Input Layer f = 2 f = 0 f = f = 3 1,16 1,1 1,2 1,3 2, ,2 3,3 3,16. f = 1. f = Output Layer

Size: px
Start display at page:

Download "Input Layer f = 2 f = 0 f = f = 3 1,16 1,1 1,2 1,3 2, ,2 3,3 3,16. f = 1. f = Output Layer"

Transcription

1 Using the Gow-And-Pune Netwok to Solve Poblems of Lage Dimensionality B.J. Biedis and T.D. Gedeon School of Compute Science & Engineeing The Univesity of New South Wales Sydney NSW 2052 AUSTRALIA ABSTRACT This pape investigates a technique fo ceating spasely connected feed-fowad neual netwoks which may be capable of poducing netwoks that have vey lage input and output layes. The achitectue appeas to be paticulaly suited to tasks that involve spase taining data as it is able to take advantage of the spaseness to futhe educe taining time. Some initial esults ae pesented based on tests on the bit compession poblem. 1. Intoduction Feed-fowad neual netwoks ae geneally esticted to elatively few neuons. Vey lage netwoks take a pohibitively long time to tain and contain so many connections that a huge taining set is often equied in ode to obtain good genealisation. This estiction on netwok size pevents the use of feed-fowad neual netwoks in applications which equie lage numbes of inputs and outputs. The taining time of a feed-fowad netwok may be educed by esticting the numbe of its inteconnections. One way of ensuing a small numbe of connections is to have a vey small numbe of hidden units which ae fully connected to thei suounding layes. Unfotunately netwoks of this sot ae seveely esticted in the amount of infomation they may contain. Bette use may be made of the limited numbe of connections by allowing nodes to instead be spasely connected (fo example see [8]). A lage numbe of nodes may be pesent in a netwok, with the aveage fan-in and fan-out of the units being small. If in addition to the netwok being spase the taining data is spase, it is possible to futhe decease taining time as not all nodes ae necessaily involved in the taining pocess fo each given patten. This pape will hencefoth only conside feed-fowad neual netwoks with one hidden laye, although the gowand-pune (GAP) technique pesented hee may also be applied to netwoks with multiple hidden layes. 2. Backgound While thee has been a vast amount of eseach into the constuction of neual netwok achitectues, most of this wok has been concened with obtaining esults fo poblems of compaatively small dimensionality. One appoach which has been adopted to deal with poblems of lage dimensionality is to subdivide the poblem into a numbe of subpoblems and then to use sepaate fully connected netwoks to addess each one. This division may be done in a numbe of ways: by input patten, by input node o by output node (see [11] in these confeence poceedings fo moe details). In addition hidden units may be gouped in vaious ways so as to educe the numbe of inteconnections. One inteesting suggestion is to use a factal stuctue as a netwok achitectue [9]. It is in geneal not obvious how to best subdivide a high dimensional poblem. This is a concen as inappopiately dividing of a poblem can advesely aect the pefomance of a system. Designing a seies of netwoks by hand to deal with a high dimensional poblem is an ad hoc pocess which is likely to be time consuming and poblematic. It is possible to use clusteing techniques to help identify goupings in the data, although this is an added complication. It also should be noted that thee will not always exist a good way of subdividing a high dimensional poblem. Spase netwoks oe anothe method fo dealing with high dimensional data. Instead of subdividing lage poblems they seek to stoe only the most signicant infomation. Spase netwoks ae often ceated by taining a fully connected netwok and then puning some

2 of its connections. This is commonly done eithe to impove netwok genealisation o to extact ules [3, 6]. Thee ae two poblems with this appoach. Fistly, taining a lage fully connected netwok is a lengthy pocess. Secondly, thee is no guaantee that the spase netwok that esults is close to having an optimal stuctue. Thee has been little eseach into taining netwoks which ae spase thoughout the couse of thei taining. A classication of netwoks whose stuctues do adapt duing the couse of thei taining is to be found in a pape by Fiesle [1]. Few of these netwoks, howeve, appea to be designed in ode to allow supevised leaning to be applied to vey high-dimensional poblems. One inteesting case of a spase neual netwok being applied to a highdimensional poblem is the aea of phoneme pobability estimation [8]. In this pape the autho found a andomly connected netwok pefomed bette than a fully connected with a lage numbe of connections. One technique which is often used to impove netwok pefomance is to add hidden nodes duing the taining of a neual netwok. This educes the likelihood of taining becoming tapped in local minima as the eo suface is fequently changed. It often impoves genealisation and can also educe taining time [2, 10]. The GAP method combines the techniques of gowing and puning to fom spase netwoks. 3. The GAP netwok The GAP netwok stats with a small numbe of fully connected units which ae tained using some easonable taining method (e.g. back-popagation o RPROP [7]). Once taining has levelled out, a numbe of netwok connections ae emoved simultaneously using a puning algoithm. The puning educes the numbe of inteconnections to a oo (call it n) that stays xed fo the duation of the entie taining. Duing the puning stage it may also be desiable to check fo and emove any neuons which have had all thei inputs and/o all thei outputs emoved, as these neuons do not fulll any useful function. Afte puning, a new neuon which is connected to all the input and output neuons is added with andom weights, and taining is ecommenced. It is desiable to use a test set to detemine when the netwok stuctue is to be adjusted and to decide when to nally stop adding hidden nodes. This epetition of puning connections and adding new fully connected nodes causes a spase netwok to develop which can potentially contain a vey lage numbe of nodes. Thoughout the pocess the numbe of connections emains capped, the maximum numbe of nodes being equal to n plus the numbe of links to one fully connected node. The nal numbe of nodes in the netwok is equal to n Using spaseness to limit activation spead It is possible to avoid many calculations in spase netwoks (such as GAP netwoks) when they ae tained with spase input pattens. Units that have only small fan-ins often fail to be activated when thee is spase input. When this occus thee is no need to pefom calculations involving these neuons fo a given patten. In RPROP and back popagation this benet is felt both duing the fowad popagation phase and when eos ae popagated backwads. Theshold values may be placed on neuons to educe the fequency of them ing. If this is not done, two equiements must be met in ode to limit the spead of activation. Fistly, biases must be puned in the same way as odinay weights. If this is not done, all the neuons (except those with 0 biases) ae activated duing the fowad popagation phase. Secondly, neuons must have zeo activity when the sum of thei inputs is zeo. The anti-symmetic sigmoid cuve cented on (0,0) and anging between -1 and 1 is one cuve that satis- es this equiement, although othes may be used. The fomula fo this cuve is: f(x) = 1? e?x 1 + e?x (1) The taining time that is saved by limiting activation spead dies in accodance to the spasity of the netwok and the taining set Limiting weights While testing the GAP netwok it became evident that it is necessay to limit the gowth of the connection weights in some way. If this is not done, the ecently added connections geneally fail to each the magnitude of the moe established connections and ae thus often pematuely puned. One way to educe this poblem is to stop taining just as the oot mean squae (RMS) is stabilising. Taining is stopped when the RMS fails to impove by at least some constant k between consecutive epochs. This esults in each stage of taining being vey quick, and gives the weights little time in which to gow. Two othe methods fo limiting the gowth of weights wee also tested. The second method tested involved decaying each weight by an amount of kw 2 pe epoch. A poblem, howeve, is evealed with this fom of decay when it is epesented as a tansfomation of weights, as below: w 0 = w? kw 2 sign(w) (2)

