检索结果-内蒙古大学图书馆

International Conference on Multimedia Information Networking and Security (MINES)

作者： Songqin Miao Futai Zhang Lei Zhang School of Computer Science and Technology Nanjing Normal University Nanjing China UNESCO Chair in Data Privacy Department of Computer Engineering and Mathematics Universitat Rovira i Virgili Catalonia Spain

Certificateless public key cryptography eliminates certificate management in traditional public key infrastructure and solves the key escrow problem in identity-based cryptography. Certificateless signcryption is one of the most important primitives in certificateless public key cryptography which achieves confidentiality and authentication simultaneously. Multi-receiver signcryption signcrypts a message to a large number of receivers. Selvi et al. proposed the first efficient and provably secure certificateless multi-receiver signcryption scheme. Recently, they found the scheme is insecure against the type I adversary and gave an enhanced one. However, we find that their enhanced scheme is still insecure against the type I adversary. In this paper, we present an attack on Selvi et al.'s enhanced scheme. Specifically, we show that a type I adversary can first replace a sender's public key and generate a signcrypted message on behalf of the sender.

关键词： Receivers Elliptic curve cryptography Encryption

来源：评论

学校读者我要写书评

暂无评论

PEDESTRIAN DETECTION VIA A LEG-DRIVEN PHYSIOLOGY FRAMEWORK

PEDESTRIAN DETECTION VIA A LEG-DRIVEN PHYSIOLOGY FRAMEWORK

引用

IEEE International Conference on Image Processing

作者： Gongbo Liang Qi Li Xiangui Kang Western Kentucky University Department of Computer Science Ogden College of Science & Engineering Guangdong Key Lab of Information Security Sun Yat-Sen University School of Data and Computer Science

ISBN: (纸本)9781467399623

In this paper, we propose a leg-driven physiology framework for pedestrian detection. The framework is introduced to reduce the search space of candidate regions of pedestrians. Given a set of vertical line segments, we can generate a space of rectangular candidate regions, based on a model of body proportions. The proposed framework can be either integrated with or without learning-based pedestrian detection methods to validate the candidate regions. A symmetry constraint is then applied to validate each candidate region to decrease the false positive rate. The experiment demonstrates the promising results of the proposed method by comparing it with Dalal & Triggs method. For example, rectangular regions detected by the proposed method has much similar area to the ground truth than regions detected by Dalal & Triggs method.

关键词： Pedestrian detection Leg Line segment Bounding box bounding boxes Line sections Leg Pedestrians Physiology candidate species vertical line ground truth inspection methods

来源：评论

学校读者我要写书评

暂无评论

Multi-View Spectral Clustering via Tensor-SVD Decomposition

Multi-View Spectral Clustering via Tensor-SVD Decomposition

引用

IEEE International Conference on Tools with Artificial Intelligence

作者： Yan Zhang Weiwei Yang Bangtian Liu Geyang Ke Yan Pan Jian Yin School of Data and Computer Science Sun Yat-sen University Guangzhou P. R. China Department of Electrical and Computer Engineering Rutgers University New Jersey USA

Multi-view clustering has attracted considerable attention in recent years, some related approaches always use matrices to represent views, and model by capturing two dimensional structure among views. The critical deficiency of these work is ignoring the space structure information of all views, which results in the mediocre performance of clustering. In this paper, we propose a novel Tensor-SVD decomposition based Multi-view Spectral Clustering algorithm(TMSC) to iron out flaws. Our method firstly puts transition probability matrices of all views into a three-order tensor, which naturally reserves the whole structure information of data. Then it establishes a low multi-rank tensor model based on tensor-SVD decomposition by fully mining the complementary information among multiple views. Another difficulty in this paper is that the optimal objective of TMSC has a low multirank constraint on the transition probability tensor, and a probabilistic simplex constraint on each fiber of the tensor. To tackle this challenging problem, we design an optimization procedure based on the Augmented Lagrangian Multiplier scheme. Experimental results on real word datasets show that TMSC has superior clustering quality over several state-of-the-art multi-view clustering approaches.

