arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 433 records · Page 24Linked to original sources

arXiv2023

Fluid Tunnel Research for Challenges of Urban Climate

Experimental investigations using wind and water tunnels have long been a staple of fluid mechanics research for a large number of applications. These experiments often single out a specific physical process to be investigated, while studies involving multiscale and multi-physics processes are rare due to the difficulty and complexity in the experimental setup. In the era of climate change, there is an increasing interest in innovative experimental studies in which fluid (wind and water) tunnels are employed for modelling multiscale, multi-physics phenomena of the urban climate. High-quality fluid tunnel measurements of urban-physics related phenomena are also much needed to facilitate the development and validation of advanced multi-physics numerical models. As a repository of knowledge in modelling these urban processes, we cover fundamentals, recommendations and guidelines for experimental design, recent advances and outlook on eight selected research areas, including (i) thermal buoyancy effects of urban airflows, (ii) aerodynamic and thermal effects of vegetation, (iii) radiative and convective heat fluxes over urban materials, (iv) influence of thermal stratification on land-atmosphere interactions, (v) pollutant dispersion, (vi) indoor and outdoor natural ventilation, (vii) wind thermal comfort, and (viii) urban winds over complex urban sites. Further, three main challenges, i.e., modelling of multi-physics, modelling of anthropogenic processes, and combined use of fluid tunnels, scaled outdoor and field measurements for urban climate studies, are discussed.

physics.flu-dyn↗

arXiv2022

Joint Communication and Sensing: Models and Potential of Using MIMO

The sixth-generation (6G) network is envisioned to integrate communication and sensing functions, so as to improve the spectrum efficiency (SE) and support explosive novel applications. Although the similarities of wireless communication and radio sensing lay the foundation for their combination, there is still considerable incompatible interest between them. To simultaneously guarantee the communication capacity and the sensing accuracy, the multiple-input and multiple-output (MIMO) technique plays an important role due to its unique capability of spatial beamforming and waveform shaping. However, the configuration of MIMO also brings high hardware cost, high power consumption, and high signal processing complexity. How to efficiently apply MIMO to achieve balanced communication and sensing performance is still open. In this survey, we discuss joint communication and sensing (JCAS) in the context of MIMO. We first outline the roles of MIMO in the process of wireless communication and radar sensing. Then, we present current advances in both communication and sensing coexistence and integration in detail. Three novel JCAS MIMO models are subsequently discussed by combining cutting-edge technologies, i.e., cloud random access networks (C-RANs), unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs). Examined from the practical perspective, the potential and challenges of MIMO in JCAS are summarized, and promising solutions are provided. Motivated by the great potential of the Internet of Things (IoT), we also specify JCAS in IoT scenarios and discuss the uniqueness of applying JCAS to IoT. In the end, open issues are outlined to envisage a ubiquitous, intelligent and secure JCAS network in the near future.

eess.SP↗

arXiv2022

A giant atom with modulated transition frequency

Giant atoms are known for the frequency-dependent spontaneous emission and associated interference effects. In this paper, we study the spontaneous emission dynamics of a two-level giant atom with dynamically modulated transition frequency. It is shown that the retarded feedback effect of the giant-atom system is greatly modified by a dynamical phase arising from the frequency modulation and the retardation effect itself. Interestingly, such a modification can in turn suppress the retarded feedback such that the giant atom behaves like a small one. By introducing an additional phase difference between the two atom-waveguide coupling paths, we also demonstrate the possibility of realizing chiral and tunable temporal profiles of the output fields. The results in this paper have potential applications in quantum information processing and quantum network engineering.

