arXiv subjects

Rui Zhang

Publications and source records attributed to Rui Zhang.

At least 865 records · Page 48Linked to original sources

arXiv2022

Predicting Cancer Treatments Induced Cardiotoxicity of Breast Cancer Patients

Cardiotoxicity induced by the breast cancer treatments (i.e., chemotherapy, targeted therapy and radiation therapy) is a significant problem for breast cancer patients. The cardiotoxicity risk for breast cancer patients receiving different treatments remains unclear. We developed and evaluated risk predictive models for cardiotoxicity in breast cancer patients using EHR data. The AUC scores to predict the CHF, CAD, CM and MI are 0.846, 0.857, 0.858 and 0.804 respectively. After adjusting for baseline differences in cardiovascular health, patients who received chemotherapy or targeted therapy appeared to have higher risk of cardiotoxicity than patients who received radiation therapy. Due to differences in baseline cardiac health across the different breast cancer treatment groups, caution is recommended in interpreting the cardiotoxic effect of these treatments.

stat.AP↗

arXiv2022

MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction

CTR prediction is essential for modern recommender systems. Ranging from early factorization machines to deep learning based models in recent years, existing CTR methods focus on capturing useful feature interactions or mining important behavior patterns. Despite the effectiveness, we argue that these methods suffer from the risk of label sparsity (i.e., the user-item interactions are highly sparse with respect to the feature space), label noise (i.e., the collected user-item interactions are usually noisy), and the underuse of domain knowledge (i.e., the pairwise correlations between samples). To address these challenging problems, we propose a novel Multi-Interest Self-Supervised learning (MISS) framework which enhances the feature embeddings with interest-level self-supervision signals. With the help of two novel CNN-based multi-interest extractors,self-supervision signals are discovered with full considerations of different interest representations (point-wise and union-wise), interest dependencies (short-range and long-range), and interest correlations (inter-item and intra-item). Based on that, contrastive learning losses are further applied to the augmented views of interest representations, which effectively improves the feature representation learning. Furthermore, our proposed MISS framework can be used as an plug-in component with existing CTR prediction models and further boost their performances. Extensive experiments on three large-scale datasets show that MISS significantly outperforms the state-of-the-art models, by up to 13.55% in AUC, and also enjoys good compatibility with representative deep CTR models.

cs.IR↗

arXiv2022

Near-Field Modelling and Performance Analysis of Modular Extremely Large-Scale Array Communications

This letter studies a new array architecture, termed as modular extremely large-scale array (XL-array), for which a large number of array elements are arranged in a modular manner. Each module consists of a moderate number of array elements and the modules are regularly arranged with the inter-module space typically much larger than signal wavelength to cater to the actual mounting structure. We study the mathematical modelling and conduct the performance analysis for modular XL-array communications, by considering the non-uniform spherical wave (NUSW) characteristic that is more suitable than the conventional uniform plane wave (UPW) assumption for physically large arrays. A closed-form expression is derived for the maximum signal-to-noise ratio (SNR) in terms of the geometries of the modular XL-array, including the total array size and module separation, as well as the user's location. The asymptotic SNR scaling law is revealed as the size of modular array goes to infinity. Furthermore, we show that the developed modelling and performance analysis include the existing results for collocated XL-array or far-field UPW assumption as special cases. Numerical results demonstrate the importance of near-field modelling for modular XL-array communications since it leads to significantly different results from the conventional far-field UPW modelling.

cs.IT↗

arXiv2022

Intelligent Reflecting Surface-Aided LEO Satellite Communication: Cooperative Passive Beamforming and Distributed Channel Estimation

