Search For:

Displaying 1-43 out of 43 total
A Novel Algorithm for Object Tracking with Particle Filtering and GVF-Snake
Found in: Intelligent Systems Design and Applications, International Conference on
By Dong Chun-li, Dong Yu-ning
Issue Date:November 2008
pp. 8-13
A novel adaptive object tracking algorithm with particle filtering and improved GVF-snake is proposed in this paper. Firstly, the initial contours of objects are obtained by using the background differencing method, and through the powerful searching abili...
Path Planning Algorithm for Mobile Robot Based on Path Grids Encoding Novel Mechanism
Found in: International Conference on Natural Computation
By Han-dong Zhang, Bao-hua Dong, Yu-wan Cen, Rui Zheng, Shuji Hashimoto, Ryo Saegusa
Issue Date:August 2007
pp. 351-356
Novel fixed-length decimal encoding mechanism is proposed, which is for techniques of path planning of mobile robot based on an improved genetic algorithm. Effective path grids are adopted to identify the robot?s motion surrounding. The obstacles can be de...
A Packet-Order-Keeping-Demultiplexer in Parallel-Structure Router Based on Flow Classification
Found in: Computer Networks and Mobile Computing, International Conference on
By Yue Chen, Yu-guo Dong, Yu-song Lin, Lan Ju-long
Issue Date:October 2003
pp. 415
This paper proposes a structure named Packet-Order-Keeping-Demultiplexer (POKD) and an efficient flow-classification-based packet-scheduling algorithm named FCS to solve the problem of maintaining packet disorder in the same flow for the parallel-structure...
The Method of Classification for Financial Distress Prediction Indexes of Sinopec Corp. and Its Subsidiaries Based on Self-Organizing Map Neural Network
Found in: 2012 Fourth International Conference on Computational and Information Sciences (ICCIS)
By Dong Yu,Sun Tao
Issue Date:August 2012
pp. 590-593
The prediction of financial distress has received considerable attention in accounting and corporate financial literatures for decades. Various quantitative prediction methods based on financial ratios derived from financial statements have been proposed. ...
The BP Neural Network Modeling on Worsted Spinning with Grey Superior Theory and Correlation Analysis
Found in: International Conference on Natural Computation
By Gui Liu, Wei-dong Yu
Issue Date:October 2008
pp. 374-378
The characteristic of worsted spinning procedures and the BP neural network modeling technology all have been summarily analyzed. Based on the nonlinear and vague relationship depend on fibers’ performance and craft parameters, the grey superior theory and...
Using the Principal Component Analysis and BP Network to Model the Worsted Fore-spinning Working Procedure
Found in: International Conference on Natural Computation
By Gui Liu, Wei-dong Yu
Issue Date:August 2007
pp. 353-360
The characteristic of worsted fore-spinning working procedure and the BP neural network modeling technology all have been summarily analyzed. Based on roving craft parameters? relevant characteristic, the principal component analysis method is proposed to ...
A Review of the Policy-Based QoS Architecture in IMS
Found in: Pervasive Computing, Signal Porcessing and Applications, International Conference on
By Bo Yu, Dong Yu, Junying Jia, Jinghua Lin
Issue Date:September 2010
pp. 189-192
IMS, the core architecture of NGN, becomes more and more important in modern telecommunication network. It is the main driving force to promote the evolution of telecommunication technology to
Dynamic Removal Algorithm for Constrained Delaunay Triangulations
Found in: Image and Graphics, International Conference on
By Dong-Yu Xu, Guang-Rong Tang, Yu-Pin Luo
Issue Date:December 2004
pp. 406--409
Delaunay Triangulations and Constrained Delaunay Triangulations are very popular tool used to analyze planar domain. An efficient removal algorithm is required when constructing the approximate skeleton of complicated dynamic planar domains. We present a f...
