检索结果-内蒙古大学图书馆

第三十四届中国控制会议

作者： Zixuan Gan Wenhua Shi Chen Ye Tongji University The Key Laboratory of Embedded System and Services Computing Ministry of Education Tongji University

ISBN: (纸本)9781467374439

This study was designed to develop solutions for facial action human computer interaction on embedded devices. This paper presents a new facial detection algorithm using dimension reduction and regionalization computing. Then, a dynamic action judgement algorithm based on simplified Facial Expression Coding system is proposed to describe human facial action. This paper also provide the facial action capture system ***, an accuracy report is presented to validate the usefulness of system.

关键词： Facial Detection,Expression Recognition,Facial Action Recognition

来源：评论

学校读者我要写书评

暂无评论

Lane Detection Method Based on Improved RANSAC Algorithm

Lane Detection Method Based on Improved RANSAC Algorithm

引用

International Symposium on Autonomous Decentralized systems (ISADAS)

作者： Jie Guo Zhihua Wei Duoqian Miao Ministry of Education Key Laboratory of Embedded System and Service Computing Shanghai China Department of Computer Science and Technology Tongji University

ISBN: (纸本)9781479982622

Lane detection based on computer vision is a key technology of Automatic Drive system for intelligent vehicles. In this paper, we propose a real-time and efficient lane detection algorithm that can detect lanes appearing in urban streets and highway roads under complex background. In order to enhance lane boundary information and to be suitable for various light conditions, we adopt canny algorithm for edge detection to get good feature points. We use the generalized curve lane parameter model, which can describe both straight and curved lanes. We propose an improved random sample consensus (RANSAC) algorithm combined with the least squares technique to estimate lane model parameters based on feature extraction. Experiments are conducted on both real road lane videos captured by Tongji University and Caltech Lane Datasets. The experimental results show that our algorithm is can meet the real time requirement and fit lane boundaries well in various challenging road conditions.

关键词： Feature extraction Roads Computational modeling Image edge detection Algorithm design and analysis Real-time systems Mathematical model

来源：评论

学校读者我要写书评

暂无评论

keystroke dynamics in password authentication for multi-user account

引用

Journal of Computational Information systems 2015年第1期11卷 321-331页

作者： Zhang, Xiaomeng Zhao, Peihai Wang, Mimi Department of Computer Science and Technology Tongji University Shanghai China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

In the field of identity authentication, existing researches on user keystroke authentication only focus on the situation in which a single user uses a single account. When multiple users share one account, there emerges the problem of inaccurate modeling. The key to construct the keyboard behaviour pattern in a single-account-for-multiple-users case is to cluster and build the unique keyboard behaviour pattern for each user under the shared account. In this paper, the original K-means clustering algorithm is improved by adding variance determination conditions. And when the number of users is unknown, the algorithm will determine whether the account is a multi-user account or not and identify the number of users under the account to carry out keyboard behaviour clustering in a single-account-for-multiple-users situation. We build a model based on keyboard behaviour data after clustering. Compared with other methods, experiments arrive at the expected results. This method can be used for keyboard behaviour authentication in real-world scenarios in which multiple users share one account at home or in companies. ©, 2014, Journal of Computational Information systems. All right reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Research on the Matthews correlation coefficients metrics of personalized recommendation algorithm evaluation

引用

International Journal of Hybrid Information Technology 2015年第1期8卷 163-172页

作者： Liu, Yingbo Cheng, Jiujun Yan, Chendan Wu, Xiao Chen, Fuzhen Key Laboratory of Embedded System and Service Computing of Ministry of Education Tongji University Shanghai China Department of Computer Science and Technology Tongji University Shanghai China

The personalized recommendation systems could better improve the personalized service for network user and alleviate the problem of information overload in the Internet. As we all know, the key point of being a successful recommendation system is the performance of recommendation algorithm. When scholars put forward some new recommendation algorithms, they claim that the new algorithms have been improved in some respects, better than previous algorithm. So we need some evaluation metrics to evaluate the algorithm performance. Due to the scholar didn’t fully understand the evaluation mechanism of recommendation algorithms. They mainly emphasized some specific evaluation metrics like Accuracy, Diversity. What’s more, the academia did not establish a complete and unified assessment of recommendation algorithms evaluation system which is credibility to do the work of recommendation evaluation. So how to do this work objective and reasonable is still a challengeable task. In this article, we discussed the present evaluation metrics with its respective advantages and disadvantages. Then, we put forward to use the Matthews Correlation Coefficient to evaluate the recommendation algorithm’s performance. All this based on an open source projects called mahout which provides a rich set of components to construct the classic recommendation algorithm. The results of the experiments show that the applicability of Matthews correlation coefficient in the relative evaluation work of recommendation algorithm. © 2015 SERSC.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

An immune approach for detecting the user's behavior of electronic transaction process

引用

Journal of Computational Information systems 2015年第2期11卷 683-692页

作者： Jiang, Shaoping Yan, Chungang Zhao, Peihai Wang, Mimi Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

In the process of electronic transaction, there are many abnormal conditions such as user's own mistakes, account theft and so on. Inspired by mechanisms of immune homeostasis, immune surveillance and immune update from the biological immune system, an immune approach for detecting the user's behavior of electronic transaction process is proposed to solve these problems and make the user's behaviors credible. By computing age of each log and cleaning up the aging logs, logs which can reflect the user's habit could be gotten and the mechanism of immune homeostasis is realized. With the newly-generated transaction sequence detected to be abnormal or not, the mechanisms of immune surveillance is achieved. Updating related sets is the realization of immune update, and the goal of detecting the user's behavior can be reached. The experimental results show that the true positive rate can reach 92% when the false positive rate is 10.8%. 1553-9105/Copyright © 2015 Binary Information Press

关键词： Physiology

来源：评论

学校读者我要写书评

暂无评论

Observer-based controller design for networked systems with multiple packet losses and mixed delay

Observer-based controller design for networked systems with ...