We consider in this paper a new intelligent reflecting surface (IRS)-aided LEO satellite communication system, by utilizing the controllable phase shifts of massive passive reflecting elements to achieve flexible beamforming, which copes with the time-varying channel between the high-mobility satellite (SAT) and ground node (GN) cost-effectively. In particular, we propose a new architecture for IRS-aided LEO satellite communication where IRSs are deployed at both sides of the SAT and GN, and study their cooperative passive beamforming (CPB) design over line-of-sight (LoS)-dominant single-reflection and double-reflection channels. Specifically, we jointly optimize the active transmit/receive beamforming at the SAT/GN as well as the CPB at two-sided IRSs to maximize the overall channel gain from the SAT to each GN. Interestingly, we show that under LoS channel conditions, the high-dimensional SAT-GN channel can be decomposed into the outer product of two low-dimensional vectors. By exploiting the decomposed SAT-GN channel, we decouple the original beamforming optimization problem into two simpler subproblems corresponding to the SAT and GN sides, respectively, which are both solved in closed-form. Furthermore, we propose an efficient transmission protocol to conduct channel estimation and beam tracking, which only requires independent processing of the SAT and GN in a distributed manner, thus substantially reducing the implementation complexity. Simulation results validate the performance advantages of the proposed IRS-aided LEO satellite communication system with two-sided cooperative IRSs, as compared to various baseline schemes such as the conventional reflect-array and one-sided IRS.

cs.IT↗

arXiv2022

Transformation between elastic dipoles, quadrupoles, octupoles and hexadecapoles driven by surfactant self-assembly in nematic emulsion

Emulsions comprising isotropic fluid drops within a nematic host are of interest for applications ranging from biodetection to smart windows, which rely on changes of molecular alignment structures around the drops in response to chemical, thermal, electric and other stimuli. We show that absorption or desorption of trace amounts of common surfactants can drive continuous transformations of elastic multipoles induced by the droplets within the uniformly aligned nematic host. Out-of-equilibrium dynamics of director structures emerge from a controlled self-assembly or desorption of different surfactants at the drop-nematic interfaces, with ensuing forward and reverse transformations between elastic dipoles, quadrupoles, octupoles and hexadecapoles. We characterize inter-transformations of droplet-induced surface and bulk defects, probe elastic pair interactions and discuss emergent prospects for fundamental science and applications of the reconfigurable nematic emulsions.

cond-mat.soft↗

arXiv2021

Distilling Object Detectors with Feature Richness

In recent years, large-scale deep models have achieved great success, but the huge computational complexity and massive storage requirements make it a great challenge to deploy them in resource-limited devices. As a model compression and acceleration method, knowledge distillation effectively improves the performance of small models by transferring the dark knowledge from the teacher detector. However, most of the existing distillation-based detection methods mainly imitating features near bounding boxes, which suffer from two limitations. First, they ignore the beneficial features outside the bounding boxes. Second, these methods imitate some features which are mistakenly regarded as the background by the teacher detector. To address the above issues, we propose a novel Feature-Richness Score (FRS) method to choose important features that improve generalized detectability during distilling. The proposed method effectively retrieves the important features outside the bounding boxes and removes the detrimental features within the bounding boxes. Extensive experiments show that our methods achieve excellent performance on both anchor-based and anchor-free detectors. For example, RetinaNet with ResNet-50 achieves 39.7% in mAP on the COCO2017 dataset, which even surpasses the ResNet-101 based teacher detector 38.9% by 0.8%. Our implementation is available at https://github.com/duzhixing/FRS.

cs.CV↗

arXiv2021

CBHE: Corner-based Building Height Estimation for Complex Street Scene Images

Building height estimation is important in many applications such as 3D city reconstruction, urban planning, and navigation. Recently, a new building height estimation method using street scene images and 2D maps was proposed. This method is more scalable than traditional methods that use high-resolution optical data, LiDAR data, or RADAR data which are expensive to obtain. The method needs to detect building rooflines and then compute building height via the pinhole camera model. We observe that this method has limitations in handling complex street scene images in which buildings overlap with each other and the rooflines are difficult to locate. We propose CBHE, a building height estimation algorithm considering both building corners and rooflines. CBHE first obtains building corner and roofline candidates in street scene images based on building footprints from 2D maps and the camera parameters. Then, we use a deep neural network named BuildingNet to classify and filter corner and roofline candidates. Based on the valid corners and rooflines from BuildingNet, CBHE computes building height via the pinhole camera model. Experimental results show that the proposed BuildingNet yields a higher accuracy on building corner and roofline candidate filtering compared with the state-of-the-art open set classifiers. Meanwhile, CBHE outperforms the baseline algorithm by over 10% in building height estimation accuracy.