3 In the equation above w is the oiginal weight and w 0 the tansfomed weight. This tansfomation is illustated in Figue 1. As can be seen, it contains w w Fig. 1: Two tansfomations fo limiting weights. The full line is w 0 = w? kw 2, and is equivalent to using kw 2 decay. k in this case is The dotted line is w 0 = k(1?e?w=k ), which is an exponential method fo limiting weights. k hee is 11. a tuning point and this implies that given two weights w1 > w2 > 0, thee is no guaantee that w 0 1 > w0 2. It thus seems that lage weights ae ovepenalised in some cases. A thid appoach fo limiting the gowth of weights is to tansfom the weights afte each epoch accoding to the following function: w 0 = k(1? e?jwj=k ) sign(w) (3) This function (also shown in Figue 1) places a limit on the magnitude of the weights yet peseves the odeing of the weights. These thee methods fo limiting the gowth of weights will be efeed to espectively as abbeviated taining, kw 2 decay and exponential limitation Specic netwok details Fo the puposes of testing, the GAP netwoks used wee kept as simple as possible fo ease of analysis and eplication. The puning algoithm used simply eliminates the connections whose weights have the smallest absolute values (this is sometimes efeed to as magnitude-based puning). Seveal connections wee emoved at the same time with no taining being done between deletions. No neuons wee emoved duing taining. The RPROP taining method was selected as it geneally pefoms bette than back popagation and it lacks the leaning ate paamete [7]. The weights and update values (used in RPROP) wee not changed when taining was ecommenced afte an adjustment of the netwok stuctue. The activation cuve used was that shown in Equation 1. No noise was employed, no was thesholding. Each of the thee methods mentioned above fo limiting the gowth of weights was tested. Except fo in the abbeviated taining case, taining was stopped at each stage of netwok gowth when the RMS had failed to impove by at least 0.1% ove 20 epochs. 4. Tests 4.1. Measuing success The GAP netwok was tested on the bit compession poblem, which although not a eal-wold poblem does allow fo an easy visual intepetation of the esults. It is also small enough to be un many times. The bit compession poblem has pattens, with each patten having one input set a dieent input in each patten. The output is the same as the input, thus ceating an auto-associative netwok. Fo a netwok with one hidden laye, the optimal spase solution to the poblem has 32 weights and hidden units, with each input connecting to its coesponding output via some hidden unit. Each hidden unit connects one and only one set of matching inputs and outputs. It is possible to compae the eal esults with this ideal. In ode to make this compaison two numbes ae used: the numbe of input-to-output connections, which measues how many coesponding input and output nodes ae connected, and the imbalance of the netwok stuctue, which eectively measues how well the hidden laye is used. In the optimal solution evey input and hidden node has one output link and evey hidden and output node has one input link. That is, evey fan-in and fan-out in the netwok is of size one. The imbalance is the sum of the absolute dieences of 1 and each fan-in o fan-out (see Equation 4 and Figue 2). 4X X imbalance = j1? f ij j (4) i=1 j=1 Input Laye f = 2 f = 0 f = 1 1,1 1,2 1,3 f 2,1= 1 f 2,2= 1 f 2,3= f 3,1= 1 f = 1 f = 0 3,2 3,3 f 4,1= 1 f 4,2= 0 f 4,3= Output Laye Fig. 2: Calculating the imbalance measue f = 3 1, f = 1 2, f = 2 3, f 4,= 1

4 Input Laye Output Laye Fig. 3: Example of a tained netwok An example of a tained netwok is given in Figue 3. The biases have been omitted as all the bias weights wee emoved by puning. The numbe of connections in this example is 15, the imbalance 4 and the nal RMS It would only be necessay to move one connection to give this netwok an ideal stuctue: the link between hidden neuon 14 and output neuon 12 would need to be moved to connect input neuon 15 and hidden neuon 5. It is inteesting to note that thee is aleady a connection between the 5 th hidden neuon and 15 th output unit. Clealy the eo is less having a connection to a hidden neuon that is neve activated than it would be to have a connection to a neuon that is activated by the wong taining pattens Results The GAP netwok was tested using each of the thee weight limitation methods descibed above with seveal values of k fo each. The best values tested fo abbeviated taining, kw 2 decay, and exponential limitation wee , and 0.11 espectively. In all cases the pefomance was faily sensitive to changes in k. This is not, howeve, necessaily a poblem as the best choice of paamete could pove to be elatively independent of the taining set used, at least fo the last two methods. Also tested was a netwok with fully connected hidden nodes which was tained, puned so as to contain 32 connections, and etained. The esults of the the fully connected netwok and the GAP netwoks (using the best values of k) ae given in Table 1. As can be seen the exponential limitation technique out-pefomed the othe methods in all but taining time. The abbeviated taining method caused taining to poceed vey quickly, although the savings have pobably been exaggeated by the simplicity of the taining data. The peiod of attening that was avoided in the case of the abbeviated taining technique made up an unusually high popotion of the taining time of the othe two techniques. It should be noted that the pefomance of the netwok when using the abbeviated taining technique was fa bette than when the RMS was allowed to stabilise futhe, assuming that no othe method was used to limit the gowth of weights. In all cases the GAP netwoks pefomed bette than the fully connected netwok and wee quicke to tain. It may be that the pefomance of fully connected netwok could be impoved by puning the netwok moe gadually, with taining being done between punings. Figue 4 shows the aveage RMS eached befoe each puning occued when using the exponential limitation method with k set to 11. The nal point shown was obtained afte the nal pune and a subsequent taining session. The nal netwok stuctue contained 32 weights wheeas while in the pocess of taining it had Conclusion The fact that the RMS dops as exta nodes ae added is encouaging as it conms that adding exta hidden nodes allows moe infomation to be

