检索结果-内蒙古大学图书馆

Proceedings of the 2019 2nd International Conference on Signal Processing and Machine Learning

作者： Enwei Zhang Hongtu Zhou Yongchao Ding Junqiao Zhao Chen Ye The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University School of Electronics and Information Engineering Shanghai P. R. China Tongji University School of Electronics and Information Engineering Shanghai P. R. China Tongji University School of Electronics and Information Engineering P. R. China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University School of Electronics and Information Engineering P. R. China

ISBN: (纸本)9781450372213

Obstacle avoiding is one of the most complex tasks for autonomous driving systems, which was also ignored by many cutting-edge end-to-end learning-based methods. The difficulties stem from the integrated process of detection and interpretation of environment and obstacles and generation of proper behaviors. We make the use of CARLA, a simulator for autonomous driving research, and collect massive human drivers' reactions to obstacles on road subjecting to given driving commands, i.e. follow, go straight, turn left and turn right for about 6 hours. A behavior-Cloning neural network architecture is proposed with the modified loss that enlarge the effects of errors for steer, which indicates the benefit to high an accuracy. We found the data augmentation of the image is crucial to the training of the proposed network. And a reasonable limit allows avoiding unexpected stop. The experiments demonstrate 3 obstacle avoidance cases: for the same type as the training dataset, other automobile and two-wheeled vehicles. Finally, the CARLA benchmark is also tested.

关键词： imitation learning obstacle avoidance end-to-end autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Random Occlusion Recovery with Noise Channel for Person Re-identification 16th

Random Occlusion Recovery with Noise Channel for Person Re-i...

引用

16th International Conference on Intelligent computing, ICIC 2020

作者： Zhang, Kun Wu, Di Yuan, Changan Qin, Xiao Wu, Hongjie Zhao, Xingming Zhang, Lijun Du, Yuchuan Wang, Hanli Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University Shanghai China Guangxi Academy of Science Nanning530025 China School of Computer and Information Engineering Nanning Normal University Nanning530299 China School of Computer Science and Technology Soochow University Suzhou215006 China School of Electronic and Information Engineering Suzhou University of Science and Technology Suzhou215009 China Fudan University Shanghai200433 China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Ministry of Education Shanghai China Collaborative Innovation Center of Intelligent New Energy Vehicle and School of Automotive Studies Tongji University Shanghai201804 China The Key Laboratory of Road and Traffic Engineering of the Ministry of Education Department of Transportation Engineering Tongji University Shanghai201804 China Department of Computer Science and Technology the Key Laboratory of Embedded System and Service Computing and Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China

ISBN: (纸本)9783030607982

Person re-identification, as the basic task of a multi-camera surveillance system, plays an important role in a variety of surveillance applications. However, the current mainstream person re-identification model based on deep learning requires a lot of labeled data, which takes a lot of time and manpower. In this study, we proposed a person re-identification method based on random occlusion recovery with noise channel. We add random occlusion blocks to the original image, use the GAN model for repair, and use the repaired image to expand the original training set. After that, the generated image is adjusted through the noise channel. Finally, we use the enhanced data set to train the baseline model. Our model achieves the state-of-the-art on Market-1501 dataset, proving that the method is effective. © 2020, Springer Nature Switzerland AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Age-Upon-Decisions Minimizing Scheduling in Internet of Things: To Be Random or to Be Deterministic?

Age-Upon-Decisions Minimizing Scheduling in Internet of Thin...

引用

作者： Dong, Yunquan Chen, Zhengchuan Liu, Shanyun Fan, Pingyi Letaief, Khaled Ben School of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing210044 China Key Laboratory of Dependable Service Computing in Cyber-Physical Society Ministry of Education Chongqing China Department of Electronic Engineering Tsinghua University Beijing China Department of Electrical and Computer Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

In this article, we consider an Internet of Things (IoT) system in which a sensor delivers updates to a monitor with exponential service time and first-come-first-served (FCFS) discipline. We investigate the freshness of the received updates and propose a new metric termed as age upon decisions (AuD), which is defined as the time elapsed from the generation of each update to the epoch it is used to make decisions (e.g., estimations, inferences, and controls). Within this framework, we aim at improving the freshness of updates at decision epochs by scheduling the update arrival process and the decision-making process. The theoretical results show that: 1) when the decisions are made according to a Poisson process, the average AuD is independent of decision rate and will be minimized if the arrival process is periodic (i.e., deterministic);2) when both the decision process and the arrival process are periodic, the average AuD is larger, but decreases with decision rate to, the average AuD of the corresponding system with the Poisson decisions (i.e., random);and 3) when both the decision process and the arrival process are periodic, the average AuD can be further decreased by optimally controlling the offset between the two processes. For practical IoT systems, therefore, it is suggested to employ periodic arrival processes and random decision processes. Nevertheless, making the periodical updates and decisions with properly controlled offset is also a promising solution, if the timing information of the two processes can be accessed by the monitor. © 2014 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Finite time anti-synchronization of complex-valued neural networks with bounded asynchronous time-varying delays

arXiv

引用

arXiv 2019年

作者： Liu, Xiwei Li, Zihan Department of Computer Science and Technology Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China

