检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Xiao, Feng Shen, Cong Chen, Yu Yang, Tian Chen, Shengyong Liao, Zhijun Tang, Jijun Tianjin University of Technology School of Computer Science and Engineering Tianjin China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China School of Basic Medical Sciences Fujian Medical University Fujian Fuzhou China College of Intelligence and Computing Tianjin University Tianjin China Key Laboratory of Systems Bioengineering Ministry of Education Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Department of Computer Science and Engineering University of South Carolina ColumbiaSC United States

ISBN: (纸本)9781665401265

Drawing support from an effective Medical Image Segmentation (MIS) is conducive to a substantial diagnostic basis for the physicians to identify the focus lesion in the patient body and give the subsequent clinical assessment of the patient status. Although various works have tried the challenging quantitative analysis problem, it is still difficult to conduct precise automatic segmentation, especially the soft tissue organs. In this decade, with the increased amount of available datasets, deep learning-based networks have achieved remarkable performance in image processing. Inspired by the state-of-the-art deep learning works, in this paper, we propose an end-to-end multi-layer network named RCGA-Net. It consists of an encoder-decoder backbone that integrates a coordinate attention mechanism based on space and channel and a global context extraction module to highlight more valuable information. To evaluate the performance of RCGA-Net, we apply it to different kinds of clinical and experimental MIS tasks to testify its generalization ability. Extensive experiments represent that our schema has taken the outperform or compatible results among the comparison methods group. Specifically, the numeric result of RCGA-Net on the pulmonary dataset has achieved a 99.12% optimum F1-score. © 2021 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Regularly Truncated M-estimators for Learning with Noisy Labels

arXiv

引用

arXiv 2023年

作者： Xia, Xiaobo Lu, Pengqian Gong, Chen Han, Bo Yu, Jun Yu, Jun Liu, Tongliang The Sydney AI Center School of Computer Science Faculty of Engineering The University of Sydney DarlingtonNSW2008 Australia The Australian AI Institute Faculty of Engineering and IT The University of Technology Sydney BroadwayNSW2007 Australia The PCA Lab The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Computing Hong Kong Polytechnic University Hong Kong The Department of Computer Science Hong Kong Baptist University Hong Kong The School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China The Department of Automation University of Science and Technology of China Hefei230026 China

The sample selection approach is very popular in learning with noisy labels. As deep networks "learn pattern first", prior methods built on sample selection share a similar training procedure: the small-loss examples can be regarded as clean examples and used for helping generalization, while the large-loss examples are treated as mislabeled ones and excluded from network parameter updates. However, such a procedure is arguably debatable from two folds: (a) it does not consider the bad influence of noisy labels in selected small-loss examples;(b) it does not make good use of the discarded large-loss examples, which may be clean or have meaningful information for generalization. In this paper, we propose regularly truncated M-estimators (RTME) to address the above two issues simultaneously. Specifically, RTME can alternately switch modes between truncated M-estimators and original M-estimators. The former can adaptively select small-losses examples without knowing the noise rate and reduce the side-effects of noisy labels in them. The latter makes the possibly clean examples but with large losses involved to help generalization. Theoretically, we demonstrate that our strategies are label-noise-tolerant. Empirically, comprehensive experimental results show that our method can outperform multiple baselines and is robust to broad noise types and levels. The implementation is available at https://***/xiaoboxia/RTM_LNL. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Modeling heterogeneous edges to represent networks with graph auto-encoder

arXiv

引用

arXiv 2021年

作者： Wang, Lu Song, Yu Huang, Hong Ye, Fanghua Shi, Xuanhua Jin, Hai National Engineering Research Center for Big Data Technology and System Wuhan China Service Computing Technology and Systems Laboratory Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Computer Science University College London London United Kingdom

In the real world, networks often contain multiple relationships among nodes, manifested as the heterogeneity of the edges in the networks. We convert the heterogeneous networks into multiple views by using each view to describe a specific type of relationship between nodes, so that we can leverage the collaboration of multiple views to learn the representation of networks with heterogeneous edges. Given this, we propose a regularized graph auto-encoders (RGAE) model, committed to utilizing abundant information in multiple views to learn robust network representations. More specifically, RGAE designs shared and private graph auto-encoders as main components to capture high-order nonlinear structure information of the networks. Besides, two loss functions serve as regularization to extract consistent and unique information, respectively. Concrete experimental results on realistic datasets indicate that our model outperforms state-of-the-art baselines in practical applications. © 2021, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

When crowdsensing meets federated learning: Privacy-preserving mobile crowdsensing system

arXiv

引用

arXiv 2021年

作者： Zhao, Bowen Liu, Ximeng Chen, Weineng the School of Computing and Information Systems Singapore Management University Singapore Singapore the College of Mathematics and Computer Science Fuzhou University Fujian China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen China the School of Computer Science and Engineering South China University of Technology Guangzhou China

