检索结果-内蒙古大学图书馆

Construct pairwise test suites based on the Bak-Sneppen model of biological evolution

World Academy of Science, Engineering and Technology 2009年 35卷 224-229页

作者： Yuan, Jianjun Jiang, Changjun Department of Computer Science and Technology The Key Lab. of 'Embedded System and Service Computing' Ministry of Education of China Tongji University Shanghai 201804 China

Pairwise testing, which requires that every combination of valid values of each pair of system factors be covered by at lease one test case, plays an important role in software testing since many faults are caused by unexpected 2-way interactions among system factors. Although meta-heuristic strategies like simulated annealing can generally discover smaller pairwise test suite, they may cost more time to perform search, compared with greedy algorithms. We propose a new method, improved Extremal Optimization (EO) based on the Bak-Sneppen (BS) model of biological evolution, for constructing pairwise test suites and define fitness function according to the requirement of improved EO. Experimental results show that improved EO gives similar size of resulting pairwise test suite and yields an 85% reduction in solution time over SA.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Reader activation scheduling in multi-reader RFID systems: A study of general case

Reader activation scheduling in multi-reader RFID systems: A...

引用

25th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2011

作者： Tang, Shaojie Wang, Cheng Li, Xiang-Yang Jiang, Changjun Department of Computer Science Illinois Institute of Technology Chicago IL 60616 United States Department of Computer Science Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

ISBN: (纸本)9780769543857

Radio frequency identification (RFID) is a technology where a reader device can "sense" the presence of a close by object by reading a tag device attached to the object. To guarantee the coverage quality, multiple RFID readers can be deployed in the given region. In this paper, we consider the problem of activation schedule for readers in a multi-reader environment. In particular, we try to design a schedule for readers to maximize the number of served tags per time-slot while avoiding various interferences. We first develop a centralized algorithm under the assumption that different readers may have different interference and interrogation radius. Next, we propose a novel algorithm which does not need any location information of the readers. Finally, we extend the previous algorithm in distributed manner in order to suit the case where no central entity exists. We conduct extensive simulations to study the performances of our proposed algorithm. And our evaluation results corroborate our theoretical analysis. © 2011 IEEE.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

KNOB particle swarm optimizer 1

引用

1st International Conference on Advances in Swarm Intelligence, ICSI 2010

作者： Zhang, Junqi Liu, Kun Tan, Ying Key Laboratory of Embedded System and Service Computing Department of Computer Science and Technology Tongji University Shanghai 200092 China Department of Machine Intelligence School of Electronics Engineering and Computer Science Peking University Beijing 100871 China

ISBN: (数字)9783642134951

ISBN: (纸本)3642134947

It is not trivial to tune the swarm behavior just by parameter setting because of the randomness, complexity and dynamic involved in particle swarm optimizer (PSO). Hundreds of variants in the literature of last decade, brought various mechanism or ideas, sometimes also from outside of the traditional metaheuristics field, to tune the swarm behavior. While, in the same time, additional parameters have to be afforded. This paper proposes a new mechanism, named KNOB, to directly tune the swarm behavior through parameter setting of PSO. KNOB is defined as the first principal component of the statistical probability sequence of exploration and exploitation allocation along the search process. The using of the KNOB to tune PSO by parameter setting is realized through a statistical mapping, between the parameter set and the KNOB, learned by a radial basis function neural network (RBFNN) simulation model. In this way, KNOB provides an easy way to tune PSO directly by its parameter setting. A simple application of KNOB to promote is presented to verify the mechanism of KNOB. © 2010 Springer-Verlag.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Real-time action recognition with enhanced motion vector CNNs

Real-time action recognition with enhanced motion vector CNN...

引用

2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

作者： Zhang, Bowen Wang, Limin Wang, Zhe Qiao, Yu Wang, Hanli Shenzhen Key Lab of Comp. Vis. and Pat. Rec. Shenzhen Institutes of Advanced Technology CAS China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Computer Vision Lab ETH Zurich Switzerland

ISBN: (纸本)9781467388511

The deep two-stream architecture [23] exhibited excellent performance on video based action recognition. The most computationally expensive step in this approach comes from the calculation of optical flow which prevents it to be real-time. This paper accelerates this architecture by replacing optical flow with motion vector which can be obtained directly from compressed videos without extra calculation. However, motion vector lacks fine structures, and contains noisy and inaccurate motion patterns, leading to the evident degradation of recognition performance. Our key insight for relieving this problem is that optical flow and motion vector are inherent correlated. Transferring the knowledge learned with optical flow CNN to motion vector CNN can significantly boost the performance of the latter. Specifically, we introduce three strategies for this, initialization transfer, supervision transfer and their combination. Experimental results show that our method achieves comparable recognition performance to the state-of-the-art, while our method can process 390.7 frames per second, which is 27 times faster than the original two-stream method.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Single camera 3D lane detection and tracking based on EKF for urban intelligent vehicle

Single camera 3D lane detection and tracking based on EKF fo...

引用

IEEE International Conference on Vehicular Electronics and Safety, ICVES 2006

作者： Min, Tian Fuqiang, Liu Zhencheng, Hu IEEE Key Laboratory of Embedded System and Service Computing Ministry of Education China Electronic and Information Engineering Department Tongji University Shanghai 201804 China Department of Computer Science Kumamoto University Kumamoto 860-8555 Japan

ISBN: (纸本)1424407591

Road boundary detection and tracking is an important and integral function in advanced driver-assistance system. This paper proposes an algorithm, which can follow multi-kinds of lane, straight and curved, quickly and robustly. The algorithm uses several masks to extract blobs of road markings, combining with KNN function to remove the disturbance. Further more, road is modeled as a 3D surface, and some important parameters of current lane are provided on real-time by tracking based on Extended Kalman Filter (EKF). The results of experiments, which have been done in urban road, show that the algorithm is adapted to many road conditions. Even in a complex driving environment, it also has a good performance. © 2006 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

A comprehensive QoS determination model for Infrastructure-as-a-service clouds

A comprehensive QoS determination model for Infrastructure-a...

