检索结果-内蒙古大学图书馆

An Active Learning Framework for Human Hand Sign Gestures and Handling Movement Epenthesis Using Enhanced Level Building Approach

引用

Procedia computer science 2015年 48卷 606-611页

作者： R. Elakkiya K. Selvamani Research Scholar Department of Computer Science & Engineering Anna University Chennai 600025 India Assistant Professor Department of Computer Science & Engineering Anna University Chennai 600025 India

Human hand detection and segmentation plays an important role in sign language recognition and human machine interaction. In this paper, a novel approach for learning a vision-based hand detection system is introduced. The main contribution of this paper includes robust boosting-based framework for real-time detection of a hand in unconstrained and heterogeneous environments. The proposed system makes use of efficient representative features which allows fast computation while changing the hand appearances and background. Moreover, this proposed strategy efficiently improves the performance while reducing the effort of hand labeling. Experimental results show that the proposed method is practically more flattering as it meets the requirements of real-time performance, accuracy and robustness. This system has been proved to work well with a reasonable amount of training samples and was computationally found to be more effective and efficient.

关键词： Sign Gestures Movement Epenthesis Level Building Algorithm Machine Learning

来源：评论

学校读者我要写书评

暂无评论

An Improved SRL Based Plagiarism Detection Technique Using Sentence Ranking

引用

Procedia computer science 2015年 46卷 223-230页

作者： Merin Paul Sangeetha Jamal Department of Computer Science Rajagiri School of Engineering and Technology Kochi-39 India Assistant Professor Department of Computer Science Rajagiri School of Engineering and Technology Kochi-39 India

Plagiarism means intellectual theft which consists of turning someone else's work as your own. Plagiarism has become widespread in many fields like institutions, companies etc. This paper proposes a new technique which uses Semantic Role Labelling and Sentence Ranking for plagiarism detection. Sentence ranking gives suspicious and original sentence pairs through vectorising the document. Then proposed method analyses and compares the ranked suspected and original documents based on the semantic allocation of each term in the sentence using SRL. It was found out that the application of sentence ranking in plagiarism detection method decreases the time of checking.

关键词： Plagiarism Plagiarism detection Semantic Role Labeling Sentence Ranking Semantic Similarity

来源：评论

学校读者我要写书评

暂无评论

Enhanced Load Balanced Min-min Algorithm for Static Meta Task Scheduling in Cloud Computing

引用

Procedia computer science 2015年 57卷 545-553页

作者： Gaurang Patel Rutvik Mehta Upendra Bhoi Computer Science & Engineering Department Parul Institute of Engineering &TechnologyVadodara Guajarat India. Assistant Professor Information TechnlogyDepartment Parul Institute of Engineering &TechnologyVadodara Guajarat India. Assistant Professor Computer Science & Engineering Department Parul Institute of TechnologyVadodara Guajarat India.

For today's most demanding service of cloud computing, there are many tasks required to be executed by the available resources to achieve best performance, reduce response time and utilize resources. There is a need of designing a new task scheduling algorithm that outperform appropriate allocation map of task. to achieve these challenges. As Load Balanced Min-Min Algorithm selects the task with minimum completion time and assigns it to appropriate resource, it sometimes does not produce better makespan and does not utilize resources effectively. This paper represents study of variety of task scheduling algorithms and modification of Load balanced Min-Min (ELBMM) algorithm for Static Meta-Task Scheduling. The modified algorithm is built based on comprehensive study of the impact of Load balanced Min-Min algorithm for Static Meta-Task Scheduling in grid computing. Enhanced Load balanced Min-Min algorithm (ELBMM) is based on Min-Min strategy and tasks rescheduling to use the unutilized resources effectively. It selects the task with maximum completion time and assigns it to appropriate resource to produce better makespan and utilize resource effectively.

关键词： Cloud Computing Meta Task Scheduling ELBMM Min-Min algorithm .

来源：评论

学校读者我要写书评

暂无评论

Credential Based Authentication Approach for Dynamic Group in Cloud Environment

引用

Procedia computer science 2015年 48卷 166-172页

作者： K. Selvamani Pradeep Kumar Arya Assistant Professor Department of Computer Science & Engineering Anna University Chennai 600025 India Research Scholar Department of Computer Science & Engineering Anna University Chennai 600025 India

Solutions provided by Cloud computing not only includes the issues inherited from related technologies such as virtualization and distributed computing, but also new concerns associated to complexity of the cloud ecosystem composed by the cloud entities and their interactions. Authentication plays an important aspect in Cloud computing. This proposed system concentrates on authentication with reasonable time factor and reduce data traffic in the Cloud computing process. In addition, this system also identifies and analysis the credential management that focus on the cloud ecosystem for dynamic groups. Moreover a framework for credential classification that analyses the unifying concept and its related service is proposed and implemented. This proposed system proves to be more efficient when compare to other existing technology.

