检索结果-内蒙古大学图书馆

作者： Wang, Shuai Chang, Tsung-Hui Cui, Ying Pang, Jong-Shi Shenzhen Research Institute of Big Data and School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China Guangdong Provincial Key Laboratory of Big Data Computing and School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China Department of Industrial and Systems Engineering University of Minnesota MinneapolisMN55455 United States Department of Industrial and Systems Engineering University of Southern California Los AngelesCA90089 United States

The non-negative matrix factorization (NMF) model with an additional orthogonality constraint on one of the factor matrices, called the orthogonal NMF (ONMF), has been found a promising clustering model and can outperform the classical K-means. However, solving the ONMF model is a challenging optimization problem because the coupling of the orthogonality and non-negativity constraints introduces a mixed combinatorial aspect into the problem due to the determination of the correct status of the variables (positive or zero). Most of the existing methods directly deal with the orthogonality constraint in its original form via various optimization techniques, but are not scalable for large-scale problems. In this paper, we propose a new ONMF based clustering formulation that equivalently transforms the orthogonality constraint into a set of norm-based non-convex equality constraints. We then apply a non-convex penalty (NCP) approach to add them to the objective as penalty terms, leading to a problem that is efficiently solvable. One smooth penalty formulation and one non-smooth penalty formulation are respectively studied. We build theoretical conditions for the penalized problems to provide feasible stationary solutions to the ONMF based clustering problem, as well as proposing efficient algorithms for solving the penalized problems of the two NCP methods. Experimental results based on both synthetic and real datasets are presented to show that the proposed NCP methods are computationally time efficient, and either match or outperform the existing K-means and ONMF based methods in terms of the clustering performance. © 1991-2012 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

INTERACTIVE MODEL WITH STRUCTURAL LOSS FOR LANGUAGE-BASED ABDUCTIVE REASONING

arXiv

引用

arXiv 2021年

作者： Li, Linhao Xu, Ming Dong, Yongfeng Li, Xin Wang, Ao The School of Artificial Intellgence The Hebei Provincial Key Laboratory of Big Data Computing Hebei University of Technology China The Lane Department of Computer Science and Electrical Engineering West Virginia University United States

The abductive natural language inference task (αNLI) is proposed to infer the most plausible explanation between the cause and the event. In the αNLI task, two observations are given, and the most plausible hypothesis is asked to pick out from the candidates. Existing methods model the relation between each candidate hypothesis separately and penalize the inference network uniformly. In this paper, we argue that it is unnecessary to distinguish the reasoning abilities among correct hypotheses;and similarly, all wrong hypotheses contribute the same when explaining the reasons of the observations. Therefore, we propose to group instead of ranking the hypotheses and design a structural loss called "joint softmax focal loss" in this paper. Based on the observation that the hypotheses are generally semantically related, we have designed a novel interactive language model aiming at exploiting the rich interaction among competing hypotheses. We name this new model for αNLI: Interactive Model with Structural Loss (IMSL). The experimental results show that our IMSL has achieved the highest performance on the RoBERTa-large pretrained model, with ACC and AUC results increased by about 1% and 5% respectively. Copyright © 2021, 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

OpenViewer: Openness-Aware Multi-View Learning

arXiv

引用

arXiv 2024年

作者： Du, Shide Fang, Zihan Tan, Yanchao Wang, Changwei Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Jinan China

Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary openness challenges. 1) Lack of Interpretability: The integration mechanisms of multi-view data in existing black-box models remain poorly explained;2) Insufficient Generalization: Most models are not adapted to multi-view scenarios involving unknown categories. To address these challenges, we propose OpenViewer, an openness-aware multi-view learning framework with theoretical support. This framework begins with a Pseudo-Unknown Sample Generation Mechanism to efficiently simulate open multi-view environments and previously adapt to potential unknown samples. Subsequently, we introduce an Expression-Enhanced Deep Unfolding Network to intuitively promote interpretability by systematically constructing functional prior-mapping modules and effectively providing a more transparent integration mechanism for multi-view data. Additionally, we establish a Perception-Augmented Open-Set Training Regime to significantly enhance generalization by precisely boosting confidences for known categories and carefully suppressing inappropriate confidences for unknown ones. Experimental results demonstrate that OpenViewer effectively addresses openness challenges while ensuring recognition performance for both known and unknown samples. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Improved publicly verifiable auditing protocol for cloud storage

Improved publicly verifiable auditing protocol for cloud sto...

