检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wu, Taoran Yu, Yiqing Xia, Bican Wang, Ji Xue, Bai Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Department of Information Science School of Mathematical Sciences Peking University China State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology China

Ensuring safety through set invariance has proven to be a valuable method in various robotics and control applications. This paper introduces a comprehensive framework for the safe probabilistic invariance verification of both discrete- and continuous-time stochastic dynamical systems over an infinite time horizon. The objective is to ascertain the lower and upper bounds of liveness probabilities for a given safe set and set of initial states. The liveness probability signifies the likelihood of the system remaining within the safe set indefinitely, starting from a state in the initial set. To address this problem, we propose optimizations for verifying safe probabilistic invariance in discrete-time and continuous-time stochastic dynamical systems. These optimizations are constructed via either using the Doob’s nonnegative supermartingale inequality-based method or relaxing the equations described in [30,32], which can precisely characterize the probability of reaching a target set while avoiding unsafe states. Finally, we demonstrate the effectiveness of these optimizations through several examples using semi-definite programming tools. Copyright © 2024, The Authors. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance

AugRmixAT: A Data Processing and Training Method for Improvi...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Liu, Xiaoliang Shen, Furao Zhao, Jian Nie, Changhai Nanjing University National Key Laboratory for Novel Software Technology China Nanjing University Department of Computer Science and Technology China School of Electronic Science and Engineering Nanjing University China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Deep neural networks are powerful, but they also have short-comings such as their sensitivity to adversarial examples, noise, blur, occlusion, etc. Moreover, ensuring the reliability and robustness of deep neural network models is crucial for their application in safety-critical areas. Much previous work has been proposed to improve specific robustness. However, we find that the specific robustness is often improved at the sacrifice of the additional robustness or generalization ability of the neural network model. In particular, adversarial training methods significantly hurt the generalization performance on unperturbed data when improving adversarial robustness. In this paper, we propose a new data processing and training method, called AugRmixAT, which can simultaneously improve the generalization ability and multiple robustness of neural network models. Finally, we validate the effectiveness of AugRmixAT on the CIFAR-10/100 and Tiny-ImageNet datasets. The experiments demonstrate that AugR-mixAT can improve the model's generalization performance while enhancing the white-box robustness, black-box robustness, common corruption robustness, and partial occlusion robustness. © 2022 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

USee: Ultrasound-Based Device-Free Eye Movement Sensing

USee: Ultrasound-Based Device-Free Eye Movement Sensing

引用

IEEE Communications Society Conference on Sensor and Ad Hoc Communications and Networks (SECON)

作者： Wen Cheng Mingzhi Pang Haoran Wan Shichen Dong Dongxu Liu Wei Wang State Key Laboratory for Novel Software Technology Nanjing University Nanjina China Department of Computer Science Princeton University Princeton USA

ISBN: (数字)9798331519186

ISBN: (纸本)9798331519193

Eye movements play a significant role in human-computer interaction and are widely recognized as an essential health indicator, making their detection both appealing and technically challenging. In this paper, we present a system named USEE that achieves high-precision capture of weak and aperiodic eye movements by utilizing fine-grained and ubiquitous ultrasound signals, capturing both blinking and more subtle saccades. We first identify signal changes associated with eye movements by capturing the unique impact of blinking. Further, we establish a pioneering relationship between the residuals from signal decomposition and subtle eye movements. Utilizing inno-vative signal processing architectures, we mitigate interference and effectively extract eye movement features. Subsequently, we employ one-dimensional convolutional operations in place of signal cross-correlation, designing filters for motion category identification and a lightweight convolutional neural network for saccade direction classification. This enables our system to serve as a foundational sensing layer for eye movement tracking, applicable across diverse applications. We implement USEE on both a research-purpose platform and a commodity Raspberry Pi. Extensive experimental results demonstrate the effectiveness of our system, achieving 91% accuracy in saccade recognition and 94% in blink detection. The system proves robust, even in challenging scenarios with strong interference, such as the presence of moving pedestrians.