Tensor Deep Stacking Networks
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Brian Hutchinson,Li Deng,Dong Yu
Issue Date:August 2013
pp. 1944-1957
A novel deep architecture, the tensor deep stacking network (T-DSN), is presented. The T-DSN consists of multiple, stacked blocks, where each block contains a bilinear mapping from two hidden layers to the output layer, using a weight tensor to incorporate...
Pipe failure prediction: A data mining method
Found in: 2013 IEEE International Conference on Data Engineering (ICDE 2013)
By Rui Wang,Weishan Dong,Yu Wang,Ke Tang,Xin Yao
Issue Date:April 2013
pp. 1208-1218
Pipe breaks in urban water distribution network lead to significant economical and social costs, putting the service quality as well as the profit of water utilities at risk. To cope with such a situation, scheduled preventive maintenance is desired, which...
Inverted Grid-Based kNN Query Processing with MapReduce
Found in: 2012 Seventh ChinaGrid Annual Conference (ChinaGrid)
By Changqing Ji,Tingting Dong,Yu Li,Yanming Shen,Keqiu Li,Wenming Qiu,Wenyu Qu,Minyi Guo
Issue Date:September 2012
pp. 25-32
With the increasing availability of LBS (Location Based Services) and mobile internet, the amount of spatial data is growing larger and larger. It poses new requirements and challenges towards cloud environments, such as how to accomplish efficient index a...
A Multiple Description Distributed Compressed Video Sensing for Robust Transmission
Found in: Computing, Measurement, Control and Sensor Network, International Conference on
By Dong Yu,Anhong Wang,Mei Zhao
Issue Date:July 2012
pp. 13-16
This paper proposes a multiple description distributed compressed video sensing (MD-DCVS) for the robust transmission of low-power video devices. In this scheme, the encoder firstly divides the video sequence into two sub-sequences (two descriptions). Then...
Smooth Spiral Cutting Operation Strategy for High Speed Machining
Found in: Computer Science and Electronics Engineering, International Conference on
By Long Chen,Dong Yu,Yue Sun,Dongfeng Yue,Yiling Zheng
Issue Date:March 2012
pp. 652-655
In five-axis computer numerically controlled (CNC) machining of sculptured surface parts, the application of high-speed machining (HSM) is recognized as an economically viable manufacturing technology. Compared with the traditional CNC machining, high-spee...
Poster title (mass spectrometric protein profiling analyses of pathological and physiological hypertrophy cardiac muscle tissues)
Found in: Computational Advances in Bio and Medical Sciences, IEEE International Conference on
By Hyekyeong Kwon, Jang-Soo Chun, Zee-Yong Park, Dong-Yu Kim
Issue Date:February 2012
pp. 1
The mammalian heart is a muscular organ that can adjust dynamic alterations in its workload. In response to physiological or pathological stimuli and development, the heart changes hypertrophic enlargement which increase in the size of individual cardiac m...
Semantic Web Service Similarity Ranking Proposal Based on Semantic Space Vector Model
Found in: Intelligent System Design and Engineering Application, International Conference on
By ZhiHao Zeng,JiPing Hu,Ting Dong,Yu Wang
Issue Date:January 2012
pp. 917-920
With the Semantic Web services technology research work continued to deepen, the number of semantic Web services on the Internet has dramatically increased how to locate available semantic Web services quickly and easily has become an urgent and key issue....
A Conical Tool Posture Control Algorithm for Five-Axis CNC Machining
Found in: Intelligent System Design and Engineering Application, International Conference on
By Cong Geng,Dong Yu,Han Zhang,Long Chen
Issue Date:January 2012
pp. 117-120
Conical surfaces are commonly used in the industrial product design. In order to improve the machining accuracy of such parts, a conical tool posture control algorithm is proposed, which abandon disadvantages of traditional linear interpolation algorithm. ...