quant-ph↗

arXiv2022

In vivo labeling and quantitative imaging of neurons using MRI

Mammalian brain is a complex organ that contains billions of neurons. These neurons form various neural circuits that control the perception, cognition, emotion and behavior. Developing in vivo neuronal labeling and imaging techniques is crucial for studying the structure and function of neural circuits. In vivo techniques can provide true physiological information that cannot be provided by ex vivo methods. In this study, we describe a new strategy for in vivo neuronal labeling and quantification using MRI. To demonstrate the ability of this new method, we used neurotropic virus to deliver oatp1a1 gene to the target neural circuit. OATP1A1 protein is expressed on the neuronal membrane and can increase the uptake of a specific MRI contrast agent (Gd-EOB-DTPA). By using T1-weighted images for observation, labeled neurons "light up" on MRI. We further use a dynamic-contrast-enhancement based method to obtain measures that provide quantitative information of labeled neurons in vivo.

q-bio.NC↗

arXiv2022

Asymptotic closure model for inertial particle transport in turbulent boundary layers

Transport equations for heavy inertial particles in turbulent boundary layers may be derived from an underlying phase-space probability density function (PDF) equation. These equations, however, are unclosed, and the standard closure approach is to use a quasi-Normal approximation (QNA) in which the fourth moments are approximated as behaving as if the velocities were Normally distributed. Except for particles with weak inertia, the QNA leads to large quantitative errors, and is not consistent with the known asymptotic predictions of Sikovsky (Flow Turbulence Combust, vol. 92, 2014, pp. 41-64) for the moments of the PDF in the viscous sublayer. We derive a new closure approximation based on an asymptotic solution to the transport equations in regions where the effect of particle inertia is significant. The new closure is consistent with the asymptotic predictions of Sikovsky, but applies even outside the viscous sublayer. Comparisons with direct numerical simulations (DNS) show that the new closure gives similar results to the QNA (with the QNA results in slightly better agreement with the DNS) when the viscous Stokes number is $St<10$, but for $St>10$ the new model is in far better agreement with the DNS than the QNA. While the predictions from the new model leave room for improvement, the results suggest that this new closure strategy is a very effective alternative to the traditional QNA approach, and the closure could be refined in future work.

physics.flu-dyn↗

arXiv2022

A Reliable Multipath Routing Protocol Based on Link Stability

Wireless NanoSensor Network (WNSN) is a new type of sensor network with broad application prospects. In view of the limited energy of nanonodes and unstable links in WNSNs, we propose a reliable multi-path routing based on link stability (RMRLS). RMRLS selects the optimal path which perfects best in the link stability evaluation model, and then selects an alternative route by the routing similarity judgment model. RMRLS uses tew paths to cope with changes in the network topology. The simulation shows that the RMRLS protocol has advantages in data packet transmission success rate and average throughput, which can improve the stability and reliability of the network.

cs.NI↗

arXiv2022

Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of the supervised counterparts in most downstream tasks. In this work, we propose a semi-supervised sentence embedding framework, GenSE, that effectively leverages large-scale unlabeled data. Our method include three parts: 1) Generate: A generator/discriminator model is jointly trained to synthesize sentence pairs from open-domain unlabeled corpus; 2) Discriminate: Noisy sentence pairs are filtered out by the discriminator to acquire high-quality positive and negative sentence pairs; 3) Contrast: A prompt-based contrastive approach is presented for sentence representation learning with both annotated and synthesized data. Comprehensive experiments show that GenSE achieves an average correlation score of 85.19 on the STS datasets and consistent performance improvement on four domain adaptation tasks, significantly surpassing the state-of-the-art methods and convincingly corroborating its effectiveness and generalization ability.Code, Synthetic data and Models available at https://github.com/MatthewCYM/GenSE.

