检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Chen, Geng Liu, Si-Jie Sun, Yu-Jia Ji, Ge-Peng Wu, Ya-Feng Zhou, Tao Northwestern Polytechnical University Xi’an710072 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering China Data Processing Center School of Power and Energy China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science Inner Mongolia University Hohhot010021 China Artificial Intelligence Institute School of Computer Science Wuhan University Wuhan430072 China

Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., object size and shape. To address these challenges, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, we compute informative attention coefficients from multi-level features with our Attention-induced Cross-level Fusion Module (ACFM), which further integrates the features under the guidance of attention coefficients. We then propose a Dual-branch Global Context Module (DGCM) to refine the fused features for informative feature representations by exploiting rich global context information. Multiple ACFMs and DGCMs are integrated in a cascaded manner for generating a coarse prediction from high-level features. The coarse prediction acts as an attention map to refine the low-level features before passing them to our Camouflage Inference Module (CIM) to generate the final prediction. We perform extensive experiments on three widely used benchmark datasets and compare C2F-Net with state-of-the-art (SOTA) models. The results show that C2F-Net is an effective COD model and outperforms SOTA models remarkably. Further, an evaluation on polyp segmentation datasets demonstrates the promising potentials of our C2F-Net in COD downstream applications. Our code is publicly available at: https://***/Ben57882/C2FNet-TSCVT. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Tissue Segmentation of Thick-Slice Fetal Brain MR Scans with Guidance from High-Quality Isotropic Volumes

arXiv

引用

arXiv 2023年

作者： Huang, Shijie Zhang, Xukun Cui, Zhiming Zhang, He Chen, Geng Shen, Dinggang School of Biomedical Engineering ShanghaiTech University Shanghai China Academy for Eng. & Tech. Fudan University Shanghai China Department of Radiology Obstetrics and Gynecology Hospital of Fudan University Shanghai China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China School of Biomedical Engineering ShanghaiTech University Shanghai201210 China Shanghai United Imaging Intelligence company Ltd. Shanghai200030 China Shanghai Clinical Research Trial Center Shanghai201210 China

Accurate tissue segmentation of thick-slice fetal brain magnetic resonance (MR) scans is crucial for both reconstruction of isotropic brain MR volumes and the quantification of fetal brain development. However, this task is challenging due to the use of thick-slice scans in clinically-acquired fetal brain data. To address this issue, we propose to leverage high-quality isotropic fetal brain MR volumes (and also their corresponding annotations) as guidance for segmentation of thick-slice scans. Due to existence of significant domain gap between high-quality isotropic volume (i.e., source data) and thick-slice scans (i.e., target data), we employ a domain adaptation technique to achieve the associated knowledge transfer (from high-quality volumes to thick-slice scans). Specifically, we first register the available high-quality isotropic fetal brain MR volumes across different gestational weeks to construct longitudinally-complete source data. To capture domain-invariant information, we then perform Fourier decomposition to extract image content and style codes. Finally, we propose a novel Cycle-Consistent Domain Adaptation Network (C2DA-Net) to efficiently transfer the knowledge learned from high-quality isotropic volumes for accurate tissue segmentation of thick-slice scans. Our C2DA-Net can fully utilize a small set of annotated isotropic volumes to guide tissue segmentation on unannotated thick-slice scans. Extensive experiments on a large-scale dataset of 372 clinically acquired thick-slice MR scans demonstrate that our C2DA-Net achieves much better performance than cutting-edge methods quantitatively and qualitatively. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

On-edge multi-task transfer learning: Model and practice with data-driven task allocation

arXiv

引用

arXiv 2021年

作者： Zheng, Zimu Chen, Qiong Hu, Chuang Wang, Dan Liu, Fangming The National Engineering Research Center for Big Data Technology and System Key Laboratory of Services Computing Technology and System Ministry of Education School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China The Edge Cloud Innovation Lab. Technical Innovation Department Cloud BU Huawei Technologies Co. Ltd. Shenzhen China The Department of Computing Hong Kong Polytechnic University Kowloon Hong Kong Hong Kong

