检索结果-内蒙古大学图书馆

IEEE advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Qiming Du Nan Li Shudan Yang Daozhu Sun Wenfu Liu State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

As an efficient information filtering tool, the recommendation system can help users obtain valuable information quickly and efficiently while effectively alleviating the information load problem. However, the classic collaborative filtering algorithm has data sparsity problems in practical applications, which affects the accuracy of recommendation. To solve this problem, this paper took movie recommendation as the research object and proposed a hybrid recommendation algorithm named K-GBDT which combined KNN and gradient boosting decision tree. Firstly, it used KNN to obtain the similar information of the target user and item for preliminary prediction. At the same time, it mined users' basic information features and potential features of users and items from the original data. Then, it tried to adopt XGBoost, LightGBM and CatBoost algorithm which were proposed base the idea of gradient boosting decision tree to build regression model. Finally, the target user's rating for the movie was predicted with the trained model, and the recommendation list was generated based on the predicted results. Compared with some classic recommendation algorithms such as NMF, Slope One, Co-Clustering and etc. Based on MovieLens datasets, results show that the mean absolute error and root mean square error of this algorithm are both low, and its recommendation accuracy is higher.

关键词： Training Distributed databases Prediction algorithms Boosting Feature extraction Motion pictures Data models

来源：评论

学校读者我要写书评

暂无评论

An overview on the designs of distributed observers in LTI multi-agent systems

引用

Science China(Technological Sciences) 2021年第11期64卷 2337-2346页

作者： PEI YingQing GU HaiBo LIU KeXin LU JinHu Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China School of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain ComputingBeihang UniversityBeijing 100191China

With the rapid development of information technologies and cloud computing, sensor networks play an increasingly important role in our society. Over the past few decades, distributed observer theory has attracted unprecedented attention due to its wide potential applications in different areas. Meanwhile, various approaches and algorithms have been proposed and investigated. The design of distributed observers is one of the frontier topics of system and control research, which has the significant theoretical values and broad application prospects. This paper attempts to review the representative models and the corresponding approaches for distributed observer design in linear time-invariant(LTI) systems. Firstly, the research backgrounds and main advances of distributed observer designs are briefly reviewed. Then, recent results of distributed observer designs for discrete-time and continuous-time LTI multi-agent systems(MASs) are introduced in detail, respectively. Finally, the prospects and the future work directions of the design of distributed observers are put forward. The main purpose of this paper is to promote the emerging topic on the designs of distributed observers, with focuses on the interdisciplinary interest from technological sciences.

关键词： multi-agent system linear time-invarient system distributed observer consensus

来源：评论

学校读者我要写书评

暂无评论

Research on Security Protocol Analysis Tool SmartVerif

Research on Security Protocol Analysis Tool SmartVerif

引用

2021 International Conference on Computer Technology, Information engineering and Electron Materials, CTIEEM 2021

作者： Lu, Siqi Han, Qingdi Miao, Xuyang Liu, Yubo State Key Laboratory of Mathematical Engineering and Advanced Computing Henan Zhengzhou450000 China Henan Key Laboratory of Network Cryptography Technology Henan Zhengzhou450000 China Department of Information Science and Engineering Ocean University of China Shandong Qingdao266100 China

Security protocols have been designed to protect the security of the network. However, many security protocols cannot guarantee absolute security in real applications. Therefore, security tests of the network protocol become particularly important. In this paper, firstly, we introduce SmartVerif, which is the first formal analysis tool to automatically verify the security of protocols through dynamic strategies. And then, we use SmartVerif to verify the pseudo-randomness of the encapsulated key of the Two-Pass AKE protocol, which was proposed by Liu's in ASIACRYPT in 2020. Finally, we summary our work and show some limitations of SmartVerif. At the same time, we also point out the direction for future improvement of SmartVerif. © Content from this work may be used under the terms of the Creative Commons Attribution 3.0 Licence.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Progressive Pretext Task Learning for Human Trajectory Prediction

