检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Zhang, Xu Tang, Yongchuan Zhou, Deyun Chongqing University School of Big Data and Software Engineering Chongqing401331 China Northwestern Polytechnical University School of Microelectronics Shaanxi Xi'an710072 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

As a generalization of probability theory, Dempster-Shafer evidence theory is superior in dealing with uncertain information. However, a counter-intuitive result is often obtained when combining highly conflicting evidence. In this paper, a new method based on similarity and Deng entropy of the evidence is proposed to measure the conflict and a new framework of fusing conflicting evidence is built based the proposed method. When most evidence has the same view, this evidence is given the higher weight. Moreover, the lower the entropy of the evidence, the stronger its ability to provide accurate information, and should be paid more attention. Experiments on real data show that this method can effectively solve the combination problem of conflicting evidence and it has a higher accuracy rate in the classification problem compared with other methods. © 2022 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

AW4C: A Commit-Aware C dataset for Actionable Warning Identification

AW4C: A Commit-Aware C Dataset for Actionable Warning Identi...

引用

International Mining software Repositories, MSR

作者： Zhipeng Liu Meng Yan Zhipeng Gao Dong Li Xiaohong Zhang Dan Yang School of Big Data and Software Engineering Chongqing University China Shanghai Institute for Advanced Study Zhejiang University China

ISBN: (数字)9798400705878

ISBN: (纸本)9798350363982

Excessive non-actionable warnings generated by static program analysis tools can hinder developers from utilizing these tools effectively. Leveraging learning-based approaches for actionable warning identification has demonstrated promise in boosting developer productivity, minimizing the risk of bugs, and reducing code smells. However, the small sizes of existing datasets have limited the model choices for machine learning researchers, and the lack of aligned fix commits limits the scope of the dataset for research. In this paper, we present AW4C, an actionable warning C dataset that contains 38,134 actionable warnings mined from more than 500 repositories on GitHub. These warnings are generated via Cppcheck, and most importantly, each warning is precisely mapped to the commit where the corrective action occurred. To the best of our knowledge, this is the largest publicly available actionable warning dataset for C programming language to date. The dataset is suited for use in machine/deep learning models and can support a wide range of tasks, such as actionable warning identification and vulnerability detection. Furthermore, we have released our dataset 1 and a general framework for collecting actionable warnings on GitHub 2 to facilitate other researchers to replicate our work and validate their innovative *** Concepts• software and its engineering → software maintenance tools; software creation and management; software testing and debugging;• Mathematics of computing → data mining.

关键词： software testing Productivity software maintenance Computer languages Codes Computer bugs Mathematics

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

Global well-posedness of the Maxwell–Landau–Lifshitz equation with spin accumulation

引用

Applied Mathematics Letters 2025年 170卷

作者： Xu, Xiuli Pu, Xueke College of Big Data and Software Engineering Zhejiang Wanli University Zhejiang315107 China School of mathematics and information science Guangzhou University Guangzhou510006 China

The Maxwell–Landau–Lifshitz equation with spin accumulation is studied in the paper. We prove the existence and uniqueness of global solutions using energy estimates method in two-dimensional space. © 2025 Else... 详细信息

关键词： Maxwell equations

来源：评论

学校读者我要写书评

暂无评论

Pretraining binarization encoders for recommendation acceleration 3

Pretraining binarization encoders for recommendation acceler...

引用

3rd International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2022

作者： Wei, Feng Chen, Shuyu Yin, Yuan Hu, Hao School of Big Data & Software Engineering Chongqing University Chongqing400044 China China Telecom Corporation Limited Chongqing Branch Chongqing401121 China

ISBN: (纸本)9781510657281

Recommendations based on similarity search are widely used. However, when the number of users and items is large, it may become an efficiency bottleneck. In this paper, we propose a high-precision, modular, and efficient recommendation component: the binarization encoder. We use Siamese neural networks to jointly learn binary codes of users and items. The Siamese networks are composed of two autoencoders, whose encoder and decoder are sharing weights further. Their latent factors are discretized as efficient representations of users and items. In order to improve the learning ability of this model, a comprehensive objective function is proposed, which considers three objectives: improving the reconstruction quality of input vectors, reducing the information redundancy between dimensions, and finetuning the predictions with observed ratings. We use collaborative filtering based on matrix factorization on real-world datasets as basic systems and evaluate the proposed method. The experimental results prove the effectiveness of our method. © 2022 SPIE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A new correlation belief transfer method in the evidence theory