cs.CV↗

arXiv2021

An Overview of Signal Processing Techniques for RIS/IRS-aided Wireless Systems

In the past as well as present wireless communication systems, the wireless propagation environment is regarded as an uncontrollable black box that impairs the received signal quality, and its negative impacts are compensated for by relying on the design of various sophisticated transmission/reception schemes. However, the improvements through applying such schemes operating at two endpoints (i.e., transmitter and receiver) only are limited even after five generations of wireless systems. Reconfigurable intelligent surface (RIS) or intelligent reflecting surface (IRS) have emerged as a new and revolutionary technology that can configure the wireless environment in a favorable manner by properly tuning the phase shifts of a large number of quasi passive and low-cost reflecting elements, thus standing out as a promising candidate technology for the next-/sixth-generation (6G) wireless system. However, to reap the performance benefits promised by RIS/IRS, efficient signal processing techniques are crucial, for a variety of purposes such as channel estimation, transmission design, radio localization, and so on. In this paper, we provide a comprehensive overview of recent advances on RIS/IRS-aided wireless systems from the signal processing perspective. We also highlight promising research directions that are worthy of investigation in the future.

eess.SP↗

arXiv2021

Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime

Understanding the black-box prediction for neural networks is challenging. To achieve this, early studies have designed influence function (IF) to measure the effect of removing a single training point on neural networks. However, the classic implicit Hessian-vector product (IHVP) method for calculating IF is fragile, and theoretical analysis of IF in the context of neural networks is still lacking. To this end, we utilize the neural tangent kernel (NTK) theory to calculate IF for the neural network trained with regularized mean-square loss, and prove that the approximation error can be arbitrarily small when the width is sufficiently large for two-layer ReLU networks. We analyze the error bound for the classic IHVP method in the over-parameterized regime to understand when and why it fails or not. In detail, our theoretical analysis reveals that (1) the accuracy of IHVP depends on the regularization term, and is pretty low under weak regularization; (2) the accuracy of IHVP has a significant correlation with the probability density of corresponding training points. We further borrow the theory from NTK to understand the IFs better, including quantifying the complexity for influential samples and depicting the variation of IFs during the training dynamics. Numerical experiments on real-world data confirm our theoretical results and demonstrate our findings.

cs.LG↗

arXiv2021

Transforming Fading Channel from Fast to Slow: Intelligent Refracting Surface Aided High-Mobility Communication

Intelligent reflecting/refracting surface (IRS) has recently emerged as a promising solution to reconfigure wireless propagation environment for enhancing the communication performance. In this paper, we study a new IRS-aided high-mobility communication system by employing the intelligent refracting surface with a high-speed vehicle to aid its passenger's communication with a remote base station (BS). Due to the environment's random scattering and vehicle's high mobility, a rapidly time-varying channel is typically resulted between the static BS and fast-moving IRS/user, which renders the channel estimation for IRS with a large number of elements more challenging. In order to reap the high IRS passive beamforming gain with low channel training overhead, we propose a new and efficient transmission protocol to achieve both IRS channel estimation and refraction optimization for data transmission. Specifically, by exploiting the quasi-static channel between the IRS and user both moving at the same high speed as well as the line-of-sight (LoS) dominant channel between the BS and IRS, the user first estimates the LoS component of the cascaded BS-IRS-user channel, based on which IRS passive refraction is designed to maximize the corresponding IRS-refracted channel gain. Then, the user estimates the resultant IRS-refracted channel as well as the non-IRS-refracted channel for setting an additional common phase shift at all IRS refracting elements so as to align these two channels for maximizing the overall channel gain for data transmission. Simulation results show significant performance improvement of the proposed design as compared to various benchmark schemes. The proposed on-vehicle IRS system is further compared with a baseline scheme of deploying fixed intelligent reflecting surfaces on the roadside to assist high-speed vehicular communications, which achieves significant rate improvement.

cs.IT↗

arXiv2021

Feature-based Recognition Framework for Super-resolution Images

In practical application, the performance of recognition network usually decreases when being applied on super-resolution images. In this paper, we propose a feature-based recognition network combined with GAN (FGAN). Our network improves the recognition accuracy by extracting more features that benefit recognition from SR images. In the experiment, we build three datasets using three different super-resolution algorithm, and our network increases the recognition accuracy by more than 6% comparing with ReaNet50 and DenseNet121.