arXiv

引用

arXiv 2024年

作者： Lin, Xiaotong Liang, Tianming Lai, Jianhuang Hu, Jian-Fang School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Human trajectory prediction is a practical task of predicting the future positions of pedestrians on the road, which typically covers all temporal ranges from short-term to long-term within a trajectory. However, existing works attempt to address the entire trajectory prediction with a singular, uniform training paradigm, neglecting the distinction between short-term and long-term dynamics in human trajectories. To overcome this limitation, we introduce a novel Progressive Pretext Task learning (PPT) framework, which progressively enhances the model's capacity of capturing short-term dynamics and long-term dependencies for the final entire trajectory prediction. Specifically, we elaborately design three stages of training tasks in the PPT framework. In the first stage, the model learns to comprehend the short-term dynamics through a stepwise next-position prediction task. In the second stage, the model is further enhanced to understand long-term dependencies through a destination prediction task. In the final stage, the model aims to address the entire future trajectory task by taking full advantage of the knowledge from previous stages. To alleviate the knowledge forgetting, we further apply a cross-task knowledge distillation. Additionally, we design a Transformer-based trajectory predictor, which is able to achieve highly efficient two-step reasoning by integrating a destination-driven prediction strategy and a group of learnable prompt embeddings. Extensive experiments on popular benchmarks have demonstrated that our proposed approach achieves state-of-the-art performance with high efficiency. Code is available at https://***/iSEE-laboratory/PPT. Copyright © 2024, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Differentiable Gated Autoencoders for Unsupervised Feature Selection

SSRN

引用

SSRN 2024年

作者： Chen, Zebin Bian, Jintang Qiao, Bo Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Unsupervised feature selection (UFS) aims to identify a subset of the most informative features from high-dimensional data without labels. However, most existing UFS methods cannot adequately capture the intricate nonlinear relationships present in high-dimensional data, limiting their ability to obtain meaningful features. In this letter, we propose a novel UFS model that leverages the autoencoder with a differentiable gating function to address this limitation. Our model optimizes a bi-level loss function to automatically select a subset of informative and stable features by capturing the nonlinear interactions between features. Furthermore, we leverage the continuous relaxation of the Bernoulli distribution to parameterize stochastic gates, thereby enabling the learning of a relaxed model through a low-variance gradient estimator. The proposed model does not necessitate prior knowledge or domain-specific tuning, making it a versatile and widely applicable method. Extensive experiments on 13 benchmark datasets demonstrate the effectiveness and superiority of the proposed method. © 2024, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Dendritic integration inspired artificial neural networks capture data correlation 24

Dendritic integration inspired artificial neural networks ca...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Chongming Liu Jingyang Ma Songting Li Douglas Zhou School of Mathematical Sciences and Institute of Natural Sciences Shanghai Jiao Tong University Shanghai China School of Mathematical Sciences and Institute of Natural Sciences and Ministry of Education Key Laboratory of Scientific and Engineering Computing Shanghai Jiao Tong University Shanghai China School of Mathematical Sciences and Institute of Natural Sciences and Ministry of Education Key Laboratory of Scientific and Engineering Computing and Shanghai Frontier Science Center of Modern Analysis Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798331314385

Incorporating biological neuronal properties into Artificial Neural Networks (ANNs) to enhance computational capabilities is under active investigation in the field of deep learning. Inspired by recent findings indicating that dendrites adhere to quadratic integration rule for synaptic inputs, this study explores the computational benefits of quadratic neurons. We theoretically demonstrate that quadratic neurons inherently capture correlation within structured data, a feature that grants them superior generalization abilities over traditional neurons. This is substantiated by few-shot learning experiments. Furthermore, we integrate the quadratic rule into Convolutional Neural Networks (CNNs) using a biologically plausible approach, resulting in innovative architectures—Dendritic integration inspired CNNs (Dit-CNNs). Our Dit-CNNs compete favorably with state-of-the-art models across multiple classification benchmarks, e.g., ImageNet-1K, while retaining the simplicity and efficiency of traditional CNNs. All source code are available at https://***/liuchongming1999/Dendritic-integration-inspired-CNN-NeurIPS-2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding

Siamese Learning with Joint Alignment and Regression for Wea...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chaolei Tan Jianhuang Lai Wei-Shi Zheng Jian-Fang Hu School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal or-der from an untrimmed video. However, existing VPG approaches are heavily reliant on a considerable number of temporal labels that are laborious and time-consuming to acquire. In this work, we introduce and explore Weakly-Supervised Video Paragraph Grounding (WSVPG) to elim-inate the need of temporal annotations. Different from pre-vious weakly-supervised grounding frameworks based on multiple instance learning or reconstruction learning for two-stage candidate ranking, we propose a novel siamese learning framework that jointly learns the cross-modal feature alignment and temporal coordinate regression without timestamp labels to achieve concise one-stage localization for WSVPG. Specifically, we devise a Siamese Grounding TRansformer (SiamGTR) consisting of two weight-sharing branches for learning complementary supervision. An Aug-mentation Branch is utilized for directly regressing the tem-poral boundaries of a complete paragraph within a pseudo video, and an Inference Branch is designed to capture the order-guided feature correspondence for localizing multi-ple sentences in a normal video. We demonstrate by exten-sive experiments that our paradigm has superior practica-bility and flexibility to achieve efficient weakly-supervised or semi-supervised learning, outperforming state-of-the-art methods trained with the same or stronger supervision.

