检索结果-内蒙古大学图书馆

A knowledge-enhanced interest segment division attention network for click-through rate prediction

Neural Computing and Applications 2024年第34期36卷 21817-21837页

作者： Liu, Zhanghui Chen, Shijie Chen, Yuzhong Su, Jieyang Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Click-through rate (CTR) prediction aims to estimate the probability of a user clicking on a particular item, making it one of the core tasks in various recommendation platforms. In such systems, user behavior data are crucial for capturing user interests, which has garnered significant attention from both academia and industry, leading to the development of various user behavior modeling methods. However, existing models still face unresolved issues, as they fail to capture the complex diversity of user interests at the semantic level, refine user interests effectively, and uncover users’ potential interests. To address these challenges, we propose a novel model called knowledge-enhanced Interest segment division attention network (KISDAN), which can effectively and comprehensively model user interests. Specifically, to leverage the semantic information within user behavior sequences, we employ the structure of a knowledge graph to divide user behavior sequence into multiple interest segments. To provide a comprehensive representation of user interests, we further categorize user interests into strong and weak interests. By leveraging both the knowledge graph and the item co-occurrence graph, we explore users’ potential interests from two perspectives. This methodology allows KISDAN to better understand the diversity of user interests. Finally, we extensively evaluate KISDAN on three benchmark datasets, and the experimental results consistently demonstrate that the KISDAN model outperforms state-of-the-art models across various evaluation metrics, which validates the effectiveness and superiority of KISDAN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Amalgamated CNN-Transformer Network for Lightweight Image Super-Resolution

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1376-1387页

作者： Fang, Jinsheng Lin, Hanjiang Zeng, Kun School of Computer Science and Engineering Minnan Normal University Zhangzhou363000 China Key Laboratory of Data Science and Intelligence Application Fujian Province University Fujian Zhangzhou363000 China School of Computer and Control engineering Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China

Recently, Transformer-based methods for single image super-resolution (SISR) have achieved better performance advantages than the methods based on convolutional neural network (CNN). Exploiting self-attention mechanism to model global context definitely improves the SR results. However, the neglect of local information will bring inevitable reduction of the network performance. In this work, we propose an Amalgamated CNN-Transformer network for lightweight SR, namely ACTSR. Specifically, an amalgamated CNN-Transformer block (ACTB) is developed to extract the useful information of both local and global features. By employing stacked ACTBs, our ACTSR extracts more informative deep features beneficially for super-resolution reconstruction to improve network performance while keeps lightweight and flexible enough. Extensive experiments on commonly used benchmark datasets validate our ACTSR outperforms the advanced competitors. Our codes are available at: https://***/ginsengf/ACTSR. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

引用

Neural Computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding Network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural Network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Meibomian glands segmentation in infrared images with limited annotation

引用

International Journal of Ophthalmology(English edition) 2024年第3期17卷 401-407页

作者： Jia-Wen Lin Ling-Jie Lin Feng Lu Tai-Chen Lai Jing Zou Lin-Ling Guo Zhi-Ming Lin Li Li College of Computer and Data Science Fuzhou UniversityFuzhou 350108Fujian ProvinceChina Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing Fuzhou UniversityFuzhou 350108Fujian ProvinceChina Shengli Clinical Medical College of Fujian Medical University Fuzhou 350001Fujian ProvinceChina Department of Ophthalmology Fujian Provincial Hospital South BranchFujian Provincial HospitalFuzhou 350001Fujian ProvinceChina

●AIM:To investigate a pioneering framework for the segmentation of meibomian glands(MGs),using limited annotations to reduce the workload on ophthalmologists and enhance the efficiency of clinical diagnosis.●METHODS:Totally 203 infrared meibomian images from 138 patients with dry eye disease,accompanied by corresponding annotations,were gathered for the study.A rectified scribble-supervised gland segmentation(RSSGS)model,incorporating temporal ensemble prediction,uncertainty estimation,and a transformation equivariance constraint,was introduced to address constraints imposed by limited supervision information inherent in scribble *** viability and efficacy of the proposed model were assessed based on accuracy,intersection over union(IoU),and dice coefficient.●RESULTS:Using manual labels as the gold standard,RSSGS demonstrated outcomes with an accuracy of 93.54%,a dice coefficient of 78.02%,and an IoU of 64.18%.Notably,these performance metrics exceed the current weakly supervised state-of-the-art methods by 0.76%,2.06%,and 2.69%,***,despite achieving a substantial 80%reduction in annotation costs,it only lags behind fully annotated methods by 0.72%,1.51%,and 2.04%.●CONCLUSION:An innovative automatic segmentation model is developed for MGs in infrared eyelid images,using scribble annotation for *** model maintains an exceptionally high level of segmentation accuracy while substantially reducing training *** holds substantial utility for calculating clinical parameters,thereby greatly enhancing the diagnostic efficiency of ophthalmologists in evaluating meibomian gland dysfunction.

