检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Cheng Zhu, Hangyu Lin, Yuhang Jiang, Changjun Department of Computer Science and Technology Tongji University Shanghai201804 China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China

Efforts toward a comprehensive description of behavior have indeed facilitated the development of representation-based approaches that utilize deep learning to capture behavioral information. As behavior complexity increases, the expressive power of these models reaches a bottleneck. We coin the term "behavioral molecular structure" and propose a new model called the Behavioral Molecular Structure (BMS). The model characterizes behaviors at the atomic level, analogizes behavioral attributes to atoms, and concretizes interrelations at the granularity of atoms using graphs. Here, we design three different downstream tasks to test the performance of the BMS model on public datasets. Additionally, we provide a preliminary theoretical analysis demonstrating that the BMS can offer effective expressiveness for complex behaviors. Copyright © 2023, The Authors. All rights reserved.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

A Privacy Preserving Algorithm Based on R-constrained Dummy Trajectory in Mobile Social Network

引用

Procedia Computer Science 2018年 129卷 420-425页

作者： Lina Ni Yanfeng Yuan Xiao Wang Jiguo Yu Jinquan Zhang College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China School of Information Science and Engineering Qufu Normal University Shandong China

Recently the research of location privacy preserving has become a hot spot. Location privacy preserving involves not only a single location privacy but also the trajectory privacy where the mobile users in different locations publish the consecutive query requests. In this paper, we consider the problem of trajectory privacy preserving in MSN. Particularly, we propose privacy preserving algorithms based on R-constraint dummy trajectory (RcDT). By constraining the generating range R of the dummy positions, the generated dummy positions are within a certain range near the real locations. Furthermore, the dummy trajectories which have higher similarity to the real trajectories are generated via constraining both the single location exposure risk and the trajectory exposure risk.

关键词： Privacy preserving mobile social network trajectory privacy location-based service R-constrained dummy trajectory

来源：评论

学校读者我要写书评

暂无评论

Covariance free incremental principal component analysis with exact mean update

引用

Journal of Computational Information systems 2013年第16期9卷 6703-6710页

作者： Zeng, Xueqiang Li, Guozheng The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China Computer Center Nanchang University Nanchang 330029 China Department of Control Science and Engineering Tongji University Shanghai 201804 China

Incremental feature extraction is an essential data preprocessing technique for large-scale and streaming data mining. Among various covariance matrix-free Incremental Principal Component Analysis (IPCA) methods, Candid Covariance-free Incremental Principal Component Analysis (CCIPCA) is a state-of-the art algorithm. Since the training samples are required to be centred, CCIPCA applies an approximate centric alignment on the input data, where only the current sample is correctly centred and all historical data are not updated properly. In this paper, we propose a novel centred incremental principal component analysis algorithm with exact historical mean update, where not only the current sample is centred, but also all historical data are updated by the current mean correctly. Compared to CCIPCA, the proposed method converges more quickly, and the performance improvement is especially obvious when the data's inherent covariance is not stable. The experiments on real streaming dataset show that the proposed method is much superior to CCIPCA in convergence speed. © 2013 Binary Information Press.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A Transformation Algorithm for Optimal Admissible Generalized Mutual Exclusion Constraints on Petri Nets with Uncontrollable Transitions

A Transformation Algorithm for Optimal Admissible Generalize...

引用

2011 IEEE International Conference on Robotics and Automation(2011年IEEE世界机器人与自动化大会 ICRA 2011)

作者： ShouGuang Wang ChengYing Wang MengChu Zhou College of Information & Electronic Engineer ngineering ing Zhe Zhejiang Gongshang UniversityHangzh College of Information & Electronic Engineer ngineering ing Zhejiang Gongshang Univ UniversityHangz The MoE Key Laboratory of Embedded System and Service Computing Tongji UniversityShanghai 200092Ch

For a class of Petri nets whose uncontrollable influence subnets are forward synchronization and backward conflict free (FSBCF) nets, this work studies their structure and properties and proposes an algorithm to transform a given generalized mutual exclusion constraint (GMEC) into an optimal admissible one. Compared with the path-based constraint transformation approaches, the proposed method has much higher computational efficiency. An example is used to illustrate the application of the proposed method.