关键词： Cloud computing Authentication Credentials Ecosystem

来源：评论

学校读者我要写书评

暂无评论

Reputed Packet Delivery Using Efficient Audit Misbehaviour Detection and Monitoring Method in Mobile Ad Hoc Networks

引用

Procedia computer science 2015年 48卷 489-496页

作者： A. Vijayakumar K. Selvamani Arya Pradeep kumar Research Scholar Department of Computer Science and EngineeringAnna University Chennai 600025 India Assistant Professor Department of Computer Science and Engineering Anna University Chennai 600025 India

Safe and secure packet delivery multi-hop Mobile Ad hoc Network (MANET) is a challenging issue in today network environment. Hence, this paper aims in proposing to identify the misbehaving nodes and eliminating them from the packet transmissions in multi-hop mobile ad hoc networks. The effective and efficient Audit Misbehaviour Detection and Monitoring Method (AMDMM) that effectively monitors the both continuous and selective packet droppers to forward the packets through the reputed nodes. In this research work, the AMDMM integrates an identification of misbehaving nodes as well as the reputation management and trustworthy route discovery based on the behavioral audits. The AMDMM evaluates nodes’ behavior on a per-packet basis, without employing energy expensive overhearing techniques or intensive acknowledgment schemes. The Simulations are carried out successfully for eliminating the misbehaving nodes from the packet transmission and to establish the effective trustworthy routing path.

关键词： Audit Monitoring: Mobile Ad hoc Networks (MANET) Misbehavior detection Reputation System

来源：评论

学校读者我要写书评

暂无评论

Adaptive and Optimized Emergency Vehicle Dispatching Algorithm for Intelligent Traffic Management System

引用

Procedia computer science 2015年 57卷 1384-1393页

作者： Partha Sarathi Chakraborty Arti Tiwari Pranshu Raj Sinha Assistant Professor Department of Computer Science and Engineering SRM University Chennai India B.Tech. CSE Student Department of Computer Science and Engineering SRM University Chennai India

Rapid development of metropolitan cities into smart cities and daily increased in number of vehicles on the roads causes increase in traffic maintenance challenges such as traffic congestion, accidents, dispatching of emergency vehicle and pollution. It will suffers people travel time, delay in response time of emergency vehicle such as ambulance, fire brigade, police etc., causes heavy loss or effects society in terms of wealth, emotions and security. The research work done in the area of Intelligent Transportation Systems and Traffic Management primarily focuses on determining effectively green light duration along with dispatching of emergency vehicle. In this research paper, we propose an algorithm which not only determines green light duration dynamically but also handles the emergency vehicle management efficiently. The objectives of the proposed algorithm are minimizing average waiting time. It always analysis the traffic situation at traffic intersection, along with continuous monitoring of emergency vehicle arrival at different lanes causes to optimize the waiting time of vehicle in lanes. It also deals with the deadlock and starvation condition, due to arrival of emergency vehicle in repeated interval of time in traffic intersection. The security level of emergency vehicle is in consideration during dispatching that assigned and verified by authorities to preserve security measures and society values. Here, the source of input on dynamic traffic condition is collected through Wireless Sensor Networks technology.

关键词： Intelligent Transportation Systems Emergency Vehicle Traffic lights Wireless Sensor Networks Traffic Management Smart Cities

来源：评论

学校读者我要写书评

暂无评论

Vision System with Audio Feedback to Assist Visually Impaired to Grasp Objects

引用

Procedia computer science 2015年 58卷 387-394页

作者： S. Gautam K.S. Sivaraman Hariharan Muralidharan A. Baskar Student Department of Computer Science and Engineering Amrita Vsishwa Vidyapeetham (University) Coimbatore India Assistant Professor Department of Computer Science and Engineering Amrita Vsishwa Vidyapeetham (University) Coimbatore India

In recent times, there have been many products that cater to the visually challenged, but only few have been readily available for regular use. The reason being, that the technology driving these products are costly, or complex to use. In this work, we propose a “Vision system with audio feedback to assist visually impaired to grasp objects”. Our proposed system eliminates these challenges, in its usability, complexity and functionality. The system is designed to serve the following: (1) Finding a desired object in the scene, in which, the object recognition is done using Weighted Matrix Algorithm from the visual input received from the camera; and (2) Assisting the user to the object's proximity, where, the user is guided using audio-feedback, at every step. This approach is represented taking the example of a commonly found object in our household. We have considered a water bottle. The above approach is found to produce suitable results.

