Risk-Based Packet Routing for Privacy and Compliance-Preserving SDN

Size: px
Start display at page:

Download "Risk-Based Packet Routing for Privacy and Compliance-Preserving SDN"

Transcription

1 Rsk-Based Packet Routng for Prvacy and Complance-Preservng SDN Karan K. Budhraja Abhshek Malvankar Mehd Bahram Chnmay Kundu Ashsh Kundu Mukesh Snghal, Unversty of Maryland, Baltmore County, MD, USA Emal: IBM Watson Health, Yorktown Heghts, NY, USA Emal: Fujtsu Laboratores of Amerca, Sunnyvale, Calforna, USA Emal: Researcher, Inda Emal: IBM Thomas J. Watson Research Center, Yorktown Heghts, NY, USA Emal: Cloud Lab, Unversty of Calforna Merced, USA Abstract Software Defned Networkng (SDN) s ncreasngly beng used n data centers as well as enterprse networks. In an envronment that has strct complance requrements, such as HIPAA complance, a crtcal role for an SDN controller s to route all data packets whle consderng data prvacypreservaton and complance-preservaton. In ths paper, we address ths problem by proposng a routng protocol for SDN whch s an effcent rsk-based swarm routng protocol. The programmable capablty of controllers s exploted n order to mnmze prvacy and complance rsks n data transmsson. The proposed routng protocol s based on the Ant Colony Optmzaton technque and machne learnng, whle the data for learnng s obtaned from OVSDB and the OpenvSwtch Database management protocol. We collect a hstory of packet transfers for tranng purposes and learn from the tranng data to effcently and ntellgently route senstve data packets whle t preserves the target complance. Ths routng s obtaned by ntellgent evcton of rules that are downloaded to the swtches. We have mplemented the proposed schemes based on an RYU controller. Index Terms SDN; cloud computng; prvacy; securty; routng; complance-preservaton. I. INTRODUCTION Software-Defned Networkng (SDN) [1], [2], [3], [4] s a networkng approach that smplfes and optmzes network operatons. Exstng work on SDN routng has not addressed the problem of data transmsson n the presence of prvacy and complance requrements. Another prvacy requrement that needs to be consdered n ths context s that only a statc or specfc routng path (a sequence of swtches) should not be used transfer hgh densty of packets carryng senstve data, snce t poses a rsk of Denal of Servce attacks as well as nference attacks. Such a scheme, f used for controlled envronment such as HIPAA, could lead to a potental nformaton leakage when attacked. In ths paper, we address data prvacy and complance restrcton challenges for transferrng senstve data n SDN envronment that preserves prvacy and adheres to the target complance, such as HIPAA. We acheve our goals that by usng: ) dstrbuted routng optmzaton by employng a swarm routng algorthm; ) defnton of prvacy, rsk and technques to compute such rsks on an SDN network usng analytcs and machne learnng; ) mnmzaton of rsk and route-randomzaton n order acheve prvacy and complance requrements. The contrbuton of ths work s a novel approach to route prvacy-senstve and complance-senstve data n an SDN envronment. Ths s acheved by reducng a noton of prvacy rsks and usng swarm-based (ant) routng [5], [6], [7]. The prvacy rsk s dynamcally computed over the network node graph and s thus holstc n nature. We perform route-randomzaton by montorng the amount of packets transmtted on the forwardng path wth help of openflow protocol and utltes such as ovs-vsctl (a utlty for queryng and confgurng ovs-vswtchd) and ovs-ofctl (to admnster OpenFlow swtches) [8]. Once we have counter metrcs, we defne rsk as a functon of number of packets transferred on the same datapath. Ths number would be calculated by an agglomeraton of offlne log montorng models n python sc-kt learn. Montorng models n ths fashon would provde features to an algorthm based on probablstc graphcal models (whch s Ant Colony Optmzaton n our case, explaned n Secton IV) for traffc spreadng across other nodes to mnmze rsk. The organzaton of the paper s as follows. Secton II dscusses relevant exstng work n ths doman and related to our research problem statement. Secton III then formalzes the problem that our work ntends to provde a soluton to. Secton IV and Secton V descrbe the detals related to the proposed soluton. Fnally, Secton VI evaluates the proposed method on vared assocated parameters and Secton VII concludes our work wth closng remarks and scope for future work and any open questons. II. RELATED WORK The concept of prvacy preservaton routng s mportant when dealng wth senstve data [9], [10]. The former cted work dscusses an attempt to dscover the patterns by whch a controller nstalls a flow, and thereby learn from request for a custom nstallaton. Ths s done from the pont of vew of an adversary. The latter preserves prvacy by usng prvatekey based encrypton for each data packet. Nether, however, consder complance-based networkng whch s explored n ths study.