关键词： Multi-view clustering Tensor-SVD Spectral clustering

来源：评论

学校读者我要写书评

暂无评论

Dual-neighbourhood information aggregation and feature fusion for prediction of miRNA–disease association

引用

computers in Biology and Medicine 2024年 181卷 109068-109068页

作者： Liu, Wei Lan, Zixin Li, Zejun Sun, Xingen Lu, Xu School of Computer Science Xiangtan University Xiangtan411105 China School of Computer Science and Engineering Hunan Institute of Technology Hengyang421002 China School of Mathematics and Computational Science Xiangtan University Xiangtan411105 China School of Computer Science Guangdong Polytechnic Normal University Guangdong Provincial Key Laboratory of Intellectual Property Big Data Guangzhou510665 China

Studying the intricate relationship between miRNAs and diseases is crucial to prevent and treat miRNA-related disorders. Existing computational methods often overlook the importance of features of different nodes and the propagation of features among heterogeneous nodes. Many prediction models focus only on the feature coding of miRNA and diseases and ignore the importance of feature aggregation. We propose a prediction method via dual-neighbourhood feature aggregation and feature fusion, which uses multiple sources of information, aggregates information on homogeneous and heterogeneous nodes and fuses learned features to predict multiple representations of disease nodes. We constructed similarity networks of multiple homogeneous nodes based on different similarity computation methods respectively, and fused the attention mechanism by using graph convolutional networks to obtain information of different levels of importance. To alleviate the problem of sparse connectivity in the dataset, we built a two-neighbourhood heterogeneous graph neural network model to integrate the homogeneous similarity network into a miRNA-disease heterogeneous network by using known miRNA–disease association information. We used the neighbourhood information associated with the nodes in the network to perform feature aggregation. In addition, we used a feature fusion module to learn the importance of different types of nodes to predict miRNA–disease associations. Our experimental results on the Human microRNA Disease database (HMDD v3.2) show that the model demonstrates superior performance. This work demonstrates the capability of our model to identify potential miRNAs associated with diseases through a case study of two common cancers. © 2024

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Prevention of Security Attacks at Wireless Network Layers using Machine Learning Techniques

Prevention of Security Attacks at Wireless Network Layers us...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Sowjanya Ramisetty G S Pradeep Ghantasala Gaurav Gupta Sonia Department of Computer Science and Engineering KG Reddy College of Engineering & Technology Hyderabad India Department of Computer Science and Engineering Alliance University Bengaluru India Yogananda School of Artificial Intelligence Computers and Data Sciences Shoolini University Solan India

Wireless sensor networks have great potential for use in flood control, weather forecasting systems, the military, and the healthcare industry. A WSN’s nodes are connected to one another and share information. When sending data between nodes, data security is essential. In the world of networking, security is a top priority. data travels along a path when it is transferred from one location to another, increasing the likelihood that a rogue node would enter the network. Detecting malicious nodes within a network presents a formidable challenge, particularly due to external assaults on data packets during their transmission between nodes. Hackers take advantage of weaknesses to manipulate and alter data as it travels from the source node to the destination node. This paper looked at machine learning algorithm-based preventive measures and layer-level security challenges.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incremental Gauss–Newton Methods with Superlinear Convergence Rates

arXiv

引用

arXiv 2024年

作者： Zhou, Zhiling Liu, Zhuanghua Liu, Chengchang Luo, Luo School of Data Science Fudan University China Department of Computer Science National University of Singapore Singapore Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

This paper addresses the challenge of solving large-scale nonlinear equations with Hölder continuous Jacobians. We introduce a novel Incremental Gauss–Newton (IGN) method within explicit superlinear convergence rate, which outperforms existing methods that only achieve linear convergence rate. In particular, we formulate our problem by the nonlinear least squares with finite-sum structure, and our method incrementally iterates with the information of one component in each round. We also provide a mini-batch extension to our IGN method that obtains an even faster superlinear convergence rate. Furthermore, we conduct numerical experiments to show the advantages of the proposed methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Potential of Reverse Distillation for Anomaly Detection

arXiv

引用

arXiv 2024年

作者： Liu, Xinyue Wang, Jianyuan Leng, Biao Zhang, Shuo School of Computer Science and Engineering Beihang University China School of Intelligence Science and Technology University of Science and Technology Beijing China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer & Technology Beijing Jiaotong University China

Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network’s over-generalization often diminishes the crucial representation differences between teacher and student in anomalous regions, leading to detection failures. To addresses this problem, the widely accepted Reverse Distillation (RD) paradigm designs asymmetry teacher and student network, using an encoder as teacher and a decoder as student. Yet, the design of RD does not ensure that the teacher encoder effectively distinguishes between normal and abnormal features or that the student decoder generates anomaly-free features. Additionally, the absence of skip connections results in a loss of fine details during feature reconstruction. To address these issues, we propose RD with Expert, which introduces a novel Expert-Teacher-Student network for simultaneous distillation of both the teacher encoder and student decoder. The added expert network enhances the student’s ability to generate normal features and optimizes the teacher’s differentiation between normal and abnormal features, reducing missed detections. Additionally, Guided Information Injection is designed to filter and transfer features from teacher to student, improving detail reconstruction and minimizing false positives. Experiments on several benchmarks prove that our method outperforms existing unsupervised AD methods under RD paradigm, fully unlocking RD’s potential. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

On Semiseparable Kernels and Efficient Computation of Regularized System Identification and Function Estimation ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 462-467页

作者： Tianshi Chen Martin S. Andersen School of Science and Engineering and Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen518172 China Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark

A long-standing problem for kernel-based regularization methods is their high computational complexity O(N 3 ), where N is the number of data points. In this paper, we show that for semiseparable kernels and some typical input signals, their computational complexity can be lowered to O(Nq 2 ), where q is the output kernel’s semiseparability rank that only depends on the chosen kernel and the input signal.

关键词： System identification kernel-based regularization semiseparable kernels kernel design efficient computation

来源：评论

学校读者我要写书评

暂无评论

Transductive zero-shot hashing for multilabel image retrieval

arXiv

引用

arXiv 2019年

作者： Zou, Qin Cao, Ling Zhang, Zheng Chen, Long Wang, Song The School of Computer Science Wuhan University Wuhan430072 China The School of Data and Computer Science Sun Yat-Sen University Guangzhou518001 China The Department of Computer Science and Engineering University of South Carolina ColumbiaSC29201 United States

Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes. While some newly introduced images may contain undefined semantic labels, which we call unseen images, zero-shot hashing (ZSH) techniques have been studied for retrieval. However, existing ZSH methods mainly focus on the retrieval of single-label images and cannot handle multilabel ones. In this article, for the first time, a novel transductive ZSH method is proposed for multilabel unseen image retrieval. In order to predict the labels of the unseen/target data, a visual-semantic bridge is built via instance-concept coherence ranking on the seen/source data. Then, pairwise similarity loss and focal quantization loss are constructed for training a hashing model using both the seen/source and unseen/target data. Extensive evaluations on three popular multilabel data sets demonstrate that the proposed hashing method achieves significantly better results than the comparison methods. © 2019, CC BY-NC-SA.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

MetaGB: A Gradient Boosting Framework for Efficient Task Adaptive Meta Learning

MetaGB: A Gradient Boosting Framework for Efficient Task Ada...

引用

IEEE International Conference on data Mining (ICDM)

作者： Manqing Dong Lina Yao Xianzhi Wang Xiwei Xu Liming Zhu Computer Science and Engineering University of New South Wales Sydney Australia School of Computer Science University of Technology Sydney Sydney Australia Data61 CSIRO Sydney Australia

ISBN: (纸本)9781665423991

Deep learning frameworks generally require sufficient training data to generalize well while fail to adapt on small or few-shot datasets. Meta-learning offers an effective means of tackling few-shot scenarios and has drawn increasing attention in recent years. Meta-optimization aims to learn a shared set of parameters across tasks for meta-learning while facing challenges in determining whether an initialization condition can be generalized to tasks with diverse distributions. In this regard, we propose a meta-gradient boosting framework that can fit diverse distributions based on a base learner (which learns shared information across tasks) and a series of gradient-boosted modules (which capture task-specific information). We evaluate the model on several few-shot learning benchmarks and demonstrate the effectiveness of our model in modulating task-specific meta-learned priors and handling diverse distributions.

关键词： Deep learning Adaptation models Image processing Neural networks Training data Boosting data mining

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：