检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5267-5276页

作者： Yang, Shuai Jiang, Tingting Dang, Qianlong Gu, Lichuan Wu, Xindong Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Hefei230036 China Northwest A & F University College of Science Yangling712100 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

Stable learning aims to learn a model that generalizes well to arbitrary unseen target domain by leveraging a single source domain. Recent advances in stable learning have focused on balancing the distribution of confounders for each feature to eliminate spurious correlations. However, previous studies treat all features equally without considering the difficulties of confounder balancing associated with different features, and regard irrelevant features as confounders, deteriorating generalization performance. To tackle these issues, this article proposes a novel triplex learning (TriL) based stable learning algorithm, which performs sample reweighting, causal feature selection, and representation learning to remove spurious correlations. Specifically, first, TriL adaptively assigns weights to the confounder balancing term of each feature in accordance with the difficulties of confounder balancing, and aligns the confounder distribution of each feature by learning a group of sample weights. Second, TriL integrates the sample weights into a weighted cross-entropy model to compute causal effects of features for excluding irrelevant features from the confounder set. Finally, TriL relearns a set of sample weights and uses them to guide a new supervised dual-autoencoder containing two classifiers to learn feature representations. TriL forces the results of two classifiers to remain consistent for removing spurious correlations by using a cross-classifier consistency regularization. Extensive experiments on synthetic and two real-world datasets show the superiority of TriL compared with seven methods. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

AccelES: Accelerating Top-K SpMV for Embedding Similarity via Low-bit Pruning 31

AccelES: Accelerating Top-K SpMV for Embedding Similarity vi...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Zhai, Jiaqi Shi, Xuanhua Huang, Kaiyi Ye, Chencheng Hu, Weifang He, Bingsheng Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China National University of Singapore School of Computing 119077 Singapore

ISBN: (纸本)9798331506476

In the realm of recommendation systems, achieving real-time performance in embedding similarity tasks is often hindered by the limitations of traditional Top-K sparse matrix-vector multiplication (SpMV) methods, which suffer from high latency due to inefficient memory access patterns. This paper identifies these critical gaps and introduces AccelES, a novel approach that significantly enhances the efficiency of Top-K SpMV. Our method employs a two-stage calculation scheme: the first stage utilizes a compact, low-bit dataset to quickly identify the most relevant entries, while the second stage performs full-precision calculations solely on this pruned subset, thereby minimizing computational overhead. Furthermore, AccelES incorporates innovative matrix representations, Ultra-CSR and Random-CSR, which optimize memory bandwidth utilization. Experimental results demonstrate that AccelES accelerates performance, surpassing state-of-the-art FPGA, GPU, and CPU solutions by factors of 3.4×, 2.5×, and 153.3×, respectively, under controlled conditions. These advancements not only enhance processing speed but also significantly improve real-time performance in recommendation systems, establishing AccelES as a pivotal contribution to the field of Top-K sparse matrix-vector multiplication. © 2025 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Penetrating remote sensing:Next-generation remote sensing for transparent earth

引用

The Innovation 2023年第6期4卷 15-16页

作者： Lizhe Wang Boxin Zuo Yuan Le Yifu Chen Jun Li International Research Center of Big Data for Sustainable Development Goals Beijing 100094China School of Computer Science China University of GeosciencesWuhan 430074China School of Geography and Information Engineering China University of GeosciencesWuhan 430074China

Building upon a unified theoretical framework(based on electromagnetic principles and considering interactions with the Earth’s subsurface materials),we consider a synergistic blend of high-spectral,electromagnetic,and diverse multi-physics techniques to introduce a new concept of penetrating remote *** seamlessly amalgamating the interplay between multiple physical fields,penetrating remote sensing allows us to understand the Earth from its surface to its interior,effectively uncovering information about the planet’s internal *** outcome of this new concept encompasses detailed imagery and three-dimensional models,offering insights into the distribution,structure,properties,and dynamic behavior of materials residing within the *** empowers us to delve into the profound layers of the Earth,unveiling its structural composition and evolutionary *** deeper understanding encompasses vital aspects concerning the Earth’s crust,mantle,and core,comprehending temperature distributions,flow patterns,and other crucial information that enriches our knowledge of the planet’s interior.

关键词： Earth planet interior

来源：评论

学校读者我要写书评

暂无评论

Task Separation and Knowledge Sharing for Class Incremental Learning 5

Task Separation and Knowledge Sharing for Class Incremental ...

引用

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

作者： Zhang, Jiali Qiao, Xiaoyan School of Computer Science and Technology Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China School of Mathematics and Information Science Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China

ISBN: (纸本)9798350368284

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

SMOTE Oversampling and Near Miss Undersampling Based Diabetes Diagnosis from Imbalanced dataset with Xai Visualization 28

SMOTE Oversampling and Near Miss Undersampling Based Diabete...

