检索结果-内蒙古大学图书馆

International Journal of Multimedia and Ubiquitous Engineering 2016年第7期11卷 1-12页

作者： Wang, Baowei Yan, Jingzhou Li, Tao Sun, Xingming Ma, Li School of Computer and Software Nanjing University of Information Science & Technology Nanjing210044 China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science & Technology Nanjing210044 China Key Laboratory of Meteorological Disaster of Ministry of Education Nanjing University of Information Science & Technology Nanjing210044 China

Among existing watermarking methods for data integrity protection in wireless sensor networks (WSNs), the problem of packet loss has not been considered. Most of methods treat packet loss as anomaly attacks, hardly being used in real network. The paper proposes a packet loss tolerated method for data integrity protection in wireless sensor networks based on double-level watermarking and threshold control. Sensory data collected by nodes generate digital watermarking for integrity detection. Watermarking will be stored in sensory data. The network will have watermarking verification and packet loss rate analysis in the sink to ensure data integrity. Through the experiment in real sensor network, this method can effectively protect data integrity with low power. © 2016 SERSC.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Tri_training for remote sensing classification based on multi-scale homogeneity

Tri_training for remote sensing classification based on mult...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jishuai Zhu Kun Tan Qian Du Jiangsu Key Laboratory of Resources and Environment Information Engineering China University of Mining and Technology Xuzhou China Department of Electrical and Computer Engineering Mississippi State University USA

ISBN: (纸本)9781509033331

In the process of hyperspectral image classification, the number of training samples is the key problem in improvement of classification performance. However, finding training samples are generally difficult and time-consuming. In this paper, we propose a novel semi-supervised approach and attempt to utilize unlabeled samples to improve classification accuracy. Specifically, active learning (AL) and multi-scale homogeneity (MSH) are integrated in a tri_training framework, where unlabeled samples are selected using AL and the labels of unlabeled samples are predicted from rough classification results with consideration of spatial neighborhood information. The MSH method is utilized to process the classification results to generate the final classification results. Moreover, we propose a novel diversity measure to select optimal classifier combination from different classifiers including support vector machine (SVM), multinomial logistic regression (MLR), extreme learning machine (ELM), k-nearest neighbor (KNN), and random forest (RF) etc. Experiments on two real hyperspectral data indicate that the new diversity measure can select an optimal classifier combination, and the proposed approach can effectively improve classification performance.

关键词： Hyperspectral imaging Classification algorithms Image classification Training Pollution measurement

来源：评论

学校读者我要写书评

暂无评论

An error beacon filtering algorithm based on particle swarm optimization for underwater wireless sensor networks

An error beacon filtering algorithm based on particle swarm ...

引用

IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB)

作者： Jingli Du Linfeng Liu Yue Ling Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing China School of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing China Ministry of Education Laboratory of Computer Network and Information Integration (Southeast University) Nanjing China

ISBN: (纸本)9781509013180

Due to the sophisticated environmental variations of water current, underwater creature touch, and strong electromagnetic interference, some beacon nodes tend to move or be damaged, which thus results in larger positioning errors of ordinary nodes. In order to solve the error beacon problem, this paper proposes an error beacon filtering algorithm based on particle swarm optimization (PSO), which can differentiate the beacon accurately. Firstly, several location errors of beacons are calculated by an improved Trilateration, and then the beacon with the maximum positioning error is filtered out through PSO. The remaining beacons are filtered out consecutively until the location error of each beacon does not exceed a preset threshold. Simulation results indicate that the proposed algorithm can detect almost all error beacons effectively with smaller variances.

关键词： Filtering algorithms Particle swarm optimization Filtering Classification algorithms Clustering algorithms Time complexity Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Ontology-based metadata matching for emergency decision-making using MapReduce

引用

International Journal of Metadata, Semantics and Ontologies 2015年第2期10卷 75-83页

作者： Zhu, Li Hu, Wei School of Economics and Management Nanjing University of Information Science and Technology Nanjing Jiangsu210044 China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing Jiangsu210023 China

Ontology matching techniques can help improve the accuracy of emergency decisionmaking on heterogeneous data. In this paper, we propose a practical approach to leverage ontology and MapReduce for matching metadata of emergency supplies. We use this approach in the domain of emergency food. Specifically, by extending the AGROVOC ontology developed by the Food and Agriculture Organisation (FAO) of United Nations, ontological descriptions of food metadata are established. Then, based on the classification of emergency functionality, the instances of food metadata within the same category are matched in a two-stage TF-IDF fashion, which is further improved with the MapReduce framework for efficient parallel computation. Our experiments on grain, meat and milk metadata retrieved from several e-commerce websites demonstrate the good performance of the proposed approach. Additionally, case study is provided to illustrate the potential use of our approach. © 2015 Inderscience Enterprises Ltd.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Tag Correspondence Model for User Tag Suggestion