引用

2013 IEEE International Conference on Automation Science and Engineering, CASE 2013

作者： Xia, Yunni Zhou, Mengchu Luo, Xin Zhu, Qingsheng Software Theory and Technology Chongqing Key Lab Chongqing University Chongqing 400030 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ 07102 United States

ISBN: (纸本)9781479915156

Cloud computing is a recently developed new technology for complex systems with massive service sharing, which is different from the resource sharing of the grid computing systems. In a cloud environment, service requests from users go through numerous provider specific steps from the instant it is submitted to when the service is fully delivered. Quality modeling and analysis of clouds are not easy tasks because of the complexity of the provisioning mechanism and the dynamic cloud environment. This study proposes an analytical modelbased approach for quality evaluation of Infrastructure-as-a-service cloud and consider expected request completion time, rejection probability, and system overhead rate as key QoS metrics. It also features with the modeling of different warming and cooling strategies of machines and the ability to identify the optimal balance between system overhead and performance. © 2013 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

FedWNS: Data Distribution-Wise Node Selection in Federated Learning via Reinforcement Learning 26

FedWNS: Data Distribution-Wise Node Selection in Federated L...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Tu, Chengwu Zhao, Shengjie Deng, Hao Tongji University School of Software Engineering Shanghai201800 China Key Laboratory of Embedded System and Service Computing Shanghai201800 China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai201800 China

ISBN: (纸本)9798350331684

To deal with the discrepancy between global and local objectives in the federated learning invoked by the non-independent, identically distributed (non-IID) data and mitigate the impact of catastrophic forgetting in the training phase, we propose a federated learning framework with data distribution-wise reinforcement learning to perform node selection to accelerate the convergence process and alleviate the accuracy degradation. In this framework, the agent on the central server observes the number of samples every node owns, the derived distribution information of every dataset, and the current local and global accuracy. Then infer the selected node-set to participate in the current federated learning round through policy network in reinforcement learning. Finally, we conduct simulations with publicly data sets. Simulation results indicate that our FedWNS outperforms the existing FedAvg and CSFedAvg on the testing accuracy and the communication rounds to reach target accuracy under different settings. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Moving object detection through efficient detection and clustering of reliable singular points

Advances in Intelligent and Soft Computing

引用

Advances in Intelligent and Soft computing 2011年 104卷 381-385页

作者： Cui, Jianzhu Wang, Ping Li, Zhipeng Li, Jing Li, Yan Key Laboratory of Embedded System and Service Computing Supported by Ministry of Education Tongji University Cao'an Highway Shanghai 4800 China

ISBN: (纸本)9783642237768

This paper presents a method to detect vehicles from a moving camera. The detection component involves a cascade of modules. First, motion estimation of singular points in video sequences is used to detect moving vehicle. Finding the image points is the selection of singular points. We impose restrictions about the gradient magnitude and the cornerness. A sparse motion vector field outlines the image motion. We obtain excellent results in real sequences in China. At last, vehicles are detected by clustering of singular points. © 2011 Springer-Verlag Berlin Heidelberg.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Top-n recommendation algorithms for cloud data

引用

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2015年第1期43卷 54-61页

作者： Huang, Zhen-Hua Department of Computer and Technology Tongji University Shanghai200092 China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai200092 China

Top-n recommendation technology has recently received a lot of attention in information service community. In this paper, we study the problem of top-n recommendation under the cloud data. Firstly, we propose a multilayer distributed storage architecture(MDSA)which can fit the need of top-n recommendation. Secondly, based on the consideration of reducing the cost of network transmission, we present the data encoding pattern which is based on the MDSA architecture. Lastly, we fast realize top-n recommendation using the map/reduce distributed programming model. For satisfying the realistic requirement, we further present three application variants of top-n recommendation. Massive experiments demonstrate that our approach is efficient and has high overall performance. ©, 2015, Chinese Institute of Electronics. All right reserved.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

A Prediction Based on Clustering and Personality Questionnaire Data for IGD Risk

A Prediction Based on Clustering and Personality Questionnai...

引用

International Conference on Natural Computation, Fuzzy systems and Knowledge Discovery

作者： Xiaoliang Gong Kun Fang Yichu Hou Bozhong Long Zongling Di Lei Cao National Key Laboratory of Embedded System and Service Computing (Ministry of Education) Tongji University Shanghai China

ISBN: (纸本)9781509040940

With the development of the Internet, a lot of people trapped in the network, especially the adolescent depending on the network game and disturbing their normal life. 579 freshmen participated in this work who were collected the personality questionnaires in the first week they came in university and their grades points average (GPA) after half year. The questionnaires were including Self-Control (SCS), Barratt impulse Inventory (BIS) and Chinese Big Five Personality (CBF). This work used multi-clustering algorithms to construct the models of predicting for Internet game disorder (IGD) risk, including FCM, K-means, and Hierarchical for training model. This is the first try to predict the risk of IGD by personality traits. The results shown the questionnaire data were well separated by different clustering algorithms into three groups who were shared the analogous personality traits which has a relationship with the behavior of IGD. But compared to the GPA of each group, the efficiency of the prediction model seems not so satisfactory. There need more efforts to optimized the model in the future.

关键词： Personality questionnaire Data IGD Risk FCM K-means Hierarchical

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：