2 The congeston control use case of Ant Colony Optmzaton (ACO) s mplemented n [5], [6], [7]. Our work extends ths dea by combnng the relatvely low tme-complexty wth respect to tradtonal shortest path problem whch s tradtonally NP-hard. We use an ant-based approxmaton soluton wth prvacy and complance constrants. III. PROBLEM DEFINITION Our work focuses on two types of rsks to the network traffc. They are as follows. A. Prvacy Exposure Consder a scenaro where the flow of packets through the network uses a fxed route or set of routes, for a gven source (s) and destnaton (d). The swtches along those routes may then dentfy the presence of communcaton between s and d. Dependng on the ntellgence capabltes of the swtches, they may then be able to learn or gather senstve nformaton about the data beng transmtted. Ths results n a leakage of prvacy for that communcaton sesson. B. Complance To dscuss complance rsk, consder a settng where a network topology has grown over tme. When plannng of changes n network topology, ths translates to vared hardware components gathered over tme. As a result, there may only be a subset of those components that are capable of adherng to a certan role or requrement. For our problem, ths means that a subset of swtches (and/or controllers) used by the network may be complant to process data transferred n regulated envronment. It therefore becomes a mandate, then, that any data travelng across the network that requres complance, be constraned to such a selected subset of network components. Ths may also be consdered for a gven (s, d) par, n whch case all routes connectng those components must be checked. In other words, network components or routes that do not comply wth complance requrement wll pose a greater rsk when caterng to HIPAA senstve data. Ths s not a favorable stuaton for our problem settng. IV. PROPOSED PRIVACY AND COMPLIANCE-PRESERVING ROUTING TECHNIQUE A crtcal role for an SDN controller s to route data packets by prvacy-preservng of all data packets. The proposed routng protocol collects a hstory of data packets for tranng purposes and t uses the tranng data to effcently and ntellgently route data packets. The key role of our swarm ntellgence routng protocol s to allow for a small amount (less than tradtonal networkng algorthms because of beng a dstrbuted ntellgence approach rather than a centralzed one) of processng (computaton by the network component wth respect to tme complexty) per data packet. In the future, ths can be extended to pushng computaton to ntellgent swtches to share the load of the controller. In order to preserve the users data prvacy n our proposed SDN routng protocol, we propose a lght-weght data prvacy method that allows the protocol effcently use meta-data of data packets n the tranng data set to ntellgently route the packets. In ths secton, we show how our proposed routng protocol preserves the users data prvacy and dscuss the varous components nvolved n the proposed soluton. A. Prvacy Exposure In order to preserve prvacy packets should be sent across multple paths. Instead of havng a fxed route or set of routes that are used for communcaton, data packets may be sent probablstcally along paths n a network. Whle a convergence mechansm may be used to ensure a bound to communcaton tme, the ntermttent passage of packets through any gven swtch wll sgnfcantly reduce the rsk of prvacy exposure. B. Complance In order to determne low-rsk routes for sendng senstve nformaton, the SDN controller could determne whch network components are complant. A path computaton then nvolvng those components could be formulated. Ths results n mnmal rsk when handlng senstve data sent across the network. An upper bound (lmt) to such routng may also be consdered. V. RISK ANALYSIS Rsk computaton provdes quantfy rsks across varous network components. Ths quantfcaton can then be used to make an optmal decson for the routng of senstve traffc. The followng are the key factors n computaton and usage of rsk quantfcaton. 1. Rsk for each router may be consdered as categorzed based on the dscusson n Secton III. Ths results n two types of rsks: () prvacy exposure rsk and () complance rsk. The prvacy exposure rsk may be quantfed by evaluatng the securty of a router and ts vulnerablty to external attacks. The complance rsk for a network may be quantfed by evaluatng the number of controls that are not mplemented n that network component.for nstance the total number of HIPAA controls s 59, ths value could be scaled by 59 to result n a value n the range (0, 1). 2. The overall (global) rsk for a graph or subgraph of network components, may then be computed and quantfed by focusng on the maxmum flow of complant route or node and low prvacy exposure data across the network. Gven a graph G(V, E), where V and E are the sets of vertces and edges respectvely (for that graph), the controller output after processng (as explaned above) wll be as follows. The controller may take one of two possble decsons. 1. Ths s the case where the controller has found a path or a set of paths across the network, by whch senstve data may be routed. The paths are selected so as to mnmze prvacy exposure and complance rsks for a gven data transmsson sesson. 2. On computaton of the rsks along varous paths n the network, the controller may not fnd any favorable path on