关键词： Human computer interaction Wireless communication Wireless sensor networks Ultrasonic imaging Tracking Interference Feature extraction Transceivers Sensors Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Revisiting Stochastic Multi-Level Compositional Optimization

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5613-5624页

作者： Wei Jiang Sifan Yang Yibo Wang Tianbao Yang Lijun Zhang National Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Key Laboratory for Novel Software Technology School of Artiicial Intelligence Nanjing University Nanjing China Department of Computer Science and Engineering Texas A&M University College Station TX USA

This paper explores stochastic multi-level compositional optimization, where the objective function is a composition of multiple smooth functions. Traditional methods for solving this problem suffer from either sub-optimal sample complexities or require huge batch sizes. To address these limitations, we introduce the Stochastic Multi-level Variance Reduction (SMVR) method. In the expectation case, our SMVR method attains the optimal sample complexity of $\mathcal {O}(1/\epsilon ^{3})$ to find an $\epsilon$ -stationary point for non-convex objectives. When the function satisfies convexity or the Polyak-Łojasiewicz (PL) condition, we propose a stage-wise SMVR variant. This variant improves the sample complexity to $\mathcal {O}(1/\epsilon ^{2})$ for convex functions and $\mathcal {O}(1/(\mu \epsilon ))$ for functions meeting the $\mu$ -PL condition or $\mu$ -strong convexity. These complexities match the lower bounds not only in terms of $\epsilon$ but also in terms of $\mu$ (for PL or strongly convex functions), without relying on large batch sizes in each iteration. Furthermore, in the finite-sum case, we develop the SMVR-FS algorithm, which can achieve a complexity of $\mathcal {O}(\sqrt{n}/\epsilon ^{2})$ for non-convex objectives, $\mathcal {O}(\sqrt{n}/\epsilon \log (1/\epsilon ))$ for convex functions and $\mathcal {O}(\sqrt{n}/\mu \log (1/\epsilon ))$ for objectives satisfying the $\mu$ -PL condition, where $n$ denotes the number of functions in each level. To make use of adaptive learning rates, we propose the Adaptive SMVR method, which maintains the same complexities while demonstrating faster convergence in practice.

关键词： Complexity theory Optimization Convex functions Convergence Training Stochastic processes Lower bound Jacobian matrices Adaptive learning Storms

来源：评论

学校读者我要写书评

暂无评论

Deep learning for change detection in remote sensing:a review

引用

Geo-Spatial Information science 2023年第3期26卷 262-288页

作者： Ting Bai Le Wang Dameng Yin Kaimin Sun Yepei Chen Wenzhuo Li Deren Li Project Planning Department Wuhan Land Arranging Storage CenterWuhanChina Department of Geography University at BuffaloThe State University of New YorkBuffaloUSA Institute of Crop Sciences Chinese Academy of Agricultural SciencesBeijingChina State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhanChina School of Computer Science Hubei University of TechnologyWuhanChina Collaborative Innovation Center of Geospatial Technology Wuhan UniversityWuhanChina

A large number of publications have incorporated deep learning in the process of remote sensing change *** these Deep Learning Change Detection(DLCD)publications,deep learning methods have demonstrated their superiority over conventional change detection ***,the theoretical underpinnings of why deep learning improves the performance of change detection remain *** of today,few in-depth reviews have investigated the mechanisms of *** such a review,five critical questions remain *** DLCD provide improved information representation for change detection?If so,how?How to select an appropriate DLCD method and why?How much does each type of change benefits from DLCD in terms of its performance?What are the major limitations of existing DLCD methods and what are the prospects for DLCD?To address these five questions,we reviewed according to the following *** grouped the DLCD information assemblages into the four unique dimensions of remote sensing:spectral,spatial,temporal,and *** the extraction of information in each dimension,the difference between DLCD and conventional change detection methods was *** proposed a taxonomy of existing DLCD methods by dividing them into two distinctive pools:separate and coupled *** advantages,limitations,applicability,and performance were thoroughly investigated and explicitly *** examined the variations in performance between DLCD and conventional change *** depicted two limitations of DLCD,*** sample and hardware and software *** on these analyses,we identified directions for future *** a result of our review,we found that DLCD’s advantages over conventional change detection can be attributed to three factors:improved information representation;improved change detection methods;and performance *** has to surpass the limitations with regard to training samples and computing infrastructure.