关键词： Automated manufacturing systems discrete event systems forbidden state problem mutual exclusion Petri nets supervisory control

来源：评论

学校读者我要写书评

暂无评论

Improved asymptotic multicast throughput for random extended networks

引用

Computer Communications 2010年第18期33卷 2195-2202页

作者： Cheng Wang Changjun Jiang Xiang-Yang Li Jiujun Cheng Department of Computer Science and Technology Tongji University Shanghai China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China Department of Computer Science Illinois Institute of Technology Chicago IL 60616 USA

We study the asymptotic throughput for random extended networks , where n ad hoc nodes are randomly deployed in a square region R ( n ) = 0 , n 2 . We directly consider the multicast throughput to unify the unicast and broadcast throughput, and design a new multicast scheme under the generalized physical model based on the so-called secondary highways system . Taking account of all possible cases of n s = ω (1) and 1 ⩽ n d ⩽ n − 1, we derive the achievable multicast throughput, where n s and n d denote the number of sessions and the number of destinations of each session. We prove that for some cases in terms of n s and n d , our scheme achieves better throughput than the existing schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Beamforming for Downlink Multi-Cell systems: A Bilevel Optimization Perspective

arXiv

引用

arXiv 2024年

作者： Chen, Xingdi Xiong, Yu Yang, Kai Department of Computer Science and Technology Tongji University China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China Shanghai Research Institute for Intelligent Autonomous Systems China

Utilization of inter-base station cooperation for information processing has shown great potential in enhancing the overall quality of communication services (QoS) in wireless communication networks. Nevertheless, such cooperations require the knowledge of channel state information (CSI) at base stations (BSs), which is assumed to be perfectly known. However, CSI errors are inevitable in practice which necessitates beamforming techniques that can achieve robust performance in the presence of channel estimation errors. Existing approaches relax the robust beamforming design problems into semidefinite programming (SDP), which can only achieve a solution that is far from being optimal. To this end, this paper views robust beamforming design problems from a bilevel optimization perspective. In particular, we focus on maximizing the worst-case weighted sum-rate (WSR) in the downlink multi-cell multi-user multiple-input single-output (MISO) system considering bounded CSI errors. We first reformulate this problem into a bilevel optimization problem and then develop an efficient algorithm based on the cutting plane method. A distributed optimization algorithm has also been developed to facilitate the parallel processing in practical settings. Numerical results are provided to confirm the effectiveness of the proposed algorithm in terms of performance and complexity, particularly in the presence of CSI uncertainties. Copyright © 2024, The Authors. All rights reserved.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

LAMPT: LAbel Mask-Predicted Transformer for Extreme Multi-label Text Classification

LAMPT: LAbel Mask-Predicted Transformer for Extreme Multi-la...

引用

IEEE International Conference on Big Data

作者： Yifan Xu Minghao Zhu 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

ISBN: (纸本)9781665480468

Extreme Multi-label text Classification ( XMC) is a task of recalling the most relevant labels for each given text from an extremely large-scale label set. It is emphasized that XMC is a more complex classification task because there are two main problems: large space of labels and the labels in XMC tasks tend to be correlated. Existing methods attempt to model label correlations by viewing the XMC task as a sequence generation problem however they still suffer from (1) using the slow serial decoding strategy where labels are predicted one-by-one. (2) needing to compare a mass of label ordering strategies in the decoding stage to achieve satisfied accuracy. In this work, we propose LAbel Mask-Predicted Transformer (LAMPT) to address the both issues, which is a novel non-autoregressive generation model that (1) enriches the input raw text representation with the additional label features by fully exploiting the label dependencies, (2) allows for efficient parallel decoding thanks to its non-autoregressive decoding formulation and mask-prediced training strategy. Experimental results demonstrate that single model performance is substantially enhanced by LAMPT. On a Wiki dataset with thirty-one thousand labels, LAMPT-XLNet accuracy has gained 1.6% relative improvement on P@3 over the LightXML-XLNet. Also, the P@1 of ensemble LAMPT is 90.00%, a significant i mprovement over the state-of-the-art ensemble LightXML (transformer-based) and AttentionXML (LSTM-based), which achieve 89.45% and 87.47%, respectively.