关键词： infrared meibomian glands images meibomian gland dysfunction meibomian glands segmentation weak supervision scribbled annotation

来源：评论

学校读者我要写书评

暂无评论

Distracted driving behaviour recognition based on transfer learning and model fusion

引用

International Journal of Wireless and Mobile Computing 2023年第2期24卷 159-168页

作者： Luo, Guantai Xiao, Wanghui Chen, Xinwei Tao, Jin Zhang, Chentao -HIT Research Institute of Engineering and Technology Quanzhou Fujian China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou Fujian China Department of Instrumental and Electrical Engineering Xiamen University Fujian Xiamen China

In the recognition of distracted driving behaviour, traditional manual feature extraction is subjective and complex;single deep convolutional network also has problems such as insufficient generalisation performance and stability. To solve the above problems, this paper proposes a distracted driving behaviour recognition method based on transfer learning and model fusion. First, based on the transfer learning method, the deep convolutional neural network models ResNet18 and ResNet34 are used to extract the features of some images, respectively. Furthermore, the pre-trained model is fine-tuned to obtain four deep convolutional neural network models. Finally, the four network models are fused by stacking method, using 5-fold cross-validation method to reduce over-fitting. Experimental results show that the recognition accuracy of distracted driving behaviour after model fusion reaches 95.47%. The fusion model has higher model generalisation performance and recognition accuracy, which can provide certain technical support for the research of distracted driving behaviour recognition. © 2023 Inderscience Enterprises Ltd.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Instance Reweighting Adversarial Training Based on Confused Label

引用

intelligent Automation & Soft Computing 2023年第8期37卷 1243-1256页

作者： Zhicong Qiu Xianmin Wang Huawei Ma Songcao Hou Jing Li Zuoyong Li Institute of Artificial Intelligence and Blockchain Guangzhou UniversityGuangzhou511442China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang UniversityFuzhou350121China

Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks,which lies in the fact that examples closer to the decision boundaries are much more vulnerable to being attacked and should be given larger *** probability margin(PM)method is a promising approach to continuously and path-independently mea-suring such closeness between the example and decision ***,the performance of PM is limited due to the fact that PM fails to effectively distinguish the examples having only one misclassified category and the ones with multiple misclassified categories,where the latter is closer to multi-classification decision boundaries and is supported to be more critical in our *** tackle this problem,this paper proposed an improved PM criterion,called confused-label-based PM(CL-PM),to measure the closeness mentioned above and reweight adversarial examples during ***-cally,a confused label(CL)is defined as the label whose prediction probability is greater than that of the ground truth label given a specific adversarial *** of considering the discrepancy between the probability of the true label and the probability of the most misclassified label as the PM method does,we evaluate the closeness by accumulating the probability differences of all the CLs and ground truth ***-PM shares a negative correlation with data vulnerability:data with larger/smaller CL-PM is safer/riskier and should have a smaller/larger *** demonstrated that CL-PM is more reliable in indicating the closeness regarding multiple misclassified categories,and reweighting adversarial training based on CL-PM outperformed state-of-the-art counterparts.

关键词： Reweighting adversarial training adversarial example boundary closeness confused label

来源：评论

学校读者我要写书评

暂无评论

Attentive Neighborhood Feature Augmentation for Semi-supervised Learning

引用

intelligent Automation & Soft Computing 2023年第8期37卷 1753-1771页

作者： Qi Liu Jing Li Xianmin Wang Wenpeng Zhao School of Computer Science and Cyber Engineering Guangzhou UniversityGuangzhou510002China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang UniversityFuzhou350121China

Recent state-of-the-art semi-supervised learning(SSL)methods usually use data augmentations as core *** methods,however,are limited to simple transformations such as the augmentations under the instance’s naive representations or the augmentations under the instance’s semantic *** tackle this problem,we offer a unique insight into data augmentations and propose a novel data-augmentation-based semi-supervised learning method,called Attentive Neighborhood Feature Aug-mentation(ANFA).The motivation of our method lies in the observation that the relationship between the given feature and its neighborhood may contribute to constructing more reliable transformations for the data,and further facilitating the classifier to distinguish the ambiguous features from the low-dense ***,we first project the labeled and unlabeled data points into an embedding space and then construct a neighbor graph that serves as a similarity measure based on the similar representations in the embedding ***,we employ an attention mechanism to transform the target features into augmented ones based on the neighbor ***,we formulate a novel semi-supervised loss by encouraging the predictions of the interpolations of augmented features to be consistent with the corresponding interpolations of the predictions of the target *** carried out exper-iments on SVHN and CIFAR-10 benchmark datasets and the experimental results demonstrate that our method outperforms the state-of-the-art methods when the number of labeled examples is limited.

