Rui Yuan

Dr. Rui Yuan

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 June 2020 in IEEE Access
Verified
Journal Article
Open access
PYPengshuai Yin
Pengshuai Yin
RYRui Yuan
Rui Yuan
YCYiming Cheng
Yiming Cheng
Qingyao WuQingyao Wu
Qingyao Wu
Segmentation of 2D images is a fundamental problem for biomedical image analysis. The most widely used architecture for biomedical image segmentation is U-Net. U-Net introduces skip-connections to restore the spatial information loss caused by down-sampling operations. However, for some tasks such as the retinal vessel segmentation, the loss information of structure can not be fully recovered since the vessels is merely a curve line that can not be detected after several convolutions. In this paper, we introduce a deep guidance network to segment the biomedical image. Our proposed network consists of a guided image filter module to restore the structure information through the guidance image. Our method enables end to end training and fast inference (43ms for one image). We conduct extensive experiments for the task of vessel segmentation and optic disc and cup segmentation. The experiments on four publicly available datasets: ORIGA, REFUGE, DRIVE, and CHASEDB1 verify the effectiveness of our method.

28 November 2019 in IEEE Access
Verified
Journal Article
Open access
CLChunshan Li
Chunshan Li
YSYukun Su
Yukun Su
RYRui Yuan
Rui Yuan
Dianhui ChuDianhui Chu
Dianhui Chu
JZJinhui Zhu
Jinhui Zhu
Automatic reading for water meter is one of the practical demands in smart city applications. Due to the high cost, it is not feasible to replace the old mechanical water meter with a new embedded electronic device. Recently, image recognition based meter reading methods have become research hotspots. However, illumination, occlusion, energy and computational consuming in IoT environment bring challenges to these methods. In this paper, we design and implement a smart water meter reading system to handle this issue. Specifically, we first propose a novel light-weight spliced convolution network to recognize the meter number, which simplifies standard 3×3 convolutions by splicing a certain number of 1×1 and 3×3 size kernel. We then prove the superiority of our network by theoretical analysis. Second, we have implemented the prototype which can handle huge real-time data base on the distributed cloud platform. Base on this system, our system can provide industrial service. Finally, we conduct real-world dataset to verify the performance of the system. The experimental results demonstrate that our proposed light-weight spliced convolution network can reduce nearly 10× computational consuming, 7× model space, and save 3× running time comparing with standard convolution network.

6 January 2020 in IEEE Access
Verified
Journal Article
Open access
XTXiaoli Tang
Xiaoli Tang
RYRui Yuan
Rui Yuan
QLQianyu Li
Qianyu Li
TWTengyun Wang
Tengyun Wang
HYHaizhi Yang
Haizhi Yang
HSHengjie Song
Hengjie Song
Recently, Knowledge Graph Embedding (KGE) has attracted considerable research efforts, since it simplifies the manipulation while preserving the inherent structure of the KG. However to some extent, most existing KGE approaches ignore the historical changes of structural information involved in dynamic knowledge graphs (DKGs). To deal with this problem, this paper presents a Timespan-aware Dynamic knowledge Graph Embedding Evolution (TDG2E) method that considers temporal evolving process of DKGs. The major innovations of our paper are two-fold. Firstly, a Gated Recurrent Units (GRU) based model is utilized in TDG2E to deal with the dependency among sub-KGs that is inevitably involved in the learning process of the dynamic knowledge graph embedding. Furthermore, we incorporate an auxiliary loss to supervise the learning process of the next sub-KG by utilizing previous structural information (i.e., the hidden state of GRU). In contrast with existing approaches in the literature (e.g., HyTE and t-TransE), TDG2E preserves structural information of current sub-KG and the temporal evolving process of the DKG simultaneously. Secondly, to further deal with the time unbalance issue underlying the DKGs, a Timespan Gate is designed in GRU. It makes TDG2E possible to model the temporal evolving process of DKGs more effectively by incorporating the timespan between adjacent sub-KGs. Extensive experiments on two large temporal datasets (i.e., YAGO11k and Wikidata12k) extracted from real-world KGs validate that the proposed TDG2E significantly outperforms traditional KGE methods in terms of Mean Rank and Hit Rate.

8 May 2018 in Open Geosciences
Verified
Journal Article
Open access
PDF file
RYRui Yuan
Rui Yuan
RZRui Zhu
Rui Zhu
JQJianhua Qu
Jianhua Qu
JWJun Wu
Jun Wu
XYXincai You
Xincai You
YZYuanquan (Nancy) Zhou
Yuanquan (Nancy) Zhou
The Mahu Depression is an important hydrocarbon-bearing foreland sag located at the northwestern margin of the Junggar Basin, China. On the northern slope of the depression, large coarse-grained proximal fan-delta depositional systems developed in the Lower Triassic Baikouquan Formation (T1b). Some lithologic hydrocarbon reservoirs have been found in the conglomerates of the formation since recent years. However, the rapid vertical and horizontal lithology variations make it is difficult to divide the base-level cycle of the formation using the conventional methods. Spectral analysis technologies, such as Integrated Prediction Error Filter Analysis (INPEFA), provide another effective way to overcome this difficultly. In this paper, processed by INPEFA, conventional resistivity logs are utilized to study the base-level cycle of the fan-delta depositional systems. The negative trend of the INPEFA curve indicates the base-level fall semi-cycles, adversely, positive trend suggests the rise semi-cycles. Base-level cycles of Baikouquan Formation are divided in single and correlation wells. One long-term base-level rise semi-cycle, including three medium-term base-level cycles, is identified overall the Baikouquan Formation. The medium-term base-level cycles are characterized as rise semi-cycles mainly in the fan-delta plain, symmetric cycles in the fan-delta front and fall semi-cycles mainly in the pro-fan-delta. The short-term base-level rise semi-cycles most developed in the braided channels, sub-aqueous distributary channels and sheet sands. While, the interdistributary bays and pro-fan-delta mud indicate short-term base-level fall semi-cycles. Finally, based on the method of INPEFA, sequence filling model of Baikouquan formation is established.

17 November 2017 in Open Geosciences
Verified
Journal Article
Open access
PDF file
RYRui Yuan
Rui Yuan
CZchangmin zhang
changmin zhang
YTYong Tang
Yong Tang
JQJianhua Qu
Jianhua Qu
XGXudong Guo
Xudong Guo
YZYuanquan (Nancy) Zhou
Yuanquan (Nancy) Zhou
Large-scale conglomerate fan-delta aprons were typical deposits on the slope of Mahu Depression during the Early Triassic. Without outcrops, it is difficult to study the lithofacies only by examining the limited cores from the main oil-bearing interval of the Baikouquan Formation. Borehole electrical imaging log provides abundant high-resolution geologic information that is obtainable only from real rocks previously. Referring to the lithology and sedimentary structure of cores, a case study of fan-deltas in the Lower Triassic Baikouquan Formation of the Mahu Depression presents a methodology for interpreting the complicated lithofacies utilizing borehole electrical images. Eleven types of lithologies and five types of sedimentary structures are summarized in borehole electrical images. The sediments are fining upward from gravel to silt and clay in the Baikouquan Formation. Fine-pebbles and granules are the main deposits in T

15 November 2018 in Arabian Journal of Geosciences
Verified
Journal Article
Closed access
PDF file
RYRui Yuan
Rui Yuan
CZChangmin Zhang
Changmin Zhang
XWXulong Wang
Xulong Wang
RZRui Zhu
Rui Zhu