检索结果-内蒙古大学图书馆

IEEE International Conference on Performance, Computing and Communications (IPCCC)

作者： Yumeng Liu Wenzhang Zhong Ke Yan Ling Tian Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

The accurate and comprehensive fault diagnosis is pivotal for the maintenance of mechanical equipment, which may directly impact the safety in production and avoid unnecessary losses of equipment. With the pervasively adopted sensing components, sensing data can be collected from mechanical equipment and analyzed for fault diagnosis. Previous solutions apply sophisticated deep learning models for such fault diagnosis tasks and have achieved impressive performance. However, these methods usually ignore the existences of diverse characteristics of faults, and formulate the fault diagnosis as a simple classification problem. Considering necessity of comprehensive and multi-view fault diagnosis, this work proposes a novel dual-view learning framework for combinatorial mechanical fault classification. The framework includes dual encoders to simultaneously learn the feature representation tied with the position and size of faults on equipment. Then these features are mutually mixed for better representation and the mixed features are merged and feed into deep neural networks for further representation learning. The query samples are classified through metric-based comparison to search for the closest type of composite fault. Moreover, the proposed framework also applies typical metric-based meta learning method to handle the issue of small training datasets, and adopts semi-supervised learning method to make use of both labeled and unlabeled samples. Finally, the experimental results on public datasets show that the proposed method can outperform previous solutions and achieve state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism

arXiv

引用

arXiv 2024年

作者： Xue, Yu Zhu, Chenchen Zhou, MengChu Wahib, Mohamed Gabbouj, Moncef School of Software Nanjing University of Information Science and Technology Jiangsu China Department of Electrical and Computer Engineering NewJersey Institute of Technology NewarkNJ07102 United States Japan Department of Computing Sciences Tampere University Tampere Finland

Neural architecture search (NAS) enables researchers to automatically explore vast search spaces and find efficient neural networks. But NAS suffers from a key bottleneck, i.e., numerous architectures need to be evaluated during the search process, which requires a lot of computing resources and time. In order to improve the efficiency of NAS, a series of methods have been proposed to reduce the evaluation time of neural architectures. However, they are not efficient enough and still only focus on the accuracy of architectures. In addition to the classification accuracy, more efficient and smaller network architectures are required in real-world applications. To address the above problems, we propose the SMEM-NAS, a pairwise comparison relation-assisted multi-objective evolutionary algorithm based on a multi-population mechanism. In the SMEM-NAS, a surrogate model is constructed based on pairwise comparison relations to predict the accuracy ranking of architectures, rather than the absolute accuracy. Moreover, two populations cooperate with each other in the search process, i.e., a main population guides the evolution, while a vice population expands the diversity. Our method aims to provide high-performance models that take into account multiple optimization objectives. We conduct a series of experiments on the CIFAR-10, CIFAR- 100 and ImageNet datasets to verify its effectiveness. With only a single GPU searching for 0.17 days, competitive architectures can be found by SMEM-NAS which achieves 78.91% accuracy with the MAdds of 570M on the ImageNet. This work makes a significant advance in the important field of NAS. Copyright © 2024, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient Hierarchical Multi-Server Authentication Protocol for Mobile Cloud Computing

引用

computers, Materials & Continua 2020年第7期64卷 297-312页

作者： Jiangheng Kou Mingxing He Ling Xiong Zihang Ge Guangmin Xie School of Computer and Software Engineering Xihua UniversityChengdu610039China Illinois Institute of Technology Miles(Main)CampusChicago60616USA

With the development of communication technologies,various mobile devices and different types of mobile services became *** emergence of these services has brought great convenience to our *** multi-server architecture authentication protocols for mobile cloud computing were proposed to ensure the security and availability between mobile devices and mobile ***,most of the protocols did not consider the case of hierarchical *** the existing protocol,when a mobile user once registered at the registration center,he/she can successfully authenticate with all mobile service providers that are registered at the registration center,but real application scenarios are not like *** some specific scenarios,some mobile service providers want to provide service only for particular *** this reason,we propose a new hierarchical multi-server authentication protocol for mobile cloud *** proposed protocol ensures only particular types of users can successfully authenticate with certain types of mobile service *** proposed protocol reduces computing and communication costs by up to 42.6%and 54.2%compared to two superior *** proposed protocol can also resist the attacks known so far.

关键词： Multi-server authentication cryptography hierarchical authentication mobile cloud computing

来源：评论

学校读者我要写书评

暂无评论

Designing Data Permissions in the Enterprise Application Environment

Designing Data Permissions in the Enterprise Application Env...

