检索结果-内蒙古大学图书馆

A peer selection prior data scheduling method for peer-to-peer media streaming system

Beijing Gongye Daxue Xuebao/Journal of Beijing University of technology 2010年第SUPPL. 1期36卷 26-30页

作者： Ji, Qi-Jin Yang, Zhe Zhu, Yan-Qin School of Computer Science and Technology Soochow University Suzhou 215006 Jiangsu China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou 215006 Jiangsu China

Data Scheduling in P2P media streaming system considers which peer to select for interesting media data. Since data scheduling decision can only be made in terms of the local information of each peer, the commonly used data block selection prior data scheduling is prone to traffic concentration to minor peers in the system and thus degrades the system throughput greatly. A peer selection prior data scheduling method is proposed in this paper, which can direct traffic to the neighbors evenly. The simulation results show that the proposed method can mitigate the load of source server more than 25% and meanwhile improve the system throughput comparing with the data block selection prior alternatives.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

Comparison of Particle Swarm Optimization algorithms in Wireless Sensor Network node localization

Comparison of Particle Swarm Optimization algorithms in Wire...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Cen Cao Qingjian Ni Xushan Yin School of Computer Science and Engineering Southeast University Nanjing China College of Software Engineering Southeast University Nanjing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China

The node localization in Wireless Sensor Network (WSN) presently plays an important role in the field of applications. Particle Swarm Optimization (PSO) algorithm is a typical swarm intelligence method. Researchers propose many PSO variants and try to apply PSO algorithm to the related problems in WSN. This paper focuses on the WSN node localization using PSO algorithm. This paper conducts the experiment simulation, comparison and evaluation work in the node localization using PSO algorithm. The performance of different PSO variants with different population topologies is analyzed. Experiment simulations show that WSN node localization using PSO algorithm can get good performance in ring topology and square topology. In particular, the two newly proposed PSO variants (GDPSO and LDPSO) have good performance on this problem. This paper proposes some useful conclusions, which will provide a valuable reference to WSN engineering field.

关键词： Topology Wireless sensor networks Sociology Statistics Heuristic algorithms Particle swarm optimization Standards

来源：评论

学校读者我要写书评

暂无评论

Chinese Lexical Based Sentiment Analysis Framework in Meteorology

Chinese Lexical Based Sentiment Analysis Framework in Meteor...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Yinan Li Fuquan Zhang Yifan Zhu Sifan Zhang Yu Mao Zhendong Niu School of Computer Science and Technology Beijing Institute of Technology Beijing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China School of Computing and Information University of Pittsburgh Pittsburgh PA USA

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Evaluating the performance of meteorological service not only relies on physical measurements but also requires public feedback. As a significant part of the evaluation, assessing the sentiment of these feedbacks gives an insightful view which can help to establish reliable decision support in policy making and emergency responding. However, climate and weather are always accompanying phenomena in the evolutionary process of human beings, making the climate and weather-related words themselves contain a large number of extend meanings in people's daily expression. These polysemy phenomena have led to a decline in the performance of traditional general sentiment calculations in the vertical field of meteorology. As far as we know, there is no Chinese sentiment calculation tool in the meteorological field, due to the different expressions between different languages. Facing with the above problems and issues, this paper proposes and establishes a sentiment analysis based on lexicon-based framework of Chinese text in the meteorological field. The framework fuses two major sentiment assessment method consists of two approaches, namely machine learning-based and knowledge based one. First, word embedding similarity and word co-occurrence methods are utilized to construct the domain sentiment dictionary which includes 8,796 negative words and 4,751 positive words. Then, by using the extend sentiment dictionary to select theme words from original text as feature, machine learning models are introduced to assess the sentiment tendency. Experiment showed that the performance of the proposed framework was improved up to 85.79% in terms of overall accuracy compared with traditional methods.

