FD receive chain. Self-interference cancellation (SIC) techniques are the key enablers for realizing the FD operation, and they could be implemented in the propagation, analog, and/or digital domains. Particularly, digital domain cancellation is typically performed using model-driven approaches, which have proven to be insufficient to seize the growing complexity of forthcoming communication systems. For the time being, machine learning (ML) data-driven approaches have been introduced for digital SIC to overcome the complexity hurdles of traditional methods. This paper reviews and summarizes the recent advances in applying ML to SIC in FD systems. Further, it analyzes the performance of various ML approaches using different performance metrics, such as the achieved SIC, training overhead, memory storage, and computational complexity. Finally, this paper discusses the challenges of applying ML-based techniques to SIC, highlights their potential solutions, and provides a guide for future research directions.
... PZT piezoelectric transducers are high-sensitivity sensors for acoustic-electric measurement, mainly employed for photoacoustic measurement of liquid and solid [15][16][17] and allowing direct contact with the analyte [18][19][20][21]. They are commonly used in medical imaging [22], the study of nanoparticle suspensions [22], and photoacoustic imaging [23]. ...
... They are commonly used in medical imaging [22], the study of nanoparticle suspensions [22], and photoacoustic imaging [23]. Apart from functioning as sensors for measuring thermal diffusivity [19,20,22], PZT piezoelectric transducers can also act as sensors for measuring acoustic vibration to obtain the concentration of trace gases [24]. In 2004, Ledermann carefully compared the structure of PZT thin-film cantilever beams with a bridge acoustic sensor and found that the measurement sensitivity of the former proved to be ppm [25] through an experiment involving the measurement of the concentration of CO2. ...
The feasibility of a scheme in which the concentration of CO2 in gas-liquid solution is directly measured based on PZT piezoelectric-photoacoustic spectroscopy was evaluated. The existing device used for the measurement of gas concentration in gas-liquid solution has several limitations, including prolonged duration, loss of gas, and high cost due to the degassing component. In this study, we developed a measuring device in order to solve the problems mentioned above. Using this device, how the intensity of the photoacoustic signal changes with the concentration of CO2 was demonstrated through experiment. The impact that variation of the laser modulation frequency has on the photoacoustic signal was also studied. Furthermore, the experimental data generated from measuring the concentration of CO2 in gas-liquid solution was verified for a wide range of concentrations. It was found that, not only can the error rate of the device be less than 7%, but the time of measurement can be within 60 s. To sum up, the scheme is highly feasible according to the experimental results, which makes measurement of the concentration of a gas in gas-liquid solution in the future more straightforward.
... In [72], the author explored Gaussian Mixture Model (GMM) based design for a FD transceiver (FDT). The SoI can be detected without estimating the channel and SIC by using this approach. ...
In-band full-duplex (IBFD) transmission has been identified as a promising solution to improve spectral efficiency as compared to half-duplex (HD) systems. One of the major challenges of FD systems is to effectively manage the self-interference (SI) produced by the transmitter antenna to the local receiver antenna. In this survey paper, we first review and discuss the preliminaries related to SI cancellation (SIC). Furthermore, this survey presents the advancements to the date of digital SIC approaches and highlights the advantages and limitations of each approach. The survey also summarizes different hardware platforms used for SIC along with their key features. Additionally, we also survey and compare different FD techniques for their SIC performances. Finally, this paper identifies a variety of new research areas in the era of machine learning and deep learning for digital SIC.
... In this paper, we propose a novel training mechanism to mitigate problems such as data sparsity, high inter-class variance, and low intra-class variance which leads to poor clustering performance. Traditional clustering algorithms such as K-means, Gaussian mixture models (GMM) [3], and spectral clustering [6] rely largely on the notion of distance; for example, K-means [9] uses Euclidean distance to assign data points to clusters. Recent advances in deep learning has led to emergence of clustering techniques parameterized by deep neural networks [15] [12] [2] [11] [16] attempting to jointly learn representations, and perform clustering relying on tools like Stochastic Gradient Descent and backpropagation with a clustering objective function. ...
... In this section, we discusses contemporary works addressing clustering using deep features. Classical clustering techniques such as K-means [9], Gaussian Mixture Models (GMM) [3], and Spectral clustering [6] are limited by their distance metrics and perform poorly when the dimensionality is high. Towards this, recent techniques such as Deep Embedded Clustering (DEC) [14], Improved Deep Embedded Clustering [4] extract deep features towards categorization in lower dimension embedding space. ...
In this paper, we propose a strategy to mitigate the problem of inefficient clustering performance by introducing data augmentation as an auxiliary plug-in. Classical clustering techniques such as K-means, Gaussian mixture model and spectral clustering are central to many data-driven applications. However, recently unsupervised simultaneous feature learning and clustering using neural networks also known as Deep Embedded Clustering (DEC) has gained prominence. Pioneering works on deep feature clustering focus on defining relevant clustering loss function and choosing the right neural network for extracting features. A central problem in all these cases is data sparsity accompanied by high intra-class and low inter-class variance, which subsequently leads to poor clustering performance and erroneous candidate assignments. Towards this, we employ data augmentation techniques to improve the density of the clusters, thus improving the overall performance. We train a variant of Convolutional Autoencoder (CAE) with augmented data to construct the initial feature space as a novel model for deep clustering. We demonstrate the results of proposed strategy on crowdsourced Indian Heritage dataset. Extensive experiments show consistent improvements over existing works.
... Using the conventional LS channel estimator [30], the cascaded channel is estimated bŷ ...