3 whch data may be transmtted wthout sgnfcant rsk n context of prvacy exposure and complance. In ths case, the controller acknowledges that the data transmsson rsk s too hgh and may decde to not send any senstve data across the network. No data transmsson sesson s ntated n ths settng. Ths stuaton can be resolved when more lowrsk resources become avalable at a later tme, or f the rsk quantfcaton of network components changes. In order to admnster the algorthm on the network across varous connected components, the followng are steps that can be followed for contnuous montorng and operaton. 1. Each SDN controller (C) s allowed to focus on an assocated graph G(V, E). Ths graph may change from tme to tme based on change n network structure, addton or removal of varous network components, or even varatons n network traffc and securty. 2. In order to mark a certan data transmsson for a low-rsk requrement, the (s, d) par may be tagged or the data packets nvolved may be tagged. Ths s a way for the controller to ensure that all other network components are able to dentfy that these data packets must adhere to a low-rsk envronment. 3. Ant Colony Optmzaton (ACO) provdes a computatonally cheap soluton to path computatons (snce t uses approxmaton) for a gven network. The controller may leverage ACO to compute optmzed routes whch adhere to prvacy exposure and complance constrants assocated wth the current data transmsson. Ths may be specfc to a packet or may be for a gven (s, d) par. The prmtve ACO algorthm only uses pheromones. For our problem settng, we also ncorporate securty rsks for each edge of the graph. These rsks may be accumulated over neghbors of several hops along a path n the network. Ths may also be extended to prevous paths used by the network. Smlar to pheromone values, quantfed rsk values also observe a gradual decay n value as tme progresses. Ths allows the use of dfferent paths for a gven data flow n the network(whch s a favorable feature n rsk-assocated envronments). In ths study, we consder several parameters for analyzng the rsk of routng of a data packet. The fnal output of rsk analyss, rsk rato, allows the SDN controller to reconfgure the forwardng table on each swtch. In order to avod the computaton overhead, we perform off-lne computaton, therefore the forwardng table s updated perodcally. A. Rsk Parameters Frst, we defne several parameters for computng rsk rato as follows. 1. Meta-data of a data packet when t s routed to a swtch and transferred to a destnaton address. Ths parameter ncludng orgn address, destnaton address, sze of data packet, prorty, n port, out port, and routng path. 2. Tmestamp wth respect to local tmezone of the node or swtch. Ths parameter assocates to three nodes at each routng step: ) orgn local tme; ) destnaton local tme; ) current swtch local tme. The tme allows us to assess each data packet or a group of data packets based on the average rate for dfferent tmes. 3. Hstory of routng path for a specfc orgn and destnaton node. Ths parameter uses a tme-stamp parameter to provde a comprehensve evaluaton. 4. Data packet content. We randomly evaluate data packet f there s a chance of plan text data transfers through the network whch mght be performed by software applcaton whch s complance unaware. Evaluaton of data packet enables the rsk analyzer to assess hgh rsk applcatons that are not encryptng orgnal data. 5. Type of data packet. Ths may correspond to dfferent protocols, such as ARP, IP4, and IP6. 6. Data Integrty. We assess a data packet by revewng mnmum of two swtches n a routng path. Data packets are randomly selected for data ntegrty evaluaton. At the same tme, the data packet may be forwarded to the destnaton and a copy could be submtted to Integrty Evaluator SDN controller that has all requred nformaton for addtonal revew. 7. Type of data packet encrypton. Packets may have dfferent levels of securty provded by dfferent types of encrypton. B. Rsk Computaton Second, we consder ACO to analyze onlne rsk rato and use a well-known clusterng algorthm, k means, to teratvely compute k centrod objects for our n crtera to fnd the rsk rato based on descrbed parameters n Secton V-A. Snce ths algorthm has more computaton overhead than ACO, t s processed on the SDN controller n an off-lne mode or t can be processed on an ndvdual node and t modfes forwardng tables of the swtches based on computed rsk factors. In the k means algorthm, let X = {x 1, x 2,..., x n } be n elements of rsk parameter objects, and S = {s 1, s 2,..., s n } whch s the set of our rsk level clusters. The goal s clusterng n parameters nto S clusters of rsk ratos. The algorthm ams to partton n parameters nto k clusters based on mnmzng the Wthn-Cluster Sum of Squares (WCSS) whch s a summaton of dstance functon of each rsk parameters to the rsk level clusters. The WCSS for each s can be defned as follows: x S x µ 2 (1) If µ be the mean of cluster of s, therefore the rsk rato can be defned as follows: k arg mn x µ 2 (2) =1 x S Ths algorthm has to perform two steps. 1) Assgn each pont to the closest cluster to generate a partton as follows: s (t) m (t) = {x p : x p m (t) 2 x p m (t) j 2, j = 1, 2,..., k (3) represents the mean value of th cluster

