检索结果-内蒙古大学图书馆

19th IEEE International Conference on Networking, Sensing and Control, ICNSC 2022

作者： Zong, Jie Ding, Zhijun The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9781665472432

Link prediction is to predict whether there is a link between two nodes in the graph, it is a very important application and plays a great role in various industries. In recent years, with the development of graph neural network technology, many algorithms make effort to study the expression of each node from the original graph data and use them to infer new links. However, most of the existing algorithms have a common problem when facing heterogeneous graphs, which is, they do not consider the weight of edges in graphs. Instead, they put all their energies into computing node features. Although a few algorithms such as RGCN are trying to take the influence of different link types into account while extracting node features, these implicit feature extractions do not start from the global information, but just calculate independently for each node. In other words, in these algorithms, even the same type of links will be abstracted into different features on different nodes. This is obviously inconsistent with reality. On the same map, the feature of the same link should be relatively fixed and should not be changed just because of different positions. In addition, when the current graph neural network algorithm is applied to link prediction, the link type to be predicted must be specified in advance, which makes the algorithm extremely inflexible. In order to solve these problems, we propose an edge weight calculation algorithm that extracts the edge feature from the whole graph. We also propose the edge-weight-based link prediction algorithm. By introducing edge weight into the MLP, there is no need to specify the target link type at the beginning of model training. It improves both the performance and efficiency of the link prediction model. Experiments on two datasets show that this edge-weight-based link prediction algorithm performs better than current algorithms and reaches SOTA. © 2022 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Will the fibers of the future be considered fibers?

引用

National Science Review 2024年第10期11卷 15-17页

作者： Dewen Xu Ya Liu Hailiang Wang Wei Yan Changjun Jiang Meifang Zhu State Key Laboratory for Modification of Chemical Fibers and Polymer Materials College of Materials Science and Engineering Donghua University Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Department of Computer Science and Technology Tongji University

Fiber materials are key materials that have changed human history and promoted the progress of human civilization. In ancient times, humans used feathers and animal skins for clothing, and later they widely employed natural fibers such as cotton, hemp, silk and wool to make fabrics(Fig. 1a). Chinese ancestors had mastered the art of natural fiber weaving as early as the Neolithic *** thousand years ago, people were already familiar with and adept at techniques for spinning natural fibers [1].

关键词： future will considered fibers

来源：评论

学校读者我要写书评

暂无评论

Adaptive Random Forest with Dynamic Detectors for Evolving Data Stream Classification 23

Adaptive Random Forest with Dynamic Detectors for Evolving D...

引用

9th International Conference on computing and Artificial Intelligence, ICCAI 2023

作者： Jin, Xuancheng Zhang, Yaying Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9781450399029

Evolving data streams containing concept drift breaks the assumption that data are independent and identically distributed (IID) in traditional machine learning models. A series of ensemble-based models have been adapted to data stream learning tasks due to the abilities of dynamic partially update and cooperate with drift detection methods. Adaptive Random Forests (ARF), one of the state-of-the-art in the stream setting, encounters high resource requirements in both efficiency and memory like all ensemble methods. We are committed to reducing running cost without compromising ARF’s performance. In this paper, we propose the Adaptive Random Forest with Dynamic Detectors (ARFDD) which utilizes diversity measurement to combine homogeneous detectors and split heterogeneous ones accordingly, leads to lower computing costs and thus speed up in applications. Experiments on all 8 synthetic and 4 real datasets show a great CPU-time thrift while avoiding performance degradation. © 2023 Copyright held by the owner/author(s).

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Research on Behavior Element Decision of Cloud Edge Collaboration Capability Based on 5g Automatic Driving Scene 5

Research on Behavior Element Decision of Cloud Edge Collabor...

引用

5th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2021

作者： Yan, Chungang Sheng, Shuo Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9781665415989

In order to meet the cloud side requirements of various traffic business scenarios, the construction of traffic cloud side collaboration platform realizes the collaboration and unification of various business resources and data on both sides of the cloud side, and the cloud side integration realizes the real-time and efficient "vehicle road cloud side"collaboration of traffic. In order to quickly meet the needs of various scenarios and provide customized cloud edge capability services, by drawing on the experience and technology R D capabilities of Companies in the industry, it helps to shorten the overall development period of the platform, reduce costs and technical risks, and quickly form product capabilities. Based on the cloud edge collaboration capability, the super edge node collects structured and unstructured data in real time, uses the edge computing power to label, filter and design thresholds, so as to detect and filter the scene behavior elements in 5g + traffic scenarios, further clarify the actor's data, gather it to the cloud for research and judgment, and improve the global decision-making ability of the cloud, Improve the real-time flow of dynamic traffic element resources. © 2021 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Genetic Fuzzy + PI Path Tracking Control of a Nonholonomic Mobile Robot

引用

电子学报(英文版) 2011年第1期20卷 31-34页

作者： CAO Zhengcai ZHAO Yingtao WU Qidi College of Information Science and Technology Beijing University of Chemical Technology Beijing China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

A mobile robot is one of the well-known nonholonomic systems. The genetic fuzzy + PI path track- ing control applied to a mobile robot is presented. The pro- posed controller composes of two fuzzy + PI controllers which are employed to control the angular velocity to- gether, and one fuzzy + PI controller that is utilized to adjust the speed of mobile robot solely. Moreover, the fuzzy controller is designed to track reference path in ap- proaching phase and PI controller is operated to diminish the tracking error in stable phase. In order to obtain bet- ter tracking performance, Genetic algorithm (GA) is used to optimize controller parameters. Finally, computer sim- ulation results are given to illustrate the effectiveness of the proposed control scheme.