引用

Artificial Intelligence, Networking and Information technology (AINIT), International Seminar on

作者： Ying Yuan Xin Yi Junbin ShangGuan School of Computer & Information Engineering Xiamen University of Technology Institute of Space Information Technology Xiamen University of Technology Xiamen China Software department Bozhongtuxin (Xiamen) Information Technology Co. Ltd Xiamen China

With the continuous improvement of social informationization, the digitalization of corporate construction is also developing comprehensively. Data, as a crucial source for creating wealth and competitive advantage, is undoubtedly the most significant asset for all enterprises. However, many companies face the dilemma of insufficient data granularity and configuration flexibility, which undermines the security and availability of their data assets. Therefore, this paper proposes an Api-based data permission control model (ADPC) based on the theoretical foundation of RBAC in the background of data application in the enterprise environment. Firstly, the model maps data objects to different levels of environmental variables in the corporate department structure, then flexibly authorizes and controls permissions through API configuration, and finally verifies its security with SQL AST. The ADPC model was implemented using the Spring Boot, Spring Security and MyBatis framework and was applied in a real enterprise environment. Through this approach, the ADPC model effectively addresses the limitations of traditional data permission control mechanisms in the enterprise application environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of machine learning algorithms for air quality index prediction

引用

Machine Learning for Computational Science and engineering 2025年第1期1卷 1-20页

作者： Desai, Tanay Kapadia, Shivam Halani, Mahir Zinzuwadia, Parth Shah, Kanish Shah, Manan Prajapati, Mitul Atul Vidyalaya Valsad India The Riverside School Ahmedabad India Department of Computer Science School of Arts and Sciences Ahmedabad University Gujarat India Software Engineer at Walmart Global Tech Sunnyvale USA Department of Chemical Engineering Pandit Deendayal Energy University Gandhinagar India S S Agrawal Institute of Engineering & Technology Devina Park Society Navsari India

In several urban industrial regions affected by air pollution, it is crucial to monitor air quality in order to improve the quality of life and prevent any damage to health. This paper mainly focuses on the prediction of air quality index (AQI) using two different machine learning algorithms SVM and KNN. In recent times, machine learning has become widely popular and relevant in the forecasting of AQI because of its ability to work with large datasets and provide highly accurate conclusions from raw data. This study helps in analyzing several international research works which helps in better understanding of the forecasting power of algorithms used and the predicted outcomes provide insights into the air quality which aid authorities in decision making. Our analysis shows that hybrid models, created using multiple algorithms, outperform traditional models involving a single algorithm. Moreover, the usage of larger datasets to train the models led to more accurate results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment

arXiv

引用

arXiv 2025年

作者： Fan, Yuchun Mu, Yongyu Wang, Yilin Huang, Lei Ruan, Junhao Li, Bei Xiao, Tong Huang, Shujian Feng, Xiaocheng Zhu, Jingbo NLP Lab School of Computer Science and Engineering Northeastern University Shenyang China NiuTrans Research Shenyang China Harbin Institute of Technology Harbin China Meituan Inc China National Key Laboratory for Novel Software Technology Nanjing University China

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training paradigm to teach models to first understand non-English questions and then reason. However, this method suffers from both substantial computational resource computing and catastrophic forgetting. The fundamental cause is that, with the primary goal of enhancing multilingual comprehension, an excessive number of irrelevant layers and parameters are tuned during the first stage. Given our findings that the representation learning of languages is merely conducted in lower-level layers, we propose an efficient multilingual reasoning alignment approach that precisely identifies and finetunes the layers responsible for handling multilingualism. Experimental results show that our method, SLAM, only tunes 6 layers' feedforward sub-layers including 6.5-8% of all parameters within 7B and 13B LLMs, achieving superior average performance than all strong baselines across 10 languages. Meanwhile, SLAM only involves one training stage, reducing training time by 4.1 - 11.9× compared to the two-stage method. Copyright © 2025, 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

IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization

arXiv

引用

arXiv 2023年

作者： Li, Zekun Qi, Lei Shi, Yinghuan Gao, Yang The State Key Laboratory for Novel Software Technology National Institute of Healthcare Data Science Nanjing University China The School of Computer Science and Engineering Southeast University China