引用

28th IEEE Symposium on computers and Communications, ISCC 2023

作者： Nayan, Nasim Mahmud Islam, Ashraful Islam, Muhammad Usama Ahmed, Eshtiak Hossain, Mohammad Mobarak Alam, Md Zahangir University of Information Technology and Sciences Department of Computer Science and Engineering Bangladesh Independent University Center for Computational and Data Sciences Bangladesh School of Computing and Informatics University of Louisiana at Lafayette United States Independent University Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350300482

This study investigated the predictive ability of ten different machine learning (ML) models for diabetes using a dataset that was not evenly distributed. Additionally, the study evaluated the effectiveness of two oversampling and undersampling methods, namely the Synthetic Minority Oversampling Technique (SMOTE) and the Near-Miss algorithm. Explainable Artificial Intelligence (Xai) techniques were employed to enhance the interpretability of the model's predictions. The results indicate that the extreme gradient boosting (XGB) model combined with SMOTE oversampling technique exhibited the highest accuracy and an F1-score of 99% and 1.00 respectively. Furthermore, the utilization of Xai methods increased the dependability of the model's decision-making process, rendering it more appropriate for clinical use. These results imply that integrating Xai with ML and oversampling techniques can enhance the early detection and management of diabetes, leading to better diagnosis and intervention. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Prediction Based on Double-Synchronized Periodic LSTM 46

Network Traffic Prediction Based on Double-Synchronized Peri...

引用

46th IEEE Annual computers, Software, and Applications Conference, COMPSAC 2022

作者： Ye, Liang Ding, Shun Liu, Chenyun Zhu, Wenhao School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Municipal Big Data Center Shanghai China

ISBN: (纸本)9781665488105

In the prediction of time series, the data scale often changes rapidly or a data series shows periodic mutation trend characteristic. A general prediction algorithm cannot obtain the periodic change information of time series in advance, resulting in a limited prediction effect. Considering this factor, the structural improvement of periodic features in a general prediction algorithm can be more suitable for some real scenarios. To solve this problem, this paper proposes a network traffic prediction model based on double-synchronized periodic LSTM (DSP-LSTM), which can comprehensively consider the good fitting ability of linear model to periodic feature data and the nonlinear prediction characteristic of neural network. The experimental results show that the improved DSP-LSTM model can show a better fitting effect when time series data have periodic trend characteristics. Compared with general prediction algorithm, the DSP-LSTM model can effectively reduce the prediction error of periodic time series, improve the prediction accuracy, and adapt well to the changes of different time series patterns. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Robust graph‐based localization for industrial Internet of things in the presence of flipping ambiguities

引用

CAai Transactions on Intelligence Technology 2023年第4期8卷 1140-1149页

作者： Mian Imtiaz ul Haq Ruhul Amin Khalil Muhannad Almutiry Ahmad Sawalmeh Tanveer Ahmad Nasir Saeed Faculty of Electrical Engineering Swedish College of Engineering and TechnologyWah CanttPakistan Department of Electrical Engineering Faculty of Electrical and Computer EngineeringUniversity of Engineering and TechnologyPeshawarPakistan Department of Electrical Engineering Remote Sensing UnitNorthern Border UniversityArarSaudi Arabia Data Science and Artificial Intelligence Department‐College of Science and Information Technology Irbid National UniversityIrbadJordan Innovation Education and Research Center for On‐Device AI Software(Bk21) Department of Computer Science and EngineeringChungnam National UniversityDaejeonRepublic of Korea Department of Electrical and Communication Engineering United Arab Emirates University(UAEU)Al AinUnited Arab Emirates

Localisation of machines in harsh Industrial Internet of Things(IIoT)environment is necessary for various ***,a novel localisation algorithm is proposed for noisy range measurements in IIoT *** position of an unknown machine device in the network is estimated using the relative distances between blind machines(BMs)and anchor machines(AMs).Moreover,a more practical and challenging scenario with the erroneous position of AM is considered,which brings additional uncertainty to the final position ***,the AMs selection algorithm for the localisation of BMs in the IIoT network is *** those AMs will participate in the localisation process,which increases the accuracy of the final location ***,the closed‐form expression of the proposed greedy successive anchorization process is derived,which prevents possible local convergence,reduces computation,and achieves Cramér‐Rao lower bound accuracy for white Gaussian measurement *** results are compared with the state‐of‐the‐art and verified through numerous simulations.