An Exploration on Improving Statistical Machine Translation Performance by Using Post-Editing Information
Found in: Multimedia and Signal Processing, International Conference on
By Dong Yu, Bo Xu
Issue Date:May 2011
pp. 274-277
Manually Post-editing (PE) is a traditional and effective way of improving machine translation outputs. However, it is costly and time consuming. In this paper, manually PE knowledge including word and phrase revision information is used for updating stati...
A Controllable P2P Streaming Delivery Network in IMS
Found in: Pervasive Computing, Signal Porcessing and Applications, International Conference on
By Jinghua Lin, Dong Yu, Junying Jia, Junchao Li
Issue Date:September 2010
pp. 206-211
Introducing Peer-to-Peer (P2P) technology into IP Multimedia Subsystem (IMS) is hard but important, especially to the streaming media service. Based on the strength analysis of IMS and P2P, three solutions with the features of signaling centralized and med...
The Design of Electro-hydraulic Servo System Based on Neural Network PID
Found in: Measuring Technology and Mechatronics Automation, International Conference on
By Yi-ping Sun, Xue-ren Dong, Yu-zhen Ma, Jing-rui Ma
Issue Date:March 2010
pp. 841-843
For the characteristics of electro-hydraulic servo system such as non-linear and time change, a new type of PID controller based on neural network is presented in this paper. The hardware uses TMS320LF2407 DSP chips as the main processor. The software uses...
Notice of Retraction Research on the Sustainable Development Ability Evaluation of Prefectural-Level City in Hebei Province
Found in: 2009 International Conference on Education Technology and Training (ETT 2009)
By Dong Yu-hong, Wang Xi-zhong
Issue Date:December 2009
pp. 286-289
Notice of Retraction After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE's Publication Principles. We hereby retract the content of this paper. Reas...
An Evaluation Model for Staff of Enterprise Based on Improve Niche Measure Method
Found in: Education Technology and Training, International Conference on
By Dong Yu-hong, Wang Xi-zhong
Issue Date:December 2009
pp. 282-285
The niche theory is derived from ecology. Introducing this theory into the area of human resource management and using it as an evaluation model for human resource, is an innovation as to enterprise management theory. Based on the previous research, we try...
A study on multilingual acoustic modeling for large vocabulary ASR
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Hui Lin, Li Deng, Dong Yu, Yi-fan Gong, Alex Acero, Chin-Hui Lee
Issue Date:April 2009
pp. 4333-4336
We study key issues related to multilingual acoustic modeling for automatic speech recognition (ASR) through a series of large-scale ASR experiments. Our study explores shared structures embedded in a large collection of speech data spanning over a number ...
Discriminative pronounciation learning using phonetic decoder and minimum-classification-error criterion
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Oriol Vinyals, Li Deng, Dong Yu, Alex Acero
Issue Date:April 2009
pp. 4445-4448
In this paper, we report our recent research aimed at improving the pronunciation-modeling component of a speech recognition system designed for mobile voice search. Our new discriminative learning technique overcomes the limitation of the traditional ways...
Cross-lingual speech recognition under runtime resource constraints
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Dong Yu, Li Deng, Peng Liu, Jian Wu, Yifan Gong, Alex Acero
Issue Date:April 2009
pp. 4193-4196
This paper proposes and compares four cross-lingual and bilingual automatic speech recognition techniques under the constraint that only the acoustic model (AM) of the native language is used at runtime. The first three techniques fall into the category of...
Using collective information in semi-supervised learning for speech recognition
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex Acero
Issue Date:April 2009
pp. 4633-4636
Training accurate acoustic models typically requires a large amount of transcribed data, which can be expensive to obtain. In this paper, we describe a novel semi-supervised learning algorithm for automatic speech recognition. The algorithm determines whet...
Maximizing global entropy reduction for active learning in speech recognition
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex Acero
Issue Date:April 2009
pp. 4721-4724
We propose a new active learning algorithm to address the problem of selecting a limited subset of utterances for transcribing from a large amount of unlabeled utterances so that the accuracy of the automatic speech recognition system can be maximized. Our...