On edge devices, data scarcity occurs as a common problem where transfer learning serves as a widely-suggested remedy. Nevertheless, transfer learning imposes heavy computation burden to the resource-constrained edge devices. Existing task allocation works usually assume all submitted tasks are equally important, leading to inefficient resource allocation at a task level when directly applied in Multi-task Transfer Learning (MTL). To address these issues, we first reveal that it is crucial to measure the impact of tasks on overall decision performance improvement and quantify task importance. We then show that task allocation with task importance for MTL (TATIM) is a variant of NP-complete Knapsack problem, where the complicated computation to solve this problem needs to be conducted repeatedly under varying contexts. To solve TATIM with high computational efficiency, we propose a data-driven Cooperative Task Allocation (DCTA) approach. Finally, we evaluate the performance of DCTA by not only a trace-driven simulation, but also a new comprehensive real-world AIOps case study which bridges model and practice via a new architecture and main components design within AIOps system. Extensive experiments show that our DCTA reduces 3.24 times of processing time, and saves 48.4% energy consumption compared with the state-of-the-art when solving TATIM. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

White spot syndrome virus (WSSV) modulates lipid metabolism in white shrimp

Communications Biology

引用

Communications Biology 2023年第1期6卷 546页

作者： Ng, Yen Siong Cheng, Cheng-Shun Ando, Masahiro Tseng, Yi-Ting He, Shu-Ting Li, Chun-Yuan Cheng, Shu-Wen Chen, Yi-Min Kumar, Ramya Liu, Chun-Hung Takeyama, Haruko Hirono, Ikuo Wang, Han-Ching Department of Biotechnology and Bioindustry Sciences College of Bioscience and Biotechnology National Cheng Kung University Tainan Taiwan Research Organization for Nano and Life Innovations Waseda University Tokyo Japan International Center for the Scientific Development of Shrimp Aquaculture National Cheng Kung University Tainan Taiwan Department of Aquaculture National Pingtung University of Science and Technology Pingtung Taiwan Department of Life Science and Medical Bioscience Waseda University Tokyo Japan Computational Bio Big-Data Open Innovation Laboratory (CBBD-OIL) National Institute of Advanced Industrial Science and Technology Tokyo Japan Institute for Advanced Research of Biosystem Dynamics Waseda Research Institute for Science and Engineering Tokyo Japan Department of Marine Biosciences Tokyo University of Marine Science and Technology Tokyo Japan

In addition to the Warburg effect, which increases the availability of energy and biosynthetic building blocks in WSSV-infected shrimp, WSSV also induces both lipolysis at the viral genome replication stage (12 hpi) to provide material and energy for the virus replication, and lipogenesis at the viral late stage (24 hpi) to complete virus morphogenesis by supplying particular species of long-chain fatty acids (LCFAs). Here, we further show that WSSV causes a reduction in lipid droplets (LDs) in hemocytes at the viral genome replication stage, and an increase in LDs in the nuclei of WSSV-infected hemocytes at the viral late stage. In the hepatopancreas, lipolysis is triggered by WSSV infection, and this leads to fatty acids being released into the hemolymph. β-oxidation inhibition experiment reveals that the fatty acids generated by WSSV-induced lipolysis can be diverted into β-oxidation for energy production. At the viral late stage, WSSV infection leads to lipogenesis in both the stomach and hepatopancreas, suggesting that fatty acids are in high demand at this stage for virion morphogenesis. Our results demonstrate that WSSV modulates lipid metabolism specifically at different stages to facilitate its replication. © 2023, The Author(s).

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Locality-Aware Energy-Efficient Accelerator for Graph Mining Applications

A Locality-Aware Energy-Efficient Accelerator for Graph Mini...