5 Taining Input-to-output Final Numbe of Pefect Best k Imbalance method connections RMS multiplications solutions Fully connected, afte puning N/A : % and etaining GAP: Abbeviated taining : % GAP: kw 2 decay : % GAP: Exponential limitation : % Table: 1: The esults fom fou sets of spase netwoks. The st ow was obtained fom a netwok with fully connected hidden nodes which was tained, puned to 32 connections and etained. The emaining thee ows show the GAP esults obtained when using thee methods of weight limitation. Except whee othewise indicated, all values ae the mean of 50 tests. RMS Numbe of hidden neuons Fig. 4: The RMS is shown plotted against the numbe of hidden units. The RMS is measued afte each peiod of taining, but befoe puning. The last point (at position 17) is the RMS afte the nal puning and a subsequent taining. stoed in the netwok even though the numbe of connections emains constant. The numbe of input-to-output connections and the imbalance gues also indicate the achitectue tends to move towads that of the optimal netwok. The bit compession poblem is a useful benchmak poblem fo evaluating GAP achitectues, as it is quick to un and the esults ae easy to intepet. 6. Futhe Wok Puning methods moe sophisticated than magnitude-based puning, such as optimal bain damage [5] and Kanin's method [4], might yield signicant impovements in GAP netwoks, as they ae subject to continuous heavy puning. The adoption of a cascade of neuons could also be wothwhile [10]. A futhe possibility is to eintoduce a few deleted connections thoughout taining, pehaps on a andom basis. The most impotant eseach still to be done is to test the GAP method on a ange of lage ealwold poblems. The authos ae cuently testing the GAP netwok in the context of infomation etieval using standad infomation etieval benchmak tests. Any applications which equie lage numbes of inputs and outputs could in time benet fom the use of the GAP achitectue. Acknowledgements The authos ae gateful to Nicholas Teadgold fo his advice concening gowing neual netwoks and use of the RPROP algoithm. Refeences [1] E. Fiesle. Compaative bibliogaphy of ontogenic neual netwoks. In Poceedings of the Intenational Confeence on Aticial Neual Netwoks (ICANN 94), pages 793{796, [2] D. Hais and T. D. Gedeon. Adaptive insetion of units in feed-fowad netwoks. In Poceedings 4th Intenational Confeence on Neual Netwoks and thei Applications, [3] D. Hais and T. D. Gedeon. Netwok eduction techniques. In Poceedings Intenational Confeence Neual Netwoks Methodologies and Applications, volume 1, pages 119{ 126, [4] E. Kanin. A simple pocedue fo puning back-popagation tained neual netwoks. IEEE Tansactions on Neual Netwoks, 1(2):239{242, [5] Y. Le Cun, J. Denke, and S. Solla. Optimal bain damage. In D. Touetzky, edito, Advances in Neual Infomation Pocessing, volume 2, pages 598{605. Mogan Kauman, [6] R. Reed. Puning algoithms, a suvey. IEEE Tansactions on Neual Netwoks, 4(5):740{ 747, [7] M. Riedmille and H. Baun. A diect adaptive method fo faste backpopagation leaning: The RPROP algoithm. In Poceedings of

6 the IEEE Intenational Confeence on Neual Netwoks (ICNN), pages 586{591, [8] N. Stom. Phoneme pobability estimation with dynamic spasely connected aticial neual netwoks. The Fee Speech Jounal, 1(5), [9] J. P. Sutton. Neuobiological and computational aspects of modulaity. In Poceedings of the Ninth Austalian Confeence on Neual Netwoks (ACNN'98), Febuay [10] N. Teadgold and T. D. Gedeon. A cascade netwok algoithm employing pogessive RPROP. In Biological and Aticial Computation: Fom Neuoscience to Technology. Intenational Wok-Confeence on Aticial and Natual Neual Netwoks (IWANN'97), pages 733{742, [11] W. X. Wen. SGNNN: Self-geneating netwok of neual netwoks. In Poceedings of the Ninth Austalian Confeence on Neual Netwoks (ACNN'98), Febuay 1998.

Controlled Information Maximization for SOM Knowledge Induced Learning

Controlled Information Maximization for SOM Knowledge Induced Learning 3 Int'l Conf. Atificial Intelligence ICAI'5 Contolled Infomation Maximization fo SOM Knowledge Induced Leaning Ryotao Kamimua IT Education Cente and Gaduate School of Science and Technology, Tokai Univeisity

More information

Journal of World s Electrical Engineering and Technology J. World. Elect. Eng. Tech. 1(1): 12-16, 2012

Journal of World s Electrical Engineering and Technology J. World. Elect. Eng. Tech. 1(1): 12-16, 2012 2011, Scienceline Publication www.science-line.com Jounal of Wold s Electical Engineeing and Technology J. Wold. Elect. Eng. Tech. 1(1): 12-16, 2012 JWEET An Efficient Algoithm fo Lip Segmentation in Colo

More information

IP Network Design by Modified Branch Exchange Method

IP Network Design by Modified Branch Exchange Method Received: June 7, 207 98 IP Netwok Design by Modified Banch Method Kaiat Jaoenat Natchamol Sichumoenattana 2* Faculty of Engineeing at Kamphaeng Saen, Kasetsat Univesity, Thailand 2 Faculty of Management

More information

A Two-stage and Parameter-free Binarization Method for Degraded Document Images

A Two-stage and Parameter-free Binarization Method for Degraded Document Images A Two-stage and Paamete-fee Binaization Method fo Degaded Document Images Yung-Hsiang Chiu 1, Kuo-Liang Chung 1, Yong-Huai Huang 2, Wei-Ning Yang 3, Chi-Huang Liao 4 1 Depatment of Compute Science and

More information

Detection and Recognition of Alert Traffic Signs

Detection and Recognition of Alert Traffic Signs Detection and Recognition of Alet Taffic Signs Chia-Hsiung Chen, Macus Chen, and Tianshi Gao 1 Stanfod Univesity Stanfod, CA 9305 {echchen, macuscc, tianshig}@stanfod.edu Abstact Taffic signs povide dives

More information

Effects of Model Complexity on Generalization Performance of Convolutional Neural Networks

Effects of Model Complexity on Generalization Performance of Convolutional Neural Networks Effects of Model Complexity on Genealization Pefomance of Convolutional Neual Netwoks Tae-Jun Kim 1, Dongsu Zhang 2, and Joon Shik Kim 3 1 Seoul National Univesity, Seoul 151-742, Koea, E-mail: tjkim@bi.snu.ac.k

More information

An Unsupervised Segmentation Framework For Texture Image Queries

An Unsupervised Segmentation Framework For Texture Image Queries An Unsupevised Segmentation Famewok Fo Textue Image Queies Shu-Ching Chen Distibuted Multimedia Infomation System Laboatoy School of Compute Science Floida Intenational Univesity Miami, FL 33199, USA chens@cs.fiu.edu

More information

Segmentation of Casting Defects in X-Ray Images Based on Fractal Dimension

Segmentation of Casting Defects in X-Ray Images Based on Fractal Dimension 17th Wold Confeence on Nondestuctive Testing, 25-28 Oct 2008, Shanghai, China Segmentation of Casting Defects in X-Ray Images Based on Factal Dimension Jue WANG 1, Xiaoqin HOU 2, Yufang CAI 3 ICT Reseach

More information

Lecture # 04. Image Enhancement in Spatial Domain

Lecture # 04. Image Enhancement in Spatial Domain Digital Image Pocessing CP-7008 Lectue # 04 Image Enhancement in Spatial Domain Fall 2011 2 domains Spatial Domain : (image plane) Techniques ae based on diect manipulation of pixels in an image Fequency

More information

And Ph.D. Candidate of Computer Science, University of Putra Malaysia 2 Faculty of Computer Science and Information Technology,

And Ph.D. Candidate of Computer Science, University of Putra Malaysia 2 Faculty of Computer Science and Information Technology, (IJCSIS) Intenational Jounal of Compute Science and Infomation Secuity, Efficient Candidacy Reduction Fo Fequent Patten Mining M.H Nadimi-Shahaki 1, Nowati Mustapha 2, Md Nasi B Sulaiman 2, Ali B Mamat

More information

On Error Estimation in Runge-Kutta Methods

On Error Estimation in Runge-Kutta Methods Leonado Jounal of Sciences ISSN 1583-0233 Issue 18, Januay-June 2011 p. 1-10 On Eo Estimation in Runge-Kutta Methods Ochoche ABRAHAM 1,*, Gbolahan BOLARIN 2 1 Depatment of Infomation Technology, 2 Depatment

More information

Spiral Recognition Methodology and Its Application for Recognition of Chinese Bank Checks

