检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Xiao, Zhenyu Xia, Pengfei Xia, Xiang-Gen Beihang University Key Laboratory of Embedded System and Service Computing Tongji University University of Delaware

The potential of doubling the spectrum efficiency of full-duplex (FD) transmission motivates us to investigate FD millimeter-wave (FD-mmWave) communication. To realize FD transmission in the mmWave band, we first introduce possible antenna configurations for FD-mmWave transmission. It is shown that, different from the cases in micro-wave band FD communications, the configuration with separate Tx/Rx antenna arrays appears more flexible in self-interference (SI) suppression while it may increase some cost and area versus that with the same array. We then model the mmWave SI channel with separate Tx/Rx arrays, where a near-field propagation model is adopted for the line-of-sight (LOS) path, and it is found that the established LOS-SI channel with separate Tx/Rx arrays also shows spatial sparsity. Based on the SI channel, we further explore approaches to mitigate SI by signal processing, and we focus on a new cancellation approach in FD-mmWave communication, i.e., beamforming cancellation. Centered on the constant-amplitude (CA) constraint of the beamforming vectors, we propose several candidate solutions. Lastly, we consider an FD-mmWave multi-user scenario, and show that even if there are no FD users in an FD-mmWave cellular system, the FD benefit can still be exploited in the FD base station. Candidate solutions are also discussed to mitigate both SI and multi-user interference (MUI) simultaneously. Copyright © 2017, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Dynamic Time-Constrained Path Recommendation with User’s Preference

Dynamic Time-Constrained Path Recommendation with User’s Pr...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Yixi Wu Yaying Zhang Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9781665442084

Path recommendation is an essential application in people’s daily life. However, drivers’ experience hidden in their driving history and their personal preferences are less considered in path planning. In this paper we propose a dynamic time-constrained path recommendation method, utilizing the historical GPS trajectory information and user preferences. First, based on graph entropy, critical intersections are extracted from trajectory information to simplify the road network structure. Then the time-dependent mostly chosen path (TDMCP) is obtained by trajectories processing to determine the time-varying paths between critical intersections. Thus the original complex road network is abstracted as a search subnet. Finally we propose an improved dynamic A* search (IDAS) on the search sub-net to find the candidate paths satisfying the time-constraints, and further allow users to set personal preferences to select the final optimal path. The proposed method is validated on the real-world data set, and the result shows that the proposed method surpasses the competing ones especially on long distance path recommendation.

关键词： Roads Conferences Entropy Trajectory History Data mining Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Quasi-synchronization for delayed systems with parameter mismatches via aperiodically intermittent control

Quasi-synchronization for delayed systems with parameter mis...

引用

International Conference on systems and Informatics (ICSAI)

作者： Xiwei Liu Ping Li Yuan Xu Ying Liu Department of Computer Science and Technology Key Laboratory of Embedded System and Service Computing Shanghai China

ISBN: (纸本)9781479954599

Quasi-synchronization is an important type of synchronization because of the parameter mismatches in the real world, so we will investigate it for a delayed network, which is master-slave coupled. By applying the aperiodically and nonlinearly intermittent control on the network, and assuming the time delay is varying, we will present some useful criteria for exponential quasi-synchronization. The main difference of this paper with previous works is that the intermittent mode is aperiodic while that in previous works is periodic. Finally, simulations are also given to show its validity.

关键词： Synchronization Mathematical model Delay effects Numerical models Observers Equations Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Feedback-based Coarse Time-Granularity POI Recommendation and Itinerary Planning

Feedback-based Coarse Time-Granularity POI Recommendation an...

引用

Chinese Automation Congress (CAC)

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

ISBN: (纸本)9781665426480

For tourists, planning their own travel itinerary to a strange city is really challenging. Although there are many researches on Point of Interests (POIs) recommendation and itinerary planning, two problems occur in currently proposed recommendation algorithms. First, the time granularity of the algorithms is too fine. POI recommendation should be considered within a more coarse-grained time factor. For example, a visitor wouldn’t like to visit a water park in winter, although he appears to love such places. However, seldom researches have taken this into consideration. Second, most of the algorithms build their models based on the tourists’ trajectory, which means, they did not consider users’ feedback. In fact, quite a number of tourists do not like their travel experience and give negative feedbacks after their visits. In this situation, we shouldn’t recommend similar POIs to this user because he may not like such kind of scenic spots at all. To address these two problems, this paper proposes an algorithm called Feedback-based Coarse Time-Granularity POI Recommendation, which can extract information from comments and distinguish tourists’ attitudes towards the POIs they have visited. At the same time, the coarse-grained time factor is considered while making recommendations. In addition, an itinerary planning algorithm is proposed. Experiments show that our algorithm can reach SOTA.

关键词： Negative feedback Automation Urban areas Planning Trajectory Time factors Data mining

来源：评论

学校读者我要写书评

暂无评论

Edge-weight-Based link prediction in heterogeneous graph

Edge-weight-Based link prediction in heterogeneous graph

引用

IEEE International Conference on Networking, Sensing and Control

作者： Jie Zong Zhijun Ding The key laboratory of embedded system and service computing ministry of education TONGJI University Shanghai China

ISBN: (纸本)9781665472449

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.