引用

IEEE/ACM International Symposium on Microarchitecture (MICRO)

作者： Pengcheng Yao Long Zheng Zhen Zeng Yu Huang Chuangyi Gui Xiaofei Liao Hai Jin Jingling Xue National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Computer Science and Engineering UNSW Sydney Australia

ISBN: (数字)9781728173832

ISBN: (纸本)9781728173849

Graph mining is becoming increasingly important due to the ever-increasing demands on analyzing complex structures in graphs. Existing graph accelerators typically hold most of the randomly-accessed data in an on-chip memory to avoid off-chip communications. However, graph mining exhibits substantial random accesses from not only vertex dimension but also edge dimension (with the latter being excessively more complex than the former), leading to significant degradations in terms of both performance and energy *** observe that the most random memory requests arising in graph mining come from accessing a small fraction of valuable (vertex and edge) data when handling real-world graphs. To exploit this extension locality with maximum parallelism, we architect GRAMER, the first graph mining accelerator. GRAMER contains a specialized memory hierarchy, where the valuable data (precisely identified through a cost-efficient heuristic) is permanently resident in a high-priority memory while others are maintained in a cache-like memory under a lightweight replacement policy. The specific pipelined processing units are carefully designed to maximize computational parallelism. GRAMER is also equipped with a work-stealing mechanism to reduce load imbalance. We have implemented GRAMER on a Xilinx Alveo U250 accelerator card. Compared with two state-of-the-art CPU-based graph mining systems, Fractal and RStream, running on a 14-core Intel E5-2680 v4 processor, GRAMER achieves not only considerable speedups (1.11 × ~ 129.95 ) but also significant energy savings (5.79 × ~ 678.34×)

关键词： Memory management Parallel processing Feature extraction Energy efficiency Fractals system-on-chip data mining

来源：评论

学校读者我要写书评

暂无评论

ADVISor: Automatic Visualization Answer for Natural-Language Question on Tabular data

ADVISor: Automatic Visualization Answer for Natural-Language...

引用

Pacific (formerly Asia-Pacific APVIS) Visualization Symposium

作者： Can Liu Yun Han Ruike Jiang Xiaoru Yuan Key Laboratory of Machine Perception (Ministry of Education) and School of EECS Peking University Beijing China National Engineering Laboratory for Big Data Analysis and Application Peking University Beijing China Beijing Engineering Technology Research Center of Virtual Simulation and Visualization Peking University Beijing China

We propose an automatic pipeline to generate visualization with annotations to answer natural-language questions raised by the public on tabular data. With a pre-trained language representation model, the input natural language questions and table headers are first encoded into vectors. According to these vectors, a multi-task end-to-end deep neural network extracts related data areas and corresponding aggregation type. We present the result with carefully designed visualization and annotations for different attribute types and tasks. We conducted a comparison experiment with state-of-the-art works and the best commercial tools. The results show that our method outperforms those works with higher accuracy and more effective visualization.

关键词： Annotations Natural languages Pipelines Neural networks data visualization Tools data mining

来源：评论

学校读者我要写书评

暂无评论

Advanced Operational Flood Monitoring in the New Era: Harnessing High-Resolution, Event Based, and Multi-Source Remote Sensing data for Flood Extent Detection and Depth Estimation

Advanced Operational Flood Monitoring in the New Era: Harnes...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Qing Yang Xinyi Shen Qingyuan Zhang Sean Helfrich Josef M. Kellndorfer William Straka Wei Hao Nicholas C. Steiner Marcelo Villa Tyler Ruff Jessie C. Moore Torres Rachel Lazzaro Cora Jackson School of Freshwater Sciences University of Wisconsin-Milwaukee Milwaukee WI USA Earth System Science Interdisciplinary Center University of Maryland College Park MD USA Center for Satellite Applications and Research National Oceanic and Atmospheric Administration College Park MD USA Earth Big Data LLC Falmouth MA USA Cooperative Institute for Meteorological Satellite Studies University of Wisconsin-Madison Madison WI USA Global Science and Technology Inc. Greenbelt MD USA Earth and Atmospheric Sciences The City College of New York New York NY USA College of Arts and Sciences Vanderbilt University Nashville TN USA Peabody College Vanderbilt University Nashville TN USA