Spiral Recognition Methodology and Its Application for Recognition of Chinese Bank Checks Spial Recognition Methodology and Its Application fo Recognition of Chinese Bank Checks Hanshen Tang 1, Emmanuel Augustin 2, Ching Y. Suen 1, Olivie Baet 2, Mohamed Cheiet 3 1 Cente fo Patten Recognition

More information

RANDOM IRREGULAR BLOCK-HIERARCHICAL NETWORKS: ALGORITHMS FOR COMPUTATION OF MAIN PROPERTIES

RANDOM IRREGULAR BLOCK-HIERARCHICAL NETWORKS: ALGORITHMS FOR COMPUTATION OF MAIN PROPERTIES RANDOM IRREGULAR BLOCK-HIERARCHICAL NETWORKS: ALGORITHMS FOR COMPUTATION OF MAIN PROPERTIES Svetlana Avetisyan Mikayel Samvelyan* Matun Kaapetyan Yeevan State Univesity Abstact In this pape, the class

More information

THE THETA BLOCKCHAIN

THE THETA BLOCKCHAIN THE THETA BLOCKCHAIN Theta is a decentalized video steaming netwok, poweed by a new blockchain and token. By Theta Labs, Inc. Last Updated: Nov 21, 2017 esion 1.0 1 OUTLINE Motivation Reputation Dependent

More information

Shortest Paths for a Two-Robot Rendez-Vous

Shortest Paths for a Two-Robot Rendez-Vous Shotest Paths fo a Two-Robot Rendez-Vous Eik L Wyntes Joseph S B Mitchell y Abstact In this pape, we conside an optimal motion planning poblem fo a pai of point obots in a plana envionment with polygonal

More information

Modelling, simulation, and performance analysis of a CAN FD system with SAE benchmark based message set

Modelling, simulation, and performance analysis of a CAN FD system with SAE benchmark based message set Modelling, simulation, and pefomance analysis of a CAN FD system with SAE benchmak based message set Mahmut Tenuh, Panagiotis Oikonomidis, Peiklis Chachalakis, Elias Stipidis Mugla S. K. Univesity, TR;

More information

Point-Biserial Correlation Analysis of Fuzzy Attributes

Point-Biserial Correlation Analysis of Fuzzy Attributes Appl Math Inf Sci 6 No S pp 439S-444S (0 Applied Mathematics & Infomation Sciences An Intenational Jounal @ 0 NSP Natual Sciences Publishing o Point-iseial oelation Analysis of Fuzzy Attibutes Hao-En hueh

More information

Slotted Random Access Protocol with Dynamic Transmission Probability Control in CDMA System

Slotted Random Access Protocol with Dynamic Transmission Probability Control in CDMA System Slotted Random Access Potocol with Dynamic Tansmission Pobability Contol in CDMA System Intaek Lim 1 1 Depatment of Embedded Softwae, Busan Univesity of Foeign Studies, itlim@bufs.ac.k Abstact In packet

More information

Illumination methods for optical wear detection

Illumination methods for optical wear detection Illumination methods fo optical wea detection 1 J. Zhang, 2 P.P.L.Regtien 1 VIMEC Applied Vision Technology, Coy 43, 5653 LC Eindhoven, The Nethelands Email: jianbo.zhang@gmail.com 2 Faculty Electical

More information

Module 6 STILL IMAGE COMPRESSION STANDARDS

Module 6 STILL IMAGE COMPRESSION STANDARDS Module 6 STILL IMAE COMPRESSION STANDARDS Lesson 17 JPE-2000 Achitectue and Featues Instuctional Objectives At the end of this lesson, the students should be able to: 1. State the shotcomings of JPE standad.

More information

Assessment of Track Sequence Optimization based on Recorded Field Operations

Assessment of Track Sequence Optimization based on Recorded Field Operations Assessment of Tack Sequence Optimization based on Recoded Field Opeations Matin A. F. Jensen 1,2,*, Claus G. Søensen 1, Dionysis Bochtis 1 1 Aahus Univesity, Faculty of Science and Technology, Depatment

More information

Prioritized Traffic Recovery over GMPLS Networks

Prioritized Traffic Recovery over GMPLS Networks Pioitized Taffic Recovey ove GMPLS Netwoks 2005 IEEE. Pesonal use of this mateial is pemitted. Pemission fom IEEE mu be obtained fo all othe uses in any cuent o futue media including epinting/epublishing

More information

Embeddings into Crossed Cubes

Embeddings into Crossed Cubes Embeddings into Cossed Cubes Emad Abuelub *, Membe, IAENG Abstact- The hypecube paallel achitectue is one of the most popula inteconnection netwoks due to many of its attactive popeties and its suitability

More information

Towards Adaptive Information Merging Using Selected XML Fragments

Towards Adaptive Information Merging Using Selected XML Fragments Towads Adaptive Infomation Meging Using Selected XML Fagments Ho-Lam Lau and Wilfed Ng Depatment of Compute Science and Engineeing, The Hong Kong Univesity of Science and Technology, Hong Kong {lauhl,

More information

A Memory Efficient Array Architecture for Real-Time Motion Estimation

A Memory Efficient Array Architecture for Real-Time Motion Estimation A Memoy Efficient Aay Achitectue fo Real-Time Motion Estimation Vasily G. Moshnyaga and Keikichi Tamau Depatment of Electonics & Communication, Kyoto Univesity Sakyo-ku, Yoshida-Honmachi, Kyoto 66-1, JAPAN

More information

An Optimised Density Based Clustering Algorithm

An Optimised Density Based Clustering Algorithm Intenational Jounal of Compute Applications (0975 8887) Volume 6 No.9, Septembe 010 An Optimised Density Based Clusteing Algoithm J. Hencil Pete Depatment of Compute Science St. Xavie s College, Palayamkottai,

More information

Optical Flow for Large Motion Using Gradient Technique

Optical Flow for Large Motion Using Gradient Technique SERBIAN JOURNAL OF ELECTRICAL ENGINEERING Vol. 3, No. 1, June 2006, 103-113 Optical Flow fo Lage Motion Using Gadient Technique Md. Moshaof Hossain Sake 1, Kamal Bechkoum 2, K.K. Islam 1 Abstact: In this

More information

IP Multicast Simulation in OPNET

IP Multicast Simulation in OPNET IP Multicast Simulation in OPNET Xin Wang, Chien-Ming Yu, Henning Schulzinne Paul A. Stipe Columbia Univesity Reutes Depatment of Compute Science 88 Pakway Dive South New Yok, New Yok Hauppuage, New Yok

More information

Combinatorial Mobile IP: A New Efficient Mobility Management Using Minimized Paging and Local Registration in Mobile IP Environments

Combinatorial Mobile IP: A New Efficient Mobility Management Using Minimized Paging and Local Registration in Mobile IP Environments Wieless Netwoks 0, 3 32, 200 200 Kluwe Academic Publishes. Manufactued in The Nethelands. Combinatoial Mobile IP: A New Efficient Mobility Management Using Minimized Paging and Local Registation in Mobile

More information

HISTOGRAMS are an important statistic reflecting the

HISTOGRAMS are an important statistic reflecting the JOURNAL OF L A T E X CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 1 D 2 HistoSketch: Disciminative and Dynamic Similaity-Peseving Sketching of Steaming Histogams Dingqi Yang, Bin Li, Laua Rettig, and Philippe

