arXiv subjects

Jiajia Guo

Publications and source records attributed to Jiajia Guo.

67 records · Page 4Linked to original sources

arXiv2021

CAnet: Uplink-aided Downlink Channel Acquisition in FDD Massive MIMO using Deep Learning

In frequency-division duplexing systems, the downlink channel state information (CSI) acquisition scheme leads to high training and feedback overheads. In this paper, we propose an uplink-aided downlink channel acquisition framework using deep learning to reduce these overheads. Unlike most existing works that focus only on channel estimation or feedback modules, to the best of our knowledge, this is the first study that considers the entire downlink CSI acquisition process, including downlink pilot design, channel estimation, and feedback. First, we propose an adaptive pilot design module by exploiting the correlation in magnitude among bidirectional channels in the angular domain to improve channel estimation. Next, to avoid the bit allocation problem during the feedback module, we concatenate the complex channel and embed the uplink channel magnitude to the channel reconstruction at the base station. Lastly, we combine the above two modules and compare two popular downlink channel acquisition frameworks. The former framework estimates and feeds back the channel at the user equipment subsequently. The user equipment in the latter one directly feeds back the received pilot signals to the base station. Our results reveal that, with the help of uplink, directly feeding back the pilot signals can save approximately 20% of feedback bits, which provides a guideline for future research.

cs.IT↗

arXiv2020

Deep Learning-Based CSI Feedback for Beamforming in Single- and Multi-cell Massive MIMO Systems

The potentials of massive multiple-input multiple-output (MIMO) are all based on the available instantaneous channel state information (CSI) at the base station (BS). Therefore, the user in frequency-division duplexing (FDD) systems has to keep on feeding back the CSI to the BS, thereby occupying large uplink transmission resources. Recently, deep learning (DL) has achieved great success in the CSI feedback. However, the existing works just focus on improving the feedback accuracy and ignore the effects on the following modules, e.g., beamforming (BF). In this paper, we propose a DL-based CSI feedback framework for BF design, called CsiFBnet. The key idea of the CsiFBnet is to maximize the BF performance gain rather than the feedback accuracy. We apply it to two representative scenarios: single- and multi-cell systems. The CsiFBnet-s in the single-cell system is based on the autoencoder architecture, where the encoder at the user compresses the CSI and the decoder at the BS generates the BF vector. The CsiFBnet-m in the multicell system has to feed back two kinds of CSI: the desired and the interfering CSI. The entire neural networks are trained by an unsupervised learning strategy. Simulation results show the great performance improvement and complexity reduction of the CsiFBnet compared with the conventional DL-based CSI feedback methods.

cs.IT↗

arXiv2020

Lightweight Convolutional Neural Networks for CSI Feedback in Massive MIMO

In frequency division duplex mode of massive multiple-input multiple-output systems, the downlink channel state information (CSI) must be sent to the base station (BS) through a feedback link. However, transmitting CSI to the BS is costly due to the bandwidth limitation of the feedback link. Deep learning (DL) has recently achieved remarkable success in CSI feedback. Realizing high-performance and low-complexity CSI feedback is a challenge in DL based communication. We develop a DL based CSI feedback network in this study to complete the feedback of CSI effectively. However, this network cannot be effectively applied to the mobile terminal because of the excessive numbers of parameters. Therefore, we further propose a new lightweight CSI feedback network based on the developed network. Simulation results show that the proposed CSI network exhibits better reconstruction performance than that of other CsiNet-related works. Moreover, the lightweight network maintains a few parameters and parameter complexity while ensuring satisfactory reconstruction performance. These findings suggest the feasibility and potential of the proposed techniques.

cs.IT↗

arXiv2020

Adversarial Attack on DL-based Massive MIMO CSI Feedback

With the increasing application of deep learning (DL) algorithms in wireless communications, the physical layer faces new challenges caused by adversarial attack. Such attack has significantly affected the neural network in computer vision. We chose DL-based analog channel state information (CSI) to show the effect of adversarial attack on DL-based communication system. We present a practical method to craft white-box adversarial attack on DL-based CSI feedback process. Our simulation results showed the destructive effect adversarial attack caused on DL-based CSI feedback by analyzing the performance of normalized mean square error. We also launched a jamming attack for comparison and found that the jamming attack could be prevented with certain precautions. As DL algorithm becomes the trend in developing wireless communication, this work raises concerns regarding the security in the use of DL-based algorithms.

