检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Makaroğlu, Didem Cakir, Altan Töreyin, Behçet Uğur Demirören Teknoloji A.S. İstanbul Turkey Signal Processing for Computational Intelligence Group Informatics Institute Istanbul Technical University Istanbul Turkey Physics Engineering Faculty of Science and Letters Istanbul Technical University Istanbul Turkey Istanbul Technical University Artificial Intelligence Data Science Research and Application Center Istanbul Turkey

Clickstream data, which come with a massive volume generated by human activities on websites, have become a prominent feature for identifying readers’ characteristics by newsrooms after the digitization of news outlets. It is essential to have elastic architectures to process the streaming data, particularly for unprecedented traffic, enabling conducting more comprehensive analyses, such as recommending mostly related articles to readers. Although the nature of clickstream data has a similar logic within websites, it has inherent limitations to recognize human behaviours when looking from a broad perspective, which brings the need to limit the problem in niche areas. This study investigates the anonymized readers’ click activities on the organizations’ websites to identify news consumption patterns following referrals from Twitter, who incidentally reach but propensity is mainly routed news content. The investigation is widened to a broad perspective by linking the log data with news content to enrich the insights rather than sticking into the web journey. Methodologies for ensemble cluster analysis with mixed-type embedding strategies are applied and compared to find similar reader groups and interests independent of time. Various internal validation perspectives are used to determine the optimality of the quality of clusters, where the Calinski Harabasz Index (CHI) is found to give a generalizable result. Our findings demonstrate that clustering a mixed-type dataset approaches the optimal internal validation scores, which we define to discriminate the clusters and algorithms considering applied strategies, when embedded by Uniform Manifold Approximation and Projection (UMAP) and using a consensus function as a key to access the most applicable hyper parameter configurations in the given ensemble rather than using consensus function results directly. Evaluation of the resulting clusters highlights specific clusters repeatedly present in the separated monthly sample

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Granule Density-Based Outlier Detection with Multi-Scale Granular Balls

arXiv

引用

arXiv 2025年

作者： Gao, Can Tan, Xiaofeng Zhou, Jie Ding, Weiping Pedrycz, Witold The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The School of Artificial Intelligence and Computer Science Nantong University Nantong226019 China The Faculty of Data Science City University of Macau Macau999078 China The Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland The Department of Electrical and Computer Engineering King Abdulaziz University Jeddah Saudi Arabia The Department of Computer Engineering Istinye University Istanbul Turkey

Outlier detection refers to the identification of anomalous samples that deviate significantly from the distribution of normal data and has been extensively studied and used in a variety of practical tasks. However, most unsupervised outlier detection methods are carefully designed to detect specified outliers, while real-world data may be entangled with different types of outliers. In this study, we propose a fuzzy rough sets-based multi-scale outlier detection method to identify various types of outliers. Specifically, a novel fuzzy rough sets-based method that integrates relative fuzzy granule density is first introduced to improve the capability of detecting local outliers. Then, a multi-scale view generation method based on granular-ball computing is proposed to collaboratively identify group outliers at different levels of granularity. Moreover, reliable outliers and inliers determined by the three-way decision are used to train a weighted support vector machine to further improve the performance of outlier detection. The proposed method innovatively transforms unsupervised outlier detection into a semi-supervised classification problem and for the first time explores the fuzzy rough sets-based outlier detection from the perspective of multi-scale granular balls, allowing for high adaptability to different types of outliers. Extensive experiments carried out on both artificial and UCI datasets demonstrate that the proposed outlier detection method significantly outperforms the state-of-the-art methods, improving the results by at least 8.48% in terms of the Area Under the ROC Curve (AUROC) index. The source codes are released at https://***/Xiaofeng-Tan/MGBOD. © 2025, CC BY.

