检索结果-内蒙古大学图书馆

2024 International Conference on Intelligent Education and Computer Technology, IECT 2024

作者： Cheng, Yan Zhou, Ziwei School of Computer Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China Prov. Key Lab. of Intelligent Information Processing and Affective Computing of Jiangxi Province 330022 China School of Software Jiangxi Normal University 330022 China

ISBN: (纸本)9798400709920

Text Sentiment Classification, a significant task in Natural Language Processing, aims to comprehend user needs and expectations by categorizing the sentiments of texts posted on platforms. Despite their utility, existing models for this task do not fully account for the influence of contextual and syntactic text features on sentiment classification. To address these issues, a text sentiment classification model based on syntactic graph attention network is proposed in this study. The model begins by extracting the contextual features of a sentence using BiGRU. It then generates a syntactic graph through a syntactic analyzer, using the contextual features as the node features of the syntactic graph. A syntactic graph attention network is constructed to extract the syntactic features of the syntactic graph. These feature vectors are then input into a softmax function to achieve text sentiment classification. Experimental results indicate that the proposed model outperforms similar models on two public datasets in terms of classification accuracy, thus demonstrating its effectiveness. © 2024 ACM.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

An Active Visual Perception Methodology for the Safety of Human-Robot Collaborations

An Active Visual Perception Methodology for the Safety of Hu...

引用

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Siyuan Cheng Pengfei Yi Mengmeng Chen Jing Dong Rui Liu Ling Wang Key Laboratory of Advanced Design and Intelligent Computing (Ministry of Education) School of Software Engineering Dalian University Dalian China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350937

In industrial settings with multiple robotic arms, ensuring human-robot interaction safety through visual feedback is essential. However, existing methods use multiple pre-set cameras to avoid occlusion, making implementation challenging in compact spaces. We propose an adaptive active visual perception method for safety in human-robot collaboration by equipping a single RGBD camera on an idle robotic arm. This method eliminates the need to add additional brackets, is low cost, and is suitable for compact environments compared to current methods. Firstly, to capture comprehensive and accurate global information as much as possible, an active visual perception strategy integrating static visual perception and proprioceptive pose optimization is designed; then, an optimization-based robot position and pose decision method is proposed by using the real-time robots state and obstacles state, which enables the camera at the end of the robot to acquire more effective views; finally, a dual-robot following strategy is proposed to ensure that it can work in tandem. The validity was proved by experimentation. The video are available at https://***/03lwb.

关键词： Visualization Service robots Robot vision systems Human-robot interaction Streaming media Cameras Manipulators

来源：评论

学校读者我要写书评

暂无评论

Image super‐resolution via dynamic network

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 837-849页

作者： Chunwei Tian Xuanyu Zhang Qi Zhang Mingming Yang Zhaojie Ju School of Software Northwestern Polytechnical UniversityXi'anChina National Engineering Laboratory for Integrated Aero‐Space‐Ground‐Ocean Big Data Application Technology Xi'anChina Research&Development Institute Northwestern Polytechnical UniversityShenzhenChina School of Economics and Management Harbin Institute of Technology at WeihaiWeihaiChina Tencent AI Lab ShenzhenChina School of Computing University of PortsmouthPortsmouthUK

Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐***,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction *** residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐*** enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying *** prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained ***,a residual learning operation is embedded in the refinement block to prevent long‐term dependency ***,a construction block is responsible for reconstructing high‐quality *** heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital *** results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and *** code of DSRNet can be obtained at https://***/hellloxiaotian/DSRNet.

关键词： CNN dynamic network image super‐resolution lightweight network

来源：评论

学校读者我要写书评

暂无评论

Tolerant Quantum Junta Testing

arXiv

引用

arXiv 2024年

作者： Chen, Zhaoyang Li, Lvzhou Luo, Jingquan Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China

Junta testing for Boolean functions has sparked a long line of work over recent decades in theoretical computer science, and recently has also been studied for unitary operators in quantum computing. Tolerant junta testing is more general and challenging than the standard version. While optimal tolerant junta testers have been obtained for Boolean functions, there has been no knowledge about tolerant junta testers for unitary operators, which was thus left as an open problem in [Chen, Nadimpalli, and Yuen, SODA2023]. In this paper, we settle this problem by presenting the first algorithm to decide whether a unitary is ϵ1-close to some quantum k-junta or is ϵ2-far from any quantum k-junta, where an n-qubit unitary U is called a quantum k-junta if it only non-trivially acts on just k of the n qubits. More specifically, we present a tolerant tester with (Equation presented), and ρ ∈ (0, 1), and the query complexity is (Equation presented), which demonstrates a trade-off between the amount of tolerance and the query complexity. Note that our algorithm is non-adaptive which is preferred over its adaptive counterparts, due to its simpler as well as highly parallelizable nature. At the same time, our algorithm does not need access to U†, whereas this is usually required in the literature. © 2024, CC BY.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