4 2) Compute the centrod of the new cluster as follows: m (t+1) = 1 x S (t) j (4) x j S (t) In ths paper, we consder fve rsk levels as follows: ) very low-rsk; ) low-rsk; ) normal; v) hgh-rsk; v) very hgh-rsk. These rsk levels correspond to cluster centers {s 1, s 2, s 3, s 4, s 5 }, respectvely. In ths scenaro the target of our algorthm s fndng a lower rsk rato for each route to dstrbutng data packets n SDN envronment. VI. EVALUATION We mplement the rsk analyzer n python by usng scktlearn lbrary. We use 10 dfferent features or data prvacy parameters as nput for analyzng the rsk rato wth 5 dfferent rsk levels as descrbed n Secton V-A. Each feature represents a rsk parameter to be used n the k means algorthm.we have mplemented our log analyss model s an offlne smulaton process (usng RYU), whch however, can be mplemented for onlne log analyss and rsk computaton. In ths experment, we consdered 10, 000 sample log records whch are generated randomly as follows. 1. Usng an ansotropc dstrbuton for 10 dfferent features when we consder dfferent tme-stamp features. We transform the orgnal feature of the tme-stamp to the cluster-dstance space. Let us consder dfferent tmestamps as the man key for ths classfcaton algorthm whle usng the other 9 features as parameters. In ths scenaro, we can dvde each day nto three perods as follows: 8:00AM-4:00PM, 4:00PM-1:00AM and 1:00AM-8:00AM. Therefore, we can evaluate all 9 features wth respect to ths tme dvson. The result of ths experment s shown n Fgure 1. Each record of 10, 000 sample records have been labeled wth ts rsk rato level. In Fgure 1, we reduce the 10-dmenson nput to a 2D as shown ponts as X-axs and Y-axs. We also label each of the ponts based on ther rsk rato wth dfferent colors when 10 features are consdered. In ths experment, we found that any securty and prvacy ssue between 4:00PM-1:00AM (the mddle cluster represents ths set of tme-stamps) ndcates a very hgh-rsk factor. For nstance, when a health-care applcaton s usng plan-text wthout encryptng the orgnal content and usng a plan-text protocol. 2. Usng dfferent varance for generatng random values for 10 dfferent features s shown Fgure 2, the rsk level for dfferent cluster have been dentfed for all 10, 000 records; and fnally 3. Usng unevenly szed blocks to generate random values for 10 dfferent features. As shown n Fgure 3, the rsk levels for dfferent clusters have been dentfed for all 10, 000 records. Consderng dfferent subjects for evaluatng the rsk n a SDN network allows the proposed method to provde a rgorous evaluaton for strct complance requrement network. In addton, mplementng ths method on each swtch even for open swtch s not feasble because the method requres heavy computaton. However, when we are usng a SDN controller we are able to collect data perodcally from the swtches and Fg. 1. Rsk level for ansotropc dstrbuton of 10 features. Multdmensonal feature vectors are reduced to two dmensons. Fg. 2. Rsk level for dfferent varances of 10 features. Clusters of rsk vared level data are observed to be well separated n ths representaton. compute the rsk factors for dfferent data packets based on ther orgn, destnaton, tme, and etc. The collected data can be revewed by an external revewer (rsk analyzer) to decde whch forwardng table s requred modfcaton. Our ACO method wll be able to use ths rsk level tag to evaluate network edge weghts and therefore forward data packets based on all consdered rsk parameters. ACO s tested by evaluatng the tme duratons of a seres of random message nteractons between hosts. Ths nvolves rule computaton for new communcatons, as well as a hard tmeout (tme after whch any rule s forcefully erased, f not erased already) by the controller. These are summarzed n Fgure 4. Expermental results are averaged over 10 runs. Wth the addton of rsk and prvacy constrants, the routng path selected may no longer be the shortest (because routng