Fuzzy Classification of Animal Fibers Using Neuro-Fuzzy Classifier
Found in: Intelligent Networks and Intelligent Systems, International Workshop on
By Xian-Jun Shi, Wei-Dong Yu
Issue Date:November 2008
pp. 119-122
Structure of cashmere and fine wool fiber is similar. It has been difficult to classify them accurately. Scale pattern is a major reference distinguishing them from each other. At present, the procedure is completed by experts of this field by analyzing SE...
Animal Fiber Classification Based on Fuzzy Neural Network
Found in: Fuzzy Systems and Knowledge Discovery, Fourth International Conference on
By Xian-Jun Shi, Zi-Hou Yuan, Gui Liu, Wei-Dong Yu
Issue Date:October 2008
pp. 195-199
Scale pattern of cashmere and fine wool is different and that is a major reference distinguishing them from each other. A technique commonly used consists of analyzing their SEM image for detecting cuticle scale edge height (CSH) of fiber. However, the met...
Identification of Animal Fiber Based on Scale Shape
Found in: Image and Signal Processing, Congress on
By Xian-Jun Shi, Wei-Dong Yu
Issue Date:May 2008
pp. 573-577
Scale structure pattern of animal fiber is different and that is a major reference distinguishing them from each other. There are four main scale parameters, including fiber diameters, scale interval, scale perimeter and scale area, can be used to describe...
Analysis on Wintertime Atmosphere Activities in the Northern Hemisphere
Found in: Innovative Computing ,Information and Control, International Conference on
By Xiu-Hong Wang, Gui-Fa Teng, Wei-Dong Yu
Issue Date:September 2007
pp. 589
The purpose of this paper is to describe the large- scale atmosphere activities in the northern hemisphere by predigesting the model. Based on NCAR/NCEP reanalysis data, the oscillation of atmosphere circulation between Arctic and middle latitude are valid...
Large-Margin Discriminative Training of Hidden Markov Models for Speech Recognition
Found in: International Conference on Semantic Computing
By Dong Yu, Li Deng
Issue Date:September 2007
pp. 429-438
Discriminative training has been a leading factor for improving automatic speech recognition (ASR) performance over the last decade. The traditional discriminative training, however, has been aimed to minimize empirical error rates on training sets, which ...
An Algorithm for 3D Image Segmentation
Found in: Image and Graphics, International Conference on
By Ding Zhi, Dong Yu-ning
Issue Date:August 2007
pp. 383-388
We propose a new 3D image segmentation method based on prediction, block-matching and partial 3D constraint in this paper. The algorithm only needs to set a few key points in the first image. We use intensity information and block-matching to optimize the ...
The Research on Real-Time Middleware for Open Architecture Controller
Found in: Real-Time Computing Systems and Applications, International Workshop on
By Dong Yu, Hu Lin, Ruifeng Guo, Jiangang Yang, Pengfei Xiao
Issue Date:August 2005
pp. 80-83
The Adoption of software platform is an effective method to resolve interoperability, portability, scalability and extensibility of Open Architecture Controller. However, there exist problems in now available proprietary software platforms for OAC. Conside...
Multi-Level Video Representation with Application to Keyframe Extraction
Found in: Multi-Media Modeling Conference, International
By Xiao-Dong Yu, Lei Wang, Qi Tian, Ping Xue
Issue Date:January 2004
pp. 117
Content-based video analysis calls for efficient video representation. In this paper, a novel multi-level representation of video is proposed based on the principle components derived from low-level visual features. It can characterize the video content fr...
Towards Survivable Intrusion Detection System
Found in: Hawaii International Conference on System Sciences
By Dong Yu, Deborah Frincke
Issue Date:January 2004
pp. 90299a
<p>Intrusion detection systems (IDS) are increasingly a key part of system defense, often operating under a high level of privilege to achieve their purposes. Therefore, the ability of an IDS to withstand attack is important in a production system.&l...