关键词： Dictionaries Meteorology Sentiment analysis Feature extraction Machine learning Vocabulary Semantics

来源：评论

学校读者我要写书评

暂无评论

MNet: Rethinking 2D/3D Networks for Anisotropic Medical Image Segmentation

arXiv

引用

arXiv 2022年

作者： Dong, Zhangfu He, Yuting Qi, Xiaoming Chen, Yang Shu, Huazhong Coatrieux, Jean-Louis Yang, Guanyu Li, Shuo LIST Key Laboratory of Computer Network and Information Integration [Southeast University Ministry of Education Nanjing China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing China Dept. of Medical Biophysics University of Western Ontario LondonON Canada

The nature of thick-slice scanning causes severe inter-slice discontinuities of 3D medical images, and the vanilla 2D/3D convolutional neural networks (CNNs) fail to represent sparse inter-slice information and dense intra-slice information in a balanced way, leading to severe underfitting to inter-slice features (for vanilla 2D CNNs) and over-fitting to noise from long-range slices (for vanilla 3D CNNs). In this work, a novel mesh network (MNet) is proposed to balance the spatial representation inter axes via learning. 1) Our MNet latently fuses plenty of representation processes by embedding multi-dimensional convolutions deeply into basic modules, making the selections of representation processes flexible, thus balancing representation for sparse inter-slice information and dense intra-slice information adaptively. 2) Our MNet latently fuses multi-dimensional features inside each basic module, simultaneously taking the advantages of 2D (high segmentation accuracy of the easily recognized regions in 2D view) and 3D (high smoothness of 3D organ contour) representations, thus obtaining more accurate modeling for target regions. Comprehensive experiments are performed on four public datasets (CT&MR), the results consistently demonstrate the proposed MNet outperforms the other methods. The code and datasets are available at: https://***/zfdong-code/MNet. © 2022, CC BY-NC-ND.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

IPv6-based dynamic quality of service control strategy for wireless network

引用

Journal of Networks 2010年第9期5卷 1098-1105页

作者： Chen, Zhifeng Zhu, Qiaoming Qian, Peide Chen, Fengyan Key Laboratory of Computer Information Processing Technology of Jiangsu Province School of Computer Science and Technology Soochow University Suzhou 215006 China Suzhou Institute of Trade and Commerce Suzhou 215009 China School of Foreign Language Soochow University Suzhou 215006 China

On the basis of the architecture for fast handover of hierarchical IPv6, a coordinated call admission control mechanism was presented, providing an end-to-end RSVP context transfer for real-time applications to overcome the weakness of the context transfer protocol which cannot meet the need of end-to-end QoS mechanisms because the contexts were only transferred between the previous and new access routers. The mechanism decreased the delay caused by re-initiate QoS signaling from scratch to reestablish QoS forwarding process, and minimized the handover service disruption. The signaling overhead and handover latencies could be reduced by adopting t he fast handover for hierarchical IPv6 architecture. The approach was compared with the re-initiating RSVP signaling to reestablish QoS states using network simulator ns2. The numerical results showed that the scheme has the less latency and packet loss than that of the re-initiating approach. © 2010 ACADEMY PUBLISHER.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Detecting Interest-Factor Influenced Abnormal Evaluation of Teaching via Multimodal Embedding and Priori Knowledge Based Neural Network

Detecting Interest-Factor Influenced Abnormal Evaluation of ...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Yu Mao Yifan Zhu Sifan Zhang Dexiu Zhang Fuquan Zhang Xiaozhong Fan School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Computer Science Minnan Normal University Zhangzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Student evaluations of teaching (SET) helps to quantitatively measure the teaching performance of classes. However, concerns arouse when the result of SET and students' final grades are highly positively correlated, which means the students may make the evaluation based on the final grades they take. For the purpose of avoiding retaliation and mutual reward rating, some methods based on statistics or rules are used to detect the presence of anomaly evaluation. Whereas, the problem is still challenging since the characteristics of this abnormal evaluation are implicit and multimodal. Besides, additional information such as the domain of subject, instructors' teaching style, and the reputation spread by students also requires corresponding prior knowledge to supplement the abnormal evaluation detection model. Therefore, in this paper, we proposed a multimodal embedding and prior knowledge based neural network to detect potential so called Interest Factor Influenced Abnormal Evaluation (IFAE). The method proposed in this paper uses SDNE and PV-DM to embed the evaluation network between students and teachers and the comment text of students. Taking into account the continuity of mutual evaluation between students and teachers during the teaching cycles and the different emphasis of students' comment texts on teachers, the features of students and teachers are comprehensively constructed. Then, the attention mechanism is used in the comment text to perform final prediction jointly with above features. The experiment result shows that our proposed model outperforms other state-of-art models which based on single type of features on F1 score by 9.25%.