5 Fg. 3. Rsk level for dfferent 10 features when usng unevenly szed blocks. Some overlap n clusters data tems across rsk levels s observed when analyzng all features. preferences no longer depend solely on physcal network dstance).whle an nteracton wth the controller (when a flow s not nstalled) takes sgnfcantly longer than bypassng t (when a flow s nstalled), the use of ACO stll allows for lower complexty than other tradtonal algorthms (as explaned n Secton II). The tme complexty for the controller can further be reduced by decreasng the amount of nformaton beng logged or retaned, and optmzng the mplementaton. ACO s an nherently parallel algorthm and may therefore take advantage of parallel compute archtectures. VII. CONCLUSION In ths paper, we proposed a novel data prvacy preservaton method for SDN routng. In ths routng algorthm, the SDN controller collects dfferent features, such as: data packet types, network topology, and data packet routng hstory. We used two methods, frst, rsk analyzer that provdes an offlne process to compute the rsk rato and the second, an onlne method to make real-tme decson for routng data packets. Frst, the SDN controller processes the data packet features by evaluatng them based on a well-known machne learnng method, k means, and t classfes the data packet based on ther level of rsks accordng to HIPPA rsk parameters. Second, we used ACO to provde a real-tme decson for routng data packets because t provdes a much lower tme complexty soluton than ts tradtonal graph algorthm counterparts. The expermental results show an evaluaton on 10 dfferent rsk parameters whch s consdered as hgh dmensonal data. The rsk analyzer s combned wth ACO to provde a holstc soluton to prvacy and rsk complant assocate to the whole SDN network. Fg. 4. Delays n communcaton (after the controller nstalls a flow) wth and wthout rsk analyss. [2] K. Krkpatrck, Software-defned networkng, Communcatons of the ACM, vol. 56, no. 9, pp , [3] N. Feamster, Software defned networkng, Coursera, [4] S. Baley, D. Bansal, L. Dunbar, D. Hood, Z. L. Ks, B. MackCrane, J. Magure, D. Malek, D. Meyer, M. Paul et al., Sdn archtecture overvew, Open Networkng Foundaton, Ver, vol. 1, [5] O. Dobrjevc, M. Santl, and M. Matjasevc, Ant colony optmzaton for qoe-centrc flow routng n software-defned networks, n Network and Servce Management (CNSM), th Internatonal Conference on. IEEE, 2015, pp [6] M. Gunes, U. Sorges, and I. Bouazz, Ara-the ant-colony based routng algorthm for manets, n Parallel Processng Workshops, Proceedngs. Internatonal Conference on. IEEE, 2002, pp [7] W. Guo, W. Zhang, and G. Lu, A comprehensve routng protocol n wreless sensor network based on ant colony algorthm, n Networks Securty Wreless Communcatons and Trusted Computng (NSWCTC), 2010 Second Internatonal Conference on, vol. 1. IEEE, 2010, pp [8] B. Pfaff, Open vswtch manual, Manual, Open vswtch. [9] M. Cont, F. De Gaspar, and L. V. Mancn, Know your enemy: Stealth confguraton-nformaton gatherng n sdn, arxv preprnt arxv: , [10] Q. Chen, C. Qan, and S. Zhong, Prvacy-preservng cross-doman routng optmzaton-a cryptographc approach, n 2015 IEEE 23rd Internatonal Conference on Network Protocols (ICNP). IEEE, 2015, pp REFERENCES [1] N. McKeown, Software-defned networkng, INFOCOM keynote talk, vol. 17, no. 2, pp , 2009.

Simulation Based Analysis of FAST TCP using OMNET++

Simulation Based Analysis of FAST TCP using OMNET++ Smulaton Based Analyss of FAST TCP usng OMNET++ Umar ul Hassan 04030038@lums.edu.pk Md Term Report CS678 Topcs n Internet Research Sprng, 2006 Introducton Internet traffc s doublng roughly every 3 months

More information

Load-Balanced Anycast Routing

Load-Balanced Anycast Routing Load-Balanced Anycast Routng Chng-Yu Ln, Jung-Hua Lo, and Sy-Yen Kuo Department of Electrcal Engneerng atonal Tawan Unversty, Tape, Tawan sykuo@cc.ee.ntu.edu.tw Abstract For fault-tolerance and load-balance

More information

The Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique

The Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique //00 :0 AM Outlne and Readng The Greedy Method The Greedy Method Technque (secton.) Fractonal Knapsack Problem (secton..) Task Schedulng (secton..) Mnmum Spannng Trees (secton.) Change Money Problem Greedy

More information

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points;

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points; Subspace clusterng Clusterng Fundamental to all clusterng technques s the choce of dstance measure between data ponts; D q ( ) ( ) 2 x x = x x, j k = 1 k jk Squared Eucldean dstance Assumpton: All features

More information

Cluster Analysis of Electrical Behavior

Cluster Analysis of Electrical Behavior Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School

More information

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Parallelism for Nested Loops with Non-uniform and Flow Dependences Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr

More information

A New Token Allocation Algorithm for TCP Traffic in Diffserv Network

A New Token Allocation Algorithm for TCP Traffic in Diffserv Network A New Token Allocaton Algorthm for TCP Traffc n Dffserv Network A New Token Allocaton Algorthm for TCP Traffc n Dffserv Network S. Sudha and N. Ammasagounden Natonal Insttute of Technology, Truchrappall,

More information

Support Vector Machines

Support Vector Machines /9/207 MIST.6060 Busness Intellgence and Data Mnng What are Support Vector Machnes? Support Vector Machnes Support Vector Machnes (SVMs) are supervsed learnng technques that analyze data and recognze patterns.