More information

Lecture 27: Voronoi Diagrams

Lecture 27: Voronoi Diagrams We say that two points u, v Y ae in the same connected component of Y if thee is a path in R N fom u to v such that all the points along the path ae in the set Y. (Thee ae two connected components in the

More information

Clustering Interval-valued Data Using an Overlapped Interval Divergence

Clustering Interval-valued Data Using an Overlapped Interval Divergence Poc. of the 8th Austalasian Data Mining Confeence (AusDM'9) Clusteing Inteval-valued Data Using an Ovelapped Inteval Divegence Yongli Ren Yu-Hsn Liu Jia Rong Robet Dew School of Infomation Engineeing,

More information

High performance CUDA based CNN image processor

High performance CUDA based CNN image processor High pefomance UDA based NN image pocesso GEORGE VALENTIN STOIA, RADU DOGARU, ELENA RISTINA STOIA Depatment of Applied Electonics and Infomation Engineeing Univesity Politehnica of Buchaest -3, Iuliu Maniu

More information

The International Conference in Knowledge Management (CIKM'94), Gaithersburg, MD, November 1994.

The International Conference in Knowledge Management (CIKM'94), Gaithersburg, MD, November 1994. The Intenational Confeence in Knowledge Management (CIKM'94), Gaithesbug, MD, Novembe 994. Hashing by Poximity to Pocess Duplicates in Spatial Databases Walid G. Aef Matsushita Infomation Technology Laboatoy

More information

ANALYTIC PERFORMANCE MODELS FOR SINGLE CLASS AND MULTIPLE CLASS MULTITHREADED SOFTWARE SERVERS

ANALYTIC PERFORMANCE MODELS FOR SINGLE CLASS AND MULTIPLE CLASS MULTITHREADED SOFTWARE SERVERS ANALYTIC PERFORMANCE MODELS FOR SINGLE CLASS AND MULTIPLE CLASS MULTITHREADED SOFTWARE SERVERS Daniel A Menascé Mohamed N Bennani Dept of Compute Science Oacle, Inc Geoge Mason Univesity 1211 SW Fifth

More information

DEADLOCK AVOIDANCE IN BATCH PROCESSES. M. Tittus K. Åkesson

DEADLOCK AVOIDANCE IN BATCH PROCESSES. M. Tittus K. Åkesson DEADLOCK AVOIDANCE IN BATCH PROCESSES M. Tittus K. Åkesson Univesity College Boås, Sweden, e-mail: Michael.Tittus@hb.se Chalmes Univesity of Technology, Gothenbug, Sweden, e-mail: ka@s2.chalmes.se Abstact:

More information

An Extension to the Local Binary Patterns for Image Retrieval

An Extension to the Local Binary Patterns for Image Retrieval , pp.81-85 http://x.oi.og/10.14257/astl.2014.45.16 An Extension to the Local Binay Pattens fo Image Retieval Zhize Wu, Yu Xia, Shouhong Wan School of Compute Science an Technology, Univesity of Science

More information

arxiv: v2 [physics.soc-ph] 30 Nov 2016

arxiv: v2 [physics.soc-ph] 30 Nov 2016 Tanspotation dynamics on coupled netwoks with limited bandwidth Ming Li 1,*, Mao-Bin Hu 1, and Bing-Hong Wang 2, axiv:1607.05382v2 [physics.soc-ph] 30 Nov 2016 1 School of Engineeing Science, Univesity

More information

A Minutiae-based Fingerprint Matching Algorithm Using Phase Correlation

A Minutiae-based Fingerprint Matching Algorithm Using Phase Correlation A Minutiae-based Fingepint Matching Algoithm Using Phase Coelation Autho Chen, Weiping, Gao, Yongsheng Published 2007 Confeence Title Digital Image Computing: Techniques and Applications DOI https://doi.og/10.1109/dicta.2007.4426801

More information

AUTOMATED LOCATION OF ICE REGIONS IN RADARSAT SAR IMAGERY

AUTOMATED LOCATION OF ICE REGIONS IN RADARSAT SAR IMAGERY AUTOMATED LOCATION OF ICE REGIONS IN RADARSAT SAR IMAGERY Chistophe Waceman (1), William G. Pichel (2), Pablo Clement-Colón (2) (1) Geneal Dynamics Advanced Infomation Systems, P.O. Box 134008 Ann Abo

More information

Conversion Functions for Symmetric Key Ciphers

Conversion Functions for Symmetric Key Ciphers Jounal of Infomation Assuance and Secuity 2 (2006) 41 50 Convesion Functions fo Symmetic Key Ciphes Deba L. Cook and Angelos D. Keomytis Depatment of Compute Science Columbia Univesity, mail code 0401

More information

A modal estimation based multitype sensor placement method

A modal estimation based multitype sensor placement method A modal estimation based multitype senso placement method *Xue-Yang Pei 1), Ting-Hua Yi 2) and Hong-Nan Li 3) 1),)2),3) School of Civil Engineeing, Dalian Univesity of Technology, Dalian 116023, China;

More information

ANN Models for Coplanar Strip Line Analysis and Synthesis

ANN Models for Coplanar Strip Line Analysis and Synthesis 200 IJCSNS Intenational Jounal of Compute Science and Netwok Secuity, VOL.8 No.10, Octobe 2008 Models fo Coplana Stip Line Analysis and J.Lakshmi Naayana D.K.Si Rama Kishna D.L.Patap Reddy Chalapathi Institute

More information

On the Conversion between Binary Code and Binary-Reflected Gray Code on Boolean Cubes

On the Conversion between Binary Code and Binary-Reflected Gray Code on Boolean Cubes On the Convesion between Binay Code and BinayReflected Gay Code on Boolean Cubes The Havad community has made this aticle openly available. Please shae how this access benefits you. You stoy mattes Citation

More information

LOSSLESS audio coding is used in such applications as

LOSSLESS audio coding is used in such applications as INTL JOURNAL OF ELECTRONICS AND TELECOMMUNICATIONS, 2013, VOL. 59, NO. 1, PP. 17 23 Manuscipt eceived Januay 10, 2013; evised Mach, 2013. DOI: 10.2478/eletel-2013-0002 Novel Ideas fo Lossless Audio Coding

More information

A New Finite Word-length Optimization Method Design for LDPC Decoder

A New Finite Word-length Optimization Method Design for LDPC Decoder A New Finite Wod-length Optimization Method Design fo LDPC Decode Jinlei Chen, Yan Zhang and Xu Wang Key Laboatoy of Netwok Oiented Intelligent Computation Shenzhen Gaduate School, Habin Institute of Technology

More information

A Neural Network Model for Storing and Retrieving 2D Images of Rotated 3D Object Using Principal Components

A Neural Network Model for Storing and Retrieving 2D Images of Rotated 3D Object Using Principal Components A Neual Netwok Model fo Stong and Reteving 2D Images of Rotated 3D Object Using Pncipal Components Tsukasa AMANO, Shuichi KUROGI, Ayako EGUCHI, Takeshi NISHIDA, Yasuhio FUCHIKAWA Depatment of Contol Engineeng,

More information

ART GALLERIES WITH INTERIOR WALLS. March 1998

ART GALLERIES WITH INTERIOR WALLS. March 1998 ART GALLERIES WITH INTERIOR WALLS Andé Kündgen Mach 1998 Abstact. Conside an at galley fomed by a polygon on n vetices with m pais of vetices joined by inteio diagonals, the inteio walls. Each inteio wall

