检索结果-内蒙古大学图书馆

2022 International Conference on Automation, Robotics and computer Engineering, ICARCE 2022

作者： Ju, Chengcheng Zhu, Yi Wang, Chenyu Jiangsu Normal University Department of Computer Science and Technology Xuzhou China Nanjing University of Aeronautics and Astronautics Ministry of Industry and Information Technology Key Laboratory of Safety-Critical Software Nanjing China

ISBN: (纸本)9781665475488

Massive open online courses (MOOCs) play a crucial role in modern education by providing users with largescale open online learning platforms. Substantial research has been conducted to reduce user learning blindness and improve user experience, particularly in personalized course recommendations based on graph neural networks. However, these efforts have focused primarily on fixed or homogeneous graphs, are vulnerable to data sparsity problems, and are difficult to scale. This study proposes to overcome this limitation using graph convolution on local subgraphs combined with an extended matrix factorization model. First, the proposed method decomposes the heterogeneous graph into multiple meta-path-based subgraphs and combines random wandering sampling methods to capture complex semantic relationships between entities while sampling nodes' influence-rich neighborhoods. Next, the attention mechanism adaptively fuses the contextual information of different subgraphs for a more comprehensive construction of user preferences. Experiments on publicly available MOOCs datasets reveal that the proposed model outperforms other benchmark models and is highly scalable while alleviating the data sparsity problem. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Space-time Constraint Resources Modeling and Safety Verification Method for Automated Vehicles 9

Space-time Constraint Resources Modeling and Safety Verifica...

引用

9th International Conference on Dependable Systems and Their Applications, DSA 2022

作者： Zhu, Yi Chen, Xiaoying Zhao, Yu School of Computer Science and Technology Jiangsu Normal University XuZhou China Ministry of Industry and Information Technology Nanjing University of Aeronautics and Astronautics Key Laboratory of Safety-Critical Software Nanjing China

ISBN: (数字)9781665488778

ISBN: (纸本)9781665488778

Automated vehicle combines physics and computation on the basis of environment perception. It can realize intelligent interaction with the environment. Automated vehicle is a typical CPS. However, the continuous changes of driving physical space bring certain challenges to the safety of CPS resources. Therefore, how to solve this kind of CPS resource safety problems caused by space and time changes becomes the key. We propose a space-time constraint resource modeling and safety verification method for automated vehicle to solve this problem. Firstly, the physical topology model is proposed to model the physical topology space of CPS, which is able to describe the topology space. Secondly, the Resource-Space Time Communicating Sequential process (RS- TCSP) is proposed by extending the resource vector on the basis of Time Communicating Sequential process(TCSP) to describe the resources in CPS topology. Thirdly, the physical topology model and RS- TCSP are mapped to bigraphs and bigraphs reactive system, respectively. The safety of CPS resources is verified by BigMC, the verification tool of bigraphs, and the counterexample path is modified. Finally, a driving scene is given to verify the effectiveness of the proposes method. © 2022 IEEE.

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

A Model-Agnostic Interpretability Approach Based on Enhanced Hierarchical Clustering

A Model-Agnostic Interpretability Approach Based on Enhanced...

引用

IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C)

作者： Xi Ding Yi Zhu Qiao Yu Chongyang Huang School of Computer Science and Technology Jiangsu Normal University Xuzhou Jiangsu China Key Laboratory of Safety-Critical Software Nanjing University of Aeronautics and Astronautics Ministry of Industry and Information Technology Nanjing Jiangsu China

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

The Local Interpretable Model-Agnostic Explanations (LIME) is a relatively novel technique for explaining black-box models. LIME generates perturbed instances of the model based on a random instance, and then approximates the original model with a linear model derived from the weighted perturbed instances, thereby providing an explanation for individual predictions. While LIME effectively addresses the opacity of black-box models, the randomness in instance generation often leads to unstable and inaccurate predictions. For a given prediction, different explanations may be generated, posing critical issues, particularly in security-sensitive domains. In response to these challenges, we propose a stable version of LIME, named DDLIME(Density and Distance-based LIME). DDLIME leverages improved hierarchical clustering and KNN algorithms to select instances that are most similar to the data, thus reducing the impact of perturbations. Additionally, the enhanced hierarchical clustering, incorporating density and distance metrics, enables DDLIME to address the limitations of traditional hierarchical clustering in clustering non-spherical clusters. Consequently, DDLIME can effectively capture complex structures and patterns within the data. The experimental results on three binary public datasets from the UCI repository demonstrate that DDLIME provides more stable explanations compared to LIME. Furthermore, compared to both baseline models, DDLIME exhibits superior performance across various evaluation metrics.