引用

第27届中国控制与决策会议

作者： Fengfeng Qian Huaicheng Yan Hongbo Shi Hao Zhang Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education School of Information Science and Engineering East China University of Science and Technology Key Laboratory of Embedded System and Service Computing Ministry of EducationTongji University

The paper focuses on a stabilizing controller design problem for networked systems with quantization,mixed delays,and a series of packet losses due to the signal transmission through the unreliable communication *** of both sensor-to-controller and controller-to-actuator are taken into account for the networked systems,and the distributed time delay is also considered in the network *** conditions for designing the controller as well as the system parameters can be obtained by solving certain linear matrix ***,the effectiveness of the designed method is proved by a numerical example.

关键词： quantization,mixed delays,multiple packet losses

来源：评论

学校读者我要写书评

暂无评论

Correlative Filters for Convolutional Neural Networks

Correlative Filters for Convolutional Neural Networks

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Peiqiu Chen Hanli Wang Jun Wu Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Department of Computer Science and Technology Tongji University Shanghai China

ISBN: (纸本)9781479986989

This paper introduces a regularization method called Correlative Filter (CF) for Convolutional Neural Network (CNN), which takes advantage of the relevance between the convolutional kernels belonging to the same convolutional layer. During the process of training with the proposed CF method, several pairs of filters are designed in a manner of randomness to contain opposite weights in low-level layers. Regarding higher level layers where synthetical features are processed, the relation between correlative filters is explored as translation of various directions. The proposed CF method attempts to optimize the inner structure of convolutional layers and it can work jointly with other regularization techniques, such as stochastic pooling, Dropout, etc. The experimental results on the competitive image classification benchmark dataset CIFAR-10 demonstrates the performance of the proposed CF method, additionally, it is also verified that the proposed CF method is wonderful to be employed to enhance several state-of-the-art regularization models.

关键词： Feature extraction Neurons Training Stochastic processes Convolution Kernel Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

Petri net based behavior description of cross-organization workflow with synchronous interaction pattern 1

Petri net based behavior description of cross-organization w...

引用

1st International Workshop on Process-Aware systems, PAS 2014

作者： Liu, Cong Zeng, Qingtian Duan, Hua Lu, Faming The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai200092 China College of Information Science and Engineering Shandong University of Science and Technology Qingdao266590 China College of Electronic Communication Shandong University of Science and Technology Qingdao266590 China College of Mathematics Shandong University of Science and Technology Qingdao266590 China

ISBN: (纸本)9783662461693

Today’s workflow systems are crossing organizational boundaries and usually involve multiple organizations or partners, and the crossorganization workflow has received much public attention from both the academia and the industry. This way the property analysis as well as system control for a cross-organization workflow is very important. In this paper, we focus on a kind of loosely coupled workflow architecture with synchronous interaction pattern, i.e. each organization owns its private workflow process and can operate independently, and they need to synchronize through certain tasks. Its behavior description approach is obtained using the synchronized shuffle operation of Petri net language. It is proved that our approach benefits the behavior characterization of cross-organizational workflow with synchronous interaction pattern and can be further used to decide and control the fairness, liveness, deadlock and trap for the cross-organization workflow. A running case of cross-organizational medical diagnosis workflow is given to validate our approaches throughout the whole paper. © Springer-Verlag Berlin Heidelberg 2015.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Null space based discriminant sparse representation large margin for face recognition

Null space based discriminant sparse representation large ma...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ying Wen Lili Hou Lianghua He Department of Computer Science and Technology East China Normal University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9781479919611

In this paper, we propose a novel subspace learning algorithm, termed as null space based discriminant sparse representation large margin (NDSLM). There are two contributions in the paper. First, we propose a new expectation to obtain the neighborhood information for large margin subspace learning, i.e., the within-neighborhood scatter and between-neighborhood scatter are modeled by the sparse reconstruction weights of the samples from the same class and different classes, respectively. Since the neighborhood information formed by sparse representation can capture non-linearities in the data, the proposed method possesses more discriminative information than the traditional large margin learning methods with the expectation using Euclidean distance, etc. Second, the large margin information integrated into the model of Fisher criterion makes the discriminating power of NDSLM further boosted. NDSLM addresses the small sample size problem by solving an eigenvalue problem in null space. Experiments on ORL, Yale, AR, Extended Yale B and CMU PIE five face databases are performed to evaluate the proposed algorithm and the results demonstrate the effectiveness of NDSLM.

关键词： Principal component analysis Silicon Pipelines Glass Databases

来源：评论

学校读者我要写书评

暂无评论

An efficient algorithm of information recommendation between groups in social networks

引用

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2015年第6期43卷 1090-1093页

作者： Huang, Zhen-Hua Zhang, Bo Fang, Qiang Xiang, Yang Department of Computer and Technology Tongji University Shanghai201804 China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai201804 China College of Information Mechanical and Electrical Engineering Shanghai Normal University Shanghai200234 China

Information recommendation between groups is one of the most important ways for information sharing and transmitting in social networks. However, it needs exponential time cost to achieve the exact optimal recommendation solution. Hence this paper proposed an efficient algorithm EAOORS (Efficient Algorithm for Obtaining Optimal Recommendation Solution) which equivalently reduced this exponential time cost problem to extended steiner tree problem, and fast achieved the approximate optimal recommendation solution in the polynomial time complexity. The experimental result shows that the EAOORS algorithm is more efficient than the existing ones. ©, 2015, Chinese Institute of Electronics. All right reserved.

关键词： Approximation algorithms

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：