检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1693-1707页

作者： Wang, Huadeng Zuo, Wenbin Li, Bingbing Pan, Xipeng Liu, Zhenbing Lan, Rushi Luo, Xiaonan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Guilin University of Electronic Technology School of Computer Science and Information Security Guilin541004 China Ganzhou Municipal Hospital Department of Pathology Ganzhou341000 China

Retinal fundus image segmentation based on deep learning is an important method for auxiliary diagnosis of ophthalmic diseases. Due to the scale difference of the blood vessels and the imbalance between foreground and background pixels in the fundus image, the deep learning network will inevitably ignore thin vessels when downsampling and feature learning. For the scale difference problem, this article aims to tackle its limitation from two perspectives: changing the supervised approach and adapting the feature learning. Correspondingly, a dilation-supervised learning method and an adaptive scale dimensional attention mechanism which are used to construct a two-stage segmentation model is proposed. Moreover, we introduce a quantitative approach to evaluate the scale difference of the blood vessels. With the help of the proposed weighted loss function, the segmentation results are refined, and the class imbalance problem between foreground and background pixels is resolved. Finally, the proposed adaptive threshold selection method is used in the postprocessing of segmentation results. The experiments on DRIVE, STARE, CHASE_DB1, and HRF datasets show that the proposed method achieves better segmentation performance compared with other state-of-the-art methods, and has good generalization ability and robustness. © 2020 IEEE.

关键词： Semantics

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 24

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

引用

24th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2024

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

ISBN: (纸本)9798350365658

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. © 2024 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Intelligent Test Paper Generation Algorithm Integrating Normal Distribution and Parallel Genetic Algorithm 5

Intelligent Test Paper Generation Algorithm Integrating Norm...

引用

5th International Conference on Intelligent Computing and Human-computer Interaction, ICHCI 2024

作者： Liu, Chuangye Huang, Guimin School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798350368284

Genetic algorithms have been widely used in intelligent test paper generation systems. However, traditional genetic algorithms cannot ensure that the difficulty of test questions is normally distributed, and are prone to falling into local optimal solutions. To address the above problems, we proposed an intelligent test paper generation algorithm that combines normal distribution and parallel genetic algorithms. In the population initialization stage, we use the cumulative distribution function (CDF) of the normal distribution to initialize the population. In the subsequent genetic operations, we designed a directed mutation mechanism and added KL divergence as a penalty number in the design of the fitness function to ensure that the difficulty of the test questions is normally distributed. At the same time, in order to speed up the efficiency of the algorithm and escape from the local optimal solution, an adaptive migration strategy was introduced. Experimental results show that the difficulty of the test questions generated by this algorithm is normally distributed, and the algorithm performance is better than other algorithms. © 2024 IEEE.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

引用

4th International Conference on computer Science and Blockchain, CCSB 2024

作者： Huang, Guimin Shi, Canjun School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798350356502

Short textual similarity has been more and more widely used in the field of natural language processing. However, people tend to pay more attention to the semantic similarity of sentences and ignore the word order similarity in sentences. For this reason, we propose a short text similarity computation model that fuses semantics and word order. In terms of semantics, we propose a adjacency-aware similarity model based on deep convolutional neural networks, which effectively exploits the adjacency relationship in sentences and extracts text features from multiple perspectives for similarity prediction. In terms of word order, a word order model incorporating an external knowledge base is proposed, which uses an external knowledge base with pointwise mutual information to construct word order dense vectors to assess word order similarity. Ultimately, we propose a comprehensive assessment model for short text similarity that incorporates semantic and word order information. We conducted experiments on the public dataset MRPC, and the experimental results show that our model outperforms existing models in terms of performance. © 2024 IEEE.

关键词： Convolutional neural networks

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 24

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

引用

24th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2024

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

ISBN: (纸本)9798350365658

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. © 2024 IEEE.

关键词： Hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation

Inference-Time Decontamination: Reusing Leaked Benchmarks fo...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Zhu, Qin Cheng, Qinyuan Peng, Runyu Li, Xiaonan Liu, Tengxiao Peng, Ru Qiu, Xipeng Huang, Xuanjing School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China College of Computer Science and Technology Zhejiang University China

ISBN: (纸本)9798891761681

The training process of large language models (LLMs) often involves varying degrees of test data contamination (Yang et al., 2023b).Although current LLMs are achieving increasingly better performance on various benchmarks, their performance in practical applications does not always match their benchmark *** of benchmarks can prevent the accurate assessment of LLMs' true ***, constructing new benchmarks is costly, labor-intensive and still carries the risk of ***, in this paper, we ask the question "Can we reuse these leaked benchmarks for LLM evaluation?" We propose Inference-Time Decontamination (ITD) to address this issue by detecting and rewriting leaked samples without altering their *** can mitigate performance inflation caused by memorizing leaked *** proof-of-concept experiments demonstrate that ITD reduces inflated accuracy by 22.9% on GSM8K and 19.0% on *** MMLU, using Inference-time Decontamination can lead to a decrease in the results of Phi3 and Mistral by 6.7% and 3.6% *** hope that ITD can provide more truthful evaluation results for large language models. © 2024 Association for Computational Linguistics.

关键词： Decontamination

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Knowledge Tracking Model with Forgetting Behavior and Graph Embedding 3

A Convolutional Knowledge Tracking Model with Forgetting Beh...