Circuit Complexity of Sparse Quantum State Preparation

arXiv

引用

arXiv 2024年

作者： Luo, Jingquan Li, Lvzhou Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China

Quantum state preparation is a fundamental and significant subroutine in quantum computing. In this paper, we conduct a systematic investigation on the circuit size for sparse quantum state preparation. A quantum state is said to be d-sparse if it has only d non-zero amplitudes. For the task of preparing an n-qubit d-sparse quantum state, we obtain the following results: • Without ancillary qubits: We propose the first approach that uses o(dn) elementary gates without using ancillary qubits. Specifically, it is proven that any n-qubit d-sparse quantum state can be prepared by a quantum circuit of size O(logdnn +n) without using ancillary qubits. This is asymptotically optimal when d = poly(n), and this optimality extends to a broader scope under some reasonable assumptions. • With limited ancillary qubits: (i) We show that any n-qubit d-sparse quantum state can be prepared by a quantum circuit of size O(logdnd) and depth Θ(log dn) using at most O(logndd) ancillary qubits, which not only reduces the circuit size compared to the one without ancillary qubits when d = ω(poly(n)), but also achieves the same asymptotically optimal depth while utilizing fewer ancillary qubits and applying fewer quantum gates compared to the result given in [Physical Review Letters, 129, 230504(2022)]. (ii) We establish the lower bound Ω(log(n+dnm)+log d + n) on the circuit size with m ancillary qubits available. Additionally, we demonstrate a slightly stronger lower bound Ω(log(dnn+m) + n) under reasonable assumptions. • With unlimited ancillary qubits: We prove that with arbitrary amount of ancillary qubits available, the circuit size for preparing n-qubit d-sparse quantum states is Θ(logdndn + n). © 2024, CC BY.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Protein Functional Family Classification Based on Multilevel Feature Information

Protein Functional Family Classification Based on Multilevel...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Zhou, Guokai Chen, Weiting East China Normal University MOE Research Center of Software/Hardware Co-Design Engineering Shanghai Key Laboratory of Trustworthy Computing Shanghai China

ISBN: (纸本)9781665468190

Next-generation sequencing technologies generated a large number of new sequenced proteins. Classifying these proteins into functional families is an important task in the field of biological protein property research. The high-cost and time-consuming drawbacks of bioassays promote the development of machine learning-based protein classification studies. However, previous work only used single level features, which were not informative enough and had classification bias. In this paper, we propose a new model named PCNM to alleviate the above problems. Different from previous work that extracts only a single level of features, the PCNM model uses a Convolutional Neural Network (CNN) module and a Global and Local feature (GL) module to extract feature at three levels: conserved domains, amino acids, and protein sequences. The experimental results of the Phages of orthologous groups dataset (POG) and the G-protein coupled receptor superfamily dataset (GPCR) show that our proposed PCNM outperforms currently available methods in five metrics: accuracy, precision, recall, F1 score, and MCC. PCNM achieves a high accuracy of 85.12% on the GPCR sub-subfamily dataset and 81.42% on the POG dataset. The robustness experiments of PCNM further demonstrate that the model alleviates the classification bias. © 2022 IEEE.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Graph-based Modeling and Simulation of Emergency Services Communication Systems

Graph-based Modeling and Simulation of Emergency Services Co...

引用

International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)

作者： Jardi Martinez Jordan Michael Stiber Computing and Software Systems Division School of Science Technology Engineering and Mathematics University of Washington Bothell Bothell WA USA

ISBN: (数字)9798331531300

ISBN: (纸本)9798331531317

Emergency Services Communication Systems (ESCS) are evolving into Internet Protocol based communication networks, promising enhancements to their function, availability, and resilience. This increase in complexity and cyber-attack surface demands better understanding of these systems’ breakdown dynamics under extreme circumstances. Existing ESCS research largely overlooks simulation and the little work that exists focuses primarily on cybersecurity threats and neglects critical factors such as non-stationarity of call arrivals. This paper introduces a robust, adaptable graph-based simulation framework and essential mathematical models for ESCS simulation. The framework uses a representation of ESCSes where each vertex is a communicating finite-state machine that exchanges messages along edges and whose behavior is governed by a discrete event queuing model. Call arrival burstiness and its connection to emergency incidents is modeled through a cluster point process. Model applicability is demonstrated through simulations of the Seattle Police Department ESCS. Ongoing work is developing GPU implementation and exploring use in cybersecurity tabletop exercises.