Design and Implementation of High-Performance Embedded Numerical Control System
Found in: 2012 IEEE 12th International Conference on Computer and Information Technology (CIT)
By Xiaohu Lu,Dong Yu,Yi Hu,Xiaobo Jia,Qiang Feng
Issue Date:October 2012
pp. 496-499
The Computer Numeric Control (CNC) is a system which executes sequential actions that describe the behaviors of the end effectors. This thesis describes an embedded numerical control system based on a heterogeneous dual-core processor. Two different operat...
A unified framework for semantic shot classification in sports videos
Found in: Proceedings of the tenth ACM international conference on Multimedia (MULTIMEDIA '02)
By Ling-Yu Duan, Min Xu, Qi Tian, Xiao-Dong Yu
Issue Date:December 2002
pp. 419-420
In this demonstration, we present a unified framework for semantic shot classification in sports videos. Unlike previous approaches, which focus on clustering by aggregating shots with similar low-level features, the proposed scheme makes use of domain kno...
ReNIC: Architectural extension to SR-IOV I/O virtualization for efficient replication
Found in: ACM Transactions on Architecture and Code Optimization (TACO)
By Jinquan Dai, Yaozu Dong, Yu Chen, Yunhong Jiang, Zhenhao Pan
Issue Date:January 2012
pp. 1-22
Virtualization is gaining popularity in cloud computing and has become the key enabling technology in cloud infrastructure. By replicating the virtual server state to multiple independent platforms, virtualization improves the reliability and availability ...
Alert confidence fusion in intrusion detection systems with extended Dempster-Shafer theory
Found in: Proceedings of the 43rd annual southeast regional conference - Volume 2 (ACM-SE 43)
By Deborah Frincke, Dong Yu
Issue Date:March 2005
pp. 142-147
Accurate identification of misuse is a key factor in determining appropriate ways to protect systems. Modern intrusion detection systems often use alerts from different sources such as hosts and sub-networks to determine whether and how to respond to an at...
RBF Neural Network Based on Fuzzy Evolution Kalman Filtering and Application in Mine Safety Monitoring
Found in: Hybrid Intelligent Systems, International Conference on
By Yong Zhang, Qing-dong Du, Shi-dong Yu, Jeng-Shyang Pan
Issue Date:August 2009
pp. 467-470
Fuzzy information fusion methods are adopted widely to resolve the complicated nonlinear problems in recent years. This paper proposes a fusion learning algorithm of radial basis function (RBF) neural network based on fuzzy evolution Kalman filtering. By u...
Quantitative Evaluation Method for the Significance of Worsted Forespinning Parameters Based on BP Network
Found in: International Conference on Natural Computation
By Gui Liu, Wei-dong Yu
Issue Date:August 2007
pp. 54-58
The BP neural network characteristic has been summarily analyzed. Based on its error back propagation method, the peculiarity of modifying its weightiness and threshold value to make the calculated error come down along the negative gradient direction, the...
Experimental Study of Combustion Regular Gasoline Engine Acceleration Transient Conditions
Found in: 2013 Fourth International Conference on Digital Manufacturing & Automation (ICDMA)
By Zhong-lu Hu,Yue-lin Li,Jiang-tao He,Dong-yu Zhang
Issue Date:June 2013
pp. 582-585
Testing on the the AJR-type gasoline Santana 2000 sedan, processed and analyzed experimental data obtained from two acceleration transient operating conditions that one is increasing speed and constant torque, another is constant speed and increase the tor...
Power Transformer Fault Diagnosis by Using the Artificial Immune Support Vector Machines
Found in: Intelligent Computation Technology and Automation, International Conference on
By Ren Jing, Huang Jia-dong, Yu Yong-zhe
Issue Date:October 2009
pp. 83-86
Dissolved gas analysis is an effective and important method for power transformer fault diagnosis. In order to improve the diagnostic accuracy of power transformer fault, the paper presents a method of hybrid intelligent algorithm of immune support vector ...