arXiv subjects

Lin Zhang

Publications and source records attributed to Lin Zhang.

At least 325 records · Page 18Linked to original sources

arXiv2020

Deep Reinforcement Learning for Multi-Agent Power Control in Heterogeneous Networks

We consider a typical heterogeneous network (HetNet), in which multiple access points (APs) are deployed to serve users by reusing the same spectrum band. Since different APs and users may cause severe interference to each other, advanced power control techniques are needed to manage the interference and enhance the sum-rate of the whole network. Conventional power control techniques first collect instantaneous global channel state information (CSI) and then calculate sub-optimal solutions. Nevertheless, it is challenging to collect instantaneous global CSI in the HetNet, in which global CSI typically changes fast. In this paper, we exploit deep reinforcement learning (DRL) to design a multi-agent power control algorithm in the HetNet. To be specific, by treating each AP as an agent with a local deep neural network (DNN), we propose a multiple-actor-shared-critic (MASC) method to train the local DNNs separately in an online trial-and-error manner. With the proposed algorithm, each AP can independently use the local DNN to control the transmit power with only local observations. Simulations results show that the proposed algorithm outperforms the conventional power control algorithms in terms of both the converged average sum-rate and the computational complexity.

cs.IT↗

arXiv2020

Towards Palmprint Verification On Smartphones

With the rapid development of mobile devices, smartphones have gradually become an indispensable part of people's lives. Meanwhile, biometric authentication has been corroborated to be an effective method for establishing a person's identity with high confidence. Hence, recently, biometric technologies for smartphones have also become increasingly sophisticated and popular. But it is noteworthy that the application potential of palmprints for smartphones is seriously underestimated. Studies in the past two decades have shown that palmprints have outstanding merits in uniqueness and permanence, and have high user acceptance. However, currently, studies specializing in palmprint verification for smartphones are still quite sporadic, especially when compared to face- or fingerprint-oriented ones. In this paper, aiming to fill the aforementioned research gap, we conducted a thorough study of palmprint verification on smartphones and our contributions are twofold. First, to facilitate the study of palmprint verification on smartphones, we established an annotated palmprint dataset named MPD, which was collected by multi-brand smartphones in two separate sessions with various backgrounds and illumination conditions. As the largest dataset in this field, MPD contains 16,000 palm images collected from 200 subjects. Second, we built a DCNN-based palmprint verification system named DeepMPV+ for smartphones. In DeepMPV+, two key steps, ROI extraction and ROI matching, are both formulated as learning problems and then solved naturally by modern DCNN models. The efficiency and efficacy of DeepMPV+ have been corroborated by extensive experiments. To make our results fully reproducible, the labeled dataset and the relevant source codes have been made publicly available at https://cslinzhang.github.io/MobilePalmPrint/.

cs.CV↗

arXiv2020

Multi-robot Cooperative Object Transportation using Decentralized Deep Reinforcement Learning

Object transportation could be a challenging problem for a single robot due to the oversize and/or overweight issues. A multi-robot system can take the advantage of increased driving power and more flexible configuration to solve such a problem. However, increased number of individuals also changed the dynamics of the system which makes control of a multi-robot system more complicated. Even worse, if the whole system is sitting on a centralized decision making unit, the data flow could be easily overloaded due to the upscaling of the system. In this research, we propose a decentralized control scheme on a multi-robot system with each individual equipped with a deep Q-network (DQN) controller to perform an oversized object transportation task. DQN is a deep reinforcement learning algorithm thus does not require the knowledge of system dynamics, instead, it enables the robots to learn appropriate control strategies through trial-and-error style interactions within the task environment. Since analogous controllers are distributed on the individuals, the computational bottleneck is avoided systematically. We demonstrate such a system in a scenario of carrying an oversized rod through a doorway by a two-robot team. The presented multi-robot system learns abstract features of the task and cooperative behaviors are observed. The decentralized DQN-style controller is showing strong robustness against uncertainties. In addition, We propose a universal metric to assess the cooperation quantitatively.