关键词： Semi-supervised learning attention mechanism feature augmentation consistency regularization

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Virtual Machine Migration Algorithm in Data Centers 3

Energy-Efficient Virtual Machine Migration Algorithm in Data...

引用

3rd International conference on Computer, Big Data and Artificial Intelligence, ICCBDAI 2022

作者： Wu, Xiaodong Zeng, Taisheng School of Mathmatics and Computer Science Quanzhou Normal University Fujian Province Quanzhou362000 China Fujian Provincial Key Laboratory of Intensive Computing Fujian Province Quanzhou362000 China Key Laboratory of Intelligent Computing and Information Processing Fujian Province University Fujian Province Quanzhou362000 China

The issue of data center power consumption is becoming increasingly serious. One of the most effective techniques for increasing resource utilization and lowering power consumption is virtual machine consolidation. This paper proposes a threshold-based energy-efficient and SLA-aware algorithm for virtual machine migration and consolidation. Based on statistics and analysis of historical virtual machine status, the algorithm dynamically obtains the upper CPU utilization threshold of the physical servers and identifies whether to perform the virtual machine migration, so as to reduce the number of active hosts to save energy. The experimental results demonstrate that the proposed algorithm has better comprehensive performance. When compared to the existing algorithm, our method can effectively decrease energy consumption and SLA violations. © Published under licence by IOP Publishing Ltd.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Extended State Observer-based Hybrid Dynamic Event-Triggered Consensus control with External Disturbances 24

Extended State Observer-based Hybrid Dynamic Event-Triggered...

引用

2nd International Conference on Frontiers of intelligent Manufacturing and Automation, CFIMA 2024

作者： Pei, Wenliang Hua, Changchun Cui, Hailong Zhao, Guanglei Ma, Zhuang The Institute of Electrical Engineering The Key Lab of Intelligent Rehabilitation and Neuroregulation in Hebei Province Key Laboratory of Intelligent Control and Neural Information Processing Ministry of Education Yanshan University Hebei China Tangshan University Hebei China

ISBN: (纸本)9798400710681

This paper solves the event-triggered robust consensus problem of disturbed multi-agent systems (MASs) in fully distributed fashion. First, a distributed extended state observer (DESO) is developed for appropriately estimating system states and external disturbances. Then, by utilising these estimates, a fully distributed event-triggering control protocol, that composes of an adaptive distributed controller to avoid using global information while maintaining desired consensus property, and a novel hybrid dynamic event-triggering mechanism (ETM) to save communication resources, is put forward for the MASs. It is notable that an auxiliary differential equation is incorporated in the triggering condition, with which, positive minimum interevent times (MIETs) are available to ease the hardware implementation, while being with adaptive coefficients, the proposed hybrid dynamic ETM can be independent of any global information. Finally, the obtained main results are testified via a numerical example. © 2024 Copyright held by the owner/author(s).

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Wood Surface Discoloration Defect Detection Based on Improved HRNet

Wood Surface Discoloration Defect Detection Based on Improve...

引用

2024 China Automation Congress, CAC 2024

作者： Zhang, Haoran Xu, Zhezhuang Zhu, Yuhang Lin, Ye College of Electrical Engineering and Automation Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798350368604

Discoloration defect detection is a significant task in the wood industry for ensuring the appearance and quality of wooden products. However, discoloration defect detection still faces some challenges due to the low contrast, blurred boundary, and slender shape of discoloration defects. To overcome these challenges, we propose a multi-branch feature encoding HRNet(MFE-HRNet) for wood surface discoloration defect detection. The network maintains high-resolution features and builds a parallel multi-resolution architecture to prevent the dilution of low-contrast discoloration defect features. Through repeated cross-fusion of multi-scale features, the network enhances the global representation of blurry features. In order to effectively preserve the detail features of the defect edge, a multi-branch feature encoding module (MFEM) is proposed as the encoding layer of the network. In the MFEM, multiple branches concurrently extract features, generating feature maps with complementary characteristics, thereby enhancing the ability of network to recognize fine details of defects. Experimental results verify the effectiveness of our method in detecting discoloration defects on wood surface. © 2024 IEEE.

关键词： Discoloration

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：