More information

Classifier Selection Based on Data Complexity Measures *

Classifier Selection Based on Data Complexity Measures * Classfer Selecton Based on Data Complexty Measures * Edth Hernández-Reyes, J.A. Carrasco-Ochoa, and J.Fco. Martínez-Trndad Natonal Insttute for Astrophyscs, Optcs and Electroncs, Lus Enrque Erro No.1 Sta.

More information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,

More information

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task Proceedngs of NTCIR-6 Workshop Meetng, May 15-18, 2007, Tokyo, Japan Term Weghtng Classfcaton System Usng the Ch-square Statstc for the Classfcaton Subtask at NTCIR-6 Patent Retreval Task Kotaro Hashmoto

More information

Smoothing Spline ANOVA for variable screening

Smoothing Spline ANOVA for variable screening Smoothng Splne ANOVA for varable screenng a useful tool for metamodels tranng and mult-objectve optmzaton L. Rcco, E. Rgon, A. Turco Outlne RSM Introducton Possble couplng Test case MOO MOO wth Game Theory

More information

Complex Numbers. Now we also saw that if a and b were both positive then ab = a b. For a second let s forget that restriction and do the following.

Complex Numbers. Now we also saw that if a and b were both positive then ab = a b. For a second let s forget that restriction and do the following. Complex Numbers The last topc n ths secton s not really related to most of what we ve done n ths chapter, although t s somewhat related to the radcals secton as we wll see. We also won t need the materal

More information

Meta-heuristics for Multidimensional Knapsack Problems

Meta-heuristics for Multidimensional Knapsack Problems 2012 4th Internatonal Conference on Computer Research and Development IPCSIT vol.39 (2012) (2012) IACSIT Press, Sngapore Meta-heurstcs for Multdmensonal Knapsack Problems Zhbao Man + Computer Scence Department,

More information

Hierarchical clustering for gene expression data analysis

Hierarchical clustering for gene expression data analysis Herarchcal clusterng for gene expresson data analyss Gorgo Valentn e-mal: valentn@ds.unm.t Clusterng of Mcroarray Data. Clusterng of gene expresson profles (rows) => dscovery of co-regulated and functonally

More information

Efficient Distributed File System (EDFS)

Efficient Distributed File System (EDFS) Effcent Dstrbuted Fle System (EDFS) (Sem-Centralzed) Debessay(Debsh) Fesehaye, Rahul Malk & Klara Naherstedt Unversty of Illnos-Urbana Champagn Contents Problem Statement, Related Work, EDFS Desgn Rate

More information

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

Learning the Kernel Parameters in Kernel Minimum Distance Classifier Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department

More information

A New Approach For the Ranking of Fuzzy Sets With Different Heights

A New Approach For the Ranking of Fuzzy Sets With Different Heights New pproach For the ankng of Fuzzy Sets Wth Dfferent Heghts Pushpnder Sngh School of Mathematcs Computer pplcatons Thapar Unversty, Patala-7 00 Inda pushpndersnl@gmalcom STCT ankng of fuzzy sets plays

More information

Research of Dynamic Access to Cloud Database Based on Improved Pheromone Algorithm

Research of Dynamic Access to Cloud Database Based on Improved Pheromone Algorithm , pp.197-202 http://dx.do.org/10.14257/dta.2016.9.5.20 Research of Dynamc Access to Cloud Database Based on Improved Pheromone Algorthm Yongqang L 1 and Jn Pan 2 1 (Software Technology Vocatonal College,

More information

Routing in Degree-constrained FSO Mesh Networks

Routing in Degree-constrained FSO Mesh Networks Internatonal Journal of Hybrd Informaton Technology Vol., No., Aprl, 009 Routng n Degree-constraned FSO Mesh Networks Zpng Hu, Pramode Verma, and James Sluss Jr. School of Electrcal & Computer Engneerng

More information

Evaluation of an Enhanced Scheme for High-level Nested Network Mobility

Evaluation of an Enhanced Scheme for High-level Nested Network Mobility IJCSNS Internatonal Journal of Computer Scence and Network Securty, VOL.15 No.10, October 2015 1 Evaluaton of an Enhanced Scheme for Hgh-level Nested Network Moblty Mohammed Babker Al Mohammed, Asha Hassan.