关键词： Granulation

来源：评论

学校读者我要写书评

暂无评论

Improving Chinese Character Representation with Formation Tree

SSRN

引用

SSRN 2024年

作者： Hong, Yang Li, Yinfei Qiao, Xiaojun Li, Rui Zhang, Junsong National Engineering Research Center for E-learning Central China Normal University No.152 Luoyu Road Hubei Wuhan430079 China Mind Art and Computation Group Department of Artificial Intelligence Xiamen University No. 4221 South Xiang’an Road Xiang’an District Fujian Xiamen361104 China National Engineering Research Center of Educational Big Data Central China Normal University No.152 Luoyu Road Hubei Wuhan430079 China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Xiamen University Ministry of Culture and Tourism Fujian Xiamen China

Learning effective representations for Chinese characters presents unique challenges, primarily due to the vast number of characters and their continuous growth, which requires models to handle an expanding category space. Additionally, the inherent sparsity of character usage complicates the generalization of learned representations. Prior research has explored radical-based sequences to overcome these issues, achieving progress in recognizing unseen characters. However, these approaches fail to fully exploit the inherent tree structure of such sequences. To address these limitations and leverage established data properties, we propose Formation Tree-CLIP (FT-CLIP). This model utilizes formation trees to represent characters and incorporates a dedicated tree encoder, significantly improving performance in both seen and unseen character recognition tasks. We further introduce masking for to both character images and tree nodes, enabling efficient and effective training. This approach accelerates training significantly (by a factor of 2 or more) while enhancing accuracy. Extensive experiments show that processing characters through formation trees aligns better with their inherent properties than direct sequential methods, significantly enhancing the generality and usability of the representations. © 2024, The Authors. All rights reserved.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-feature Fusion for Epileptic Focus Localization Based on Tensor Representation

Multi-feature Fusion for Epileptic Focus Localization Based ...

引用

Asia-Pacific Signal and Information processing Association Annual Summit and Conference (APSIPA)

作者： Xuyang Zhao Jordi Solé-Casals Qibin Zhao Jianting Cao Toshihisa Tanaka Tokyo University of Agriculture and Technology Japan Tensor Learning Team RIKEN Center for Advanced Intelligence Project Japan Data and Signal Processing Research Group University of Vic-Central University of Catalonia Catalonia University of Cambridge United Kingdom College of Artificial Intelligence Nankai University China Saitama Institute of Technology Japan

ISBN: (纸本)9781665441629

Epileptic focus localization based on intracranial electroencephalogram (iEEG) signal is a key task before the patient's surgery, which is time-consuming by visual diagnosis of clinical experts and its accuracy directly affects the effectiveness of surgery. Recently, many machine learning methods have been applied to automatic epileptic focus localization. However, most studies have performed feature extraction and classification based on single type of features, leading to less robustness to noises and degraded performance. In this paper, inspired by making a diagnosis from multiple angles in practical situation, we proposed a multi-set feature fusion strategy by using tensor representation technique. As compared to the existing linear fusion strategy, our proposed tensor fusion approach can significantly enhance the expressive power of the model by taking into account the feature interaction information. We integrate tensor fusion strategy into deep convolutional neural network, yielding a new method for automatic epileptic focus localization. Experimental results demonstrate that our proposed model based on multi-set tensor fusion can achieve the best performance among single type features based models and the linear fusion model.

关键词： Location awareness Visualization Tensors Surgery Machine learning Information processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

On the robustness of EEG tensor completion methods

引用

Science China(Technological Sciences) 2021年第9期64卷 1828-1842页

作者： DUAN Feng JIA Hao ZHANG ZhiWen FENG Fan TAN Ying DAI YangYang CICHOCKI Andrzej YANG ZhengLu CAIAFA Cesar F. SUN Zhe SOLE-CASALS Jordi College of Artificial Intelligence Nankai UniversityTianjin 300350China Skolkowo Institute of Science and Technology Moscow 121205Russia College of Computer Science Hangzhou Dianzi UniversityHangzhou 310018China Department of Informatics Nicolaus Copernicus UniversityTorun 87-100Poland Systems Research Institute Polish Academy of SciencesWarsaw 01-447Poland College of Computer Science Nankai UniversityTianjin 300350China Instituto Argentino de Radioastronom´ıa IAR-CCT La Plata CONICET/CIC-PBA/UNLPVilla Elisa 1894Argentina Computational Engineering Applications Unit Head Office for Information Systems and CybersecurityRIKENWako-Shi 351-0106Japan Department of Psychiatry University of CambridgeCambridge CB28AHUK Data and Signal Processing Research Group University of Vic-Central University of CataloniaCatalonia 08500Spain