关键词：模糊PI控制器移动机器人机器人控制非完整系统路径跟踪遗传算法模糊控制器控制器参数

来源：评论

学校读者我要写书评

暂无评论

Local-directed network coding in vehicular ad-hoc networks

Local-directed network coding in vehicular ad-hoc networks

引用

18th International Symposium on Intelligent Signal Processing and Communication systems, ISPACS 2010

作者： Haojie, Luo Zhang, Dongdong Ye, Chen Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China

ISBN: (纸本)9781424473717

In this paper, we proposed a novel network coding method called local-directed network coding to improve the throughput of the vehicular ad-hoc network. Different from other vehicular network coding methods, we consider the direction of packet transmission. In detail, the intermediate node selects one main packet and some sub-packets from forwards and backwards sending queues, and then encodes these packets into one packet to broadcast. Simulation results show that our approach can efficiently improve the throughput of application layer in vehicular networks. © 2010 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Traffic flow prediction model based on deep belief network and genetic algorithm

Traffic flow prediction model based on deep belief network a...

引用

作者： Zhang, Yaying Huang, Guan Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai200092 China

Traffic flow prediction plays an indispensable role in the intelligent transportation system. The effectiveness of traffic control and management relies heavily on the prediction accuracy. The authors propose a model based on deep belief networks (DBNs) to predict the traffic flow. Moreover, they use Fletcher-Reeves conjugate gradient algorithm to optimise the fine-tuning of model's parameters. Since the traffic flow has various features at different times such as weekday, weekend, daytime and nighttime, the hyper-parameters of the model should adapt to the time. Therefore, they employ the genetic algorithm to find the optimal hyper-parameters of DBN models for different times. The dataset from Caltrans Performance Measurement system was used to evaluate the performance of their models. The experimental results demonstrate that the proposed model achieved better performance in different times. © The Institution of Engineering and Technology 2018.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-View Metrics Enhanced Heterogeneous Graph Neural Network for Extractive Summarization

Multi-View Metrics Enhanced Heterogeneous Graph Neural Netwo...

引用

2021 China Automation Congress, CAC 2021

作者： Zhang, Chaobo Wang, Junli Qi, Hongda Yan, Chungang Jiang, Changjun Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai201804 China

ISBN: (纸本)9781665426473

Currently, many works regarded extractive summarization as a binary classification problem. However, the metric of the summary classification is always too singular and cannot fully utilize sentence features. To address this issue, we propose a multi-view metrics enhanced heterogeneous graph neural network for extractive summarization (MHGS). Firstly, the text is modeled as a heterogeneous graph, which contains two types of nodes, namely, words and sentences. Secondly, in the graph update layer, cross-sentence relationships and long-distance associations are obtained through the indirect connection of words and the direct connection between sentences. Then, we design multi-view metrics including relevance, redundancy, new information, and Rouge to help the model improve the quality of the summary. Finally, to evaluate the effectiveness of the method, some experiments are conducted on the CNN & DailyMail dataset. The experimental results show a generally higher performance of MHGS compared with related methods. © 2021 IEEE

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis for one-place unbounded Petri nets based on modified reachability trees

Analysis for one-place unbounded Petri nets based on modifie...

引用

2012 9th IEEE International Conference on Networking, Sensing and Control, ICNSC 2012

作者： Wang, Yu Ding, ZhiJun Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China

ISBN: (纸本)9781467303880

Analysis approaches of reachability decision is fundamental to Petri nets theory;however, the relevant research work in the past cannot always guarantee the correctness of analysis conclusions. This paper firstly reveals the root cause of wrong conclusions, which are drawn in analysis for deadlock of Petri nets based on modified reachability trees (MRT), and then proposes the rectified calculation of the next-state function and some corresponding definitions, which guarantee MRT's usefulness and correctness in analyzing reachability and deadlock of one-place unbounded Petri nets. Finally, a necessary and sufficient condition of MRT's reachability and the theoretical proof are presented. Examples are given to illustrate the method. © 2012 IEEE.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Vehicle queue length measurement based on a modified local variance and LBP

Vehicle queue length measurement based on a modified local v...

引用

9th International Conference on Intelligent computing, ICIC 2013

作者： Chai, Qin Cheng, Cheng Liu, Chunmei Chen, Hongzhong Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University 201804 Shanghai China

ISBN: (纸本)9783642396779

The real-time traffic parameters are necessary to dynamic traffic light control at intersection due to the serious traffic congestion. In this paper, we describe an approach for the real-time vehicle queue length measurement in a video-based traffic monitoring system. It is built on the property of a modified local variance in video frames, which does not rely on any sort of motion detection. In addition, a shadow removal approach is also presented with a simplified LBP as well as this local variance. Experimental results show that the proposed approach can highly improve the performance of the queue length measurement in real time, and it can be efficiently applied in a variety of traffic scenes. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Local binary pattern

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：