cs.CV↗

arXiv2021

Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction

Click-through rate prediction is one of the core tasks in commercial recommender systems. It aims to predict the probability of a user clicking a particular item given user and item features. As feature interactions bring in non-linearity, they are widely adopted to improve the performance of CTR prediction models. Therefore, effectively modelling feature interactions has attracted much attention in both the research and industry field. The current approaches can generally be categorized into three classes: (1) naïve methods, which do not model feature interactions and only use original features; (2) memorized methods, which memorize feature interactions by explicitly viewing them as new features and assigning trainable embeddings; (3) factorized methods, which learn latent vectors for original features and implicitly model feature interactions through factorization functions. Studies have shown that modelling feature interactions by one of these methods alone are suboptimal due to the unique characteristics of different feature interactions. To address this issue, we first propose a general framework called OptInter which finds the most suitable modelling method for each feature interaction. Different state-of-the-art deep CTR models can be viewed as instances of OptInter. To realize the functionality of OptInter, we also introduce a learning algorithm that automatically searches for the optimal modelling method. We conduct extensive experiments on four large datasets. Our experiments show that OptInter improves the best performed state-of-the-art baseline deep CTR models by up to 2.21%. Compared to the memorized method, which also outperforms baselines, we reduce up to 91% parameters. In addition, we conduct several ablation studies to investigate the influence of different components of OptInter. Finally, we provide interpretable discussions on the results of OptInter.

cs.LG↗

arXiv2021

Environment-Aware Beam Selection for IRS-Aided Communication with Channel Knowledge Map

Intelligent reflecting surface (IRS)-aided communication is a promising technology for beyond 5G (B5G) systems, to reconfigure the radio environment proactively. However, IRS-aided communication in practice requires efficient channel estimation or passive beam training, whose overhead and complexity increase drastically with the number of reflecting elements/beam directions. To tackle this challenge, we propose in this paper a novel environment-aware joint active and passive beam selection scheme for IRS-aided wireless communication, based on the new concept of channel knowledge map (CKM). Specifically, by utilizing both the location information of the user equipment (UE), which is readily available in contemporary wireless systems with ever-increasing accuracy, and the environment information offered by CKM, the proposed scheme achieves efficient beam selection with either no real-time training required (training-free beam selection) or only moderate training overhead (light-training beam selection). Numerical results based on practical channels obtained using commercial ray tracing software are presented, which demonstrate the superior performance of the proposed scheme over various benchmark schemes.

cs.IT↗

arXiv2021

High-Intensity and Uniform Red-Green-Blue Triple Reflective Bands Achieved by Rationally-Designed Ultrathin Heterostructure Photonic Crystals

The relationships between material constructions and reflective spectrum patterns are important properties of photonic crystals. One particular interesting reflectance profile is a high-intensity and uniform three-peak pattern with peak positions right located at the red, green, and blue (RGB, three original colors) region. For ease of construction, a seek for using one-dimensional photonic crystals to achieve RGB triple reflective bands is a meaningful endeavor. Only very limited previous studies exist, all relying on traditional periodic photonic crystals (PPCs) and of large thickness. The underlying physical principles remain elusive, leaving the question of thickness limit to achieve RGB bands unaddressed. Here, we present the first detailed work to explore the thickness limit issue based on both theoretical and experimental investigation. A set of heuristically derived design principles are used to uncover that the break of translational symmetry, thus introducing heterostructure photonic crystals (HPCs), is essential to reduce the total optical path difference (OPD) to ~ 3200nm (the theoretical limit) while still exhibiting high-quality RGB bands. A systematic experiment based on a 12-layer heterostructure construction was performed and well confirmed the theoretical predictions. The associated three-peak properties are successfully used to realize quantum dot fluorescent enhancement phenomena. Furthermore, the HPC exhibits unusually stability against solvent stimulus, in strong contrast to typical behaviors reported in PPCs. Our work for the first time proposes and verifies important rational rules for designing ultrathin HPCs toward RGB reflective bands, and provides insights for a wider range of explorations of light manipulation in photonic crystals.