During the acquisition of electroencephalographic(EEG) signals, data may be missing or corrupted by noise and artifacts. To reconstruct the incomplete data, EEG signals are firstly converted into a three-order tensor(multi-dimensional data) of shape time × channel × trial. Then, the missing data can be efficiently recovered by applying a tensor completion method(TCM).However, there is not a unique way to organize channels and trials in a tensor, and different numbers of channels are available depending on the EEG setting used, which may affect the quality of the tensor completion results. The main goal of this paper is to evaluate the robustness of EEG completion methods with several designed parameters such as the ordering of channels and trials, the number of channels, and the amount of missing data. In this work, the results of completing missing data by several TCMs were compared. To emulate different scenarios of missing data, three different patterns of missing data were ***, the amount of missing data on completion effects was analyzed, including the time lengths of missing data and the number of channels or trials affected by missing data. Secondly, the numerical stability of the completion methods was analyzed by shuffling the indices along channels or trials in the EEG data tensor. Finally, the way that the number of electrodes of EEG tensors influences completion effects was assessed by changing the number of channels. Among all the applied TCMs, the simultaneous tensor decomposition and completion(STDC) method achieves the best performance in providing stable results when the amount of missing data or the electrode number of EEG tensors is changed. In other words, STDC proves to be an excellent choice of TCM, since permutations of trials or channels have almost no influence on the complete results. The STDC method can efficiently complete the missing EEG signals. The designed simulations can be regarded as a procedure to validate whether or

关键词： electroencephalogram corrupted data missing data tensor completion tensor decomposition

来源：评论

学校读者我要写书评

暂无评论

Effective node vaccination and containing strategies to halt SIR epidemic spreading in real-world face-to-face contact networks

Effective node vaccination and containing strategies to halt...

引用

2022 RIVF International Conference on Computing and Communication Technologies, RIVF 2022

作者： Nguyen, Ngoc-Kim-Khanh Nguyen, Thanh-Trung Nguyen, Tuan-Anh Sartori, Fabio Turchetto, Massimiliano Scotognella, Francesco Alfieri, Roberto Cassi, Davide Nguyen, Quang Bellingeri, Michele Sciences Van Lang University Faculty of Fundamental 69/68 Dang Thuy Tram Street Ward 13 Binh Thanh District Ho Chi Minh Viet Nam Research Group of Intelligent Data Processing System Ho Chi Minh City University of Foreign Languages - Information Technology Ho Chi Minh City Viet Nam Università di Parma Dipartimento di Scienze Matematiche Fisiche e Informatiche via G.P. Usberti 7/a Parma43124 Italy Politecnico di Milano Dipartimento di Fisica Piazza Leonardo da Vinci 32 Milano20133 Italy Institute of Fundamental and Applied Sciences Duy Tan University Ho Chi Minh700000 Viet Nam

ISBN: (纸本)9781665461665

We model the COVID-19 spreading by running SIR Monte-Carlo simulations in four real face-to-face contact networks. We evaluate the effectiveness of the 'facemask use' and 'vaccination policies' to curb epidemic spreading. We model the facemask use policy by assuming a lower individual infection probability β. We found that while this strategy can delay the disease spreading, it does not significantly reduce the total number of infected individuals (TI), as 80% of the total population still is infected at the end of the epidemic. We model vaccination by setting individual's infection probability β=0, which is equivalent to remove nodes/individuals from the network. The vaccination was found to be very effective. Even with a partial vaccination of 30% of the population nodes selected considering their centrality measure ranking, such as degree, betweenness, or PageRank, it was possible to reduce the TI of 14%. Finally, yet importantly, random partial vaccination is not effective at all, meaning that most of the unvaccinated population will be infected. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Improving Pre-movement Pattern Detection with Filter Bank Selection

arXiv

引用

arXiv 2022年

作者： Jia, Hao Sun, Zhe Duan, Feng Zhang, Yu Caiafa, Cesar F. Solé-Casals, Jordi Data and Signal Processing Research Group University of Vic-Central University of Catalonia Vic Spain Computational Engineering Applications Unit Head Office for Information Systems and Cybersecurity RIKEN Saitama Japan College of Artificial Intelligence Nankai University Tianjin China Department of Bioengineering Lehigh University BethlehemPA18015 United States Instituto Argentino de Radioastronomía CONICET CCT La Plata/CIC-PBA/UNLP V. Elisa Argentina