关键词： Education Feature extraction Neural networks Data mining Knowledge based systems computer science Quality control

来源：评论

学校读者我要写书评

暂无评论

Multi-stage Objective Function Optimized Hand-Eye Self-calibration of Robot in Autonomous Environment 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Liu, Kaibo Zheng, Wangli Min, Huasong Lin, Yunhan School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Hubei Wuhan430065 China State Grid Electric Power Research Institute Jiangsu Nanjing211106 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Hubei Wuhan430081 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

In the application scenario of robot autonomous tasks, the robot needs to be able to complete calibration online and automatically to achieve self-maintenance, which differs from traditional robot hand-eye calibration in that the traditional robot hand-eye calibration requires a dedicated calibration board to assist offline completion. Aiming at the problem that the existing self-calibration methods cannot be optimized as a whole, which leads to low accuracy and instability of the solution, a multi-stage objective function optimization self-calibration algorithm is proposed, which describes the solution of hand-eye self-calibration as a minimization objective function problem involving multiple stages. An optimization method based on the minimization of re-projection error is designed to compensate for the results, which uses an efficient Oriented fast and rotated brief (ORB) feature extraction algorithm and introduces a scoring mechanism to retain more correct matching points in the feature matching stage. Two different types of experiments were designed to validate our method. One is a single camera dataset experiment, which shows that our method is more accurate and robust than the existing self-calibration method;the other is an application platform experiment, which verifies the feasibility and availability of our method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

A feature selection algorithm based on Hoeffding inequality and mutual information

International Journal of Signal Processing, Image Processing...

引用

International Journal of Signal processing, Image processing and Pattern Recognition 2015年第11期8卷 433-444页

作者： Yin, Chunyong Feng, Lu Ma, Luyu Yin, Zhichao Wang, Jin School of Computer and Software Jiangsu Key Laboratory of Meteorological Observation and Information Processing Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing China Nanjing No.1 Middle School Nanjing China

With the rapid development of the Internet, the application of data mining in the Internet is becoming more and more extensive. However, the data source’s complex feature redundancy leads that data mining process becomes very inefficient and complex. So feature selection research is essential to make data mining more efficient and simple. In this paper, we propose a new way to measure the correlation degree of internal features of dataset which is a mutation of mutual information. Additionally we also introduce Hoeffding inequality as constraint of constructing algorithm. During the experiments, we use C4.5 classification algorithm as test algorithm and compare HSF with BIF(feature selection algorithm based on mutual information). Experiments results show that HSF performances better than BIF[1] in TP and FP rate, what’s more the feature subset obtained by HSF can significantly improve the TP, FP and memory usage of C4.5 classification algorithm. © 2015 SERSC.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Intrusion detection based on fuzzy reasoning

Intrusion detection based on fuzzy reasoning

引用

26th Chinese Control Conference, CCC 2007

作者： Fei, Yu Yue, Shen Guiping, Liao Linfeng, Zhang Cheng, Xu School of Computer Andinformation Engineering Hunan Agricultural University Changsha 410128 China Guangdong Province Key Lab. of Electronic Commerce Market Application Technology Guangdong University of Business Studies Guangzhou 510320 China Jiangsu Provincial Key Laboratory of Computer Information Processing Technology Suzhou University Suzhou 2150063 China

ISBN: (纸本)7900719229

The paper proposes a new network intrusion detection system based on fuzzy neural network by redesigning the intrusion detection system's architecture and arithmetic. In order to overcome the difficulty of specifying the membership function of rules depending on experiences of experts in multi-dimension space.,neural network is introduced to distinguish non-linearly input/output characteristics of complex system and to generate rule sets and membership functions automatically. The new architecture adopts the network processor to collect and analyse the data in the low layer of network.,and to establish a prototype system. This system demonstrated in this experiment appears to be better intrusion detection ability, moreover, which is able to detect unknown attack and plays down false alarms.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

未来视频技术专题(英文)

引用

China Communications 2013年第5期 8-10页

作者：陈熙霖朱秀昌王桥胡栋 Ming-Ting SUN the Institute of Computing Technology Chinese Academy of Sciences (CAS) the IEEE Transactions on Image Processing the Journal of Computer Science and Technology the Chinese Journal of Computers College of Communications and Information Engineering NUPT Image Processing and Image Communications Key Laboratory of Information Industrial Ministry and Jiangsu Province Signal and Information Processing Laboratory Southeast University

In the past few years, video has become one of the most powerful engines to push communications forward. The increasing of digital video technology requires larger and larger bandwidth for various applications, such as IPTV, VOD, video phone, mobile search, etc. The goal of this Feature Topic column is to present and highlight the latest progress and future video-related technologies. We hope this

关键词： IEEE over

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：