引用

Journal of computer Science & technology 2015年第5期30卷 1063-1072页

作者：涂存超刘知远孙茂松 Department of Computer Science and Technology Tsinghua University Beijing 100084 China State Key Laboratory on Intelligent Technology and Systems Tsinghua University Beijing 100084 China National Laboratory for Information Science and Technology Tsinghua University Beijing 100084 China Jiangsu Collaborative Innovation Center for Language Ability Jiangsu Normal University Xuzhou 221009 China

Some microblog services encourage users to annotate themselves with multiple tags, indicating their attributes and interests. User tags play an important role for personalized recommendation and information retrieval. In order to better understand the semantics of user tags, we propose Tag Correspondence Model （TCM） to identify complex correspondences of tags from the rich context of microblog users. The correspondence of a tag is referred to as a unique element in the context which is semantically correlated with this tag. In TCM, we divide the context of a microblog user into various sources （such as short messages, user profile, and neighbors）. With a collection of users with annotated tags, TCM can automatically learn the correspondences of user tags from multiple sources. With the learned correspondences, we are able to interpret implicit semantics of tags. Moreover, for the users who have not annotated any tags, TCM can suggest tags according to users＇ context information. Extensive experiments on a real-world dataset demonstrate that our method can efficiently identify correspondences of tags, which may eventually represent semantic meanings of tags.

关键词： microblog user tag suggestion tag correspondence model probabilistic graphical model context

来源：评论

学校读者我要写书评

暂无评论

A heuristic scheduling algorithm based on PSO in the cloud computing environment

引用

International Journal of Future Generation Communication and Networking 2016年第1期9卷 349-362页

作者： Xue, Shengjun Shi, Wenling Xu, Xiaolong School of Computer and Software Nanjing University of Information Science and Technology Nanjing China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

In the face of a large number of task requests submitted by users, the data center in the cloud need not only to finish these massive tasks but also to satisfy the user's service demand. How to dividethe resources of the system reasonably and schedule these tasks efficiently isa problem that need be solved in the cloud computing. The task scheduling of workflow is a kind of scheduling model for the most partresearched in cloud computing. The scheduling goal is alwaysdecided by user's QoS(Quality of Service)and the scheduling goal of existing scheduling algorithm is alwayssingle. Based on the price model a scheduling algorithm is proposed which can realize the multiple targets in this article, and the scheduling algorithm is Service Cost Optimizationbased on Particle Swarm Optimization(PSO-SC).PSO-SC algorithm can adapt to dynamic cloud environment, and it not only shortens the completion time of tasks but also minimizesuser's cost of task when schedule tasks. In this paper, experiment and analyze the task scheduling of workflow under the cloud computing environment, and the experimental results show that the algorithm proposed in this paper has very good scheduling performance and can reachthe goal of task scheduling of tasks. © 2016 SERSC.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Performance modeling and evaluation of real-time traffic status query for intelligent traffic systems

Performance modeling and evaluation of real-time traffic sta...

引用

Asia-Pacific Conference on Communications

作者： Jie Ding Rui Wang Xiao Chen State Key Laboratory for Novel Software Technology Nanjing University China School of Information Engineering Yangzhou University Yangzhou China State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China

ISBN: (纸本)9781509006779

As product of the combination of Internet technology and sensor network, Internet of things (IoT) greatly facilitates the mutual interaction of the information world and physical world. Furthermore, with the rapid development of modern transportation systems, as a typical successful application of IoT in the real life, intelligent traffic system (ITS) has a great significance on management of the traffic information and transport infrastructure. Therefore, in order to achieve the efficient use of transportation resources, it is particularly important to evaluate and analyze the performance of ITS. In this paper, an advanced high level formalization - Performance Evaluation process algebra (PEPA), a kind of stochastic process algebra (SPA), is adopted to model the process of real-time traffic status query in ITS. Meanwhile, by using fluid approximation approach to analyze performance of the model and then the performance parameters of the system in practical application can be achieved accurately.