关键词： Measurement Accuracy Perturbation methods Clustering algorithms Closed box Predictive models Nearest neighbor methods Prediction algorithms Stability analysis Software reliability

来源：评论

学校读者我要写书评

暂无评论

Safety decision of autonomous driving behavior based on Bayesian network and its verification method

Safety decision of autonomous driving behavior based on Baye...

引用

IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C)

作者： Zexin Li Yi Zhu Li Zhao Ying Zhao School of Computer Science and Technology Jiangsu Normal University Xuzhou Jiangsu China Key Laboratory of Safety-Critical Software Nanjing University of Aeronautics and Astronautics Ministry of Industry and Information Technology Nanjing Jiangsu China

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

With the increasing visibility of autonomous vehicles, the assurance of safe and precise behavioral decisions presents a substantial challenge within the realm of autonomous driving. The complexity of physical space, uncertainty in duration-space data, and human subjectivity complicate the assurance of existing behavior decision-making methods. To address these challenges, a safety decision method for autonomous driving based on Bayesian network is proposed. Firstly, semantic relations among risk elements in driving scenario are represented using knowledge graph, and the hierarchical structure and node information of the Bayesian network are determined based on expert knowledge and historical experience. Behavior decision actions are derived through Bayesian network inference. Secondly, leveraging the Bayesian network structure and inference results, a Duration-space Resource Timed Communicating Sequential process is construct to verify the security of time and space resources. Thirdly, the constructed process is converted into Bigraphs and use the CPS MODEL CHECKER for security verification. Finally, the effectiveness of the proposed method is verified using a highway lane change overtaking scenario.

关键词： Uncertainty Roads Decision making Bayes methods Safety Software reliability Security Time factors Automobiles Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Classification Method of Ethereum Smart Contracts Based on Statistical Model Checking

Classification Method of Ethereum Smart Contracts Based on S...

引用

IEEE International Conference on Software Quality, Reliability and Security (QRS)

作者： Miaoer Li Yi Zhu Yali Liu Chan Yin School of Computer Science and Technology Jiangsu Normal University Xuzhou Jiangsu China Key Laboratory of Safety-Critical Software (Nanjing University of Aeronautics and Astronautics) Ministry of Industry and Information Technology Nanjing Jiangsu China

ISBN: (数字)9798350365634

ISBN: (纸本)9798350365641

The integration of blockchain and smart contracts facilitates efficient and secure data exchange and value transfer. Nevertheless, the reliability of smart contracts has emerged as a critical concern. The vulnerabilities in contracts are intricately linked to their categories, emphasizing the significance of smart contract classification for enhancing code, user, and system security. Formal verification methods offer a robust means to validate the accuracy of contract classification and mitigate vulnerabilities. However, conventional machine learning approaches often lack precision and overlook the impact of account transaction behavior on classification during contract execution. This study introduces an Ethereum smart contract classification methodology based on statistical model detection. Through an examination of five smart contract types and ensuring the logical exclusivity of each, we delineate and formalize the internal logic of each contract type. We establish the contract automata network, devise conversion rules from contract source code to the automata network, and verify class properties using the statistical model detection tool UPPAAL-SMC. Lastly, we showcase the efficacy of our proposed methodology through a practical contract case.

关键词： Solid modeling Analytical models Atmospheric modeling Smart contracts Automata Model checking Blockchains

