检索结果-内蒙古大学图书馆

作者： Zhang, Baobing Li, Siguang Huang, Zhengwen Rahi, Babak H. Wang, Qicong Li, Maozhen Department of Electronic and Computer Engineering Brunel University London London United Kingdom The Key Laboratory of Embedded Systems and Service Computing Tongji University Shanghai China College of Electrical Engineering Binzhou University Binzhou China Department of Computer Science Xiamen University Xiamen China

Most existing tracking-by-detection approaches are affected by abrupt pedestrian pose changes, lighting conditions, scale changes, and real-time processing, which leads to issues such as detection errors and drifts. To deal with these issues, we present a novel multi-person tracking framework by introducing a new Gaussian Process Regression based observation model, which learns in a semi-supervised manner. The background information is taken into consideration to build the discriminative tracker, training samples are re-weighted appropriately to ease the impact of the potential sample misalignment and noisy during model updating. Unlabeled samples from the current frame provide rich information, which is used for enhancing the tracking inference. Experimental results show that the proposed approach outperforms a number of state-of-the-art methods on some benchmark datasets. © 2018 John Wiley & Sons, Ltd.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

Team of Bayesian optimization algorithms to solve task assignment problems in heterogeneous computing systems

Team of Bayesian optimization algorithms to solve task assig...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Jie Li JunQi Zhang Qi Kang ChangJun Jiang Ministry of Education China Key Laboratory of Embedded System and Service Computing Department of Computer Science and Technology Tongji University Shanghai Department of Control Science and Engineering Tongji University Shanghai China

ISBN: (纸本)9781479938414

A Bayesian optimization algorithm (BOA) belongs to estimation of distribution algorithms (EDAs). It is characterized by combining a Bayesian network and evolutionary algorithms to solve nearly decomposable optimization problems. BOA is less popularly applied to solve high dimensionality complex optimization problems. A key reason is that the cost of training all dimensions by BOA becomes expensive with the increase of problem dimensionality. Since data are relatively sparse in a high dimensional space, even though BOA can train all dimensions simultaneously, the interdependent relations between different dimensions are difficult to learn. Its search ability is thus significantly reduced. In this paper, we propose a team of Bayesian optimization algorithms (TBOA) to search and learn dimensionality. TBOA consists of multiple BOAs, in which each BOA corresponds to a dimension of the solution domain and it is responsible for the search of this dimension's value region. The proposed TBOA is used to solve the real problem of task assignment in heterogeneous computing systems. Extensive experiments demonstrate that the computational cost of the overall training in TBOA is decreased very significantly while keeping high solution accuracy.

关键词： Bayes methods Sociology Statistics Optimization Computational efficiency Joints Probability distribution

来源：评论

学校读者我要写书评

暂无评论

A Novel ICD Coding Method Based on Associated and Hierarchical Code Description Distillation

arXiv

引用

arXiv 2024年

作者： Zhang, Bin Wang, Junli Key Laboratory of Embedded System and Service Computing Tongji University Ministry of Education Shanghai201804 China Collaborative Innovation Center for Financial Network Security Tongji University Shanghai201804 China

ICD(International Classification of Diseases) coding involves assigning ICD codes to patients visit based on their medical notes. ICD coding is a challenging multilabel text classification problem due to noisy medical document inputs. Recent advancements in automated ICD coding have enhanced performance by integrating additional data and knowledge bases with the encoding of medical notes and codes. However, most of them ignore the code hierarchy, leading to improper code assignments. To address these problems, we propose a novel method based on associated and hierarchical code description distillation (AHDD) for better code representation learning and avoidance of improper code *** utilize the code description and the hierarchical structure inherent to the ICD codes. Therefore, in this paper, we leverage the code description and the hierarchical structure inherent to the ICD codes. The code description is also applied to aware the attention layer and output layer. Experimental results on the benchmark dataset show the superiority of the proposed method over several state-of-the-art baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Semantic enhanced deep learning for image classification

Semantic enhanced deep learning for image classification

引用

作者： Li, Siguang Li, Maozhen Jiang, Changjun The Key Laboratory of Embedded Systems and Service Computing Tongji University Shanghai China College of Electrical Engineering Binzhou University BinzhouShandong China Department of Electronic and Computer Engineering Brunel University London UxbridgeUB8 3PH United Kingdom