In this paper, we studied the finite time anti-synchronization of master-slave coupled complex-valued neural networks (CVNNs) with bounded asynchronous time-varying delays. With the decomposing technique and the generalized {ξ, ∞}-norm, several criteria for ensuring the finite-time anti-synchronization are obtained. The whole anti-synchronization process can be divided into two parts: first, the norm of each error state component will change from initial values to 1 in finite time, then from 1 to 0 in fixed time. Therefore, the whole time is finite. Finally, one typical numerical example is presented to demonstrate the correctness of our obtained results. key words: Anti-synchronization, asynchronous, complex-valued neural network, finite time, time-varying delay Copyright © 2019, The Authors. All rights reserved.

关键词： Time varying control systems

来源：评论

学校读者我要写书评

暂无评论

Improving read performance of lsm-tree based KV stores via dual grained caches 21

Improving read performance of lsm-tree based KV stores via d...

引用

21st IEEE International Conference on High Performance computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and systems, HPCC/SmartCity/DSS 2019

作者： Li, Xiang Xu, Guangping Fan, Hao Lu, Hongli Tang, Bo Xue, Yanbing Zong, Ziliang School of Computer Science and Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin China Key Laboratory of Computer Vision and System Ministry of Education China Department of Computer Science Texas State University San MarcosTX United States

ISBN: (纸本)9781728120584

key-value (KV) stores based on the Log-Structure Merge tree (LSM-tree) have been widely used in modern storage systems (e.g. LevelDB and RocksDB) to achieve high write throughput. However, conventional LSM-tree design has high latency for random read operations, especially in the workloads with concurrent read and write operations. This paper proposes a dual-grained cache scheme to improve the performance of LSM-tree based KV stores, in which a coarse-grained cache improves read performance by leveraging spatial locality and a fine-grained cache tracks the frequently accessed KV pairs. We implement the dual-grained caching on a LSM-tree simulator and evaluate its performance using various Yahoo! Cloud service Benchmark (YCSB) workloads. Our experimental results show that the proposed way of dual-grained caches can significantly improve the read performance of KV stores without sacrificing the advantages of the LSM-tree for write-intensive workloads. © 2019 IEEE.

关键词： Compaction Throughput Conferences Indexes Computer science Benchmark testing Distributed databases

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

Multi-granularity ensemble sample selection and label correction for classification with noisy labels

引用

Applied Soft computing 2025年 180卷

作者： Kecan Cai Hongyun Zhang Witold Pedrycz Duoqian Miao Chaofan Chen Department of Computer Science and Technology Tongji University Shanghai 201804 PR China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 PR China Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 2R3 Canada Systems Research Institute Polish Academy of Sciences 00-901 Warsaw Poland Istinye University Faculty of Engineering and Natural Sciences Department of Computer Engineering Sariyer/Istanbul Turkiye

Sample selection is crucial in classification tasks with noisy labels, yet most existing sample selection methods rely on a single criterion. These approaches often face challenges, including low purity of selected clean samples, and underfitting due to an insufficient number of selected clean training samples. To address these challenges, this paper proposes GNet-SSLC, a novel multi-granularity network framework that integrates multiple criteria ensemble sample selection (SS) and multiple views label correction (LC). In the SS phase, this paper proposes a metric learning-based dual k-Nearest Neighbor (k-NN) sample selection method. This method first uses corrected soft labels from the initial k-NN round to guide the selection of clean samples in the subsequent k-NN round. To further enhance selection accuracy, we combine this dual k-NN approach with a small loss sample selection technique through a voting mechanism. This multiple criteria ensemble method addresses the issues of low purity and instability inherent in single criterion approaches. In the LC phase, this paper designs a multiple views label correction framework that generates high-quality pseudo-labels for selected noisy samples. A key innovation of the framework is the design of a regularized contrastive learning loss, which optimizes the semi-supervised learning process by leveraging multiple views of training samples. The additional inclusion of training samples with high-quality pseudo-labels can effectively mitigate underfitting caused by a limited number of clean training samples. Experimental results on both synthetic and real-world noisy datasets indicate that GNet-SSLC enhances the purity and stability of the selected clean samples, and significantly improves classification performance. The enhancement is particularly notable with high noise rate dataset, such as CIFAR-100 dataset with 80% noise rate, achieving a 19.3% increase in classification accuracy compared to the baseline method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical attention generative adversarial networks for cross-domain sentiment classification

arXiv

引用

arXiv 2019年

作者： Zhang, Yuebing Miao, Duoqian Wang, Jiaqi Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain data. In recent years, many researchers have used deep neural network models for cross-domain sentiment classification task, many of which use Gradient Reversal Layer (GRL) to design an adversarial network structure to train a domain-shared sentiment classifier. Different from those methods, we proposed Hierarchical Attention Generative Adversarial Networks (HAGAN) which alternately trains a generator and a discriminator in order to produce a document representation which is sentimentdistinguishable but domain-indistinguishable. Besides, the HAGAN model applies Bidirectional Gated Recurrent Unit (Bi-GRU) to encode the contextual information of a word and a sentence into the document representation. In addition, the HAGAN model use hierarchical attention mechanism to optimize the document representation and automatically capture the pivots and non-pivots. The experiments on Amazon review dataset show the effectiveness of HAGAN. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Several classes of linear codes with few weights derived from Weil sums