关键词： Training Industries Semantics Predictive models Prediction algorithms Feature extraction 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

IEEE International Conference on Networking, Sensing and Control

作者： Yu Wang Zhi Jun Ding Key Laboratory of Embedded System and Service Computing Ministry of Education University of Tongji Shanghai China Key Laboratory of Embedded ystem nd Service Computing Ministry of Education University of Tongji Shanghai China

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.

关键词： Petri nets system recovery Firing Laboratories Educational institutions Analytical models Mathematical model

来源：评论

学校读者我要写书评

暂无评论

The preference relation and its application in the information system

The preference relation and its application in the informati...

引用

IEEE International Conference on Computer Science and Automation Engineering (CSAE)

作者： Zhao Mingqing Key Laboratory of Embedded System and Service Computing Ministry of Education University of Tongji Shanghai China

In order to strengthen the traditional information system's capacity of describing practical problems, preference relation is introduced into information system and the concepts of preference information system, preference decision table, and information utility function are offered in this paper. In addition, the existence theorem of information utility function and several applications of information utility function in knowledge acquisition are provided.

关键词： Information systems Knowledge acquisition Economics Clustering methods Transforms Information science Approximation methods

来源：评论

学校读者我要写书评

暂无评论

Quality assessment for color images with tucker decomposition

Quality assessment for color images with tucker decompositio...

引用

IEEE International Conference on Image Processing

作者： Cheng, Cheng Wang, Hanli Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

As an extension of the singular value decomposition based approaches, a novel metric based on Tucker decomposition for color image quality assessment is proposed in this paper. It extracts both the spacial and chromatic information of a color image with Tucker decomposition. As compared to most of the other existing quality metrics for color images, the key advantage of the proposed metric is that it treats the color image as a whole entity instead of an assembly of three independent visual channels, and thus the interrelation among the different visual channels is well involved. Experimental results on the LIVE Database Release 2 demonstrate that the proposed metric can generally achieve similar or better performance than other metrics.

关键词： Tensile stress Measurement Image color analysis Color Matrix decomposition Image quality Vectors

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Scalable Algorithm for the Traveling Salesman Problem

An Efficient and Scalable Algorithm for the Traveling Salesm...

引用

2014 IEEE 5th International Conference on Software Engineering and service Science

作者： Chen Ye Zhongcheng Yang Tianxing Yan Key Laboratory on Embedded System and Service Computing College of Electronics and Information EngineeringTongji University

This paper presents a genetic algorithm based on dynamic programming for solving large-scale instance of the Traveling Salesman Problem(TSP) to ***,an improved dynamic programming algorithm is described to deal with large-scale data,and then it is used as crossover and mutation operator in the genetic *** results show that this novel method with good stability can solve TSP with very-large-scale,effectively reduce the error rate,and improve the solution precision while keeping computational complexity relatively low.

关键词： traveling salesman problem genetic algorithm dynamic programming optimization

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Heterogeneous Credit Card Fraud Detection Model Based on Deep Reinforcement Training Subset Selection

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4026-4041页

作者： Zhu, Kun Zhang, Nana Ding, Weiping Jiang, Changjun the Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China Collaborative Innovation Center for Financial Network Security Tongji University Shanghai201804 China the School of Computer Science and Technology Donghua University Shanghai201620 China the School of Information Science and Technology Nantong University Nantong226019 China

Heterogeneous fraud detection is an important means of credit card security assurance, which can utilize historical transaction records in a source and target domain to build an effective fraud detection model. Nevertheless, large feature distribution differences between source and target transaction instances and the complex intrinsic structure hidden behind transaction data make it difficult for existing credit card fraud detection (CCFD) models to capture and transfer the most informative feature representations and seriously hinder detection performance. In this work, we propose a novel adaptive heterogeneous CCFD model named adaptive heterogeneous credit card fraud detection model based on deep reinforcement training subset selection (RTAHC) based on deep reinforcement training subset selection, which mainly contains two components: selection distribution generator (SDG) and transaction fraud detector (TFD, including feature extractor with an attention mechanism and classifier). The SDG can generate the selection probability distribution vector via the reinforcement reward mechanism, and then transaction instances in the source domain relevant to the target domain are selected. The feature extractor with an attention mechanism can learn the abstract deep semantic feature representations of selected source transaction instances and the target domain. The joint training of SDG and TFD can provide more real-time and accurate transaction feature representations to reduce the distribution discrepancy between the two domains. We verify the detection performance of RTAHC across a large real-world credit card transaction dataset and four public datasets. Experimental results demonstrate that the RTAHC model can exhibit competitive CCFD performance. Impact Statement—With the rise of artificial intelligence (AI)generated models, credit card fraud has become increasingly rampant, which also causes tens of billions of U.S. dollars in credit card losses worldwide every year

关键词： Hidden Markov models

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：