cs.CL↗

arXiv2022

IRS-Assisted RF-powered IoT Networks:System Modeling and Performance Analysis

Emerged as a promising solution for future wireless communication systems, intelligent reflecting surface (IRS) is capable of reconfiguring the wireless propagation environment by adjusting the phase-shift of a large number of reflecting elements. To quantify the gain achieved by IRSs in the radio frequency (RF) powered Internet of Things (IoT) networks, in this work, we consider an IRS-assisted cellular-based RFpowered IoT network, where the cellular base stations (BSs) broadcast energy signal to IoT devices for energy harvesting (EH) in the charging stage, which is utilized to support the uplink (UL) transmissions in the subsequent UL stage. With tools from stochastic geometry, we first derive the distributions of the average signal power and interference power which are then used to obtain the energy coverage probability, UL coverage probability, overall coverage probability, spatial throughput and power efficiency, respectively. With the proposed analytical framework, we finally evaluate the effect on network performance of key system parameters, such as IRS density, IRS reflecting element number, charging stage ratio, etc. Compared with the conventional RF-powered IoT network, IRS passive beamforming brings the same level of enhancement in both energy coverage and UL coverage, leading to the unchanged optimal charging stage ratio when maximizing spatial throughput.

cs.NI↗

arXiv2022

Contextual Learning in Fourier Complex Field for VHR Remote Sensing Images

Very high-resolution (VHR) remote sensing (RS) image classification is the fundamental task for RS image analysis and understanding. Recently, transformer-based models demonstrated outstanding potential for learning high-order contextual relationships from natural images with general resolution (224x224 pixels) and achieved remarkable results on general image classification tasks. However, the complexity of the naive transformer grows quadratically with the increase in image size, which prevents transformer-based models from VHR RS image (500x500 pixels) classification and other computationally expensive downstream tasks. To this end, we propose to decompose the expensive self-attention (SA) into real and imaginary parts via discrete Fourier transform (DFT) and therefore propose an efficient complex self-attention (CSA) mechanism. Benefiting from the conjugated symmetric property of DFT, CSA is capable to model the high-order contextual information with less than half computations of naive SA. To overcome the gradient explosion in Fourier complex field, we replace the Softmax function with the carefully designed Logmax function to normalize the attention map of CSA and stabilize the gradient propagation. By stacking various layers of CSA blocks, we propose the Fourier Complex Transformer (FCT) model to learn global contextual information from VHR aerial images following the hierarchical manners. Universal experiments conducted on commonly used RS classification data sets demonstrate the effectiveness and efficiency of FCT, especially on very high-resolution RS images.

cs.CV↗

arXiv2022

Analyzing and Evaluating Faithfulness in Dialogue Summarization

Dialogue summarization is abstractive in nature, making it suffer from factual errors. The factual correctness of summaries has the highest priority before practical applications. Many efforts have been made to improve faithfulness in text summarization. However, there is a lack of systematic study on dialogue summarization systems. In this work, we first perform the fine-grained human analysis on the faithfulness of dialogue summaries and observe that over 35% of generated summaries are faithfully inconsistent respective the source dialogues. Furthermore, we present a new model-level faithfulness evaluation method. It examines generation models with multi-choice questions created by rule-based transformations. Experimental results show that our evaluation schema is a strong proxy for the factual correctness of summarization models. The human-annotated faithfulness samples and the evaluation toolkit are released to facilitate future research toward faithful dialogue summarization.

cs.CL↗

arXiv2022

DeepFlame: A deep learning empowered open-source platform for reacting flow simulations

In this work, we introduce DeepFlame, an open-source C++ platform with the capabilities of utilising machine learning algorithms and pre-trained models to solve for reactive flows. We combine the individual strengths of the computational fluid dynamics library OpenFOAM, machine learning framework Torch, and chemical kinetics program Cantera. The complexity of cross-library function and data interfacing (the core of DeepFlame) is minimised to achieve a simple and clear workflow for code maintenance, extension and upgrading. As a demonstration, we apply our recent work on deep learning for predicting chemical kinetics (Zhang et al. Combust. Flame vol. 245 pp. 112319, 2022) to highlight the potential of machine learning in accelerating reacting flow simulation. A thorough code validation is conducted via a broad range of canonical cases to assess its accuracy and efficiency. The results demonstrate that the convection-diffusion-reaction algorithms implemented in DeepFlame are robust and accurate for both steady-state and transient processes. In addition, a number of methods aiming to further improve the computational efficiency, e.g. dynamic load balancing and adaptive mesh refinement, are explored. Their performances are also evaluated and reported. With the deep learning method implemented in this work, a speed-up of two orders of magnitude is achieved in a simple hydrogen ignition case when performed on a medium-end graphics processing unit (GPU). Further gain in computational efficiency is expected for hydrocarbon and other complex fuels. A similar level of acceleration is obtained on an AI-specific chip - deep computing unit (DCU), highlighting the potential of DeepFlame in leveraging the next-generation computing architecture and hardware.

