检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robotics and Systems

作者： K.R. Guruprasad Prithviraj Dasgupta Assistant Professor at the Department of Mechanical Engineering National Institute of Technology Karnataka Surathkal India. Associate Professor at the Department of Computer Science University of Nebraska at Omaha NE USA.

ISBN: (纸本)9781467317375

We consider the problem of distributed partitioning of an environment by a set of robots so that each robot performs its operations in the region within the corresponding cell. Voronoi partitioning is one of the most attractive techniques that has been used to solve this problem. It has been used in several distributed multi-robotic system and sensor network applications, such as sensor coverage, search and rescue, and coverage path planning. For a truly distributed implementation of such problems, each robot should be able to compute the corresponding Voronoi cell in a distributed manner. Further, in a practical application, the robots' sensors may have limited range, thus each robot may operate within a portion of its Voronoi cell constrained by the sensor range. We describe a distributed algorithm for computation of this range constrained Voronoi cell where each robot independently constructs chords corresponding to other robots that are within a distance of twice its sensor circle radius. A robot then uses a simple and fast technique to remove inessential chords to calculate the vertices of its Voronoi cell. We prove completeness and correctness of the proposed algorithm, and also provide the upper and lower bounds on the computational complexity of our algorithm. The theoretical results are validated with the help of experiments to show that for different values of sensor ranges, our proposed algorithm incurs a time complexity that is significantly lower than that of the existing full Voronoi partition computation algorithm. The maximum number of steps required by our algorithm is also shown to be within a constant times the lower bound given by the number of neighbors of each node.

关键词： correctness rescue sensor network Robot Rescue accuracy class Sensor networks multi-robot systems Sensors complexity classes Distribute operating range Lower bound range sensor partitions Path planning

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of segmentation techniques for land cover types using remote sensing images

Performance analysis of segmentation techniques for land cov...

引用

IEEE India Conference (INDICON)

作者： S Bharathi V J Shreyas R P Anirudh S M Sanketh P Deepa Shenoy K R Venugopal L M Patnaik Department of MCA Dr. Ambedkar Institute of Technology Bangalore India Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore India Department of Computer Science and Engineering UVCE Bangalore India Honorary Professor Indian Institute of Science Bangalore India

Information extraction is a very challenging task because remote sensing images are very complicated and can be influenced by many factors. The information we can derive from a remote sensing image mostly depends on the image segmentation results. Image segmentation is an important processing step in most image, video and computer vision applications. Extensive research has been done in creating many different approaches and algorithms for image segmentation. Labeling different parts of the image has been a challenging aspect of image processing. Various algorithms for automating the segmentation process have been proposed, tested and evaluated to find the most ideal algorithm to be used for different types of images. In this paper we explore segmentation techniques of satellite images using two algorithms - Quick Shift and Level Set. Quick Shift is a mode seeking algorithm which instead of iteratively shifting each point towards a local mean forms a tree of links to the nearest neighbor which increases the density. Level Set is a curve propagation algorithm based on the Partial-Differential Equation (PDE) method that provides a direct way to estimate the geometric properties of the evolving structure. The aim of this paper is to analyse the above two approaches and declare one of the two methods to be efficient for segmentation on remote sensing applications.

关键词： Image segmentation Level set Remote sensing Classification algorithms Robustness Vegetation Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

An analysis on business intelligence models to improve business performance

An analysis on business intelligence models to improve busin...

引用

International Conference on Advances in Engineering, science and Management (ICAESM)

作者： A. Martin T. Miranda Lakshmi V. Prasanna Venkatesan Research Scholar Pondicherry University Puducherry Assislant Professor Department of Computer Science Saint Joseph's College Cuddalore India Department of Computer Science St. Joseph's College Department of Banking Technology Pondicherry University Puducherry Puducherry

Business intelligence is an effective technology to take right decisions at right time for the survival of any business. Business intelligence can be applied to all kind decision making and prediction analysis. Business performance can be identified by using bankruptcy prediction. In this research we are developing a business intelligence model to predict the business performance by using bankruptcy prediction as well as we are finding important features to improve the prediction accuracy of bankruptcy model. The proposed BI model applies both Quantitative and Qualitative factors to predict bankruptcy. Quantitative factors are measured from financial variables and Qualitative factors are measured from non-financial variables using data mining techniques. To identify the important features from the quantitative bankruptcy models this research work applies Real Genetic Algorithm. The Real Genetic Algorithm analysis the non linear relation between financial variables in Fulmer bankruptcy model and identifies important features. The experimental result shows that accuracy level of original threshold value α and generated threshold value β is more than 90%.