引用

3rd International Conference on Electronics and information technology, EIT 2024

作者： Huang, Guimin Huang, Zhiqing Guilin University of Electronic Technology School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798350369151

With the prevalence of various intelligent educational systems, it is imperative to uncover learners' proficiency in mastering knowledge points through their prior practice circumstances. Knowledge tracking is an extremely beneficial instrument in this regard. Among them, Convolutional Knowledge Tracking (CKT) has demonstrated excellent performance in numerous KT tasks, while it does not take into account the phenomenon of forgetting and the interconnection between knowledge points. In order to tackle these problems, we propose a model called FGE-CKT, which integrates forgetting behavior and graph embedding with CKT. Our model addresses the drawbacks of forgetting characteristics by modelling three key factors affecting students' forgetting behaviors through a fully connected neural net: repeated knowledge learning times, adjacent learning interval and interval between visits to repeat knowledge. At the same time, convolutional neural networks are used to simultaneously extract and incorporate connections between knowledge points into the model's input portion. It was confirmed by experiments on two well-established datasets that FGE-CKT achieved significant improvements in AUC performance. © 2024 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Interest-Aware Message-Passing GCN for Recommendation 24

A Dynamic Interest-Aware Message-Passing GCN for Recommendat...

引用

24th IEEE International Conference on Software Quality, Reliability and Security Companion, QRS-C 2024

作者： He, Weichao Zhu, Yi Song, Mei Wu, Zixin Hao, Guosheng School of Computer Science and Technology Jiangsu Normal University Jiangsu Xuzhou China Jiangsu Engineering Technology Research Center of Ict in Education Jiangsu Xuzhou China Ministry of Industry and Information Technology Key Laboratory of Safety-Critical Software Jiangsu Nanjing China

ISBN: (纸本)9798350365658

Over the past few years, Graph Convolutional Networks (GCN) have emerged as a promising tool in the field of recommendation. They have the ability to effectively learn user and item embeddings by leveraging collaborative signals from higher-order neighbors. Nevertheless, the recommendation models based on GCN also face a common issue. As more layers are added, the node embeddings start to become increasingly similar and eventually become indistin-guishable, leading to a decline in performance. To address the issues at hand, we present a recommendation model called DIMP-GCN. This model utilizes a Dynamic Interest-aware Message-Passing approach, where users and interacted items are organized into distinct subgraphs based on their interests. Within each subgraph, single-layer graph convolution operations are performed. As a result, the users who have been updated are divided based on their interests once again, leading to dynamic changes in subgraph partitioning as the network layers stack. Nodes are able to acquire more accurate representations through this process. We conduct extensive experiments on three established datasets, showcasing the superior performance of our DIMP-GCN compared to other state-of-the-art GCN-based recommendation models. © 2024 IEEE.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Dual Radial-Resonant Wide Beamwidth Circular Sector Microstrip Patch Antennas

引用

Chinese Journal of Electronics 2023年第4期32卷 710-719页

作者： MAO Xiaohui LU Wenjun JI Feiyan XING Xiuqiong ZHU Lei Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications Key Laboratory of Wireless Sensor Network & Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau

In this article, a design approach to a radial-resonant wide beamwidth circular sector patch antenna is advanced. As properly evolved from a U-shaped d ipole, a prototype magnetic dipole can be fit in the radial direction of a circular sector patch radiator, with its length set as the positive odd-integer multiples of onequarter wavelength. In this way, multiple TM0m（m = 1,2,...） modes resonant circular sector patch antenna with short-circuited circumference and widened E-plane beamwidth can be realized by proper excitation and perturbations. Prototype antennas are then designed and fabricated to validate the design approach. Experimental results reveal that the E-plane beamwidth of a dual-resonant antenna fabricated on air/Teflon substrate can be effectively broadened to 128°/120°, with an impedance bandwidth of 17.4%/7.1%, respectively. In both cases, the antenna heights are strictly limited to no more than 0.03-guided wavelength. It is evidently validated that the proposed approach can effectively enhance the operational bandwidth and beamwidth of a microstrip patch antenna while maintaining its inherent low profile merit.

关键词： Geometry Patch antennas Perturbation methods Prototypes Magnetic resonance Microstrip antennas Bandwidth

来源：评论

学校读者我要写书评

暂无评论

MRA-Depth: Multi-Resolution Attention based Monocular Depth Estimation 5

MRA-Depth: Multi-Resolution Attention based Monocular Depth ...

引用

5th International Conference on Robotics and computer Vision, ICRCV 2023

作者： Wen, Jing Niu, Lukuan School of Computer Information and Technology Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China School of Computer Information and Technology Shanxi University Taiyuan China

ISBN: (纸本)9798350326369

Delicate feature would become weaker or even disappear as going through deeper network layer, which results in jagged edges of objects in the depth estimation. To address this problem, we propose a multi-resolution attention based monocular depth estimation by capturing and recalibrating the dependencies of channels between different resolutions, including: we develop a multi-resolution attention encoder by embedding resolution and spatial attention, so as to extract the higher quality features in encoder, and we design a reusable multi-resolution fusion model in decoder, in which different scale features are integrated and then extract multi-resolution attention maps, so as to enhance detail information locally and perspective structure features globally. Experimental results illustrate the proposed network is capable to predict more precise depth and sharper contour, and to outperforms related methods on the KITTI benchmark. © 2023 IEEE.

关键词： Network layers

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：