关键词： Object Recognition Weighted Matrix Visually Impaired Audio Output Hu Moments

来源：评论

学校读者我要写书评

暂无评论

Development of wireless gyroscope-free inertial measurement unit 6

Development of wireless gyroscope-free inertial measurement ...

引用

Joint 6th International Conference on Advances in Experimental Structural engineering, AESE 2015 and 11th International Workshop on Advanced Smart Materials and Smart Structures Technology, ANCRiSST 2015

作者： Yang, Yang Yu, Xiong Bill Research Assistant Dept. of Electrical Engineering and Computer Science Case Western Reserve University ClevelandOH United States Dept. of Civil Engineering Case Western Reserve University ClevelandOH United States

This paper aims to develop a wireless gyroscope-free inertial measurement unit (GF-IMU) in order to directly measure the transversal acceleration as well as the angular acceleration and angular velocity of target structure. The sensor board only contains four 3-axial accelerometers. Multiple distributed orthogonal triads of accelerometers that consist of three non-planar distributed triads equally spaced from a central triad as a specific configuration is developed. Twelve channels of analog acceleration data is collected and transferred to digital signal using a customized data acquisition board, and then wirelessly transmitted to gateway node using iMote2 board. The iMote2 module follow IEEE 802.15.4 communication protocol. As using accelerations sensors it is not possible to determine the direction of rotation. To overcome this drawback, a weighted average coefficient is applied to fuse the information of angular acceleration and the angular velocity and thus robustly estimate the direction of rotation. The GF-IMU system is evaluated by ABB IRB140 6DOF robotic arm. This design achieves much lower power consumption, smaller dimension and lower cost than traditional inertial sensor systems. It shows great potential in analysing the translation and rotation of certain structure for the purpose of structure health monitoring (SHM) applications. © International Conference on Advances in Experimental Structural engineering. All rights reserved.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Neighbor Coverage Protocol for Reducing Rebroadcast in MANET

引用

Procedia computer science 2015年 47卷 417-423页

作者： R. Ragul Ravi V. Jayanthi PG Scholar Department of Computer science and Engineering Coimbatore institute of technology Coimbatore and 641014 India Assistant Professor Department of Computer science and Engineering Coimbatore institute of technology Coimbatore and 641014 India

Wireless networks adapt easily to changes and offers flexibility in the configuration of the network. In MANET, each node will change its location dynamically and configure itself according to the environment. An effective mechanism for route discovery in such networks is broadcasting, but routing overhead associated with broadcasting can be large in high dynamic networks. To reduce this routing overhead in MANETs, a neighbor coverage based probabilistic rebroadcast protocol is used. To determine the rebroadcast order, a novel rebroadcast delay is used and it obtains the more accurate additional coverage ratio by sensing neighbor coverage knowledge. The rebroadcast probability is calculated by merging the additional coverage ratio and connectivity factor. In the proposed method Energy Efficient Neighbor Coverage Protocol(EENCP) is introduced. In this, the node does not forward RREQ unless there is sufficient energy (battery lifetime), and until the node density in its surrounding exceeds a particular threshold. These two parameters are defined taking into consideration various statistics. EENCP analyzes these two parameters, when implementing routing discovery, and avoiding the unnecessary information sending efficiently and avoid unnecessary information transfer.

关键词： AODV DSR MANET NCPR Overhead coverage ratio

来源：评论

学校读者我要写书评

暂无评论

An Analytic Model to Optimize Search Results Using Collaborative Searching Methods

引用

Procedia computer science 2015年 57卷 1255-1264页

作者： Analp Pathak Partha Sarathi Chakraborty Semanti Sinha Mahapatra Assistant Professor Department of Computer Science and Engineering SRM University Chennai India B. Tech. CSE Student Department of Computer Science and Engineering SRM University Chennai India

In this paper, we present the idea of an ‘Analytic Search Engine Model’ that utilizes the regularly generated social media data for opinion formation. It combines the user ratings from different SNS platforms and analyzes them to form a collective opinion about a local business and ranks results in terms of this opinion formation, which ensures the reliability and quality of search results. This new mode of ranking web pages is termed as social rank, which is explained in this paper in details. It also gives the introduction to analytic search engine model, its architecture and the problems it may meet in future are presented.

关键词： Search Engine Social Search Engine Real Time Search Engine Analytic Search Engine Model Social Rank Socialytics

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：