More information

Comparison of Heuristics for Scheduling Independent Tasks on Heterogeneous Distributed Environments

Comparison of Heuristics for Scheduling Independent Tasks on Heterogeneous Distributed Environments Comparson of Heurstcs for Schedulng Independent Tasks on Heterogeneous Dstrbuted Envronments Hesam Izakan¹, Ath Abraham², Senor Member, IEEE, Václav Snášel³ ¹ Islamc Azad Unversty, Ramsar Branch, Ramsar,

More information

Virtual Machine Migration based on Trust Measurement of Computer Node

Virtual Machine Migration based on Trust Measurement of Computer Node Appled Mechancs and Materals Onlne: 2014-04-04 ISSN: 1662-7482, Vols. 536-537, pp 678-682 do:10.4028/www.scentfc.net/amm.536-537.678 2014 Trans Tech Publcatons, Swtzerland Vrtual Machne Mgraton based on

More information

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz Compler Desgn Sprng 2014 Regster Allocaton Sample Exercses and Solutons Prof. Pedro C. Dnz USC / Informaton Scences Insttute 4676 Admralty Way, Sute 1001 Marna del Rey, Calforna 90292 pedro@s.edu Regster

More information

Distributed Resource Scheduling in Grid Computing Using Fuzzy Approach

Distributed Resource Scheduling in Grid Computing Using Fuzzy Approach Dstrbuted Resource Schedulng n Grd Computng Usng Fuzzy Approach Shahram Amn, Mohammad Ahmad Computer Engneerng Department Islamc Azad Unversty branch Mahallat, Iran Islamc Azad Unversty branch khomen,

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization Problem efntons and Evaluaton Crtera for Computatonal Expensve Optmzaton B. Lu 1, Q. Chen and Q. Zhang 3, J. J. Lang 4, P. N. Suganthan, B. Y. Qu 6 1 epartment of Computng, Glyndwr Unversty, UK Faclty

More information

Analysis of Collaborative Distributed Admission Control in x Networks

Analysis of Collaborative Distributed Admission Control in x Networks 1 Analyss of Collaboratve Dstrbuted Admsson Control n 82.11x Networks Thnh Nguyen, Member, IEEE, Ken Nguyen, Member, IEEE, Lnha He, Member, IEEE, Abstract Wth the recent surge of wreless home networks,

More information

An Entropy-Based Approach to Integrated Information Needs Assessment

An Entropy-Based Approach to Integrated Information Needs Assessment Dstrbuton Statement A: Approved for publc release; dstrbuton s unlmted. An Entropy-Based Approach to ntegrated nformaton Needs Assessment June 8, 2004 Wllam J. Farrell Lockheed Martn Advanced Technology

More information

Distributed Middlebox Placement Based on Potential Game

Distributed Middlebox Placement Based on Potential Game Int. J. Communcatons, Network and System Scences, 2017, 10, 264-273 http://www.scrp.org/ournal/cns ISSN Onlne: 1913-3723 ISSN Prnt: 1913-3715 Dstrbuted Mddlebox Placement Based on Potental Game Yongwen

More information

Constructing Minimum Connected Dominating Set: Algorithmic approach

Constructing Minimum Connected Dominating Set: Algorithmic approach Constructng Mnmum Connected Domnatng Set: Algorthmc approach G.N. Puroht and Usha Sharma Centre for Mathematcal Scences, Banasthal Unversty, Rajasthan 304022 usha.sharma94@yahoo.com Abstract: Connected

More information

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning Outlne Artfcal Intellgence and ts applcatons Lecture 8 Unsupervsed Learnng Professor Danel Yeung danyeung@eee.org Dr. Patrck Chan patrckchan@eee.org South Chna Unversty of Technology, Chna Introducton

More information

Assignment # 2. Farrukh Jabeen Algorithms 510 Assignment #2 Due Date: June 15, 2009.

Assignment # 2. Farrukh Jabeen Algorithms 510 Assignment #2 Due Date: June 15, 2009. Farrukh Jabeen Algorthms 51 Assgnment #2 Due Date: June 15, 29. Assgnment # 2 Chapter 3 Dscrete Fourer Transforms Implement the FFT for the DFT. Descrbed n sectons 3.1 and 3.2. Delverables: 1. Concse descrpton

More information

Discriminative Dictionary Learning with Pairwise Constraints

Discriminative Dictionary Learning with Pairwise Constraints Dscrmnatve Dctonary Learnng wth Parwse Constrants Humn Guo Zhuoln Jang LARRY S. DAVIS UNIVERSITY OF MARYLAND Nov. 6 th, Outlne Introducton/motvaton Dctonary Learnng Dscrmnatve Dctonary Learnng wth Parwse

More information

A Binarization Algorithm specialized on Document Images and Photos

A Binarization Algorithm specialized on Document Images and Photos A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a

More information

TPL-Aware Displacement-driven Detailed Placement Refinement with Coloring Constraints