cs.RO↗

arXiv2020

Deep Image Translation for Enhancing Simulated Ultrasound Images

Ultrasound simulation based on ray tracing enables the synthesis of highly realistic images. It can provide an interactive environment for training sonographers as an educational tool. However, due to high computational demand, there is a trade-off between image quality and interactivity, potentially leading to sub-optimal results at interactive rates. In this work we introduce a deep learning approach based on adversarial training that mitigates this trade-off by improving the quality of simulated images with constant computation time. An image-to-image translation framework is utilized to translate low quality images into high quality versions. To incorporate anatomical information potentially lost in low quality images, we additionally provide segmentation maps to image translation. Furthermore, we propose to leverage information from acoustic attenuation maps to better preserve acoustic shadows and directional artifacts, an invaluable feature for ultrasound image interpretation. The proposed method yields an improvement of 7.2% in Fréchet Inception Distance and 8.9% in patch-based Kullback-Leibler divergence.

cs.CV↗

arXiv2020

Deep Network for Scatterer Distribution Estimation for Ultrasound Image Simulation

Simulation-based ultrasound training can be an essential educational tool. Realistic ultrasound image appearance with typical speckle texture can be modeled as convolution of a point spread function with point scatterers representing tissue microstructure. Such scatterer distribution, however, is in general not known and its estimation for a given tissue type is fundamentally an ill-posed inverse problem. In this paper, we demonstrate a convolutional neural network approach for probabilistic scatterer estimation from observed ultrasound data. We herein propose to impose a known statistical distribution on scatterers and learn the mapping between ultrasound image and distribution parameter map by training a convolutional neural network on synthetic images. In comparison with several existing approaches, we demonstrate in numerical simulations and with in-vivo images that the synthesized images from scatterer representations estimated with our approach closely match the observations with varying acquisition parameters such as compression and rotation of the imaged domain.

cs.CV↗

arXiv2020

Learning Global and Local Consistent Representations for Unsupervised Image Retrieval via Deep Graph Diffusion Networks

Diffusion has shown great success in improving accuracy of unsupervised image retrieval systems by utilizing high-order structures of image manifold. However, existing diffusion methods suffer from three major limitations: 1) they usually rely on local structures without considering global manifold information; 2) they focus on improving pair-wise similarities within existing images input output transductively while lacking flexibility to learn representations for novel unseen instances inductively; 3) they fail to scale to large datasets due to prohibitive memory consumption and computational burden due to intrinsic high-order operations on the whole graph. In this paper, to address these limitations, we propose a novel method, Graph Diffusion Networks (GRAD-Net), that adopts graph neural networks (GNNs), a novel variant of deep learning algorithms on irregular graphs. GRAD-Net learns semantic representations by exploiting both local and global structures of image manifold in an unsupervised fashion. By utilizing sparse coding techniques, GRAD-Net not only preserves global information on the image manifold, but also enables scalable training and efficient querying. Experiments on several large benchmark datasets demonstrate effectiveness of our method over state-of-the-art diffusion algorithms for unsupervised image retrieval.

cs.CV↗

arXiv2020

One-Shot Object Detection without Fine-Tuning

Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited. In this paper, we attempt to enrich such categories by addressing the one-shot object detection problem, where the number of annotated training examples for learning an unseen class is limited to one. We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module, the combination of which integrates metric learning with an anchor-free Faster R-CNN-style detection pipeline, eventually eliminating the need to fine-tune on the support images. We also propose novel training strategies that effectively improve detection performance. Extensive quantitative and qualitative evaluations were performed and our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.