A new correlation belief transfer method in the evidence the...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Zhang, Xu Tang, Yongchuan Zhou, Deyun Chongqing University School of Big Data and Software Engineering Chongqing401331 China School of Microelectronics Northwestern Polytechnical University Shaanxi Xi'an710072 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Dempster-Shafer evidence theory (D-S evidence theory) is an effective method in dealing with uncertain information. However, it may get counterintuitive results when using traditional Dempste's combination rule directly to fuse highly conflicting data. How to manage conflict in data fusion is still an open issue in D-S evidence theory. In this paper, a new correlation belief function is proposed to modify the basic belief assignment before combination in closed-world. The method transfers the belief from a certain proposition to another related proposition to avoid the loss of information when data are fused, which effectively solves the problem of conflict management in D-S evidence theory. The advantage of the proposed method is that it does not lose belief value in main propositions related to decision-making and also expresses the conflict information effectively. Several numerical examples and experiments with real data sets from the University of California Irvine Machine Learning Repository are adopted to verify the rationality and validity of the proposed method. © 2022 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion 38

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Multi-Hop Knowledge Reasoning Based on Retentive Network 7

Sequence-to-Sequence Multi-Hop Knowledge Reasoning Based on ...

引用

7th International Conference on Computer Information Science and Application Technology, CISAT 2024

作者： Su, Ruilin Zhang, Wanshan Yu, Dunhui Hubei University Wuhan China Wuhan430062 China Hubei University School of Computer Science and Information Engineering Wuhan430062 China Hubei University Hubei Key Laboratory of Big Data Intelligent Analysis and Application Wuhan430062 China Engineering and Technical Research Center of Hubei Province in Software Engineering Wuhan430062 China

ISBN: (纸本)9798350375107

Multi-hop Knowledge Reasoning is a task that involves generating an answer given a query and a knowledge graph. Existing sequence-to-sequence reasoning models use the Transformer to encode and decode sequences, but these models have some flaws, such as the inability to effectively handle long-sequence reasoning and susceptibility to exposure bias. To address these issues, we provides a sequence-to-sequence reasoning model named STSR, which is based on Retentive Network. Aiming at improving training efficiency through parallel training, this model leverages the advantages in Retentive Network, reduce time overhead, and enhance reasoning efficiency through iterative reasoning. It effectively mitigates the problems of high spatial overhead and low efficiency in long-sequence reasoning faced by the Transformer. Moreover, it retains and updates historical information during the encoding and decoding process, enhancing the model's memory and generalization capabilities. Additionally, the Scheduled Sampling method is adopted to alleviate the exposure bias introduced during reasoning, which involves using the model's own output as the input for the next moment with a certain probability during training, instead of using the true label. We conduct the experiment on six public datasets, with the results showing that the proposed model outperforms existing baseline models in terms of precision and generation quality. This paper provides a new solution for the task of sequence-to-sequence multihop knowledge reasoning and also demonstrates the potential application of the Retentive Network in natural language processing. © 2024 IEEE.

关键词： Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning Under Hybrid Perturbations for Robust Acute Lymphoblastic Leukemia Classification 39

Adversarial Learning Under Hybrid Perturbations for Robust A...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Jie Liu, Xinyuan Liu, Xintong Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

ISBN: (纸本)157735897X

Acute lymphoblastic leukemia is a childhood cancer prevalent worldwide, which can prove fatal within weeks or months. However, current diagnosis models based on machine learning and deep learning methods fail to consider device noise (pixel-level perturbations) and rotation/translation (spatial-transformed perturbations), which can undermine the model's robustness. Adversarial training is a potential solution to this issue. This paper presents a hybrid perturbation adversarial training (HPAT) strategy that leverages two types of adversarial samples: pixel-level adversarial samples and spatial adversarial samples. This work generates these hybrid adversarial samples through Projected Gradient Descent (PGD) in couple with spatial transformation based on the Bayesian optimization (STBO) algorithm, respectively. This work introduced the Mixed Batch Normalization (MixBN) module to handle both adversarial samples and clean samples, alleviating the problem of clean accuracy degradation due to adversarial training. The proposed hybrid adversarial training strategy is tested on the public acute lymphoblastic leukemia dataset and found that it outperformed existing acute lymphoblastic cell classification models. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

THE DIMENSION OF THE NON-DENSE ORBIT SET FOR EXPANDING MAPS

arXiv

引用

arXiv 2023年

作者： Qu, Congcong College of Big Data and software Engineering Zhejiang Wanli University Zhejiang Ningbo315107 China

In this paper, we give a new proof for the Hausdorff dimension of the non-dense orbit set for expanding maps. This proof is based on the sharp lower bound of the Hausdorff dimension of repellers given by Cao, Pesin and Zhao in [CPZ]. Besides, we prove that the Carathéodory singular dimension of non-dense orbit set equals that of the repeller. Copyright © 2023, The Authors. All rights reserved.

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：