引用

作者： Zhang, Jindan Lin, Chuan Ogiela, Urszula Nedjah, Nadia Sangaiah, Arun K. Wang, Xuan Department of Electronic Information Xianyang Vocational Technical College Xianyang China Guizhou Provincial Key Laboratory of Public Big Data GuiZhou University Guiyang China Pedagogical University of Krakow Krakow Poland Department of Electronics Engineering and Telecommunications at the Faculty of Engineering State University of Rio de Janeiro Rio de Janeiro Brazil School of Computing Science and Engineering Vellore Institute of Technology Vellore India

Outsourcing data to cloud servers is a popular service for data owners, however, how to check the integrity and freshness of the outsourced data is very challenge. Recently, Jin et al. proposed a cloud auditing protocol with full integrity and freshness support for cloud data, unfortunately in this article, we show their proposal is not secure. Concretely, the cloud servers can forge the authentication tag and thus has the ability to forge proof of data possession, which obviously invalidates their cloud auditing protocol. We also give a new cloud auditing protocol and analysis its security and performance. The results show our protocol is more efficient and secure. © 2020 John Wiley & Sons, Ltd.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

data-Driven Active Power Dispatch for Wind Farms 13

Data-Driven Active Power Dispatch for Wind Farms

引用

13th IEEE data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Jiao, Xuguo Zhang, Daoyuan Wang, Xin Ma, Zhaoxing Zhang, Zhenyong Liu, Wenfeng School of Information and Control Engineering Qingdao University of Technology Qingdao266520 China College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China College of Computer Science and Technology Guizhou University State Key Laboratory of Public Big Data Guiyang550025 China School of Civil Engineering Qingdao University of Technology Qingdao266520 China

ISBN: (纸本)9798350361674

Active power dispatch of wind farms plays an important role in power grid scheduling. In this paper, a data-driven active power dispatch strategy for wind farms is proposed, which uses the key point of minimizing the standard deviation of wind turbines' output power series to reduce their fluctuations. First, to build the optimization problem, the historical active power output data of each wind turbine is collected from the Supervisory Control And data Acquisition (SCADA) system. Then, the objective function is developed based on the idea of minimizing the standard deviation of the output power time series. Meanwhile, considering the constraints of wind turbines' output power and active power balance of the grid, the feasible domain of the cost function is constructed. Further, to solve the proposed nonlinear optimization problem with equality and inequality constraints, the trust region interior point method (TRIPM) is employed to explore optimal solution within the feasible domain. Finally, actual data collected from wind farms is used to test effectiveness of the designed approach and experimental results show that our method can achieve better output power smoothing performance than conventional Proportional Dispatch (PD) method. © 2024 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

No-Reference Stereoscopic Image Quality Assessment Based on Binocular Collaboration

SSRN

引用

SSRN 2024年

作者： Guo, Wenzhong Wang, Hanling Ke, Xiao Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fujian Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou University Fuzhou350116 China

Stereoscopic images usually consist of a left view, a right view, and depth information. Stereoscopic/3D image quality assessment (SIQA) is often more challenging compared to 2D-IQA due to the usual scene differences between left and right views and the complexity of the binocular vision fusion process. To address the problem of quality prediction bias of multi-distortion images, we investigated the visual physiology and the processing of visual information by the primary visual cortex of the human brain and proposed a no-reference stereoscopic image quality evaluation method. The method mainly includes an innovative end-to-end NR-SIQA neural network with a picture patch generation algorithm. The algorithm generates a saliency map by fusing the left and right views and then guides the image cropping in the database based on the saliency map. The proposed models are validated and compared based on publicly available databases. The results show that the model and algorithm together outperform the state-of-the-art NR-SIQA metric in the LIVE 3D database and the WIVC 3D database, and have excellent results in the specific noise metric. The model generalization experiments demonstrate a certain degree of generality of our proposed model. © 2024, The Authors. All rights reserved.

关键词： database systems

来源：评论

学校读者我要写书评

暂无评论

Automatic Text Summarization Based on Transformer and Switchable Normalization

Automatic Text Summarization Based on Transformer and Switch...