Semi-supervised learning (SSL) aims to leverage massive unlabeled data when labels are expensive to obtain. Unfortunately, in many real-world applications, the collected unlabeled data will inevitably contain unseen-class outliers not belonging to any of the labeled classes. To deal with the challenging open-set SSL task, the mainstream methods tend to first detect outliers and then filter them out. However, we observe a surprising fact that such approach could result in more severe performance degradation when labels are extremely scarce, as the unreliable outlier detector may wrongly exclude a considerable portion of valuable inliers. To tackle with this issue, we introduce a novel open-set SSL framework, IOMatch, which can jointly utilize inliers and outliers, even when it is difficult to distinguish exactly between them. Specifically, we propose to employ a multi-binary classifier in combination with the standard closed-set classifier for producing unified open-set classification targets, which regard all outliers as a single new class. By adopting these targets as open-set pseudo-labels, we optimize an open-set classifier with all unlabeled samples including both inliers and outliers. Extensive experiments have shown that IOMatch significantly outperforms the baseline methods across different benchmark datasets and different settings despite its remarkable simplicity. Our code and models are available at https://***/nukezil/IOMatch. Copyright © 2023, The Authors. All rights reserved.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

ALOFT: A Lightweight MLP-Like Architecture with Dynamic Low-Frequency Transform for Domain Generalization

ALOFT: A Lightweight MLP-Like Architecture with Dynamic Low-...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jintao Guo Na Wang Lei Qi Yinghuan Shi State Key Laboratory for Novel Software Technology Nanjing University National Institute of Healthcare Data Science Nanjing University School of Computer Science and Engineering Southeast University

Domain generalization (DG) aims to learn a model that generalizes well to unseen target domains utilizing multiple source domains without re-training. Most existing DG works are based on convolutional neural networks (CNNs). However, the local operation of the convolution kernel makes the model focus too much on local representations (e.g., texture), which inherently causes the model more prone to overfit to the source domains and hampers its generalization ability. Recently, several MLP-based methods have achieved promising results in supervised learning tasks by learning global interactions among different patches of the image. Inspired by this, in this paper, we first analyze the difference between CNN and MLP methods in DG and find that MLP methods exhibit a better generalization ability because they can better capture the global representations (e.g., structure) than CNN methods. Then, based on a recent lightweight MLP method, we obtain a strong baseline that outperforms most state-of-the-art CNN-based methods. The baseline can learn global structure representations with a filter to suppress structureirrelevant information in the frequency space. Moreover, we propose a dynAmic LOw-Frequency spectrum Transform (ALOFT) that can perturb local texture features while preserving global structure features, thus enabling the filter to remove structure-irrelevant information sufficiently. Extensive experiments on four benchmarks have demonstrated that our method can achieve great performance improvement with a small number of parameters compared to SOTA CNN-based DG methods. Our code is available at https://***/lingeringlight/ALOFT/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization

DomainDrop: Suppressing Domain-Sensitive Channels for Domain...

引用

International Conference on computer Vision (ICCV)

作者： Jintao Guo Lei Qi Yinghuan Shi State Key Laboratory for Novel Software Technology Nanjing University National Institute of Healthcare Data Science Nanjing University School of Computer Science and Engineering Southeast University

Deep Neural Networks have exhibited considerable success in various visual tasks. However, when applied to unseen test datasets, state-of-the-art models often suffer performance degradation due to domain shifts. In this paper, we introduce a novel approach for domain generalization from a novel perspective of enhancing the robustness of channels in feature maps to domain shifts. We observe that models trained on source domains contain a substantial number of channels that exhibit unstable activations across different domains, which are inclined to capture domain-specific features and behave abnormally when exposed to unseen target domains. To address the issue, we propose a DomainDrop framework to continuously enhance the channel robustness to domain shifts, where a domain discriminator is used to identify and drop unstable channels in feature maps of each network layer during forward propagation. We theoretically prove that our framework could effectively lower the generalization bound. Extensive experiments on several benchmarks indicate that our framework achieves state-of-the-art performance compared to other competing methods. Our code is available at https://***/lingeringlight/DomainDrop.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

arXiv

引用

arXiv 2023年

作者： Wang, Xiran Zhang, Jian Qi, Lei Shi, Yinghuan The State Key Laboratory for Novel Software Technology National Institute of Healthcare Data Science Nanjing University China The School of Computer Science and Engineering Southeast University China

Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains. However, most current methods do not account for a common realistic scenario where the source and target domains have different classes. To overcome this deficiency, open set domain generalization (OSDG) then emerges as a more practical setting to recognize unseen classes in unseen domains. An intuitive approach is to use multiple one-vs-all classifiers to define decision boundaries for each class and reject the outliers as unknown. However, the significant class imbalance between positive and negative samples often causes the boundaries biased towards positive ones, resulting in misclassification for known samples in the unseen target domain. In this paper, we propose a novel meta-learning-based framework called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC), which considers gradient matching towards inter-domain and inter-class splits simultaneously to find a generalizable boundary balanced for all tasks. Experimental results demonstrate that MEDIC not only outperforms previous methods in open set scenarios, but also maintains competitive close set generalization ability at the same time. Our code is available at https://***/zzwdx/MEDIC. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

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：