372 Hits in 2.0 sec

STJLA: A Multi-Context Aware Spatio-Temporal Joint Linear Attention Network for Traffic Forecasting [article]

Yuchen Fang, Yanjun Qin, Haiyong Luo, Fang Zhao, Chenxing Wang
2021 arXiv   pre-print
INTRODUCTION Yuchen Fang, Yanjun Qin, Fang Zhao, and Chenxing Wang are with the School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications  ...  (Corresponding author: Haiyong Luo; Fang Zhao.) Fig. 1 : 1 Fig. 1: The receptive field (orange nodes) of the red node increases as the time moves backward in the spatio-temporal graph.  ... 
arXiv:2112.02262v1 fatcat:e2bagkvdpjdu7awhyoig2pbxeu

CDGNet: A Cross-Time Dynamic Graph-based Deep Learning Model for Traffic Forecasting [article]

Yuchen Fang, Yanjun Qin, Haiyong Luo, Fang Zhao, Liang Zeng, Bo Hui, Chenxing Wang
2021 arXiv   pre-print
CDGNet: A Cross-Time Dynamic Graph-based Deep Learning Model for Traffic Forecasting Yuchen  ...  None, –, Online Fang, et al.  ... 
arXiv:2112.02736v1 fatcat:qspala2jy5ajbeuxndgonaka7i

From Brain Science to Artificial Intelligence

Jingtao Fan, Lu Fang, Jiamin Wu, Yuchen Guo, Qionghai Dai
2020 Engineering  
Compliance with ethics guidelines Jingtao Fan, Lu Fang, Jiamin Wu, Yuchen Guo, and Qionghai Dai declare that they have no conflicts of interest or financial conflicts to disclose.  ... 
doi:10.1016/j.eng.2019.11.012 fatcat:qqw7gh5gpbaidhaxado4iw6ipq

Rosacea Treatment: Review and Update

Hanlin Zhang, Keyun Tang, Yuchen Wang, Rouyu Fang, Qiuning Sun
2020 Dermatology and Therapy  
Hanlin Zhang, Keyun Tang, Yuchen Wang, Rouyu Fang, and Qiuning Sun have nothing to disclose. Medical Writing and Editorial Assistance.  ... 
doi:10.1007/s13555-020-00461-0 pmid:33170491 fatcat:vh7l4gbd5rgpfc7uicjv4xbelm

Psychological distress among health professional students during the COVID-19 outbreak

Yuchen Li, Yue Wang, Jingwen Jiang, Unnur A. Valdimarsdóttir, Katja Fall, Fang Fang, Huan Song, Donghao Lu, Wei Zhang
2020 Psychological Medicine  
IP address:, on 16 Jul 2020 at 14:49:18, subject to the Cambridge Core terms of use, available at Yuchen Li et al.  ... 
doi:10.1017/s0033291720001555 pmid:32389148 pmcid:PMC7225209 fatcat:57tmpnnvlvgdxp56zguedkswfm

Universal Trading for Order Execution with Oracle Policy Distillation [article]

Yuchen Fang, Kan Ren, Weiqing Liu, Dong Zhou, Weinan Zhang, Jiang Bian, Yong Yu, Tie-Yan Liu
2021 arXiv   pre-print
Fang was doing internship at Microsoft Research Asia.  ...  discussed in (Cartea, Jaimungal, and Penalva 2015) , the main challenge of order execution lies in a trade-off between avoiding harmful "market impact" caused by large * The work was conducted when Yuchen  ... 
arXiv:2103.10860v1 fatcat:zxistflw6bhvxjppdtjzeulaqe

Spatio-Temporal meets Wavelet: Disentangled Traffic Flow Forecasting via Efficient Spectral Graph Attention Network [article]

Yuchen Fang, Yanjun Qin, Haiyong Luo, Fang Zhao, Bingbing Xu, Chenxing Wang, Liang Zeng
2022 arXiv   pre-print
., 2020; Li and Zhu, 2021; Fang et al., 2021] , propose multiple variants of GCN to improve performance by expanding spatial receptive fields.  ...  RNN to capture spatiotemporal dependencies through back-propagation.STFGNN[Li and Zhu, 2021]expands the spatial receptive field by a novel fusion operation of various spatial and temporal graphs.STGODE[Fang  ... 
arXiv:2112.02740v2 fatcat:xbaudqqkbzhz5jjiva3gmkx33y

An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph [article]