关键词： Location awareness Computer vision Grounding Annotations Semantics Semisupervised learning Transformers

来源：评论

学校读者我要写书评

暂无评论

Programming Logic Modeling and Cross-Program Defect Detection Method for Object-Oriented Code

引用

Computers, Materials & Continua 2020年第7期64卷 273-295页

作者： Yan Liu Wenyuan Fang Qiang Wei Yuan Zhao Liang Wang State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Strategic Support Force Information Engineering UniversityZhengzhou450001China The School of Computing Newcastle UniversityNewcastle upon TyneNE45TGUK

Code defects can lead to software vulnerability and even produce vulnerability *** research shows that the code detection technology with text analysis can judge whether object-oriented code files are defective to some ***,these detection techniques are mainly based on text features and have weak detection capabilities across *** with the uncertainty of the code and text caused by the developer’s personalization,the programming language has a stricter logical specification,which reflects the rules and requirements of the language itself and the developer’s potential way of *** article replaces text analysis with programming logic modeling,breaks through the limitation of code text analysis solely relying on the probability of sentence/word occurrence in the code,and proposes an object-oriented language programming logic construction method based on method constraint relationships,selecting features through hypothesis testing ideas,and construct support vector machine classifier to detect class files with defects and reduce the impact of personalized programming on detection *** the experiment,some representative Android applications were selected to test and compare the proposed *** terms of the accuracy of code defect detection,through cross validation,the proposed method and the existing leading methods all reach an average of more than 90%.In the aspect of cross program detection,the method proposed in this paper is superior to the other two leading methods in accuracy,recall and F1 value.

关键词： Method constraint relationship programming logic code defect hypothesis test

来源：评论

学校读者我要写书评

暂无评论

Circular Decomposition and Cross-Modal Recombination for Multimodal Sentiment Analysis

Circular Decomposition and Cross-Modal Recombination for Mul...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Haijian Liang Weicheng Xie Xilin He Siyang Song Linlin Shen School of Computer Science & Software Engineering Computer Vision Institue Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University School of Computing and Mathematical Sciences University of Leicester National Engineering Laboratory for Big Data System Computing Technology Shenzhen University

Multimodal Sentiment Analysis is a burgeoning research area, leveraging various modalities to predict the sentiment score. Nevertheless, previous studies have disregarded the impact of noise interference on specific modal sentiments during video recording, thereby compromising the accuracy of sentiment prediction. In this paper, we propose the Guided Circular Decomposition and Cross-Modal Recombination (GCD-CMR) model, which aims to eliminate contaminated sentiment features in a fine-grained way. To achieve this, we utilize tailored global information specific to each modality to guide the circular decomposing process in the GCD module, to produce a set of sentiment prototypes. Subsequently, in the CMR module, we align cross-modal sentiment prototypes and remove the contaminated prototypes for recombination. Experimental results on two publicly available datasets demonstrate that our model surpasses state-of-the-art models, confirming the effectiveness of our proposed method. We release the code at: https://***/nianhua20/GCD-CMR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning a Coordinated Network for Detail-Refinement Multiexposure Image Fusion

引用

IEEE Transactions on Circuits and Systems for Video Technology 2023年第2期33卷 713-727页

作者： Li, Jiawei Liu, Jinyuan Zhou, Shihua Zhang, Qiang Kasabov, Nikola K. Ministry of Education School of Software Engineering Dalian University Key Laboratory of Advanced Design and Intelligent Computing Dalian116622 China Dalian University of Technology School of Software Technology Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1010 New Zealand Ulster University Intelligent Systems Research Center LondonderryBT52 1SA United Kingdom

Nowadays, deep learning has made rapid progress in the field of multi-exposure image fusion. However, it is still challenging to extract available features while retaining texture details and color. To address this difficult issue, in this paper, we propose a coordinated learning network for detail-refinement in an end-to-end manner. Firstly, we obtain shallow feature maps from extreme over/under-exposed source images by a collaborative extraction module. Secondly, smooth attention weight maps are generated under the guidance of a self-attention module, which can draw a global connection to correlate patches in different locations. With the cooperation of the two aforementioned used modules, our proposed network can obtain a coarse fused image. Moreover, by assisting with an edge revision module, edge details of fused results are refined and noise is suppressed effectively. We conduct subjective qualitative and objective quantitative comparisons between the proposed method and twelve state-of-the-art methods on two available public datasets, respectively. The results show that our fused images significantly outperform others in visual effects and evaluation metrics. In addition, we also perform ablation experiments to verify the function and effectiveness of each module in our proposed method. The source code can be achieved at https://***/lok-18/LCNDR. © 1991-2012 IEEE.

关键词： Extraction

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：