Mobile crowdsensing (MCS) is an emerging sensing data collection pattern with scalability, low deployment cost, and distributed characteristics. Traditional MCS systems suffer from privacy concerns and fair reward distribution. Moreover, existing privacy-preserving MCS solutions usually focus on the privacy protection of data collection rather than that of data processing. To tackle faced problems of MCS, in this paper, we integrate federated learning (FL) into MCS and propose a privacy-preserving MCS system, called CROWDFL. Specifically, in order to protect privacy, participants locally process sensing data via federated learning and only upload encrypted training models. Particularly, a privacy-preserving federated averaging algorithm is proposed to average encrypted training models. To reduce computation and communication overhead of restraining dropped participants, discard and retransmission strategies are designed. Besides, a privacy-preserving posted pricing incentive mechanism is designed, which tries to break the dilemma of privacy protection and data evaluation. Theoretical analysis and experimental evaluation on a practical MCS application demonstrate the proposed CROWDFL can effectively protect participants privacy and is feasible and efficient. © 2021, CC BY.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

System architecture for high-performance permissioned blockchains

引用

Frontiers of computer Science 2019年第6期13卷 1151-1165页

作者： Libo FENG Hui ZHANG Wei-Tek TSAI Simeng SUN State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China Digital Society&Blockchain Laboratory School of Computer ScienceBeihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100191China School of Computing Informatics and Decision Systems EngineeringArizona State UniversityTempeUSA

Blockchain(BC),as an emerging distributed database technology with advanced security and reliability,has attracted much attention from experts who devoted to efinance,intellectual property protection,the internet of things(IoT)and so ***,the inefficient transaction processing speed,which hinders the BC’s widespread,has not been well tackled *** this paper,we propose a novel architecture,called Dual-Channel Parallel Broadcast model(DCPB),which could address such a problem to a greater extent by using three methods which are dual communication channels,parallel pipeline processing and block broadcast *** the dual-channel model,one channel processes transactions,and the other engages in the execution of *** parallel pipeline processing allows the system to operate *** block generation strategy improves the efficiency and speed of *** experiments have been applied to BeihangChain,a simplified prototype for BC system,illustrates that its transaction processing speed could be improved to 16K transaction per second which could well support many real-world scenarios such as BC-based energy trading system and Micro-film copyright trading system in CCTV.

关键词： blockchain concurrency performance dualchannel model parallel pipeline consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Improved impossible differential cryptanalysis of large-block Rijndael

引用

Science China(Information Sciences) 2019年第3期62卷 5-18页

作者： Ya LIU Yifan SHI Dawu GU Bo DAI Fengyu ZHAO Wei LI Zhiqiang LIU Zhiqiang ZENG Engineering Research Center of Optical Instrument and System Ministry of Education Shanghai Key Lab of Modern Optical System University of Shanghai for Science and Technology State Key Laboratory of Cryptology Department of Computer Science and Engineering Shanghai Jiao Tong University School of Computer Science and Technology Donghua University Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Key Laboratory of Integrated Administration Technologies for Information Security Science and Technology on Information Assurance Laboratory

Rijndael is a substitution-permutation network（SPN） block cipher for the AES development process. Its block and key sizes range from 128 to 256 bits in steps of 32 bits, which can be denoted by Rijndael-b-k, where b and k are the block and key sizes, respectively. Among them, Rijndael-128-128/192/256,that is, AES, has been studied by many researchers, and the security of other large-block versions of Rijndael has been exploited less frequently. However, more attention has been paid to large-block versions of block ciphers with the fast development of quantum computers. In this paper, we propose improved impossible differential attacks on 10-round Rijndael-256-256, 10-round Rijndael-224-256, and 9-round Rijndael-224-224 using precomputation tables, redundancies of key schedules, and multiple impossible differentials. For 10-round Rijndael-256-256, the data, time, and memory complexities of our attack were approximately 2244.4chosen plaintexts, 2240.1encryptions, and 2181.4blocks, respectively. For 10-round Rijndael-224-256, the data, time, and memory complexities of our attack were approximately 2214.4chosen plaintexts, 2241.3encryptions, and 2183.4blocks, respectively. For 9-round Rijndael-224-224, the data, time, and memory complexities of our attack are approximately 2214.4chosen plaintexts, 2113.4encryptions, and 287.4blocks,respectively, or 2206.6chosen plaintexts, 2153.6encryptions, and 2111.6blocks, respectively. To the best of our knowledge, our results are currently the best on Rijndael-256-256 and Rijndael-224-224/256.