Channel acquisition is one of the main challenges for the deployment of reconfigurable intelligent surface (RIS) aided communication system. This is because RIS has a large number of reflective elements, which are passive devices without active transmitting/receiving and signal processing abilities. In this paper, we study the uplink channel estimation for the RIS aided multi-user multi-input multi-output (MIMO) system. Specifically, we propose a novel channel estimation protocol for the above system to estimate the cascade channel, which consists of the channels from the base station (BS) to the RIS and from the RIS to the user. Further, we recognize the cascaded channels are typically sparse, this allows us to formulate the channel estimation problem into a sparse channel matrix recovery problem using the compressive sensing (CS) technique, with which we can achieve robust channel estimation with limited training overhead. In particular, the sparse channel matrixes of the cascaded channels of all users have a common row-column-block sparsity structure due to the common channel between BS and RIS. By considering such a common sparsity, we further propose a two-step procedure based multi-user joint channel estimator. In the first step, by considering common column-block sparsity, we project the signal into the common column subspace for reducing complexity, quantization error, and noise level. In the second step, by considering common row-block sparsity, we apply all the projected signals to formulate a multi-user joint sparse matrix recovery problem, and we propose an iterative approach to solve this non-convex problem efficiently. Moreover, the optimization of the training reflection sequences at the RIS is studied to improve the estimation performance.
The double linear transformation model
$\bm Y = \bm {AXB}+ \bm W$
plays an important role in a variety of science and engineering applications, where
$\bm X$
is estimated through known transformation matrices
$\bm A$
and
$\bm B$
from the noisy measurement
$\bm Y$
. Decoupling
$\bm X$
from
$\bm Y$
is a formidable task due to the high complexity brought by the multiplication of the unknown matrix (vector) with the transformation matrix (M-UMTM). Unitary approximate message passing (UAMP) has been verified as a low complexity and strong robustness solution to the M-UMTM problems. However, it has only been used to tackle the problems with a single linear transformation matrix. In this work, we develop a generalized algorithm, namely, generalized double UAMP (GD-UAMP) for the target model, which not only inherits the low complexity of AMP, but also enhances robustness by employing double unitary transformation. As a generalized algorithm, GD-UAMP can be applied to address the generalized Bayesian inference problem, i.e., the arbitrary prior probability of
$\bm X$
and likelihood function of
$\bm Z$
, where
$\bm Z= \bm {AXB}$
is the noiseless measurement. We verify the feasibility of the proposed algorithm in the channel estimation problem for various wireless communication systems. Numerical results demonstrate that the proposed algorithm can perfectly fit different scenarios and showcase superior performance compared with benchmarks.
Channel acquisition is one of the main challenges for the deployment of reconfigurable intelligent surface (RIS) aided communication systems. This is because an RIS has a large number of reflective elements, which are passive devices with no active transmitting/receiving abilities. In this paper, we study the channel estimation problem for the RIS aided multi-user millimeter-wave (mmWave) multi-input multi-output (MIMO) system. Specifically, we propose a novel channel estimation protocol for the above system to estimate the cascaded channels, which are the products of the channels from the base station (BS) to the RIS and from the RIS to the users. Further, since the cascaded channels are typically sparse, this allows us to formulate the channel estimation problem as a sparse recovery problem using compressive sensing (CS) techniques, thereby allowing the channels to be estimated with less training overhead. Moreover, the sparse channel matrices of the cascaded channels of all users have a common block sparsity structure due to the common channel between the BS and the RIS. To take advantage of the common sparsity pattern, we propose a two-step multi-user joint channel estimation procedure. In the first step, we make use of the common column-block sparsity and project the received signals onto the common column subspace. In the second step, we make use of the row-block sparsity of the projected signals and propose a multi-user joint sparse matrix recovery algorithm that takes into account the common channel between the BS and the RIS.
In this paper, we propose a strategy to mitigate the problem of inefficient clustering performance by introducing data augmentation as an auxiliary plug-in. Classical clustering techniques such as K-means, Gaussian mixture model, and spectral clustering are central to many data-driven applications. However, recently unsupervised simultaneous feature learning and clustering using neural networks also known as Deep Embedded Clustering (DEC) has gained prominence. Pioneering works on deep feature clustering focus on defining relevant clustering loss function and choosing the right neural network for extracting features. A central problem in all these cases is data sparsity accompanied by high intra-class and low inter-class variance, which subsequently leads to poor clustering performance and erroneous candidate assignments. Toward this, we employ data augmentation techniques to improve the density of the clusters, thus improving the overall performance. We train a variant of Convolutional Autoencoder (CAE) with augmented data to construct the initial feature space as a novel model for deep clustering. We demonstrate the results of proposed strategy on crowdsourced Indian Heritage dataset. Extensive experiments show consistent improvements over existing works.
In this paper, we propose a categorization strategy to handle the incremental nature of data by identifying concepts of drift in the data stream. In the world of digitalization, the total amount of data created, captured, copied, and consumed is increasing rapidly, reaching a few zettabytes. Various fields of data mining and machine learning applications involve clustering as their principal component, considering the non-incremental nature of the data. However, many real-world machine learning algorithms need to adapt to this ever-growing global data sphere to continually learn new patterns. In addition, the model needs to be acquainted with the continuous change in the distribution of the input data. Towards this, we propose a clustering algorithm termed as Progressive Clustering to foresee the phenomenon of increase in data and sustain it until the pattern of the data changes considerably. We demonstrate the results of our clustering algorithm by simulating various instances of the incremental nature of the data in the form of a data stream. We demonstrate the results of our proposed methodology on benchmark MNIST and Fashion-MNIST datasets and evaluate our strategy using appropriate quantitative metrics.KeywordsUnsupervised learningIncremental dataConcept drift