cs.CV↗

arXiv2020

Stability of dynamical topology against dynamical noise in quantum quenches

Equilibrium topological phases are robust against weak static disorder but may break down in the strong disorder regime. Here we explore the stability of the quench-induced emergent dynamical topology in the presence of dynamical noise. We develop an analytic theory and show that for weak noise, the quantum dynamics induced by quenching an initial trivial phase to Chern insulating regime exhibits robust emergent topology on certain momentum subspaces called band inversion surfaces (BISs). The dynamical topology is protected by the minimal oscillation frequency over the BISs, mimicking a bulk gap of the dynamical phase. Singularities emerge in the quench dynamics, with the minimal oscillation frequency vanishing on the BISs if increasing noise to critical strength, manifesting a dynamical topological transition, beyond which the emergent topology breaks down. Two types of dynamical transitions are predicted. Interestingly, we predict a sweet spot in the critical transition when noise couples to all three spin components in the same strength, in which case the dynamical topology survives at arbitrarily strong noise regime. This work unveils novel features of the dynamical topology under dynamical noise, which can be probed with control in experiment.

cond-mat.mes-hall↗

arXiv2020

Uncertainty Relations Based on Modified Wigner-Yanase-Dyson Skew Information

Uncertainty relation is a core issue in quantum mechanics and quantum information theory. We introduce modified generalized Wigner-Yanase-Dyson (MGWYD) skew information and modified weighted generalizedWigner-Yanase-Dyson (MWGWYD) skew information, and establish new uncertainty relations in terms of the MGWYD skew information and MWGWYD skew information.

quant-ph↗

arXiv2020

Coherence and complementarity based on modified generalized skew information

We introduce modified generalized Wigner-Yanase-Dyson (MGWYD) skew information and modified weighted generalized Wigner-Yanase-Dyson (MWGWYD) skew information. By revisiting state-channel interaction based on MGWYD skew information, a family of coherence measures with respect to quantum channels is proposed. Furthermore, explicit analytical expressions of these coherence measures of qubit states are derived with respect to different quantum channels. Moreover, complementarity relations based on MGWYD skew information and MWGWYD skew information are also presented. Specifically, the conservation relations are investigated, while two interpretations of them including symmetry-asymmetry complementarity and wave-particle duality have been proposed.

quant-ph↗

arXiv2020

Value-Decomposition Networks based Distributed Interference Control in Multi-platoon Groupcast

Platooning is considered one of the most representative 5G use cases. Due to the small spacing within the platoon, the platoon needs more reliable transmission to guarantee driving safety while improving fuel and driving efficiency. However, efficient resource allocation between platoons has been a challenge, especially considering that the channel and power selected by each platoon will affect other platoons. Therefore, platoons need to coordinate with each other to ensure the groupcast quality of each platoon. To solve these challenges, we model the multi-platoon resource selection problem as Markov games and then propose a distributed resource allocation algorithm based on Value-Decomposition Networks. Our scheme utilizes the historical data of each platoon for centralized training. In distributed execution, agents only need their local observations to make decisions. At the same time, we decrease the training burden by sharing the neural network parameters. Simulation results show that the proposed algorithm has excellent convergence. Compared with another multi-agent algorithm (MARL) and random algorithm, our proposed solution can dramatically reduce the probability of platoon groupcast failure and improve the quality of platoon groupcast.

cs.NI↗

arXiv2020

Joint Optimization of Spectrum and Energy Efficiency Considering the C-V2X Security: A Deep Reinforcement Learning Approach