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Remote-sensed flood monitoring is rapidly advanced by the growing abundance of satellite data. This study presents the progress in building an operational system that harnesses the power of spatially high-resolution (HR), multi-source remote sensing data for event-based flood extent and depth mapping. By integrating pioneering extent retrieval—Radar Produced Inundation Diary (RAPID), Self-supervised Waterbody Detection (SWD), and depth retrieval processors, Global-LOCAL Solvers Integration Algorithm (GLOCAL), and the Emulated Flood Recession Algorithm (EFRA)—our proposed framework marks a significant leap in flood monitoring capabilities. The upgraded RAPID addresses the complexities of Synthetic Aperture Radar (SAR) flood mapping in diverse environments, including snow-covered and arid regions, enhancing adaptability and consistency across multiple SAR satellites such as ESA Sentinel-1, CSA RADARSAT Constellation Mission (RCM), MDA RADARSAT-2 (RS2), and Capella. Meanwhile, SWD brings a method to automatically map flood extents from high-resolution optical images, including Planet, Sentinel-2, and Landsat, during clear weather conditions. GLOCAL and EFRA are tailored for depth estimation from the generated HR remotely sensed flood extents, and HR or VHR topography. Both algorithms tolerate the error from extent and topography, with EFRA physically considering the influence of micro-topography. The proposed framework has proven to produce consistent flood extent results across multi-source, high-resolution satellite images and demonstrates robust depth estimation with various input DEMs. Validation against USGS high water masks yields 1.01 m RMSE when 1 m resolution DEM is used. With continuous development and integration into NOAA's near real-time operational platform, these approaches do not only improve the resolution and dependability of operational flood monitoring globally but also significantly bolster emergency response strategies.

关键词： Satellites Image resolution Estimation Sentinel-1 Surfaces Satellite images Floods

来源：评论

学校读者我要写书评

暂无评论

Low-Temperature Growing Anatase TiO2/SnO2 Multi-dimensional Heterojunctions at MXene Conductive Network for High-Efficient Perovskite Solar Cells

引用

Nano-Micro Letters 2020年第3期12卷 199-217页

作者： Linsheng Huang Xiaowen Zhou Rui Xue Pengfei Xu Siliang Wang Chao Xu Wei Zeng Yi Xiong Hongqian Sang Dong Liang National Engineering Research Center for Agro‑Ecological Big Data Analysis and Application School of Electronics and Information EngineeringAnhui UniversityNo.111 Jiulong RoadHefei 230601People’s Republic of China Science and Technology Institute Hubei Key Laboratory of Biomass Fibers and Eco‑Dyeing and FinishingWuhan Textile UniversityWuhan 430073People’s Republic of China School of Physics and Technology MOE Key Laboratory of Artificial Micro‑and Nano‑Structures and Center for Electron MicroscopyWuhan UniversityWuhan 430072People’s Republic of China Department of Physics King’s College LondonThe StrandLondon WC2R 2LSUK

A multi-dimensional conductive heterojunction structure,composited by TiO2,SnO2,and Ti3C2TX MXene,is facilely designed and applied as electron transport layer in efficient and stable planar perovskite solar *** on an oxygen vacancy scramble effect,the zero-dimensional anatase TiO2 quantum dots,surrounding on two-dimensional conductive Ti3C2TX sheets,are in situ rooted on three-dimensional SnO2 nanoparticles,constructing nanoscale TiO2/SnO2 *** fabrication is implemented in a controlled lowtemperature anneal method in air and then in N2 *** the optimal MXene content,the optical property,the crystallinity of perovskite layer,and internal interfaces are all facilitated,contributing more amount of carrier with effective and rapid transferring in *** champion power conversion efficiency of resultant perovskite solar cells achieves 19.14%,yet that of counterpart is just 16.83%.In addition,it can also maintain almost 85%of its initial performance for more than 45 days in 30–40%humidity air;comparatively,the counterpart declines to just below 75%of its initial performance.