关键词： Real-time systems Global Positioning System Internet of things Servers Vehicles Satellites

来源：评论

学校读者我要写书评

暂无评论

Cloud-Base Distribution and Cirrus Properties Based on Micropulse Lidar Measurements at a Site in Southeastern China

引用

Advances in Atmospheric Sciences 2015年第7期32卷 991-1004页

作者： Jianjun LIU Zhanqing LI ZHENG Youfei Maureen CRIBB State Laboratory of Earth Surface Process and Resource Ecology and College of Global Change and Earth System Science Beijing Normal University Earth System Science Interdisciplinary Center University of Maryland Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Nanjing University of Information Science and Technology

The cloud fraction （CF） and cloud-base heights （CBHs）, and cirrus properties, over a site in southeastern China from June 2008 to May 2009, are examined by a ground-based lidar. Results show that clouds occupied the sky 41% of the time. Significant seasonal variations in CF were found with a maximum/minimum during winter/summer and similar magnitudes of CF in spring and autumn. A distinct diurnal cycle in the overall mean CF was seen. Total, daytime, and nighttime annual mean CBHs were 3.05 ± 2.73 km, 2.46 ± 2.08 kin, and 3.51 ± 3.07 km, respectively. The lowest/highest CBH occurred around noon/midnight. Cirrus clouds were present ～36.2% of the time at night with the percentage increased in summer and decreased in spring. Annual mean values for cirrus geometrical properties were 8.89 ± 1.65 km, 9.80 ± 1.70 kin, 10.73 ± 1.86 km and 1.83± 0.91 km for the base, mid-cloud, top height, and the thickness, respectively. Seasonal variations in cirrus geometrical properties show a maximum/minimum in summer/winter for all cirrus geometrical parameters. The mean cirrus lidar ratio for all cirrus cases in our study was ～ 25 ± 17 sr, with a smooth seasonal trend. The cirrus optical depth ranged from 0.001 to 2.475, with a mean of 0.34 ± 0.33. Sub-visual, thin, and dense cirrus were observed in ～12%, 43%, and 45% of the cases, respectively. More frequent, thicker cirrus clouds occurred in summer than in any other season. The properties of cirrus cloud over the site are compared with other lidar-based retrievals of midlatitude cirrus cloud properties.

关键词： cloud-base distribution cirrus propertfes lidar southeastern China

来源：评论

学校读者我要写书评

暂无评论

Fall detection using machine learning algorithms

Fall detection using machine learning algorithms

引用

International Conference on Software, Telecommunications and computer Networks (SoftCOM)

作者： Pranesh Vallabh Reza Malekian Ning Ye Dijana Capeska Bogatinoska Department of Electrical Electronic and Computer Engineering University of Pretoria Pretoria South Africa Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing Jiangsu Province China College of Computer Nanjing University of Posts and Telecommunications Nanjing China Faculty of Computer Science and Engineering University of Information Science and Technology “St. Paul the Apostle” Ohrid Republic of Macedonia

ISBN: (纸本)9781509025787

In this paper, the recognition of and the differentiation between fall activities and activities of daily living (ADL) was performed using the MobiFall dataset. A large database was constructed to train and validate the model. Feature selection methods were implemented to reduce dimensionality. Five different classification algorithms were implemented and evaluated based on their accuracy' sensitivity, and specificity achieved. The k-Nearest Neighbors' algorithm obtained an overall accuracy of 87.5% with a sensitivity of 90.70%, and a specificity of 83.78%.

关键词： Feature extraction Accelerometers Sensors Hidden Markov models Machine learning algorithms Gyroscopes Acceleration

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Library Books Search and Management System Using RFID technology

Design and Implementation of Library Books Search and Manage...

引用

International Conference on Intelligent Networking and Collaborative Systems (INCOS)

作者： Haiming Cheng Ling Huang He Xu Yifan Hu Xu An Wang School of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks College of Internet of Things Nanjing University of Posts and Telecommunications Nanjing China Key Laboratory of Information and Network Security Engineering University of Chinese Armed Police Force Xi'an China

Radio Frequency Identification technology (RFID) is the key technology to realize the Internet of things. Currently, using RFID to locate objects indoor is a hot topic in the research on the application of RFID. In this paper, we propose an RFID system based on RFID technology and Wi-Fi wireless communication technology. And we design a corresponding handheld device client software to realize a visual book search and management system. This system can not only greatly improve the efficiency of book search and management but also save the manpower and material resources to a large extent, which has a practical application value.

关键词： Collaboration

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：