引用

Finite Fields and Their Applications 2025年 108卷

作者： Zhao Hu Mingxiu Qiu Nian Li Xiaohu Tang Liwei Wu Key Laboratory of Intelligent Sensing System and Security (Hubei University) Ministry of Education the Hubei Provincial Engineering Research Center of Intelligent Connected Vehicle Network Security School of Cyber Science and Technology Hubei University Wuhan 430062 China State Key Laboratory of Integrated Service Networks Xi'an 710071 China Hubei Key Laboratory of Applied Mathematics Faculty of Mathematics and Statistics Hubei University Wuhan 430062 China Information Coding & Transmission Key Lab of Sichuan Province CSNMT Int. Coop. Res. Centre (MoST) Southwest Jiaotong University Chengdu 610031 China Wuhan Maritime Communication Research Institute China

Linear codes with few weights have applications in secret sharing, authentication codes, association schemes and strongly regular graphs. In this paper, several classes of t -weight linear codes over F q are presented with the defining sets given by the intersection, difference and union of two certain sets, where t = 3 , 4 , 5 , 6 and q is an odd prime power. By using Weil sums and Gauss sums, the parameters and weight distributions of these codes are determined completely. Moreover, three classes of optimal codes meeting the Griesmer bound are obtained, and computer experiments show that many (almost) optimal codes can be derived from our constructions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A two-phase approach for locally differentially private fuzzy co-clustering

引用

Information Sciences 2025年 718卷

作者： Pengfei Zhang Jianlong An Xiang Cheng Youwen Zhu Ji Zhang Zhikun Zhang State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining No. 168 Shungeng Road Tianjiaan District 232001 Huainan China School of Computer Science and Engineering Anhui University of Science and Technology No. 168 Shungeng Road Tianjiaan District 232001 Huainan China Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics No. 237 Longquan Road Kunming 650221 Yunnan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) No. 3501 Daxue Road Jinan 255020 Shandong China Key Laboratory of Equipment Data Security and Guarantee Technology Guilin University of Electronic Technology No. 1 Jinji Road Guilin 541010 Guangxi China State Key Laboratory of Networking and Switching Technology No. 10 Xitucheng Road Haidian District 100876 Beijing China Beijing University of Posts and Telecommunications No. 10 Xitucheng Road Haidian District 100876 Beijing China College of Computer and Data Science Nanjing University of Aeronautics and Astronautics No. 29 Yudao Street Qinhuai District Nanjing 210016 Jiangsu China School of Mathematics Physics and Computing University of Southern Queensland West Street Toowoomba 4350 Queensland Australia College of Computer Science and Technology Zhejiang University No. 38 Zheda Road Xihu District 310027 Hangzhou China

Clustering analysis is important for providing personalized services across various user experience optimization. As an advanced clustering technique, Fuzzy Co-Clustering ( FCC ) excels at handling high-dimensional data by simultaneously grouping both samples and attributes while allowing objects to belong to multiple clusters. To alleviate the potential privacy risks posed by directly using raw data, researchers often employ local differential privacy (LDP) techniques for protection. However, current clustering studies under LDP either directly perform clustering on the high-dimensional data, which necessitates splitting the privacy budget heavily, leading to excessive noise injection, or fail to adequately address the impact of Laplacian noise on both objective function modeling and distance metric selection, resulting in reduced clustering accuracy. To address these limitations, we present a two-phase approach SONY , which allocates part of the privacy budget to evaluate attribute importance and perform dimensionality reduction accordingly, and then utilizes the remaining budget to conduct noise-aware clustering on the pruned data. Our key technical contributions include: (1) a Noise-aware Similarity Calculation method ( NSC ) that replaces traditional Euclidean distance with a specialized metric which accounts for the statistical properties of Laplacian noise; (2) an importance-driven dimension reduction and budget allocation method ( IDRBA ) which optimizes both attribute selection and privacy budget allocation; and (3) an outlier-aware objective function calculation method ( OOC ) which enhances robustness against potential noise-induced outliers. We provide theoretical guarantees for SONY 's convergence, privacy preservation, utility bounds, and computational complexity. Experimental evaluations conducted on two real-world datasets and one synthetic dataset, demonstrate that SONY outperforms the state-of-the-arts by at least 14% in F-Measure and 10% in Entrop

关键词： Fuzzy co-clustering Local differential privacy Privacy protection Two phase

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：