关键词： Analytical models computer architecture Computational modeling Predictive models Business Accuracy

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Detection of DDoS Attacks in IEEE 802.15.4 Low Rate Wireless Personal Area Network

引用

Procedia Engineering 2012年 38卷 3855-3863页

作者： C. Balarengadurai S. Saraswathi Research Scholar Department of Computer Science & Engineering Manonmaniam Sundarnar University Thirunelveli 627 012 India Associate Professor Department of Information Technology Pondicherry Engineering College Puducherry 605 014 India

IEEE 802.15.4 Low rate wireless personal area networks (LR-WPANs) offer device level wireless connectivity. They bring to light a host of new applications as well as enhance existing applications. Due to their low cost, low power consumption and self-organization features, LR-WPANs are ideal for applications such as public security, battle field monitoring, inventory tracking as well as home and office automation. Nevertheless, one critical issue, security, needs to be solved before LR-WPANs are commonly accepted. Pursuing security in LR-WPANs is a challenging task. On one hand, wireless communications are inherently susceptible to interception and interference. On the other hand, most devices in LR-WPANs are resource-constrained and lack physical safeguards. DDoS attacks are a major security problem in wireless networks. DDoS is that lots of clients simultaneously send service requests to certain server on the internet thro wireless network such that this server is too busy to provide normal services for others. Attackers using legitimate packets and often changing package information, so that traditional detection methods based on feature descriptions are difficult to detect it. To date, various approaches have been proposed to detect DDoS attacks, but with limited success when they are used in the real world. This paper mainly focus on comparative analysis of DDoS attacks, detection and mitigation techniques are generally used. Beside this, we investigate about the approaches proposed that are considered efficient to survive in DDoS attacks. Finally, we conclude by highlighting the potential areas which can be targeted to optimized in minimizing the effects of DDoS attacks

关键词： IEEE 802.15.4 DDoS PHY Layer MAC Layer Attacks Detection

来源：评论

学校读者我要写书评

暂无评论

An ontological approach for effective knowledge engineering

An ontological approach for effective knowledge engineering

引用

International Conference on Software Engineering and Mobile Application Modelling and Development (ICSEMA 2012)

作者： S. Vigneshwari M. Aramudhan Research Scholar Department of Computer Science and Engineering Sathyabama University Chennai Tamil Nadu India Associate Professor and Head Department of Information Technology Perunthalaivar Kamarajar Institute of Science and Technology Karaikal Tamil Nadu India

Ontologies are efficient way of getting a better idea about a particular domain. There are various forms of ontologies. Certain ontologies are reusable and are available online. Some other ontology can be developed for a specific purpose and are used to yield precise results in the field of knowledge engineering and automated tasks. If we want to gather information between different ontologies of different domains a cross ontology mining method has to be implemented for mining the semantic data. A framework has been discussed here for advanced ontology mining which can be very much useful to the semantic society.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Supervised ANN Method for Memory Failure signature Classification

A Supervised ANN Method for Memory Failure signature Classif...

引用

2012 IEEE 11th International Conference on Solid-State and Integrated Circuit technology(ICSICT-2012)

作者： Jianbo Li Yu Huang Wu-Tung Cheng Chris Schuermyer Dong Xiang Department of Computer Science and Technology Mentor Graphics Corporation School of Software Tsinghua University

ISBN: (纸本)9781467324748

Failure bitmaps of manufactured memory arrays may contain the information associated to some systematic defects and have hence been used to monitor the process and improve the memory *** is very important to develop a method to extract and classify the fault signatures in the failure *** fault signatures can be classified into two categories:local fault signatures and global fault *** on the local fault signatures,this paper introduces a supervised one-layer ANN method to solve the signature classification *** method is efficient for recognizing the local fault signatures in the failure bitmaps,and more importantly,it has the ability to find new signatures unseen before.

关键词： red ANN A Supervised ANN Method for Memory Failure signature Classification

来源：评论

学校读者我要写书评

暂无评论

Dimensionality reduction based on the classifier models: Performance Issues in the prediction of Lung cancer

Dimensionality reduction based on the classifier models: Per...

引用

CSI International Conference on Software Engineering (CONSEG)

作者： K. Balachandran R. Anitha Research scholar & Associate Professor Computer Science & Engineering Department Christ University Bangalore Karnataka India Director MCA KSR College of Technology Tirunchengodu Tamil Nadu India

Dimensionality reduction is an essential feature to reduce the complexity of the computations in the large data set environment. When handling large quantum of medical data set, as in the case like, Lung cancer prediction, based on symptoms and Risk factors, number of attributes/ dimensions pose a major challenge. Here in this study an attempt is made to compare the performance of the attribute selection models prior and after applying the classifier models. A total of 16 classifier models are chosen, which are based on statistical, rule based, logic based and artificial Neural network approaches. Feature set selection and ranking of attributes are done based on individual models. Confusion matrix of the models before and after dimensionality reduction is computed. Based on the confusion matrix result the models are compared and based on the performance optimal model is chosen. It is found that Multi-layer perceptron based artificial neural network model gives better performance compared to other approaches.