来源：评论

学校读者我要写书评

暂无评论

Robust restoration of low-dose cerebral perfusion CT images using NCS-Unet

引用

Nuclear Science and Techniques 2022年第3期33卷 62-76页

作者： Kai Chen Li-Bo Zhang Jia-Shun Liu Yuan Gao Zhan Wu Hai-Chen Zhu Chang-Ping Du Xiao-Li Mai Chun-Feng Yang Yang Chen Southeast University Nanjing 210096China School of Cyber Science and Engineering Southeast UniversityNanjing 210096China Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of EducationNanjing 210096China Department of Radiology General Hospital of the Northern Theater of the Chinese People’s Liberation ArmyShenyang 110016China Laboratory of Image Science and Technology The School of Computer Science and EngineeringSoutheast UniversityNanjing 210096China Department of Radiology Nanjing Drum Tower HospitalThe Affiliated Hospital of Nanjing University Medical SchoolNanjing 210008China Jiangsu Key Laboratory of Molecular and Functional Imaging Department of RadiologyZhongda HospitalSoutheast UniversityNanjing 210009China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and EngineeringSoutheast UniversityNanjing 210096China

Cerebral perfusion computed tomography(PCT)is an important imaging modality for evaluating cerebrovascular diseases and stroke *** widespread public concern about the potential cancer risks and health hazards associated with cumulative radiation exposure in PCT imaging,considerable research has been conducted to reduce the radiation dose in X-ray-based brain perfusion *** the dose of X-rays causes severe noise and artifacts in PCT *** solve this problem,we propose a deep learning method called *** exceptional characteristics of non-subsampled contourlet transform(NSCT)and the Sobel filter are introduced into *** decomposes the convolved features into high-and low-frequency *** decomposed high-frequency component retains image edges,contrast imaging traces,and noise,whereas the low-frequency component retains the main image *** Sobel filter extracts the contours of the original image and the imaging traces caused by the contrast agent *** extracted information is added to NCS-Unet to improve its performance in noise reduction and artifact *** and quantitative analyses demonstrated that the proposed NCS-Unet can improve the quality of low-dose cone-beam CT perfusion reconstruction images and the accuracy of perfusion parameter calculations.

关键词： Cerebral perfusion CT Low-dose Image denoising Perfusion parameters

来源：评论

学校读者我要写书评

暂无评论

A Novel Partial Domain Adaptation Method for Cross-Domain Specific Emitter Identification

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Han, Guangjie Zhang, Yu Xu, Zhengwei Wang, Weitao Hohai University Jiangsu Key Laboratory of Power Transmission and Distribution Equipment Technology Changzhou213022 China Henan Normal University College of Computer and Information Engineering Xinxiang453007 China

In wireless communication networks (WCN), specific emitter identification (SEI) technology is significant for guaranteeing cybersecurity and can effectively defend against network attacks. Compared to traditional SEI methods that depend on specific training data or environmental conditions, cross-domain recognition study has attracted widespread attention for dynamic WCN. However, in a more general scenario, the target domain (TD) sometimes represents a subset of source domain (SD), i.e., in partial domain adaptation (PDA), which has not been well addressed. To solve this concern, we present a novel selective partial domain adaptation method based on complex-valued convolutional block attention module (CSPDA) for SEI, which tackles the domain shift challenge caused by the inconsistency in emitter categories between SD and TD. The proposed method includes a mixed feature extraction module that efficiently extracts representative features from both source and target raw signals at multiple levels, reducing feature information loss. In addition, by using the maximum of cosine (MoC) assessment mechanism and a data information filtering strategy, we can dynamically select the appropriate source signal samples to match each target signal sample. Experiment results on real-world data show that the CSPDA method achieves a recognition accuracy of 73.46% at -5 dB and 89.28% at 20 dB, outperforming other transfer learning and domain adaptation methods in PDA tasks. © 2015 IEEE.

关键词： information filtering

来源：评论

学校读者我要写书评

暂无评论

Dual-Source CBCT for Larger Longitudinal Coverage: System Design and Image Reconstruction 46

Dual-Source CBCT for Larger Longitudinal Coverage: System De...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Zhang, Xusheng Lyu, Tianling Shi, Yijie Zhong, Xinyun Wu, Zhan Xi, Yan Wang, Shijie Chen, Yang Zhu, Wentao Southeast University School of Software Nanjing China Zhejiang Lab Hangzhou China First-Imaging Tech. Shanghai China Southeast University Laboratory of Image Science and Technology The School of Computer Science and Engineering Nanjing China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Nanjing China

ISBN: (纸本)9798350371499

The application of CBCT systems in intraoperative environments has become increasingly common, but concurrent CBCT systems are unsuitable for situations that require a large longitudinal imaging FoV, such as orthopedics. To increase longitudinal coverage, we developed a dual-source CBCT (DS-CBCT) system in which two ray sources are symmetrically placed along the central plane. After further analyzing its geometric characteristics, we propose an analytical reconstruction algorithm termed DT-FDK specialized for DS-CBCT, which combines cone-beam rebinning and two rays with smaller cone angles among the four conjugate rays to further suppress cone beam artifacts. The system design and reconstruction algorithm are tested on both simulated and real-scanned data. Results show that the DS-CBCT can expand the effective imaging volume by 37.1% compared to single-source CBCT systems. The reconstructed images by DT-FDK also show improved image quality compared to traditional reconstruction algorithms. © 2024 IEEE.