cs.IT↗

arXiv2019

3-D Positioning and Environment Mapping for mmWave Communication Systems

Millimeter-wave (mmWave) cloud radio access networks (CRANs) provide new opportunities for accurate cooperative localization, in which large bandwidths, large antenna arrays, and increased densities of base stations allow for their unparalleled delay and angular resolution. Combining localization into communications and designing simultaneous localization and mapping (SLAM) algorithms are challenging problems. This study considers the joint position and velocity estimation and environment mapping problem in a three-dimensional mmWave CRAN architecture. We first embed cooperative localization into communications and establish the joint estimation and mapping model with hybrid delay and angle measurements. Then, we propose a closed-form weighted least square (WLS) solution for the joint estimation and mapping problems. The proposed WLS estimator is proven asymptotically unbiased and confirmed by simulations as effective in achieving the Cramer-Rao lower bound (CRLB) and the desired decimeter-level accuracy. Furthermore, we propose a WLS-Net-based SLAM algorithm by embedding neural networks into the proposed WLS estimators to replace the linear approximations. The solution possesses both powerful learning ability of the neural network and robustness of the proposed geometric model, and the ensemble learning is applied to further improve positioning accuracy. A public ray-tracing dataset is used in the simulations to test the performance of the WLS-Net-based SLAM algorithm, which is proven fast and effective in attaining the centimeter-level accuracy.

cs.IT↗

arXiv2019

Compression and Acceleration of Neural Networks for Communications

Deep learning (DL) has achieved great success in signal processing and communications and has become a promising technology for future wireless communications. Existing works mainly focus on exploiting DL to improve the performance of communication systems. However, the high memory requirement and computational complexity constitute a major hurdle for the practical deployment of DL-based communications. In this article, we investigate how to compress and accelerate the neural networks (NNs) in communication systems. After introducing the deployment challenges for DL-based communication algorithms, we discuss some representative NN compression and acceleration techniques. Afterwards, two case studies for multiple-input-multiple-output (MIMO) communications, including DL-based channel state information feedback and signal detection, are presented to show the feasibility and potential of these techniques. We finally identify some challenges on NN compression and acceleration in DL-based communications and provide a guideline for subsequent research.

cs.IT↗

arXiv2019

Convolutional Neural Network based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis

Massive multiple-input multiple-output (MIMO) is a promising technology to increase link capacity and energy efficiency. However, these benefits are based on available channel state information (CSI) at the base station (BS). Therefore, user equipment (UE) needs to keep on feeding CSI back to the BS, thereby consuming precious bandwidth resource. Large-scale antennas at the BS for massive MIMO seriously increase this overhead. In this paper, we propose a multiple-rate compressive sensing neural network framework to compress and quantize the CSI. This framework not only improves reconstruction accuracy but also decreases storage space at the UE, thus enhancing the system feasibility. Specifically, we establish two network design principles for CSI feedback, propose a new network architecture, CsiNet+, according to these principles, and develop a novel quantization framework and training strategy. Next, we further introduce two different variable-rate approaches, namely, SM-CsiNet+ and PM-CsiNet+, which decrease the parameter number at the UE by 38.0% and 46.7%, respectively. Experimental results show that CsiNet+ outperforms the state-of-the-art network by a margin but only slightly increases the parameter number. We also investigate the compression and reconstruction mechanism behind deep learning-based CSI feedback methods via parameter visualization, which provides a guideline for subsequent research.

eess.SP↗

arXiv2019

A Distributed Multi-RF Chain Hybrid mmWave Scheme for Small-cell Systems

This paper proposes a distributed hybrid millimeter wave (mmWave) scheme to exploit the structure of a Densely Deployed Distributed (DDD) small-cell-base-stations (SBSs) system for serving multiple users in a geographic area. Both the SBSs and the users are equipped with full access hybrid architectures with multi-antenna arrays and multiple radio frequency chains. Unlike the conventional cellular networks where users receive data streams from their nearest BSs, the users in our proposed scheme simultaneously receive data streams from different SBSs. With appropriate design of analog beamformers, co-channel multi-data-stream interference can be mitigated and the extra spatial degrees of freedom induced by the geographic distributed SBSs are exploited for data multiplexing. Analytical and simulation results show that the proposed scheme can improve the system sum-rate considerably, especially when the number of scattering components in millimeter wave channels is limited.