关键词： Deep learning change detection remote sensing review information representation

来源：评论

学校读者我要写书评

暂无评论

Evaluating Logical Expressions by Membrane Systems

引用

Chinese Journal of Electronics 2025年第2期23卷 278-283页

作者： Ping Guo Jinfang Ji Haizhu Chen Ran Liu College of Computer Science Chongqing University Chongqing China Chongging Key Laboratory of Software Theory and Technology Chongqing China Department of Software Engineering Chongqing College of Electronic Engineering Chongqing China

Boolean and relational operations, which are defined for solving mathematically logical problems, are always required in computing models. Membrane computing is a kind of distributed parallel computing model. In this paper, we design different membranes for implementing primary Boolean and relational operations respectively. And based on these membranes, a membrane system can be constructed by a present algorithm for evaluating a logical expression. Some examples are given to illustrate how to perform the Boolean, relational operations and evaluate the logical expression correctly in these membrane systems.

关键词： Computational modeling Parallel processing Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Bilinear Graph Neural Network-Enhanced Web Services Classification 23

Bilinear Graph Neural Network-Enhanced Web Services Classifi...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Zhang, Lulu Cao, Buqing Peng, Mi Qing, Yueying Kang, Guosheng Liu, Jianxun Fletcher, Kenneth K. School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory of Service Computing and New Software Service Technology Xiangtan China University of Massachusetts Boston Department of Computer Science Boston United States

ISBN: (纸本)9781665494571

With the growing number of Web services, classifying Web services accurately and efficiently has become a challenging problem. Effective service classification is conducive to improving the quality of service discovery and the efficiency of service composition. Existing graph neural network methods represent the target service node by a weighted sum of the features of the neighbor service nodes, and have achieved remarkable results in service classification. However, these methods ignore the impact of possible interactions between neighbor service nodes on the target service node. To address this problem, we propose a Web services classification method based on bilinear graph neural network. Our proposed method can model the bilinear interactions between neighbor service nodes and effectively improve the accuracy of service classification. First, our proposed model uses the Word2Vec model to extract the latent semantic vectors from service description documents. We then construct the service relationship network according to tags and shared annotation relationships of Web services. Next, a bilinear aggregator is used to model the pairwise interactions between neighbor service nodes, highlighting the local common attributes. Finally, the bilinear aggregator is combined with the weighted sum aggregator to construct a bilinear graph neural network, which can learn more comprehensive representations of services. The experimental results on the real dataset from ProgrammableWeb show that the classification accuracy of the proposed method is greatly improved compared with DeepWalk, Node2Vec, GCN, and GAT. © 2021 IEEE.

关键词： Smart cities Annotations Mashups Semantics Quality of service Feature extraction Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Arithmetic Expression Evaluations with Membranes

引用

Chinese Journal of Electronics 2025年第1期23卷 55-60页

作者： Ping Guo Haizhu Chen Hui Zheng College of Computer Science Chongqing University Chongqing China Chongqing Key Laboratory of Software Theory and Technology Chongqing China Department of Software Engineering Chongqing College of Electronic Engineering Chongqing China

Arithmetic operations and expression evaluations are fundamental in computing models. This paper firstly designs arithmetic membranes without priority rules for basic arithmetic operations, and then proposes an algorithm to construct expression P systems based on several of such membranes after designing synchronous and asynchronous transmission strategies among the membranes. For any arithmetic expression, an expression P system can be built to evaluate it effectively. Finally, we discuss different parallelism strategies through which different expression P systems can be built for an arithmetic expression.