关键词： Adaptation models Protocols Law enforcement Computational modeling Stochastic processes Emergency services Mathematical models Telecommunications Internet Resilience

来源：评论

学校读者我要写书评

暂无评论

Accelerate Bit Manipulation in XiangShan Processer Using RISC-V B Extension and Instruction Fusion

Accelerate Bit Manipulation in XiangShan Processer Using RIS...

引用

2022 International Conference on Cloud computing, Internet of Things, and Computer Applications, CICA 2022

作者： Zhang, Fawang Tang, Dan Cai, Ye College of Computer Science and Software Engineering Shenzhen University Shenzhen China State Key Laboratory of Computer Architecture Institute of Computing Technology Beijing China

ISBN: (纸本)9781510656673

In the field of high-performance computing, some application scenarios make extensive use of bit manipulation. RISC-V foundation issues B extension to reduce the number of instructions during the static compilation. But this extension does not cover the more frequent operations fully. Instruction fusion technology can fuse multiple instructions into one instruction at the decode stage to dynamically reduce the number of instructions. Therefore, this technology can supplement RISC-V B extension uncovered instruction, enhancing the processor’s capabilities for bit manipulation. This paper implements the RISC-V B extension 1.0 version on the Xiangshan processor. For accelerating more bit manipulation, we profiled general benchmarks by the simulator, proposed ten new instructions fusion targets, and implemented a fusion decode unit. Finally, we use Coremark and SPEC CPU 2006 integer to evaluate the performance. The Coremark results show that dynamic instructions reduce by 18.14%, and the performance improves by 12.09%. © 2022 SPIE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Appley: Approximate Shapley Value for Model Explainability in Linear Time

Appley: Approximate Shapley Value for Model Explainability i...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Shafiul Alam, Md Xie, Ying Kennesaw State University Analytics and Data Science Kennesaw United States Kennesaw State University College of Computing and Software Engineering Kennesaw United States

ISBN: (纸本)9781665480451

We have seen complex deep learning models out-performing human benchmarks in many areas (e.g. computer vision, natural language processing). Clever architectures and higher model complexity are two of the major drivers of such outstanding performances. Higher model complexity generally makes the decision-making process of a model opaque to human perception. But understanding the decision-making process is very important for many reasons including enhancing trust in the model's prediction, improving model robustness, gaining actionable insight from why a model made a particular prediction and discovering new knowledge about a problem. Model explainability has been an active area of research for some time now, but the problem is still far from being solved. An established way of model explanation is to assign a score to each variable (also known as variable attribution), which represents the importance of the variable in a particular prediction of a model. In a lot of techniques, the scoring process involves distributing the output to each variable. This is challenging when the model is complex and consists of a high degree of interaction terms. A coalition game theoretic approach called Shapley Value provides a fair way to tackle the challenge. However, the growth of computation time of the exact Shapley Values is exponential in the number of variables. Hence, many attribution techniques use approximations instead of the exact Shapley Value as attribution. In this manuscript, we propose a novel variable attribution technique called Appley (short for Approximate Shapley) by approximating the Shapley Values in linear time. Moreover, we show that the 'Appley' attributions are generally closer to the exact Shapley Values than an existing well-known and comparable attribution technique. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Partial SQL Query Assessment

Partial SQL Query Assessment

引用

Proceedings of the International Convention MIPRO

作者： Mario Fabijanić Igor Mekterović Software Engineering Algebra University College Zagreb Croatia Faculty of Electrical Engineering and Computing University of Zagreb Croatia

Automated grading systems in education have been around for sixty years. They have found applications in areas such as online learning systems where virtually an unlimited number of users can test their knowledge that would not be possible to evaluate manually. Implementations within Massive Open Online Courses are a good practice in which users can do the self-testing, and get instant feedback, making the learning process more efficient. Within universities, automated grading systems allow teachers to evaluate solutions and provide feedback for thousands of submissions in a short time. This paper presents an overview of methods used in automatic SQL query evaluation systems, from early implementations when the goal was only to evaluate solutions binary, to today when they enable functionalities like partial and configurable evaluation, rich and customized feedback, learning analytics, learning pattern detection, code quality check, plagiarism detection. These methods are not exclusive, and combining different approaches makes an automated grading system more comprehensive and applicable. Automatic assessment system of SQL queries developed at Algebra University College will be presented as an example of a system which uses dynamic and static analysis, awards partial points, and gives feedback to students based on the wrong parts of their solutions.

关键词：

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：