physics.flu-dyn↗

arXiv2022

An Energy Balance Cluster Network Framework Based on SWIPT

Wireless NanoSensor Network (WNSN) is a brand-new type of sensor network with broad application prospects. In view of the limited energy of nano-nodes and unstable links in WNSNs, we propose an energy balance cluster network framework (EBCNF) based on Simultaneous Wireless Information and Power Transfer (SWIPT). The EBCNF framework extends the network lifetime of nanonodes and uses a clustering algorithm called EBACC (an energy balance algorithm for intra-cluster and inter-cluster nodes) to make the energy consumption of nodes more uniform. Simulation shows that the EBCNF framework can make the network energy consumption more uniform, reduce the error rate of data transmission and the average network throughput, and can be used as an effective routing framework for WNSNs.

cs.NI↗

arXiv2022

Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation

Session-based recommendation (SBR) aims to predict the user next action based on the ongoing sessions. Recently, there has been an increasing interest in modeling the user preference evolution to capture the fine-grained user interests. While latent user preferences behind the sessions drift continuously over time, most existing approaches still model the temporal session data in discrete state spaces, which are incapable of capturing the fine-grained preference evolution and result in sub-optimal solutions. To this end, we propose Graph Nested GRU ordinary differential equation (ODE), namely GNG-ODE, a novel continuum model that extends the idea of neural ODEs to continuous-time temporal session graphs. The proposed model preserves the continuous nature of dynamic user preferences, encoding both temporal and structural patterns of item transitions into continuous-time dynamic embeddings. As the existing ODE solvers do not consider graph structure change and thus cannot be directly applied to the dynamic graph, we propose a time alignment technique, called t-Alignment, to align the updating time steps of the temporal session graphs within a batch. Empirical results on three benchmark datasets show that GNG-ODE significantly outperforms other baselines.

cs.IR↗

arXiv2022

SAGA: Stochastic Whole-Body Grasping with Contact

The synthesis of human grasping has numerous applications including AR/VR, video games and robotics. While methods have been proposed to generate realistic hand-object interaction for object grasping and manipulation, these typically only consider interacting hand alone. Our goal is to synthesize whole-body grasping motions. Starting from an arbitrary initial pose, we aim to generate diverse and natural whole-body human motions to approach and grasp a target object in 3D space. This task is challenging as it requires modeling both whole-body dynamics and dexterous finger movements. To this end, we propose SAGA (StochAstic whole-body Grasping with contAct), a framework which consists of two key components: (a) Static whole-body grasping pose generation. Specifically, we propose a multi-task generative model, to jointly learn static whole-body grasping poses and human-object contacts. (b) Grasping motion infilling. Given an initial pose and the generated whole-body grasping pose as the start and end of the motion respectively, we design a novel contact-aware generative motion infilling module to generate a diverse set of grasp-oriented motions. We demonstrate the effectiveness of our method, which is a novel generative framework to synthesize realistic and expressive whole-body motions that approach and grasp randomly placed unseen objects. Code and models are available at https://jiahaoplus.github.io/SAGA/saga.html.