关键词： Computational modeling Biological system modeling Parallel processing Biomembranes Compounds Arithmetic

来源：评论

学校读者我要写书评

暂无评论

How Well Static Type Checkers Work with Gradual Typing? A Case Study on Python

How Well Static Type Checkers Work with Gradual Typing? A Ca...

引用

IEEE/ACM International Conference on Program Comprehension (ICPC)

作者： Wenjie Xu Lin Chen Chenghao Su Yimeng Guo Yanhui Li Yuming Zhou Baowen Xu State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China

Python has become increasingly popular and widely used in many fields. Dynamic features of Python provide much convenience for developers. However, they can also cause many type-related bugs undetected until runtime, which increases the cost of maintenance. Static type checking is essential to find bugs early, and the introduction of gradual typing and type annotations makes it easier to perform static type analysis. However, it remains to be investigated how well gradual typing improves real bug detection. Therefore, we conducted a comprehensive study on three widely used checkers: MyPy, PyRight, and PyType. We used a benchmark containing 10 popular Python projects with 40 real type-related bugs. First, we performed static type checking on the projects with and without type annotations to evaluate the effectiveness of finding real bugs. Second, we manually analyzed the missing bugs and investigated the reasons. The results show that the three tools can detect 29 of the 40 studied bugs after annotating, while only 14 bugs are detected before annotating. We also found that type annotations can substantially improve the ability of static type checkers to detect real bugs. A detailed analysis of bugs missed by the checkers shows that: (i) the accuracy of type analysis is challenged when it comes to programs with complicated dynamic features, such as dynamically changing object’s attributes, even with annotations; (ii) the inaccurate type annotations can undermine the ability of static type checkers to detect real bugs; (iii) static type checkers have different checking strategies in some cases, which has an impact on real bug detection. Our study can not only enable developers to better understand static type checking and make better use of them but also guide future research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services

Seed Feature Maps-based CNN Models for LEO Satellite Remote ...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Lu, Zhichao Ding, Chuntao Wang, Shangguang Cheng, Ran Juefei-Xu, Felix Boddeti, Vishnu Naresh Sun Yat-sen University School of Software Engineering Zhuhai China Beijing Jiaotong University School of Computer and Information Technology Beijing China Beijing University of Posts and Telecommunications Key Laboratory of Networking and Switching Technology Beijing China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China New York University New YorkNY United States Michigan State University Department of Computer Science and Engineering East LansingMI United States

ISBN: (纸本)9798350304855

Deploying high-performance convolutional neural network (CNN) models on low-earth orbit (LEO) satellites for rapid remote sensing image processing has attracted significant interest from industry and academia. However, the limited resources available on LEO satellites contrast with the demands of resource-intensive CNN models, necessitating the adoption of ground-station server assistance for training and updating these models. Existing approaches often require large floating-point operations (FLOPs) and substantial model parameter transmissions, presenting considerable challenges. To address these issues, this paper introduces a ground-station server-assisted framework. With the proposed framework, each layer of the CNN model contains only one learnable feature map (called the seed feature map) from which other feature maps are generated based on specific rules. The hyperparameters of these rules are randomly generated instead of being trained, thus enabling the generation of multiple feature maps from the seed feature map and significantly reducing FLOPs. Furthermore, since the random hyperparameters can be saved using a few random seeds, the ground station server assistance can be facilitated in updating the CNN model deployed on the LEO satellite. Experimental results on the ISPRS Vaihingen, ISPRS Potsdam, UAVid, and LoveDA datasets for semantic segmentation services demonstrate that the proposed framework outperforms existing state-of-the-art approaches. In particular, the SineFM-based model achieves a higher mIoU than the UNetFormer on the UAVid dataset, with 3.3 × fewer parameters and 2.2 × fewer FLOPs. © 2023 IEEE.

关键词： Neural network models

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：