Cellular vehicle-to-everything (C-V2X) communication, as a part of 5G wireless communication, has been considered one of the most significant techniques for Smart City. Vehicles platooning is an application of Smart City that improves traffic capacity and safety by C-V2X. However, different from vehicles platooning travelling on highways, C-V2X could be more easily eavesdropped and the spectrum resource could be limited when they converge at an intersection. Satisfying the secrecy rate of C-V2X, how to increase the spectrum efficiency (SE) and energy efficiency (EE) in the platooning network is a big challenge. In this paper, to solve this problem, we propose a Security-Aware Approach to Enhancing SE and EE Based on Deep Reinforcement Learning, named SEED. The SEED formulates an objective optimization function considering both SE and EE, and the secrecy rate of C-V2X is treated as a critical constraint of this function. The optimization problem is transformed into the spectrum and transmission power selections of V2V and V2I links using deep Q network (DQN). The heuristic result of SE and EE is obtained by the DQN policy based on rewards. Finally, we simulate the traffic and communication environments using Python. The evaluation results demonstrate that the SEED outperforms the DQN-wopa algorithm and the baseline algorithm by 31.83 % and 68.40 % in efficiency. Source code for the SEED is available at https://github.com/BandaidZ/OptimizationofSEandEEBasedonDRL.

cs.NI↗

arXiv2020

Edge-assisted Viewport Adaptive Scheme for real-time Omnidirectional Video transmission

Omnidirectional applications are immersive and highly interactive, which can improve the efficiency of remote collaborative work among factory workers. The transmission of omnidirectional video (OV) is the most important step in implementing virtual remote collaboration. Compared with the ordinary video transmission, OV transmission requires more bandwidth, which is still a huge burden even under 5G networks. The tile-based scheme can reduce bandwidth consumption. However, it neither accurately obtain the field of view(FOV) area, nor difficult to support real-time OV streaming. In this paper, we propose an edge-assisted viewport adaptive scheme (EVAS-OV) to reduce bandwidth consumption during real-time OV transmission. First, EVAS-OV uses a Gated Recurrent Unit(GRU) model to predict users' viewport. Then, users were divided into multicast clusters thereby further reducing the consumption of computing resources. EVAS-OV reprojects OV frames to accurately obtain users' FOV area from pixel level and adopt a redundant strategy to reduce the impact of viewport prediction errors. All computing tasks were offloaded to edge servers to reduce the transmission delay and improve bandwidth utilization. Experimental results show that EVAS-OV can save more than 60\% of bandwidth compared with the non-viewport adaptive scheme. Compared to a two-layer scheme with viewport adaptive, EVAS-OV still saves 30\% of bandwidth.

cs.MM↗

arXiv2020

Reinforcement Learning Driven Adaptive VR Streaming with Optical Flow Based QoE

With the merit of containing full panoramic content in one camera, Virtual Reality (VR) and 360-degree videos have attracted more and more attention in the field of industrial cloud manufacturing and training. Industrial Internet of Things (IoT), where many VR terminals needed to be online at the same time, can hardly guarantee VR's bandwidth requirement. However, by making use of users' quality of experience (QoE) awareness factors, including the relative moving speed and depth difference between the viewpoint and other content, bandwidth consumption can be reduced. In this paper, we propose OFB-VR (Optical Flow Based VR), an interactive method of VR streaming that can make use of VR users' QoE awareness to ease the bandwidth pressure. The Just-Noticeable Difference through Optical Flow Estimation (JND-OFE) is explored to quantify users' awareness of quality distortion in 360-degree videos. Accordingly, a novel 360-degree videos QoE metric based on PSNR and JND-OFE (PSNR-OF) is proposed. With the help of PSNR-OF, OFB-VR proposes a versatile-size tiling scheme to lessen the tiling overhead. A Reinforcement Learning(RL) method is implemented to make use of historical data to perform Adaptive BitRate(ABR). For evaluation, we take two prior VR streaming schemes, Pano and Plato, as baselines. Vast evaluations show that our system can increase the mean PSNR-OF score by 9.5-15.8% while maintaining the same rebuffer ratio compared with Pano and Plato in a fluctuate LTE bandwidth dataset. Evaluation results show that OFB-VR is a promising prototype for actual interactive industrial VR. A prototype of OFB-VR can be found in https://github.com/buptexplorers/OFB-VR.