Pre-movement decoding plays an important role in movement detection and is able to detect movement onset with low-frequency electroencephalogram (EEG) signals before the limb moves. In related studies, pre-movement decoding with standard task-related component analysis (STRCA) has been demonstrated to be efficient for classification between movement state and resting state. However, the accuracies of STRCA differ among subbands in the frequency domain. Due to individual differences, the best subband differs among subjects and is difficult to be determined. This study aims to improve the performance of the STRCA method by a feature selection on multiple subbands and avoid the selection of best subbands. This study first compares three frequency range settings (M1: subbands with equally spaced bandwidths;M2: subbands whose high cut-off frequencies are twice the low cut-off frequencies;M3: subbands that start at some specific fixed frequencies and end at the frequencies in an arithmetic sequence.). Then, we develop a mutual information based technique to select the features in these subbands. A binary support vector machine classifier is used to classify the selected essential features. The results show that M3 is a better setting than the other two settings. With the filter banks in M3, the classification accuracy of the proposed FBTRCA achieves 0.8700±0.1022, which means a significantly improved performance compared to STRCA (0.8287±0.1101) as well as to the cross validation and testing method (0.8431±0.1078). Copyright © 2022, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

SMART CITY DEVELOPMENT STRATEGY PROFILE: USE CASE MODELING BASED on SIMPLICIAL COMPLEXES 5

SMART CITY DEVELOPMENT STRATEGY PROFILE: USE CASE MODELING B...

引用

5th International Conference on Smart data and Smart Cities, SDSC 2020

作者： Berrou, Y. Soulier, E. Calvez, P. Birregah, B. Vidal, P. Dupont, E. Carballa, B. Blot, G. Guery, M. Troyes France Computer Science and Artificial Intelligence Laboratory ENGIE Lab CRIGEN Stains France Department of System Modelling and Dependability UTT Troyes France Urbanity Master University of Le Havre Normandie Le Havre France Research and Innovation Strategy National Agency of Territories' Cohesion Paris France Chronos Group France Data Nostra France

According to three workshops organized as part of a study on public service delegation of data, use case definitions appeared to be a common issue for cities. To facilitate this step in city projects, one possibility is to define their profiles precisely and to compare these to their development strategies to highlight whether they are aligned, and eventually, to adjust the activities accordingly. In this context, a smart city profile model was developed based on the bibliometric analysis of smart cities in the work of (Mora and Deakin, 2019). Thereafter, a smart city model was developed based on the Smart Grid Architecture Model to aid in implementing the use cases, as presented in the work of (Gottschalk et al., 2017) and the IEC 62559-2 standard. Finally, four smart city profiles were identified and a profile characterization method was proposed using simplicial complexes. The results of the analysis of a smart city profile using this method enabled an in-depth understanding of the profile, which can aid cities in identifying new use cases to implement to be in line with their strategic development. © 2020 Y. Berrou et al.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

g-circulant matrix and its matrix-vector multiplication algorithm on transformer neural network

引用

AIP Conference Proceedings 2024年第1期3201卷

作者： Euis Asriani Intan Muchtadi-Alamsyah Ayu Purwarianti Doctoral Program of Mathematics Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Indonesia Algebra Research Group Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Indonesia University Center of Excellence on Artificial Intelligence for Vision Natural Language Processing and Big Data Analytics (U-CoE AI-VLB) Institut Teknologi Bandung Indonesia Informatics Research Group School of Electrical Engineering and Informatics Institut Teknologi Bandung Indonesia

A g-circulant matrix is an n-dimensional matrix Cn,g that can be expressed as Cn,g=[c(gr−s)modn]r,s=0n−1 . This study will investigate the use of g-circulant matrices as weight matrices on transformer neural networks for machine translation. On transformer model tested, the g-circulant weight matrix undergoes multiplication with any vector and involves the DCT-DST algorithm. This algorithm is proposed as a substitute for the commonly used FFT algorithm. For this reason, an orthogonal matrix Un,g was defined by multiplying the Un matrix and appropriate permutation matrix, where Un matrix is a matrix that is spanned by the combination of the real and imaginary parts of eigenvectors of the real 1-circulant matrix. Then we form a Schur decomposition of the g-circulant matrix, composes the Qn,g matrix, and using the DCT-DST to formulate the multiplication of Qn,gUn,g. We discovered that 2-circulant matrices are outperform compared to the other g-circulant matrices and the original model of transformer in terms of accuracy and loss training.

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：