Extracting training data semantics mainly depends on manual annotation samples prepared in advance, and semantic mapping largely relies on the prior conditions in image classification. A majority of the data samples in reality are unlabeled data, which necessitates a more efficient way to extract image semantics in classification. Deep learning, as an advanced machine learning technique, has recently received significant attention from both the academia and industry. Deep learning has the potential to extract semantic features from images in an automated way to fill up the semantic gap. This paper presents 2 novel deep learning models (ie, stacked denoising auto-encoder and convolution deep Boltzmann machine). A stacked denoising auto-encoder builds on a stacked auto-encoder but uses a denoising auto-encoder to improve the learning quality. Convolution deep Boltzmann machine combines the convolutional neural network model with the deep Boltzmann machine. These 2 models are evaluated on CIFAR-10 and STL-10 datasets, respectively. Experimental results show that the proposed 2 models outperform the original models in terms of both precision and recall. Copyright © 2017 John Wiley & Sons, Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Routing Strategy for SDN Large Flow Based on Deep Reinforcement Learning

Routing Strategy for SDN Large Flow Based on Deep Reinforcem...

引用

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

作者： Yu Ke Junli Wang Chungang Yan Jiamin Yao Key Laboratory of Embedded System and Service Computing Collaborative Innovation Center for Financial Network Security (Tongji University) Ministry of Education National (Province-Ministry Joint) Tongji University Shanghai China

With the expansion of network scale, traditional routing strategies in Software-Defined Networking (SDN) have difficulty adapting to fast traffic variability. The large flow in the network occupies 80% of the network traffic. An unreasonable schedule of the large flow will lead to the emergence of bottleneck links and reduce the network performance. To solve the above problems, this paper proposes a different routing method, called Routing Strategy for SDN Large Flow Based on Deep Reinforcement Learning (RSDRL). Considering the links in the network that can carry large flow are limited, RSDRL can schedule large flow firstly and generate routing strategies adaptively. At the same time, in order to avoid the occurrence of congestion, RSDRL quantifies the degree of congestion in the network to implement routing. Experiments show that the proposed model has better Quality of service (QoS) performance under the test traffic, realizing a reasonable schedule of traffic.

关键词： Deep learning Training Knowledge engineering Schedules Adaptation models Reinforcement learning Quality of service

来源：评论

学校读者我要写书评

暂无评论

Extended and improved slicing technologies for Petri nets

引用

High Technology Letters 2013年第1期19卷 98-104页

作者： Yu, Wangyang Yan, Chungang Ding, Zhijun Fang, Xianwen Department of Computer Science and Technology Tongji University Shanghai 201804 China Key Lab. of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 China

Petri net is an important tool to model and analyze concurrent systems, but Petri net models are frequently large and complex, and difficult to understand and modify. Slicing is a technique to remove unnecessary parts with respect to a criterion for analyzing programs, and has been widely used in specification level for model reduction, but researches on slicing of Petri nets are still limited. According to the idea of program slicing, this paper extends slicing technologies of Petri nets to four kinds of slices, including backward static slice, backward dynamic slice, forward static slice and forward dynamic slice. Based on the structure properties, the algorithms of obtaining two kinds of static slice are constructed. Then, a new method of slicing backward dynamic slice is proposed based on local reachability graph which can locally reflect the dynamic properties of Petri nets. At last, forward dynamic slice can be obtained through the reachability marking graph under a special marking. The algorithms can be used to reduce the size of Petri net, which can provide the basic technical support for simplifying the complexity of formal verification and analysis. © by HIGH TECHNOLOGY LETTERS PRESS.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method

arXiv

引用

arXiv 2024年

作者： Lin, Jiayi Zhang, Chenyang Tong, Haibo Zhang, Dongyu Hong, Qingqing Hou, Bingxuan Wang, Junli Key Laboratory of Embedded System and Service Computing Tongji University Ministry of Education Shanghai201804 China Collaborative Innovation Center for Financial Network Security Tongji University Shanghai201804 China