关键词： Cramér‐Rao lower bound greedy successive anchorization industrial internet of things localization

来源：评论

学校读者我要写书评

暂无评论

Multi-StudentNet: a Semi-supervised Deep-Learning Framework for Endometrial Segmentation in Transvaginal Ultrasound Images

Multi-StudentNet: a Semi-supervised Deep-Learning Framework ...

引用

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Peng, Boyuan Liu, Yiyang Zhu, Xin Huang, Jie Wang, Wenwen Fang, Li Zhou, Qin Graduate Department of Computer Science and Engineering The University of Aizu Fukushima Aizu-Wakamatsu Japan Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Chiyodaku Tokyo Japan Graduate Department of Computer Science and Engineering Division of Information Systems The University of Aizu Fukushima Aizu-Wakamatsu Japan Department of Obstetrics and Gynecology Tongji Hospital Huazhong University of Science and Technology Hubei Wuhan China

ISBN: (纸本)9798350350548

Semi-supervised learning (SSL) is a promising solution for the problem of insufficient medical labeled data. However, it is still a challenging task to segment transvaginal ultrasound (TVUS) images because of their poor contrast and speckle noise. In this study, we propose Multi-StudentNet, a semi-supervised deep-learning framework for endometrial segmentation in TVUS images. This method employs multiple student models to effectively integrate labeled and unlabeled data, improving the reliability and performance of segmentation while significantly reducing the need for extensive manual labeling. By leveraging the weights of multiple models, our framework facilitates feature sharing, which enhances model robustness. Specifically, Multi-StudentNet achieves a Dice coefficient (DSC) of 0.81 and a specificity of 0.99. Our multi-student models consistently outperform single-student models across various conditions, including normal, polyp, and cancer cases. Extensive experiments demonstrate that Multi-StudentNet achieves state-of-the-art performance in both accuracy and robustness. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-view Transformer-Based Network for Prerequisite Learning in Concept Graphs 23rd

Multi-view Transformer-Based Network for Prerequisite Learn...

引用

23rd International Semantic Web Conference, ISWC 2024

作者： Wang, Zhichun Shao, Yifeng Peng, Boci Li, Bangui Li, Yun Wang, Qianren Li, Nijun School of Artificial Intelligence Beijing Normal University Beijing China Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education Beijing China School of Intelligence Science and Technology Peking University Beijing China School of Computer Science and Engineering Beihang University Beijing China Advanced Cognitive AI Lab Shanghai Huawei Technologies Shanghai China

ISBN: (纸本)9783031778438

Prerequisite learning is the task of identifying prerequisite relations among concepts, which is important for many ai-based educational applications. Previous approaches explore different kinds of learning resources to obtain useful features for predicting prerequisites. Early approaches use handcrafted features while recent approaches use neural networks to encode information of concepts. To further improve the results of prerequisite learning, we build concept graphs to include comprehensive information about concepts from open data and learning resources, and propose a Multi-view Transformer-based Network (MTN) to encode multi-view features of concepts in the graph. Multi-view features are fused to make accurate predictions of concept prerequisites. We evaluate our approach on four public datasets and compare it with recently published approaches. The results show that our approach can achieve state-of-the-art results in the task of prerequisite learning. The source code and data are available at https://***/kg-bnu/MTN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Semantic Template-based Convolutional Neural Network for Text Classification

引用

ACM Transactions on Asian and Low-Resource Language Information Processing 2023年第11期22卷 1-21页

作者： Chang, Yung-Chun Ng, Siu Hin Chen, Jung-Peng Liang, Yu-Chi Hsu, Wen-Lian Graduate Institute of Data Science Taipei Medical University Taipei Taiwan Clinical Big Data Research Center Taipei Medical University Hospital Taipei Taiwan Snhcc Tigp Academia Sinica National Cheng Chi University Taipei Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan Department of Computer Science and Information Engineering College of Information and Electrical Engineering Asia University Taichung Taiwan Pervasive Ai Research Labs Ministry of Science and Technology Hsinchu City Taiwan

We propose a semantic template-based distributed representation for the convolutional neural network called Semantic Template-based Convolutional Neural Network (STCNN) for text categorization that imitates the perceptual behavior of human comprehension. STCNN is a highly automatic approach that learns semantic templates that characterize a domain from raw text and recognizes categories of documents using a semantic-infused convolutional neural network that allows a template to be partially matched through a statistical scoring system. Our experiment results show that STCNN effectively classifies documents in about 140,000 Chinese news articles into predefined categories by capturing the most prominent and expressive patterns and achieves the best performance among all compared methods for Chinese topic classification. Finally, the same knowledge can be directly used to perform a semantic analysis task. © 2023 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Semantics

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：