physics.optics↗

arXiv2021

Two distinct approaches to tune multiple reflective bands of one-dimensional photonic crystal at normal incidence

One-dimensional photonic crystals (1D PC) represent a class of periodic optical material, composed of alternating media with different dielectric constants along one direction. The most important property of 1D PCs is their photonic band-gap. However, multiple reflective bands are rarely reported in this research area. In this paper we demonstrate the tunability of multiple reflective bands in conventional 1D PC structure and 1D PC heterostructure. For both two types of 1D PC construction, positions of multiple reflective bands can be regulated under certain principles. In addition, structural color is revealed by transforming reflection spectra into CIE coordinates. It is indicated that the CIE coordinate shifts caused by multiple reflective bands behave quite different compared to those caused by one major photonic band-gap. The two approaches reported in this work may provide insights for the application of 1D PC in areas such as displays, sensors, and decoration.

physics.optics↗

arXiv2021

IRS-Aided Wireless Relaying: Optimal Deployment and Capacity Scaling

In this letter, we consider an intelligent reflecting surface (IRS)-aided wireless relaying system, where a decode-and-forward relay (R) is employed to forward data from a source (S) to a destination (D), aided by M passive reflecting elements. We consider two practical IRS deployment strategies, namely, single-IRS deployment where all reflecting elements are mounted on one single IRS that is deployed near S, R, or D, and multi-IRS deployment where the reflecting elements are allocated over three separate IRSs which are deployed near S, R, and D, respectively. Under the line-of-sight (LoS) channel model, we characterize the capacity scaling orders with respect to an increasing M for the IRS-aided relay system with different IRS deployment strategies. For single-IRS deployment, we show that deploying the IRS near R achieves the highest capacity as compared to that near S or D. While for multi-IRS deployment, we propose a practical cooperative IRS passive beamforming design which is analytically shown to achieve a larger capacity scaling order than the single-IRS deployment (i.e., near R or S/D) when M is sufficiently large. Numerical examples are provided, which validate our theoretical results.

cs.IT↗

arXiv2021

A Survey on Millimeter-Wave Beamforming Enabled UAV Communications and Networking

Unmanned aerial vehicles (UAVs) have found widespread commercial, civilian, and military applications. Wireless communication has always been one of the core technologies for UAV. However, the communication capacity is becoming a bottleneck for UAV to support more challenging application scenarios. The heavily-occupied sub-6 GHz frequency band is not sufficient to meet the ultra high-data-traffic requirements. The utilization of the millimeter-wave (mmWave) frequency bands is a promising direction for UAV communications, where large antenna arrays can be packed in a small area on the UAV to perform three-dimensional (3D) beamforming. On the other hand, UAVs serving as aerial access points or relays can significantly enhance the coverage and quality of service of the terrestrial mmWave cellular networks. In this paper, we provide a comprehensive survey on mmWave beamforming enabled UAV communications and networking. The technical potential of and challenges for mmWave-UAV communications are presented first. Then, we provide an overview on relevant mmWave antenna structures and channel modeling. Subsequently, the technologies and solutions for UAV-connected mmWave cellular networks and mmWave-UAV ad hoc networks are reviewed, respectively. Finally, we present open issues and promising directions for future research in mmWave beamforming enabled UAV communications and networking.

eess.SP↗

arXiv2021

Towards Emotion-Aware User Simulator for Task-Oriented Dialogue

The performance of a task-completion dialogue agent usually affects the user experience: when the conversation system yields an unreasonable response, users may feel dissatisfied. Besides, early termination often occurs in disappointing conversations. However, existing off-the-shelf user simulators generally assume an ideal and cooperative user, which is somewhat different from a real user, and inevitably lead to a sub-optimal dialogue policy. In this paper, we propose an emotion-aware user simulation framework for task-oriented dialogue, which is based on the OCC emotion model to update user emotions and drive user actions, to generate simulated behaviors that more similar to real users. We present a linear implementation (The source code will be released soon.) that is easy to understand and extend, and evaluate it on two domain-specific datasets. The experimental results show that the emotional simulation results of our proposed framework conform to common sense and have good versatility for different domains. Meanwhile, our framework provides us with another perspective to understand the improvement process of the dialogue policy model based on reinforcement learning.

cs.HC↗