Multi-Span Question Answering (MSQA) requires models to extract one or multiple answer spans from a given context to answer a question. Prior work mainly focuses on designing specific methods or applying heuristic strategies to encourage models to predict more correct predictions. However, these models are trained on gold answers and fail to consider the incorrect predictions. Through a statistical analysis, we observe that models with stronger abilities do not predict less incorrect predictions compared with other models. In this work, we propose Answering-Classifying-Correcting (ACC) framework, which employs a post-processing strategy to handle incorrect predictions. Specifically, the ACC framework first introduces a classifier to classify the predictions into three types and exclude "wrong predictions", then introduces a corrector to modify "partially correct predictions". Experiments on several MSQA datasets show that ACC framework significantly improves the Exact Match (EM) scores, and further analysis demostrates that ACC framework efficiently reduces the number of incorrect predictions, improving the quality of predictions.1 © 2024, CC BY-NC-ND.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Property analysis of composable web services

Telkomnika (Telecommunication Computing Electronics and Cont...

引用

Telkomnika (Telecommunication computing Electronics and Control) 2016年第2期14卷 734-740页

作者： Liu, Wei Wang, Lu Du, Yuyue Wang, Pin Yan, Chun State Key Laboratory of Mining Disaster Prevention and Control Shandong University of Science and Technology Qingdao China College of Information Science and Engineering Shandong University of Science Technology Qingdao China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

Web services are basic components constructing a flexible business process software. By composing multiple Web services, a complicated business process across organization and departments can be formed. This paper present a formal model of composable Web services: composed service process nets (CSPNs). Properties of Composable Web services are analyzed based on CSPNs. The relation between a CSPN and its corresponding Web service process subnets are discussed. The property analysis methods of CSPNs are come up with. A dynamic property of CSPNs can be determined based on static net structures by means of the proposed methods. © 2016 Universitas Ahmad Dahlan.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Modeling and monitoring of online shopping business processes based on system behavior patterns

引用

Journal of Computational Information systems 2013年第12期9卷 4691-4698页

作者： Yu, Wangyang Yan, Chungang Ding, Zhijun Zhong, Junzhu Department of Computer Science and Technology Tongji University Shanghai 201804 China Key Lab. of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 China

Online shopping integrating third-party payment platforms (TPPs) has rapidly developed recently. The integration leads to new security problems derived from complex interactions among Application Programming Interfaces (APIs), and the detection of such defects in application-level is costly and difficult. To deal with these security issues at the online stages, this paper presents a framework of modeling and monitoring online shopping business processes from the point of legal behavior patterns. We present Online Shopping Net (OSN) to model the normal business process, and make it as the legal behavior pattern used to monitor system behaviors. Then, a monitor based on OSN is constructed. The system behaviors beyond the legal behavior pattern would be alarmed and blocked. It is a novel attempt to guarantee the security of online shopping from the point of behaviors and online monitoring. Using the active defense tactics, we can effectively prevent the illegal behaviors of the users at application-level instead of constantly fixing bugs of applications. As a case study, we simulate an e-commerce site and a TPP, and the monitor can effectively prevent the malicious behaviors appearing recently. © 2013 by Binary Information Press.

关键词： Application programming interfaces (API)

来源：评论

学校读者我要写书评

暂无评论

A Dual-stage Attention Based SDN Traffic Prediction Method

A Dual-stage Attention Based SDN Traffic Prediction Method

引用

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

作者： Chenjing Gao Junli Wang Chungang Yan Key Laboratory of Embedded System and Service Computing (Tongji University) Ministry of Education National (Province-Ministry Joint) Collaborative Innovation Center for Financial Network Security Tongji University Shanghai China

Traffic matrix is the main research object of traffic prediction in software-defined networking. Accurate and timely traffic matrix prediction plays an important role in avoiding network congestion. While various methods have been proposed in previous studies to solve the SDN traffic prediction problem, few of them consider both inter- and intra-flow features. In this paper, we propose a dual-stage attention based Traffic Prediction method for the SDN traffic matrix prediction task. First, our method uses temporal pattern attention as the inter-flow attention mechanism before the encoding stage to realize adaptive feature extraction. Then, temporal attention is introduced as the intra-flow attention mechanism before the decoding stage to capture long-term temporal dependencies. Finally, we use the autoregressive module to handle the highly dynamic SDN traffic volume. Experimental results show that our proposed SDN traffic prediction method can capture more traffic features and improve the SDN traffic matrix prediction performance to some extent.

关键词： Network topology Time series analysis Prediction methods Machine learning Feature extraction Graph neural networks Encoding

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：