关键词： Training Correlation Text categorization Information services Big Data Predictive models Transformers

来源：评论

学校读者我要写书评

暂无评论

Two-Dimensional Reverse Time Migration for Multi-Input Multi-Output system by Shot Correlation Method with Noise Effect

Two-Dimensional Reverse Time Migration for Multi-Input Multi...

引用

IEEE International Conference on Microwaves, Communications, Antennas and Electronic systems, COMCAS

作者： Huan Wang Yuxian Zhang Mei Song Tong Zhixiang Huang Naixing Feng School of Electronic and Information Engineering Anhui University Hefei Anhui China The Key Laboratory of Embedded System and Service Computing of the Ministry of Education College of Electronics and Information Engineering Tongji University Shanghai China

ISBN: (数字)9798350348187

ISBN: (纸本)9798350348194

In this paper, we propose a shot correlation reverse time migration (SC-RTM) method for multiple-input-multiple-output (MIMO) ground penetrating radar (GPR) imaging to improve image contrast. In GPR applications, noise is unavoidable in radar echo signals and can cause artifacts in the subsurface reconstructed image. Since in general the correlation among noise signals is weaker than that in target signals, a shot correlation image operator is proposed to integrate all shot images and arrive at the final reconstructed image with artifacts suppression and resolution improvement. In numerical experiments, to test the performance of artifacts suppression, we add different noise levels in the synthetic GPR data. It is shown that the noise is effectively suppressed and the contrast between targets and artifacts is improved in reconstructed images of the SC-RTM method by more than 15 dB. The measured MIMO GPR echo signals with significant noises are successfully processed by the SC-RTM method to yield high contrast subsurface images.

关键词： Microwave antennas Correlation Ground penetrating radar Noise Radar imaging Radar antennas Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Automated web service composition supporting conditional branch structures

引用

Enterprise Information systems 2014年第1期8卷 121-146页

作者： Wang, Pengwei Ding, Zhijun zhijun_ding@*** Jiang, Changjun Zhou, Mengchu Department of Computer Science and Technology Tongji University Shanghai 201804 China Key Laboratory of “Embedded System and Service Computing” Ministry of Education Shanghai 201804 China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ 07102 USA

The creation of value-added services by automatic composition of existing ones is gaining a significant momentum as the potential silver bullet in service-oriented architecture. However, service composition faces two aspects of difficulties. First, users' needs present such characteristics as diversity, uncertainty and personalisation; second, the existing services run in a real-world environment that is highly complex and dynamically changing. These difficulties may cause the emergence of nondeterministic choices in the process of service composition, which has gone beyond what the existing automated service composition techniques can handle. According to most of the existing methods, the process model of composite service includes sequence constructs only. This article presents a method to introduce conditional branch structures into the process model of composite service when needed, in order to satisfy users' diverse and personalised needs and adapt to the dynamic changes of real-world environment. UML activity diagrams are used to represent dependencies in composite service. Two types of user preferences are considered in this article, which have been ignored by the previous work and a simple programming language style expression is adopted to describe them. Two different algorithms are presented to deal with different situations. A real-life case is provided to illustrate the proposed concepts and methods. [ABSTRACT FROM AUTHOR]

关键词： conditional branch structure control construct service composition user preference web service

来源：评论

学校读者我要写书评

暂无评论

A top-down algorithm for finding principal curves from complex patterns data

引用

ICIC Express Letters 2011年第3期5卷 797-802页

作者： Zhang, Hongyun Miao, Duoqian Xie, Chen Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University No. 1239 Siping Road Shanghai 201804 China School of Electronic and Information Engineering Tongji University No. 1239 Siping Road Shanghai 201804 China

Principal curves are a well established tool in data analysis and processing, but for complex pattern data with high curvature, high dispersion and self-intersecting, such as spiral-shaped curves, existing methods did not perform well. To solve the problem, a top-down strategy is introduced to extract principal curves from complex pattern data. Firstly, the thinning-based method is used to create rudimentary principal graph of data set, and then merging the contiguous vertices. Finally, the fitting-and-smoothing step introduced by Kégl is improved to optimize the principal graph, and Kégl's restructuring step is used to rectify imperfections of principal graph. This algorithm has been not only tested on simulated data sets but also applied to image skeletonization. Experimental results indicate the effectiveness of the proposed method on finding principal curves from complex pattern data sets. © 2011 ISSN 1881-803X.

关键词： Image enhancement

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：