More information

Generalized Grey Target Decision Method Based on Decision Makers Indifference Attribute Value Preferences

Generalized Grey Target Decision Method Based on Decision Makers Indifference Attribute Value Preferences Ameican Jounal of ata ining and Knowledge iscovey 27; 2(4): 2-8 http://www.sciencepublishinggoup.com//admkd doi:.648/.admkd.2724.2 Genealized Gey Taget ecision ethod Based on ecision akes Indiffeence Attibute

More information

Positioning of a robot based on binocular vision for hand / foot fusion Long Han

Positioning of a robot based on binocular vision for hand / foot fusion Long Han 2nd Intenational Confeence on Advances in Mechanical Engineeing and Industial Infomatics (AMEII 26) Positioning of a obot based on binocula vision fo hand / foot fusion Long Han Compute Science and Technology,

More information

Transmission Lines Modeling Based on Vector Fitting Algorithm and RLC Active/Passive Filter Design

Transmission Lines Modeling Based on Vector Fitting Algorithm and RLC Active/Passive Filter Design Tansmission Lines Modeling Based on Vecto Fitting Algoithm and RLC Active/Passive Filte Design Ahmed Qasim Tuki a,*, Nashien Fazilah Mailah b, Mohammad Lutfi Othman c, Ahmad H. Saby d Cente fo Advanced

More information

Hierarchically Clustered P2P Streaming System

Hierarchically Clustered P2P Streaming System Hieachically Clusteed P2P Steaming System Chao Liang, Yang Guo, and Yong Liu Polytechnic Univesity Thomson Lab Booklyn, NY 11201 Pinceton, NJ 08540 Abstact Pee-to-pee video steaming has been gaining populaity.

More information

A Novel Automatic White Balance Method For Digital Still Cameras

A Novel Automatic White Balance Method For Digital Still Cameras A Novel Automatic White Balance Method Fo Digital Still Cameas Ching-Chih Weng 1, Home Chen 1,2, and Chiou-Shann Fuh 3 Depatment of Electical Engineeing, 2 3 Gaduate Institute of Communication Engineeing

More information

Separability and Topology Control of Quasi Unit Disk Graphs

Separability and Topology Control of Quasi Unit Disk Graphs Sepaability and Topology Contol of Quasi Unit Disk Gaphs Jiane Chen, Anxiao(Andew) Jiang, Iyad A. Kanj, Ge Xia, and Fenghui Zhang Dept. of Compute Science, Texas A&M Univ. College Station, TX 7784. {chen,

More information

Obstacle Avoidance of Autonomous Mobile Robot using Stereo Vision Sensor

Obstacle Avoidance of Autonomous Mobile Robot using Stereo Vision Sensor Obstacle Avoidance of Autonomous Mobile Robot using Steeo Vision Senso Masako Kumano Akihisa Ohya Shin ichi Yuta Intelligent Robot Laboatoy Univesity of Tsukuba, Ibaaki, 35-8573 Japan E-mail: {masako,

More information

INFORMATION DISSEMINATION DELAY IN VEHICLE-TO-VEHICLE COMMUNICATION NETWORKS IN A TRAFFIC STREAM

INFORMATION DISSEMINATION DELAY IN VEHICLE-TO-VEHICLE COMMUNICATION NETWORKS IN A TRAFFIC STREAM INFORMATION DISSEMINATION DELAY IN VEHICLE-TO-VEHICLE COMMUNICATION NETWORKS IN A TRAFFIC STREAM LiLi Du Depatment of Civil, Achitectual, and Envionmental Engineeing Illinois Institute of Technology 3300

More information

The EigenRumor Algorithm for Ranking Blogs

The EigenRumor Algorithm for Ranking Blogs he EigenRumo Algoithm fo Ranking Blogs Ko Fujimua N Cybe Solutions Laboatoies N Copoation akafumi Inoue N Cybe Solutions Laboatoies N Copoation Masayuki Sugisaki N Resonant Inc. ABSRAC he advent of easy

More information

Scaling Location-based Services with Dynamically Composed Location Index

Scaling Location-based Services with Dynamically Composed Location Index Scaling Location-based Sevices with Dynamically Composed Location Index Bhuvan Bamba, Sangeetha Seshadi and Ling Liu Distibuted Data Intensive Systems Laboatoy (DiSL) College of Computing, Geogia Institute

More information

Image Enhancement in the Spatial Domain. Spatial Domain

Image Enhancement in the Spatial Domain. Spatial Domain 8-- Spatial Domain Image Enhancement in the Spatial Domain What is spatial domain The space whee all pixels fom an image In spatial domain we can epesent an image by f( whee x and y ae coodinates along

More information

Title. Author(s)NOMURA, K.; MOROOKA, S. Issue Date Doc URL. Type. Note. File Information

Title. Author(s)NOMURA, K.; MOROOKA, S. Issue Date Doc URL. Type. Note. File Information Title CALCULATION FORMULA FOR A MAXIMUM BENDING MOMENT AND THE TRIANGULAR SLAB WITH CONSIDERING EFFECT OF SUPPO UNIFORM LOAD Autho(s)NOMURA, K.; MOROOKA, S. Issue Date 2013-09-11 Doc URL http://hdl.handle.net/2115/54220

More information

Communication vs Distributed Computation: an alternative trade-off curve

Communication vs Distributed Computation: an alternative trade-off curve Communication vs Distibuted Computation: an altenative tade-off cuve Yahya H. Ezzeldin, Mohammed amoose, Chistina Fagouli Univesity of Califonia, Los Angeles, CA 90095, USA, Email: {yahya.ezzeldin, mkamoose,

More information

Configuring RSVP-ATM QoS Interworking

Configuring RSVP-ATM QoS Interworking Configuing RSVP-ATM QoS Intewoking Last Updated: Januay 15, 2013 This chapte descibes the tasks fo configuing the RSVP-ATM QoS Intewoking featue, which povides suppot fo Contolled Load Sevice using RSVP

More information

User Specified non-bonded potentials in gromacs

User Specified non-bonded potentials in gromacs Use Specified non-bonded potentials in gomacs Apil 8, 2010 1 Intoduction On fist appeaances gomacs, unlike MD codes like LAMMPS o DL POLY, appeas to have vey little flexibility with egads to the fom of

More information

ADDING REALISM TO SOURCE CHARACTERIZATION USING A GENETIC ALGORITHM

ADDING REALISM TO SOURCE CHARACTERIZATION USING A GENETIC ALGORITHM ADDING REALISM TO SOURCE CHARACTERIZATION USING A GENETIC ALGORITHM Luna M. Rodiguez*, Sue Ellen Haupt, and Geoge S. Young Depatment of Meteoology and Applied Reseach Laboatoy The Pennsylvania State Univesity,

More information

Adaptation of TDMA Parameters Based on Network Conditions

Adaptation of TDMA Parameters Based on Network Conditions Adaptation of TDMA Paametes Based on Netwok Conditions Boa Kaaoglu Dept. of Elect. and Compute Eng. Univesity of Rocheste Rocheste, NY 14627 Email: kaaoglu@ece.ocheste.edu Tolga Numanoglu Dept. of Elect.