Jiarui Jin, Jiarui Qin, Yuchen Fang, Kounianhua Du, Weinan Zhang, Yong Yu, Zheng Zhang, Alexander J. Smola
2020 arXiv   pre-print
There is an influx of heterogeneous information network (HIN) based recommender systems in recent years since HIN is capable of characterizing complex graphs and contains rich semantics. Although the existing approaches have achieved performance improvement, while practical, they still face the following problems. On one hand, most existing HIN-based methods rely on explicit path reachability to leverage path-based semantic relatedness between users and items, e.g., metapath-based similarities.
more » ... These methods are hard to use and integrate since path connections are sparse or noisy, and are often of different lengths. On the other hand, other graph-based methods aim to learn effective heterogeneous network representations by compressing node together with its neighborhood information into single embedding before prediction. This weakly coupled manner in modeling overlooks the rich interactions among nodes, which introduces an early summarization issue. In this paper, we propose an end-to-end Neighborhood-based Interaction Model for Recommendation (NIRec) to address the above problems. Specifically, we first analyze the significance of learning interactions in HINs and then propose a novel formulation to capture the interactive patterns between each pair of nodes through their metapath-guided neighborhoods. Then, to explore complex interactions between metapaths and deal with the learning complexity on large-scale networks, we formulate interaction in a convolutional way and learn efficiently with fast Fourier transform. The extensive experiments on four different types of heterogeneous graphs demonstrate the performance gains of NIRec comparing with state-of-the-arts. To the best of our knowledge, this is the first work providing an efficient neighborhood-based interaction model in the HIN-based recommendations.
arXiv:2007.00216v1 fatcat:cruhwo3hdzdmpe5v3cvdboafaa

PANDA: A Gigapixel-level Human-centric Video Dataset [article]

Xueyang Wang, Xiya Zhang, Yinheng Zhu, Yuchen Guo, Xiaoyun Yuan, Liuyu Xiang, Zerun Wang, Guiguang Ding, David J Brady, Qionghai Dai, Lu Fang
2020 arXiv   pre-print
We present PANDA, the first gigaPixel-level humAN-centric viDeo dAtaset, for large-scale, long-term, and multi-object visual analysis. The videos in PANDA were captured by a gigapixel camera and cover real-world scenes with both wide field-of-view (~1 square kilometer area) and high-resolution details (~gigapixel-level/frame). The scenes may contain 4k head counts with over 100x scale variation. PANDA provides enriched and hierarchical ground-truth annotations, including 15,974.6k bounding
more » ... , 111.8k fine-grained attribute labels, 12.7k trajectories, 2.2k groups and 2.9k interactions. We benchmark the human detection and tracking tasks. Due to the vast variance of pedestrian pose, scale, occlusion and trajectory, existing approaches are challenged by both accuracy and efficiency. Given the uniqueness of PANDA with both wide FoV and high resolution, a new task of interaction-aware group detection is introduced. We design a 'global-to-local zoom-in' framework, where global trajectories and local interactions are simultaneously encoded, yielding promising results. We believe PANDA will contribute to the community of artificial intelligence and praxeology by understanding human behaviors and interactions in large-scale real-world scenes. PANDA Website:
arXiv:2003.04852v1 fatcat:q7hlcktvkjgvrjt2fw7fqkoz6m

An Evaluation of Blood Compatibility of Silver Nanoparticles

He Huang, Wenjia Lai, Menghua Cui, Ling Liang, Yuchen Lin, Qiaojun Fang, Ying Liu, Liming Xie
2016 Scientific Reports  
doi:10.1038/srep25518 pmid:27145858 pmcid:PMC4857076 fatcat:vexz4ito7vbcfnrhgaabkpf4z4

Best-Effort FPGA Programming: A Few Steps Can Go a Long Way [article]

Jason Cong, Zhenman Fang, Yuchen Hao, Peng Wei, Cody Hao Yu, Chen Zhang, Peipei Zhou
2018 arXiv   pre-print
FPGA-based heterogeneous architectures provide programmers with the ability to customize their hardware accelerators for flexible acceleration of many workloads. Nonetheless, such advantages come at the cost of sacrificing programmability. FPGA vendors and researchers attempt to improve the programmability through high-level synthesis (HLS) technologies that can directly generate hardware circuits from high-level language descriptions. However, reading through recent publications on FPGA
more » ... using HLS, one often gets the impression that FPGA programming is still hard in that it leaves programmers to explore a very large design space with many possible combinations of HLS optimization strategies. In this paper we make two important observations and contributions. First, we demonstrate a rather surprising result: FPGA programming can be made easy by following a simple best-effort guideline of five refinement steps using HLS. We show that for a broad class of accelerator benchmarks from MachSuite, the proposed best-effort guideline improves the FPGA accelerator performance by 42-29,030x. Compared to the baseline CPU performance, the FPGA accelerator performance is improved from an average 292.5x slowdown to an average 34.4x speedup. Moreover, we show that the refinement steps in the best-effort guideline, consisting of explicit data caching, customized pipelining, processing element duplication, computation/communication overlapping and scratchpad reorganization, correspond well to the best practice guidelines for multicore CPU programming. Although our best-effort guideline may not always lead to the optimal solution, it substantially simplifies the FPGA programming effort, and will greatly support the wide adoption of FPGA-based acceleration by the software programming community.
arXiv:1807.01340v1 fatcat:6ocpzvp2cvgkninbtyvvyk7yiu