引用

IEEE International Conference on Big data and Cloud computing (BdCloud)

作者： Tao Luo Kun Guo Hong Guo College of Mathematics and Computer Sciences Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou University Fuzhou China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

With the development of text summarization research, the methods based on RNN with the Encoder-Decoder model gradually become the mainstream. However, RNN tends to forget previous context information and leads to the lack of original information. That will reduce the accuracy of the generated summarizations. The Transformer model uses the self-attention mechanism to encode and decode historical information so that it can achieve better performance than RNN in learning context information. In this paper, a text summarization model based on transformer and switchable normalization is proposed. The accuracy of the model is improved by optimizing the normalization layer. Compared with other models, the new model has a great advantage in understanding words' semantics and associations. Experimental results in English Gigaword dataset show that the proposed model can achieve high ROUGE values and make the summarization more readable.

关键词： Decoding Switches Context modeling Vocabulary Task analysis data mining Semantics

来源：评论

学校读者我要写书评

暂无评论

A Fragile Watermarking Algorithm for Speech Authentication by Modifying Least Significant Digits

A Fragile Watermarking Algorithm for Speech Authentication b...

引用

International Conference on Computers, Communications, and Systems (ICCCS)

作者： Qing Qian Yunhe Cui School of Information International Joint Research Center for Data Science and High-Performance Computing Guizhou University of Finance and Economics Guiyang China School of Computer Science and Technology Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guiyang China

ISBN: (数字)9781728161365

ISBN: (纸本)9781728161372

Speech content is often faced with malicious forgery and tampering in transit. Therefore, we introduce a novel fragile watermarking algorithm by modifying the least significant digits for speech content authentication and tampering recovery. In this letter, the proposed authentication scheme consists of two processes: the first one is watermark generation and embedding, the second one is content authentication and recovery. In the former process, the compressed speech signal, frame number and check information are generated based on speech content to form a watermark. Subsequently, the generated watermark is embedded into the least significant digits of speech sampling points using the proposed watermarking algorithm. In the latter process, the embedded watermark is utilized to locate the tampered area and recover that tampered content synchronously. Experimental results show that the proposed watermarking algorithm is fragile to common signal processing. Additionally, it has favorable inaudibility, accurate location ability and high recovery quality.

关键词： Watermarking Authentication Speech coding Signal to noise ratio Speech processing

来源：评论

学校读者我要写书评

暂无评论

Beyond Graph Convolutional Network: An Interpretable Regularizer-centered Optimization Framework

arXiv

引用

arXiv 2023年

作者： Wang, Shiping Wu, Zhihao Chen, Yuhong Chen, Yong College of Computer and Data Science Fuzhou University China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University China School of Computer Science Beijing University of Posts and Telecommunications China

Graph convolutional networks (GCNs) have been attracting widespread attentions due to their encouraging performance and powerful generalizations. However, few work provide a general view to interpret various GCNs and guide GCNs’ designs. In this paper, by revisiting the original GCN, we induce an interpretable regularizer-centerd optimization framework, in which by building appropriate regularizers we can interpret most GCNs, such as APPNP, JKNet, DAGNN, and GNN-LF/HF. Further, under the proposed framework, we devise a dual-regularizer graph convolutional network (dubbed tsGCN) to capture topological and semantic structures from graph data. Since the derived learning rule for tsGCN contains an inverse of a large matrix and thus is time-consuming, we leverage the Woodbury matrix identity and low-rank approximation tricks to successfully decrease the high computational complexity of computing infinite-order graph convolutions. Extensive experiments on eight public datasets demonstrate that tsGCN achieves superior performance against quite a few state-of-the-art competitors w.r.t. classification *** Codes 68T07 Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

BIG-MOE: BYPASS ISOLATED GATING MOE FOR GENERALIZED MULTIMODAL FACE ANTI-SPOOFING

arXiv

引用

arXiv 2024年

作者： Ma, Yingjie Yu, Zitong Lin, Xun Xie, Weicheng Shen, Linlin Great Bay University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators;(2) Gated networks’ susceptibility to input noise affecting decision-making;(3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues;(2) An isolation gating mechanism to counteract input noise;(3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIGMoE. Copyright © 2024, The Authors. All rights reserved.

关键词： HTTP

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：