More information

Several algorithms exist to extract edges from point. system. the line is computed using a least squares method.

Several algorithms exist to extract edges from point. system. the line is computed using a least squares method. Fast Mapping using the Log-Hough Tansfomation B. Giesle, R. Gaf, R. Dillmann Institute fo Pocess Contol and Robotics (IPR) Univesity of Kalsuhe D-7618 Kalsuhe, Gemany fgieslejgafjdillmanng@ia.uka.de C.F.R.

More information

Topological Characteristic of Wireless Network

Topological Characteristic of Wireless Network Topological Chaacteistic of Wieless Netwok Its Application to Node Placement Algoithm Husnu Sane Naman 1 Outline Backgound Motivation Papes and Contibutions Fist Pape Second Pape Thid Pape Futue Woks Refeences

More information

Information Retrieval. CS630 Representing and Accessing Digital Information. IR Basics. User Task. Basic IR Processes

Information Retrieval. CS630 Representing and Accessing Digital Information. IR Basics. User Task. Basic IR Processes CS630 Repesenting and Accessing Digital Infomation Infomation Retieval: Basics Thosten Joachims Conell Univesity Infomation Retieval Basics Retieval Models Indexing and Pepocessing Data Stuctues ~ 4 lectues

More information

On the Forwarding Area of Contention-Based Geographic Forwarding for Ad Hoc and Sensor Networks

On the Forwarding Area of Contention-Based Geographic Forwarding for Ad Hoc and Sensor Networks On the Fowading Aea of Contention-Based Geogaphic Fowading fo Ad Hoc and Senso Netwoks Dazhi Chen Depatment of EECS Syacuse Univesity Syacuse, NY dchen@sy.edu Jing Deng Depatment of CS Univesity of New

More information

Any modern computer system will incorporate (at least) two levels of storage:

Any modern computer system will incorporate (at least) two levels of storage: 1 Any moden compute system will incopoate (at least) two levels of stoage: pimay stoage: andom access memoy (RAM) typical capacity 32MB to 1GB cost pe MB $3. typical access time 5ns to 6ns bust tansfe

More information

Automatically Testing Interacting Software Components

Automatically Testing Interacting Software Components Automatically Testing Inteacting Softwae Components Leonad Gallaghe Infomation Technology Laboatoy National Institute of Standads and Technology Gaithesbug, MD 20899, USA lgallaghe@nist.gov Jeff Offutt

More information

Signal integrity analysis and physically based circuit extraction of a mounted

Signal integrity analysis and physically based circuit extraction of a mounted emc design & softwae Signal integity analysis and physically based cicuit extaction of a mounted SMA connecto A poposed geneal appoach is given fo the definition of an equivalent cicuit with SMAs mounted

More information

A VECTOR PERTURBATION APPROACH TO THE GENERALIZED AIRCRAFT SPARE PARTS GROUPING PROBLEM

A VECTOR PERTURBATION APPROACH TO THE GENERALIZED AIRCRAFT SPARE PARTS GROUPING PROBLEM Accepted fo publication Intenational Jounal of Flexible Automation and Integated Manufactuing. A VECTOR PERTURBATION APPROACH TO THE GENERALIZED AIRCRAFT SPARE PARTS GROUPING PROBLEM Nagiza F. Samatova,

More information

TCBAC: An Access Control Model for Remote Calibration System

TCBAC: An Access Control Model for Remote Calibration System JOURNAL OF SOFTWARE, VOL. 8, NO., DECEMBER 03 339 TCBAC: An Access Contol Model fo Remote Calibation System Zhuokui Wu School of Mechanical & Automotive Engineeing, South China Univesity of Technology,

More information

Multi-azimuth Prestack Time Migration for General Anisotropic, Weakly Heterogeneous Media - Field Data Examples

Multi-azimuth Prestack Time Migration for General Anisotropic, Weakly Heterogeneous Media - Field Data Examples Multi-azimuth Pestack Time Migation fo Geneal Anisotopic, Weakly Heteogeneous Media - Field Data Examples S. Beaumont* (EOST/PGS) & W. Söllne (PGS) SUMMARY Multi-azimuth data acquisition has shown benefits

More information

Fifth Wheel Modelling and Testing

Fifth Wheel Modelling and Testing Fifth heel Modelling and Testing en Masoy Mechanical Engineeing Depatment Floida Atlantic Univesity Boca aton, FL 4 Lois Malaptias IFMA Institut Fancais De Mechanique Advancee ampus De lemont Feand Les

More information

Performance Optimization in Structured Wireless Sensor Networks

Performance Optimization in Structured Wireless Sensor Networks 5 The Intenational Aab Jounal of Infomation Technology, Vol. 6, o. 5, ovembe 9 Pefomance Optimization in Stuctued Wieless Senso etwoks Amine Moussa and Hoda Maalouf Compute Science Depatment, ote Dame

More information

SYSTEM LEVEL REUSE METRICS FOR OBJECT ORIENTED SOFTWARE : AN ALTERNATIVE APPROACH

SYSTEM LEVEL REUSE METRICS FOR OBJECT ORIENTED SOFTWARE : AN ALTERNATIVE APPROACH I J C A 7(), 202 pp. 49-53 SYSTEM LEVEL REUSE METRICS FOR OBJECT ORIENTED SOFTWARE : AN ALTERNATIVE APPROACH Sushil Goel and 2 Rajesh Vema Associate Pofesso, Depatment of Compute Science, Dyal Singh College,

More information

High Performance Computing on GPU for Electromagnetic Logging

High Performance Computing on GPU for Electromagnetic Logging Intenational Confeence "Paallel and Distiuted Computing Systems" High Pefomance Computing on GPU fo lectomagnetic Logging Glinskikh V.N. Kontoovich A.. pov M.I. Tofimuk Institute of Petoleum Geology and

More information

Comparisons of Transient Analytical Methods for Determining Hydraulic Conductivity Using Disc Permeameters

Comparisons of Transient Analytical Methods for Determining Hydraulic Conductivity Using Disc Permeameters Compaisons of Tansient Analytical Methods fo Detemining Hydaulic Conductivity Using Disc Pemeametes 1,,3 Cook, F.J. 1 CSRO Land and Wate, ndoooopilly, Queensland The Univesity of Queensland, St Lucia,

More information

On Adaptive Bandwidth Sharing with Rate Guarantees

On Adaptive Bandwidth Sharing with Rate Guarantees On Adaptive Bandwidth Shaing with Rate Guaantees N.G. Duffield y T. V. Lakshman D. Stiliadis y AT&T Laboatoies Bell Labs Rm A175, 180 Pak Avenue Lucent Technologies Floham Pak, 101 Cawfods Cone Road NJ

More information

A ROI Focusing Mechanism for Digital Cameras

A ROI Focusing Mechanism for Digital Cameras A ROI Focusing Mechanism fo Digital Cameas Chu-Hui Lee, Meng-Feng Lin, Chun-Ming Huang, and Chun-Wei Hsu Abstact With the development and application of digital technologies, the digital camea is moe popula

More information

Lecture #22 Pipelining II, Cache I

Lecture #22 Pipelining II, Cache I inst.eecs.bekeley.edu/~cs61c CS61C : Machine Stuctues Lectue #22 Pipelining II, Cache I Wiewold cicuits 2008-7-29 http://www.maa.og/editoial/mathgames/mathgames_05_24_04.html http://www.quinapalus.com/wi-index.html