A Review on Graphene-Based Nano-Electromechanical Resonators: Fabrication, Performance, and Applications

Yang Xiao, Fang Luo, Yuchen Zhang, Feng Hu, Mengjian Zhu, Shiqiao Qin
2022 Micromachines  
The emergence of graphene and other two-dimensional materials overcomes the limitation in the characteristic size of silicon-based micro-resonators and paved the way in the realization of nano-mechanical resonators. In this paper, we review the progress to date of the research on the fabrication methods, resonant performance, and device applications of graphene-based nano-mechanical resonators, from theoretical simulation to experimental results, and summarize both the excitation and detection
more » ... chemes of graphene resonators. In recent years, the applications of graphene resonators such as mass sensors, pressure sensors, and accelerometers gradually moved from theory to experiment, which are specially introduced in this review. To date, the resonance performance of graphene-based nano-mechanical resonators is widely studied by theoretical approaches, while the corresponding experiments are still in the preliminary stage. However, with the continuous progress of the device fabrication and detection technique, and with the improvement of the theoretical model, suspended graphene membranes will widen the potential for ultralow-loss and high-sensitivity mechanical resonators in the near future.
doi:10.3390/mi13020215 pmid:35208343 pmcid:PMC8880531 fatcat:iaqvxr3rkjgabdhgpzrdaixqve

DNA computing for combinational logic

Ziyuan SHEN, Chuan ZHANG, Xiaohu YOU, Yuchen ZHUANG, Lulu GE, Jiejun JIN, Zhiwei ZHONG, Zaichen ZHANG, Chongzhou FANG, Yuxiang LU
2019 Scientia Sinica Informationis  
With the progressive scale-down of semiconductor's feature size, people are looking forward to More Moore and More than Moore. In order to offer a possible alternative implementation process, people are trying to figure out a feasible transfer from silicon to molecular computing. Such transfer lies on bio-based modules programming with computer-like logic, aiming at realizing the Turing machine. To accomplish this, the DNAbased combinational logic is inevitably the first step we have taken care
more » ... of. This timely overview paper introduces combinational logic synthesized in DNA computing from both analog and digital perspectives separately. Stateof-the-art research progress is summarized for interested readers to quick understand DNA computing, initiate discussion on existing techniques and inspire innovation solutions. We hope this paper can pave the way for the future DNA computing synthesis.
doi:10.1360/n112019-00007 fatcat:4oy65pfaljbqdf7aijitlalq4u

Exotic Physical Properties of 2D Materials Modulated by Moiré Superlattices

Beibei Shi, Pengfei Qi, Meiling Jiang, Yuchen Dai, Feng Lin, Han Zhang, Zheyu Fang
2021 Materials Advances  
Van der Waals heterostructures of two-dimensional materials are naturally endowed with the nanoscale moiré pattern, which has become a versatile platform for studying novel quantum phenomena during past decades. Here,...
doi:10.1039/d1ma00263e fatcat:wvgs273on5gmfm4dmc7avs55re

A Review of Data Cleaning Methods for Web Information System

Jinlin Wang, Xing Wang, Yuchen Yang, Hongli Zhang, Binxing Fang
2019 Computers Materials & Continua  
Web information system (WIS) is frequently-used and indispensable in daily social life. WIS provides information services in many scenarios, such as electronic commerce, communities, and edutainment. Data cleaning plays an essential role in various WIS scenarios to improve the quality of data service. In this paper, we present a review of the state-of-the-art methods for data cleaning in WIS. According to the characteristics of data cleaning, we extract the critical elements of WIS, such as
more » ... ractive objects, application scenarios, and core technology, to classify the existing works. Then, after elaborating and analyzing each category, we summarize the descriptions and challenges of data cleaning methods with sub-elements such as data & user interaction, data quality rule, model, crowdsourcing, and privacy preservation. Finally, we analyze various types of problems and provide suggestions for future research on data cleaning in WIS from the technology and interactive perspective.
doi:10.32604/cmc.2020.08675 fatcat:jusi6zu7rzg65po5sowrpxlwxm
« Previous Showing results 1 — 15 out of 372 results