关键词： Cones

来源：评论

学校读者我要写书评

暂无评论

Non-Line-Of-Sight Target Localization in T-Shaped Roadways Using Simo Fmcw Millimeter-Wave Radar

SSRN

引用

SSRN 2024年

作者： Hu, Qingsong Luo, Yujia Wang, Liudi Cheng, Yuanxun Zhang, Yuansheng Yuan, Shuya Kou, Zhihao School of Information and Control Engineering China University of Mining & Technology Jiangsu Xuzhou221116 China State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process Beijing100032 China Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing100032 China

The hazardous and complex nature of underground mining imposes stringent safety requirements on autonomous driving. T-shaped roadways, common in such environments, present significant challenges for non-line-of-sight (NLOS) target localization. Traditional underground positioning technologies often fail in these settings due to severe signal attenuation and multipath effects, leading to potential accidents. This manuscript proposes a novel localization algorithm using single-input-multi-output (SIMO) Frequency Modulated Continuous Wave (FMCW) millimeter-wave radar to address these challenges. We analyze millimeter wave multipath propagation in T-shaped tunnels and construct an FMCW multipath echo model. Using CA-CAFAR and MVDR algorithms, we accurately estimate target distance and angle information. Additionally, a theoretical false point matching elimination method is designed to improve positioning accuracy by mitigating false target interference. Field tests in typical T-shaped NLOS scenarios demonstrate the method's high-precision positioning, enhancing the safety and efficiency of autonomous vehicles in coal mines. © 2024, The Authors. All rights reserved.

关键词： Coal mines

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Retinopathy Classification with OCT Images via Disentangling Representation and Adaptation Networks

Cross-Domain Retinopathy Classification with OCT Images via ...

引用

Optoelectronics Global Conference (OGC)

作者： Wickramaarachchi Minidu Thiranjaya Yuan Li Lei Tao Yuemei Luo Jiangsu Provincial Key Laboratory of Intelligent Medical Image Computing (iMIC) School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China Jiangsu Provincial Key Laboratory of Intelligent Medical Image Computing (iMIC) School of Computer Science Nanjing University of Information Science and Technology Nanjing China Jiangsu Provincial Key Laboratory of Intelligent Medical Image Computing (iMIC) School of Future Technology Nanjing University of Information Science and Technology Nanjing China

ISBN: (数字)9798350391466

ISBN: (纸本)9798350391473

Deep learning methods have shown significant potential in retinopathy classification using optical coherence tomography (OCT) images. However, substantial challenges arise due to domain shift issues, which are attributable to heterogeneity in data collection devices, variations in subject populations, and discrepancies in imaging protocols and parameters. To address these, we propose a novel approach leveraging Disentangling Representation and Adaptation Networks (DRANet) to enhance the robustness and generalization of retinopathy classification models across different OCT datasets. Our methodology involves developing DRANet, a specialized network architecture designed to disentangle representations of data and facilitate domain adaptation. DRANet includes components for learning invariant representations across domains through adversarial training, ensuring robustness against domain shifts. DRANet encodes individual representations of content and style from both source and target images. Then, it adapts the domain by incorporating the transferred style factor into the content factor, along with learnable weights specified for each domain. This learning framework allows bidirectional domain. After conducting extensive experiments conducted on three public datasets achieved accuracies of $\mathrm{8 8 \%, ~} \mathrm{9 0 \%}$, and $\mathrm{9 2 \%}$ under three cross-domain scenarios, demonstrating the efficacy of our approach in mitigating domain shift effects and improving retinopathy classification performance.

关键词： Training Deep learning Protocols Retinopathy Optical coherence tomography Imaging Coherence Network architecture Data collection Robustness

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：