More information

Effective Missing Data Prediction for Collaborative Filtering

Effective Missing Data Prediction for Collaborative Filtering Effective Missing Data Pediction fo Collaboative Filteing Hao Ma, Iwin King and Michael R. Lyu Dept. of Compute Science and Engineeing The Chinese Univesity of Hong Kong Shatin, N.T., Hong Kong { hma,

More information

Quality Aware Privacy Protection for Location-based Services

Quality Aware Privacy Protection for Location-based Services In Poceedings of the th Intenational Confeence on Database Systems fo Advanced Applications (DASFAA 007), Bangkok, Thailand, Apil 9-, 007. Quality Awae Pivacy Potection fo Location-based Sevices Zhen Xiao,,

More information

Prediction of Time Series Using RBF Neural Networks: A New Approach of Clustering

Prediction of Time Series Using RBF Neural Networks: A New Approach of Clustering 138 The Intenational Aab Jounal of Infomation Technology, Vol. 6,. 2, Apil 2009 Pediction of Time Seies Using RBF Neual Netwoks: A New Appoach of Clusteing Mohammed Awad 2, Hécto Pomaes 1, Ignacio Rojas

More information

Event-based Location Dependent Data Services in Mobile WSNs

Event-based Location Dependent Data Services in Mobile WSNs Event-based Location Dependent Data Sevices in Mobile WSNs Liang Hong 1, Yafeng Wu, Sang H. Son, Yansheng Lu 3 1 College of Compute Science and Technology, Wuhan Univesity, China Depatment of Compute Science,

More information

Cryptanalysis of Hwang-Chang s a Time-Stamp Protocol for Digital Watermarking

Cryptanalysis of Hwang-Chang s a Time-Stamp Protocol for Digital Watermarking Cyptanalysis of Hwang-Chang s a Time-Stamp Potocol fo Digital Watemaking *Jue-Sam Chou, Yalin Chen 2, Chung-Ju Chan 3 Depatment of Infomation Management, Nanhua Univesity Chiayi 622 Taiwan, R.O.C *: coesponding

More information

A TSK-Type Recurrent Neuro-Fuzzy Systems for Fault Prognosis

A TSK-Type Recurrent Neuro-Fuzzy Systems for Fault Prognosis Jounal of Softwae Engineeing and Applications, 2012, 5, 477-482 http://dx.doi.og/10.4236/jsea.2012.57055 Published Online July 2012 (http://www.scip.og/jounal/jsea) 477 A SK-ype ecuent Neuo-Fuzzy Systems

More information

INDEXATION OF WEB PAGES BASED ON THEIR VISUAL RENDERING

INDEXATION OF WEB PAGES BASED ON THEIR VISUAL RENDERING INDEXATION OF WEB PAGES BASED ON THEIR VISUAL RENDERING Emmanuel Buno Univesité du Sud Toulon-Va / LSIS CNRS BP 20132, F-83957 La Gade buno@univ-tln.f Nicolas Faessel LSIS CNRS Domaine Univesitaie de Saint-Jéôme

More information

Effective Data Co-Reduction for Multimedia Similarity Search

Effective Data Co-Reduction for Multimedia Similarity Search Effective Data Co-Reduction fo Multimedia Similaity Seach Zi Huang Heng Tao Shen Jiajun Liu Xiaofang Zhou School of Infomation Technology and Electical Engineeing The Univesity of Queensland, QLD 472,

More information

Annales UMCS Informatica AI 2 (2004) UMCS

Annales UMCS Informatica AI 2 (2004) UMCS Pobane z czasopisma Annales AI- Infomatica http://ai.annales.umcs.pl Annales Infomatica AI 2 (2004) 33-340 Annales Infomatica Lublin-Polonia Sectio AI http://www.annales.umcs.lublin.pl/ Embedding as a

More information

Geophysical inversion with a neighbourhood algorithm I. Searching a parameter space

Geophysical inversion with a neighbourhood algorithm I. Searching a parameter space Geophys. J. Int. (1999) 138, 479 494 Geophysical invesion with a neighbouhood algoithm I. Seaching a paamete space Malcolm Sambidge Reseach School of Eath Sciences, Institute of Advanced studies, Austalian

More information

A Mathematical Implementation of a Global Human Walking Model with Real-Time Kinematic Personification by Boulic, Thalmann and Thalmann.

A Mathematical Implementation of a Global Human Walking Model with Real-Time Kinematic Personification by Boulic, Thalmann and Thalmann. A Mathematical Implementation of a Global Human Walking Model with Real-Time Kinematic Pesonification by Boulic, Thalmann and Thalmann. Mashall Badley National Cente fo Physical Acoustics Univesity of

More information

XFVHDL: A Tool for the Synthesis of Fuzzy Logic Controllers

XFVHDL: A Tool for the Synthesis of Fuzzy Logic Controllers XFVHDL: A Tool fo the Synthesis of Fuzzy Logic Contolles E. Lago, C. J. Jiménez, D. R. López, S. Sánchez-Solano and A. Baiga Instituto de Micoelectónica de Sevilla. Cento Nacional de Micoelectónica, Edificio

More information

Efficient protection of many-to-one. communications

Efficient protection of many-to-one. communications Efficient potection of many-to-one communications Miklós Molná, Alexande Guitton, Benad Cousin, and Raymond Maie Iisa, Campus de Beaulieu, 35 042 Rennes Cedex, Fance Abstact. The dependability of a netwok

More information

Parallel processing model for XML parsing

Parallel processing model for XML parsing Recent Reseaches in Communications, Signals and nfomation Technology Paallel pocessing model fo XML pasing ADRANA GEORGEVA Fac. Applied Mathematics and nfomatics Technical Univesity of Sofia, TU-Sofia

More information

Gravitational Shift for Beginners

Gravitational Shift for Beginners Gavitational Shift fo Beginnes This pape, which I wote in 26, fomulates the equations fo gavitational shifts fom the elativistic famewok of special elativity. Fist I deive the fomulas fo the gavitational

More information

Voting-Based Grouping and Interpretation of Visual Motion

Voting-Based Grouping and Interpretation of Visual Motion Voting-Based Gouping and Intepetation of Visual Motion Micea Nicolescu Depatment of Compute Science Univesity of Nevada, Reno Reno, NV 89557 micea@cs.un.edu Géad Medioni Integated Media Systems Cente Univesity

More information

DEVELOPMENT OF A PROCEDURE FOR VERTICAL STRUCTURE ANALYSIS AND 3D-SINGLE TREE EXTRACTION WITHIN FORESTS BASED ON LIDAR POINT CLOUD

DEVELOPMENT OF A PROCEDURE FOR VERTICAL STRUCTURE ANALYSIS AND 3D-SINGLE TREE EXTRACTION WITHIN FORESTS BASED ON LIDAR POINT CLOUD IAPRS Volume XXXVI, Pat 3 / W52, 27 DEVELOPMENT OF A PROCEDURE FOR VERTICAL STRUCTURE ANALYSIS AND 3D-SINGLE TREE EXTRACTION WITHIN FORESTS BASED ON LIDAR POINT CLOUD Yunsheng Wang a,*, Holge Weinacke

More information