关键词： block cipher Rijndael precomputation tables impossible di?erentials multiple impossible differential attacks

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Safe Reinforcement Learning for High-Speed Autonomous Racing

Two-Stage Safe Reinforcement Learning for High-Speed Autonom...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Jingyu Niu Yu Hu Beibei Jin Yinhe Han Xiaowei Li Research Center for Intelligent Computing Systems State Key Laboratory of Computer Architecture ICT CAS University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728185262

ISBN: (纸本)9781728185279

Decision making for autonomous driving is a safety-critical control problem. Prior works of safe reinforcement learning either tackle the problem with reward shaping or with modifying the reinforcement learning exploration process. However, the former cannot guarantee the safety during the learning process, while the latter relies heavily on expertise to design exquisite exploration policy. Currently, only short-term decision makings for low-speed driving were achieved in road scenes with basic geometries. In this paper, we propose a two-stage safe reinforcement learning algorithm to automatically learn a long-term policy for high-speed driving that guarantees safety during the entire training. In the first learning stage, model-free reinforcement learning is followed by a rule-based safeguard module to avoid danger at low speed without expert ne-tuning. In the second learning stage, the rule-based module is replaced with a data-driven counterpart to develop a closed-form analytical safety solution for high-speed driving. Moreover, an adaptive reward function is designed to match the different objectives of the two learning stages for faster convergence to an optimal policy. Experiments are conducted on a racing simulator TORCS which has complex racing tracks (e.g. sharp turns, hills). Compared with the state-of-the-art baselines, the results show that our method achieves zero safety violation and quickly converges to a more efficient and stable policy with an average speed of 127 km/h (3.3% higher than the best result of baselines) and an average swing of 3.96 degrees.

关键词： Training Geometry Roads Decision making Reinforcement learning Safety Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Lightdet: A Lightweight and Accurate Object Detection Network

Lightdet: A Lightweight and Accurate Object Detection Networ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Qiankun Tang Jie Li Zhiping Shi Yu Hu Research Center for Intelligent Computing Systems State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing Advanced Innovation Center for Imaging Theory and Technology Capital Normal University

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

The extensive computational burden limits the usage of accurate but complex object detectors in resource-bounded scenarios. In this paper, we present a lightweight object detector, named LightDet, to address this dilemma. We design a lightweight backbone that is able to capture rich low-level features by the proposed Detail-Preserving Module. To effectively aggregate bottom and top-down features, we introduce an efficient Feature-Preserving and Refinement Module. A lightweight prediction head is employed to further reduce the entire network complexity. Experimental results show that our LightDet achieves 75.5% mAP on PASCAL VOC 2007 at the speed of 250 FPS and 24.0% mAP on MS COCO dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Small file read performance optimization based on redis cache in distributed storage system 13th

Small file read performance optimization based on redis cach...

引用

13th International Conference on Genetic and Evolutionary computing, ICGEC 2019

作者： Wei, Bizhong Deng, Liqiang Fan, Ya Ye, Miao School of Computer Science and Information Security Guilin University of Electronic Technology GuilinGuangxi541004 China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology GuilinGuangxi541004 China Guangxi Colleges and Universities Key Laboratory of Cloud Computing and Complex Systems Guilin University of Electronic Technology GuilinGuangxi541004 China

ISBN: (纸本)9789811533075

At present, small files stored in most of the distributed storage systems account for a large proportion, how to improve the storage efficiency of small file has long been a hot issue in the academic community. In the existing methods, researchers usually integrate small files into content-related large files for association storage. The shortcoming is that if we read some small files in a large file, the entire large file must be read into the cache space, which greatly reduces the utilization of the cache space. To solve this defect, this paper designs a scheme based on the combination of cache replacement optimization algorithm and multi-level cache dynamic elimination mechanism. We compute the content heat value of the cache object by the cache replacement optimization algorithm, and then through the multi-level cache dynamic elimination mechanism we expel the object with low content heat value in the cache space to reserve enough space for the new arrived object. This proposed method not only improves the cache space utilization, but also increases the cache data search efficiency and hit rate. Series of experiments and their result show that the cache hit rate obtained by our proposed method is 14% higher than the LRU cache replacement algorithm and 52% higher than the LFU cache replacement algorithm, which can optimize the reading performance of small files based on Redis cache. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Exploring spatial-temporal multi-frequency analysis for high-fidelity and temporal-consistency video prediction

arXiv

引用

arXiv 2020年

作者： Jin, Beibei Hu, Yu Tang, Qiankun Niu, Jingyu Shi, Zhiping Han, Yinhe Li, Xiaowei Research Center for Intelligent Computing Systems State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Capital Normal University

Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current predictive models, which lead to image distortion and temporal inconsistency. In this paper, we point out the necessity of exploring multi-frequency analysis to deal with the two problems. Inspired by the frequency band decomposition characteristic of Human Vision System (HVS), we propose a video prediction network based on multi-level wavelet analysis to deal with spatial and temporal information in a unified manner. Specifically, multi-level spatial discrete wavelet transform decomposes each video frame into anisotropic sub-bands with multiple frequencies, helping to enrich structural information and reserve fine details. On the other hand, multi-level temporal discrete wavelet transform which operates on time axis decomposes the frame sequence into sub-band groups of different frequencies to accurately capture multi-frequency motions under fixed frame rate. Extensive experiments on diverse datasets demonstrate that our model shows significant improvements on fidelity and temporal consistency over the state-of-the-art works. Copyright © 2020, The Authors. All rights reserved.

关键词： Discrete wavelet transforms

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：