关键词： Lungs Computational modeling Artificial neural networks Expert systems Breast cancer

来源：评论

学校读者我要写书评

暂无评论

Human Behavior State Profile Mapping Based on Recalibrated Speech Affective Space Model

Human Behavior State Profile Mapping Based on Recalibrated S...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： N. Kamaruddin A. Wahab Abdul Wahab is now a Professor with the Faculty of Information and Communication Technology Department of Computer Science International Islamic University Malaysia (IIUM) 53100 Jalan GombakKuala Lumpur MALAYSIA

ISBN: (纸本)9781424441198

People typically associate health with only physical health. However, health is also interconnected to mental and emotional health. People who are emotionally healthy are in control of their behaviors and experience better quality of life. Hence, understanding human behavior is very important in enusuring the complete understanding of one's holistic health. In this paper, we attempt to map human behavior state (HBS) profiles onto recalibrated speech affective space model (rSASM). Such an approach is derived from hypotheses that: 1) Behavior is influenced by emotion, 2) Emotion can be quantified through speech, 3) Emotion is dynamic and changes over time and 4) the emotion conveyance is conditioned by culture. Empirical results illustrated that the proposed approach can complement other types of behavior analysis in such a way that it offers more explanatory components from the perspective of emotion primitives (valence and arousal). Four different driving HBS;namely: distracted, laughing, sleepy and normal are profiled onto the rSASM to visualize the correlation between HBS and emotion. This approach can be incorporated in the future behavior analysis to envisage better performance.

关键词： associate physical incorporated

来源：评论

学校读者我要写书评

暂无评论

An approach for efficient multimedia transmission using cache in mobile ad hoc networks

引用

Journal of Computational Information Systems 2012年第18期8卷 7567-7578页

作者： Vijayakumar, P.D.R. Ravichandran, D.T. Research Scholar and Assistant Professor Dept. of Computer Science and Engineering Info Institute of Engineering Coimbatore Tamil Nadu India India Principal Hindusthan Institute of Technology Coimbatore Tamil Nadu India India

Problem Statement: Mobile ad hoc networks have been the subject of active research for a number of years. Mobile ad hoc networking (MANET) community provides us with a wealth of technologies that enable the source and the destination nodes to route the data through a number of intermediate forwarding nodes. Approach: This paper proposes a cross layer based caching technique for transmitting multimedia data in mobile ad hoc networks (CBC). Cross layer technique is used to increase the packet delivery ratio by sharing the data using common database. Caching technique the buffer management decreases the average delay in the data transmission. Results: The simulation results prove that the proposed algorithm (CBC) outperforms when compared to the CCCL, Cooperative caching with cross layering and prefetching approach and hybrid cache in terms of packet delivery ratio and the average delay. Conclusions: The proposed algorithm is compared with CCCL and hybrid cache in terms of packet delivery ratio and average delay and shown that CBC performs better. The cross layer technique and buffer management helps in increasing the packet delivery ratio and caching technique and buffer management, prior detection of the link failure using signal strength helps in reducing the delay of the transmission in the system. © 2012 Binary Information Press.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Flow for Memory Failure Bitmap Classification

A Hybrid Flow for Memory Failure Bitmap Classification

引用

Asian Test Symposium (ATS)

作者： Jianbo Li Yu Huang Wu-Tung Cheng Chris Schuermyer Dong Xiang Eric Faehn Ruth Farrugia Department of Computer Science and Technology Tsinghua University Beijing China Mentor Graphics Corporation Wilsonville OR USA School of Software Tsinghua University Beijing China ST-Microelectronics Crolles France ST-Ericsson Grenoble France

Failure bitmaps of manufactured memory arrays may contain the information of some systematic defects and have hence been used to monitor the process and to improve the memory yield. It is important to have an accurate flow to classify the memory failure bitmap signatures. The memory bitmap signature classification can be either dictionary based or machine learning based. This paper introduces a hybrid flow that can combine dictionary based and machine learning based methods. The proposed method can enhance the accuracy of signature classification, and more importantly, it has the capability of learning new memory bitmap signatures unseen before.

关键词： Artificial neural networks Shape Vectors Dictionaries Neurons Training Support vector machine classification

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：