cs.MM↗

arXiv2020

Real-Time Monitoring of Area Angles with Synchrophasor Measurements

This paper develops a comprehensive framework of Area Angle Monitoring (AAM) to monitor the stress of bulk power transfer across an area of a power transmission system in real-time. Area angle is calculated from synchrophasor measurements to provide alert to system operators if the area angle exceeds pre-defined thresholds. This paper proposes general methods to identify these warning and emergency thresholds, and tests a mitigation strategy to relieve the area stress when the area angle exceeds the threshold. In order to handle the limited coverage of synchrophasor measurements, this paper proposes methods to estimate phase angles for boundary buses without synchrophasor measurements, which extends the application of AAM. AAM is verified for a power transmission area in the Western Electricity Coordinating Council system with both simulated data and synchrophasor measurements recorded from real events. A utility deployment to test the framework for monitoring area angle with live-stream and recorded synchrophasor data is described.

math.DS↗

arXiv2020

Quantum simulation for three-dimensional chiral topological insulator

Quantum simulation, as a state-of-art technique, provides the powerful way to explore topological quantum phases beyond natural limits. Nevertheless, a previously-not-realized three-dimensional (3D) chiral topological insulator, and demonstrate by quantum quenches a complete study of both the bulk and surface topological physics. First, a dynamical bulk-surface correspondence in momentum space is observed, showing that the bulk topology of the 3D phase uniquely corresponds to the nontrivial quench dynamics emerging on 2D momentum hypersurfaces called band inversion surfaces (BISs), equivalent to the bulk-boundary correspondence in real space. Further, the symmetry protection of the 3D chiral phase is uncovered by measuring dynamical spin textures on BISs, which exhibit perfect (broken) topology when the chiral symmetry is preserved (broken). Finally we measure the topological charges to characterize directly the bulk topology, and identify an emergent dynamical topological transition when varying the quenches from deep to shallow regimes. This work opens a new avenue of quantum simulation towards for the complete study of topological quantum phases.

quant-ph↗

arXiv2020

Constructing mutually unbiased bases from unextendible maximally entangled bases

We study mutually unbiased bases (MUBs) in which all the bases are unextendible maximally entangled ones. We first present a necessary and sufficient condition of constructing a pair of MUBs in $C^2 \otimes C^4$. Based on this condition, an analytical and necessary condition for constructing MUBs is given. Moreover we illustrate our approach by some detailed examples in $C^2 \otimes C^4$. The results are generalized to $C^2 \otimes C^d$ $(d\geq 3)$ and a concrete example in $C^2 \otimes C^8$ is given.

quant-ph↗

arXiv2020

Bayesian Spatial Models for Voxel-wise Prostate Cancer Classification Using Multi-parametric MRI Data

Multi-parametric magnetic resonance imaging (mpMRI) plays an increasingly important role in the diagnosis of prostate cancer. Various computer-aided detection algorithms have been proposed for automated prostate cancer detection by combining information from various mpMRI data components. However, there exist other features of mpMRI, including the spatial correlation between voxels and between-patient heterogeneity in the mpMRI parameters, that have not been fully explored in the literature but could potentially improve cancer detection if leveraged appropriately. This paper proposes novel voxel-wise Bayesian classifiers for prostate cancer that account for the spatial correlation and between-patient heterogeneity in mpMRI. Modeling the spatial correlation is challenging due to the extreme high dimensionality of the data, and we consider three computationally efficient approaches using Nearest Neighbor Gaussian Process (NNGP), knot-based reduced-rank approximation, and a conditional autoregressive (CAR) model, respectively. The between-patient heterogeneity is accounted for by adding a subject-specific random intercept on the mpMRI parameter model. Simulation results show that properly modeling the spatial correlation and between-patient heterogeneity improves classification accuracy. Application to in vivo data illustrates that classification is improved by spatial modeling using NNGP and reduced-rank approximation but not the CAR model, while modeling the between-patient heterogeneity does not further improve our classifier. Among our proposed models, the NNGP-based model is recommended considering its robust classification accuracy and high computational efficiency.

stat.AP↗