cs.CV↗

arXiv2022

EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices

Understanding social interactions from egocentric views is crucial for many applications, ranging from assistive robotics to AR/VR. Key to reasoning about interactions is to understand the body pose and motion of the interaction partner from the egocentric view. However, research in this area is severely hindered by the lack of datasets. Existing datasets are limited in terms of either size, capture/annotation modalities, ground-truth quality, or interaction diversity. We fill this gap by proposing EgoBody, a novel large-scale dataset for human pose, shape and motion estimation from egocentric views, during interactions in complex 3D scenes. We employ Microsoft HoloLens2 headsets to record rich egocentric data streams (including RGB, depth, eye gaze, head and hand tracking). To obtain accurate 3D ground truth, we calibrate the headset with a multi-Kinect rig and fit expressive SMPL-X body meshes to multi-view RGB-D frames, reconstructing 3D human shapes and poses relative to the scene, over time. We collect 125 sequences, spanning diverse interaction scenarios, and propose the first benchmark for 3D full-body pose and shape estimation of the social partner from egocentric views. We extensively evaluate state-of-the-art methods, highlight their limitations in the egocentric scenario, and address such limitations leveraging our high-quality annotations. Data and code are available at https://sanweiliti.github.io/egobody/egobody.html.

cs.CV↗

arXiv2022

Towards Modern Card Games with Large-Scale Action Spaces Through Action Representation

Axie infinity is a complicated card game with a huge-scale action space. This makes it difficult to solve this challenge using generic Reinforcement Learning (RL) algorithms. We propose a hybrid RL framework to learn action representations and game strategies. To avoid evaluating every action in the large feasible action set, our method evaluates actions in a fixed-size set which is determined using action representations. We compare the performance of our method with the other two baseline methods in terms of their sample efficiency and the winning rates of the trained models. We empirically show that our method achieves an overall best winning rate and the best sample efficiency among the three methods.

cs.AI↗

arXiv2022

LFGCF: Light Folksonomy Graph Collaborative Filtering for Tag-Aware Recommendation

Tag-aware recommendation is a task of predicting a personalized list of items for a user by their tagging behaviors. It is crucial for many applications with tagging capabilities like last.fm or movielens. Recently, many efforts have been devoted to improving Tag-aware recommendation systems (TRS) with Graph Convolutional Networks (GCN), which has become new state-of-the-art for the general recommendation. However, some solutions are directly inherited from GCN without justifications, which is difficult to alleviate the sparsity, ambiguity, and redundancy issues introduced by tags, thus adding to difficulties of training and degrading recommendation performance. In this work, we aim to simplify the design of GCN to make it more concise for TRS. We propose a novel tag-aware recommendation model named Light Folksonomy Graph Collaborative Filtering (LFGCF), which only includes the essential GCN components. Specifically, LFGCF first constructs Folksonomy Graphs from the records of user assigning tags and item getting tagged. Then we leverage the simple design of aggregation to learn the high-order representations on Folksonomy Graphs and use the weighted sum of the embeddings learned at several layers for information updating. We share tags embeddings to bridge the information gap between users and items. Besides, a regularization function named TransRT is proposed to better depict user preferences and item features. Extensive hyperparameters experiments and ablation studies on three real-world datasets show that LFGCF uses fewer parameters and significantly outperforms most baselines for the tag-aware top-N recommendations.

cs.IR↗

arXiv2022

Service Modeling and Delay Analysis of Packet Delivery over a Wireless Link

For delay analysis of packet delivery over a wireless link, several novel ideas are introduced. One is to construct an equivalent $G/G/1$ non-lossy queueing model to ease the analysis, enabled by exploiting empirical models of packet error rate, packet service time and packet loss rate obtained from measurement. The second is to exploit a classical queueing theory result to approximate the mean delay. For estimating the delay distribution, the newly developed stochastic network calculus (SNC) theory is made use of, forming the third idea. To enable this SNC based analysis, a stochastic service curve characterization of the link is introduced, relying on a packet service time model obtained from the empirical models. The focused link is a 802.15.4 wireless link. Extensive experimental investigation under a wide range of settings was conducted. The proposed ideas are validated with the experiment results. The validation confirms that the proposed approaches, integrating both empirical and analytical modes, are effective for service modeling and delay analysis. This suggests an integrated approach, now found previously, for quantitative understanding of the delay performance of packet delivery over a wireless link.

cs.PF↗