cs.IT↗

arXiv2018

Enhancing Cellular Performance through Device-to-Device Distributed MIMO

The integration of local device-to-device (D2D) communications and cellular connections has been intensively studied to satisfy co-existing D2D and cellular communication demand. In future cellular networks, there will be numerous standby users possessing D2D communication capabilities in close proximity to each other. Considering that these standby users do not necessarily request D2D communications all the time, in this paper we propose a hybrid D2D-cellular scheme to make use of these standby users and to improve the rate performance for cellular users. More specifically, through D2D links, a virtual antenna array can be formed by sharing antennas across different terminals to realize the diversity gain of MIMO channels. This paper considers the use of millimeter wave (mmWave) links to enable high data rate D2D communications. We then design an orthogonal D2D multiple access protocol and formulate the optimization problem of joint cellular and D2D resource allocation for downlink transmissions using the proposed scheme. We obtain a closed-form solution for D2D resource allocation, which reveals useful insights for practical system design. Numerical results from extensive system-level simulations demonstrate that the rate performance of cellular users is significantly improved.

cs.IT↗

arXiv2018

Multi-Beam NOMA for Hybrid mmWave Systems

In this paper, we propose a multi-beam non-orthogonal multiple access (NOMA) scheme for hybrid millimeter wave (mmWave) systems and study its resource allocation. A beam splitting technique is designed to generate multiple analog beams to serve multiple users for NOMA transmission. Compared to conventional mmWave orthogonal multiple access (mmWave-OMA) schemes, the proposed scheme can serve more than one user on each radio frequency (RF) chain. Besides, in contrast to the recently proposed single-beam mmWave-NOMA scheme which can only serve multiple NOMA users within the same beam, the proposed scheme can perform NOMA transmission for the users with an arbitrary angle-of-departure (AOD) distribution. This provides a higher flexibility for applying NOMA in mmWave communications and thus can efficiently exploit the potential multi-user diversity. Then, we design a suboptimal two-stage resource allocation for maximizing the system sum-rate. In the first stage, assuming that only analog beamforming is available, a user grouping and antenna allocation algorithm is proposed to maximize the conditional system sum-rate based on the coalition formation game theory. In the second stage, with the zero-forcing (ZF) digital precoder, a suboptimal solution is devised to solve a non-convex power allocation optimization problem for the maximization of the system sum-rate which takes into account the quality of service (QoS) constraint. Simulation results show that our designed resource allocation can achieve a close-to-optimal performance in each stage. In addition, we demonstrate that the proposed multi-beam mmWave-NOMA scheme offers a higher spectral efficiency than that of the single-beam mmWave-NOMA and the mmWave-OMA schemes.

cs.IT↗

arXiv2018

A Multi-Beam NOMA Framework for Hybrid mmWave Systems

In this paper, we propose a multi-beam non-orthogonal multiple access (NOMA) framework for hybrid millimeter wave (mmWave) systems. The proposed framework enables the use of a limited number of radio frequency (RF) chains in hybrid mmWave systems to accommodate multiple users with various angles of departures (AODs). A beam splitting technique is introduced to generate multiple analog beams to facilitate NOMA transmission. We analyze the performance of a system when there are sufficient numbers of antennas driven by a single RF chain at each transceiver. Furthermore, we derive the sufficient and necessary conditions of antenna allocation, which guarantees that the proposed multi-beam NOMA scheme outperforms the conventional time division multiple access (TDMA) scheme in terms of system sum-rate. The numerical results confirm the accuracy of the developed analysis and unveil the performance gain achieved by the proposed multi-beam NOMA scheme over the single-beam NOMA scheme.

cs.IT↗

arXiv2017

A deep learning-based method for relative location prediction in CT scan images

Relative location prediction in computed tomography (CT) scan images is a challenging problem. In this paper, a regression model based on one-dimensional convolutional neural networks is proposed to determine the relative location of a CT scan image both robustly and precisely. A public dataset is employed to validate the performance of the study's proposed method using a 5-fold cross validation. Experimental results demonstrate an excellent performance of the proposed model when compared with the state-of-the-art techniques, achieving a median absolute error of 1.04 cm and mean absolute error of 1.69 cm.

cs.CV↗

arXiv2017

Fairness Comparison of Uplink NOMA and OMA

In this paper, we compare the resource allocation fairness of uplink communications between non-orthogonal multiple access (NOMA) schemes and orthogonal multiple access (OMA) schemes. Through characterizing the contribution of the individual user data rate to the system sum rate, we analyze the fundamental reasons that NOMA offers a more fair resource allocation than that of OMA in asymmetric channels. Furthermore, a fairness indicator metric based on Jain's index is proposed to measure the asymmetry of multiuser channels. More importantly, the proposed metric provides a selection criterion for choosing between NOMA and OMA for fair resource allocation. Based on this discussion, we propose a hybrid NOMA-OMA scheme to further enhance the users fairness. Simulation results confirm the accuracy of the proposed metric and demonstrate the fairness enhancement of the proposed hybrid NOMA-OMA scheme compared to the conventional OMA and NOMA schemes.

cs.IT↗