关键词： In situ fabrication Multi-dimensional heterojunction Oxygen vacancy scramble effect Electron transport layer Perovskite solar cells

来源：评论

学校读者我要写书评

暂无评论

XGBoost and CNN-based prediction of external forces and stress-strain during solidification reduction in casting

引用

Progress in Natural Science: Materials International 2025年

作者： Yi Nian Chaojie Zhang Xinyu Tang Youcheng Zong Jiale Li Liqiang Zhang Yingxue Wang School of Metallurgical Engineering Anhui University of Technology Maanshan 243032 Anhui China College of Information Science and Engineering Northeastern University Shenyang 110057 Liaoning China National Engineering Research Center for Public Safety Risk Perception and Control by Big Data (RPP) China Academic of Electronics and Information Technology Shuangyuan Street Beijing 100043 China

The continuous casting reduction process can effectively improve defects such as central segregation and porosity in the billets, making it a key process for enhancing billets quality. This study aims to investigate the required external force during the solidification reduction process and the equivalent stress-strain distribution at various positions inside the billets, and to construct predictive models for equivalent stress-strain and external force based on the reduction amount. Through conducting laboratory ingot solidification process reduction tests and finite element numerical simulations, the corresponding parameters including external force, reduction amount, equivalent stress, and equivalent strain were obtained. data augmentation and random noise processing were applied to the parameter features, and predictive models for external force using the XGBoost algorithm and for equivalent stress-strain using a convolutional neural networks were constructed. The results indicate that as the reduction amount increases, the required external force increases, and the equivalent stress-strain inside the billet is much higher than at the surface. Furthermore, in the external force prediction model, the MAPE value of the XGBoost algorithm is 8.15 %, while in the equivalent stress-strain model, the R 2 value of the convolutional neural networks training set is 0.92. These results demonstrate that both the external force prediction model and the equivalent stress-strain prediction model exhibit high accuracy, and robustness in predictive tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DualFS: A Coordinative Flash File system with Flash Block Dual-mode Switching

DualFS: A Coordinative Flash File System with Flash Block Du...

引用

IEEE International Conference on Computer Design: VLSI in Computers and Processors, (ICCD)

作者： Bing Wu Mengye Peng Dan Feng Wei Tong Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology

ISBN: (数字)9781728197104

ISBN: (纸本)9781728197111

As users' demand for large-capacity storage continues to grow, the widely used NAND flash memory always adopts multi-bit per cell and 3D-stacking technology to improve the storage density however impairing flash performance. Modern flash chips allow flash blocks to switch between multi-bit per cell and one-bit per cell, which gives the potential to benefit from the high performance of Single-Level Cells (SLC, i.e. one-bit per cell). However, the semantic gap caused by the block I/O interface and flash translation layer (FTL) prevents the performance of the underlying flash memory from being fully utilized. In this paper, we propose a log-structured file system, called DualFS. DualFS allows flash blocks to switch between the original-mode and SLC-mode in a free manner and uses these SLC blocks to accelerate critical requests. DualFS dynamically adjusts the capacity of the SLC-mode area according to the total size of valid data to maintain the device a negligible capacity degradation. Besides, DualFS draws advantages from the Open-Channel solid-state disk (SSD) by using software semantic information to guide data placement and management. In particular, since writing the same amount of data to the SLC block will impair more endurance, DualFS proposes a novel life management scheme which throttles the ratio of writing to SLC-mode area within a certain window, thereby accurately control the endurance of SSD. Last, DualFS integrates the garbage collection (GC) procedure, which is directly driven by the file system and merges the GC of the SLC-mode area and the original-mode area. The experiment results show that DualFS offers an average 22.2% performance improvement than the state of art flash file system based on the open-channel SSD. Compared with other storage systems based on flash block dual-mode switching feature, the average performance of DualFS also exhibits considerable improvements by 13.3% to 24.6%. Moreover, DualFS effectively reduces the read response time

关键词： File systems Semantics Switches Writing Software Time factors Flash memories

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：