TPL-Aware Displacement-driven Detailed Placement Refinement with Coloring Constraints TPL-ware Dsplacement-drven Detaled Placement Refnement wth Colorng Constrants Tao Ln Iowa State Unversty tln@astate.edu Chrs Chu Iowa State Unversty cnchu@astate.edu BSTRCT To mnmze the effect of process

More information

Related-Mode Attacks on CTR Encryption Mode

Related-Mode Attacks on CTR Encryption Mode Internatonal Journal of Network Securty, Vol.4, No.3, PP.282 287, May 2007 282 Related-Mode Attacks on CTR Encrypton Mode Dayn Wang, Dongda Ln, and Wenlng Wu (Correspondng author: Dayn Wang) Key Laboratory

More information

DESIGNING TRANSMISSION SCHEDULES FOR WIRELESS AD HOC NETWORKS TO MAXIMIZE NETWORK THROUGHPUT

DESIGNING TRANSMISSION SCHEDULES FOR WIRELESS AD HOC NETWORKS TO MAXIMIZE NETWORK THROUGHPUT DESIGNING TRANSMISSION SCHEDULES FOR WIRELESS AD HOC NETWORKS TO MAXIMIZE NETWORK THROUGHPUT Bran J. Wolf, Joseph L. Hammond, and Harlan B. Russell Dept. of Electrcal and Computer Engneerng, Clemson Unversty,

More information

Fuzzy Filtering Algorithms for Image Processing: Performance Evaluation of Various Approaches

Fuzzy Filtering Algorithms for Image Processing: Performance Evaluation of Various Approaches Proceedngs of the Internatonal Conference on Cognton and Recognton Fuzzy Flterng Algorthms for Image Processng: Performance Evaluaton of Varous Approaches Rajoo Pandey and Umesh Ghanekar Department of

More information

Dynamic Bandwidth Provisioning with Fairness and Revenue Considerations for Broadband Wireless Communication

Dynamic Bandwidth Provisioning with Fairness and Revenue Considerations for Broadband Wireless Communication Ths full text paper was peer revewed at the drecton of IEEE Communcatons Socety subject matter experts for publcaton n the ICC 008 proceedngs. Dynamc Bandwdth Provsonng wth Farness and Revenue Consderatons

More information

OPTIMAL CONFIGURATION FOR NODES IN MIXED CELLULAR AND MOBILE AD HOC NETWORK FOR INET

OPTIMAL CONFIGURATION FOR NODES IN MIXED CELLULAR AND MOBILE AD HOC NETWORK FOR INET OPTIMAL CONFIGURATION FOR NODE IN MIED CELLULAR AND MOBILE AD HOC NETWORK FOR INET Olusola Babalola D.E. Department of Electrcal and Computer Engneerng Morgan tate Unversty Dr. Rchard Dean Faculty Advsor

More information

Resource and Virtual Function Status Monitoring in Network Function Virtualization Environment

Resource and Virtual Function Status Monitoring in Network Function Virtualization Environment Journal of Physcs: Conference Seres PAPER OPEN ACCESS Resource and Vrtual Functon Status Montorng n Network Functon Vrtualzaton Envronment To cte ths artcle: MS Ha et al 2018 J. Phys.: Conf. Ser. 1087

More information

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms Course Introducton Course Topcs Exams, abs, Proects A quc loo at a few algorthms 1 Advanced Data Structures and Algorthms Descrpton: We are gong to dscuss algorthm complexty analyss, algorthm desgn technques

More information

An Optimal Algorithm for Prufer Codes *

An Optimal Algorithm for Prufer Codes * J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,

More information

Parallel matrix-vector multiplication

Parallel matrix-vector multiplication Appendx A Parallel matrx-vector multplcaton The reduced transton matrx of the three-dmensonal cage model for gel electrophoress, descrbed n secton 3.2, becomes excessvely large for polymer lengths more

More information

Performance Comparison of a QoS Aware Routing Protocol for Wireless Sensor Networks

Performance Comparison of a QoS Aware Routing Protocol for Wireless Sensor Networks Communcatons and Network, 2016, 8, 45-55 Publshed Onlne February 2016 n ScRes. http://www.scrp.org/journal/cn http://dx.do.org/10.4236/cn.2016.81006 Performance Comparson of a QoS Aware Routng Protocol

More information

User Authentication Based On Behavioral Mouse Dynamics Biometrics

User Authentication Based On Behavioral Mouse Dynamics Biometrics User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA

More information

OPTIMAL VIDEO SUMMARY GENERATION AND ENCODING. (ICIP Draft v0.2, )

OPTIMAL VIDEO SUMMARY GENERATION AND ENCODING. (ICIP Draft v0.2, ) OPTIMAL VIDEO SUMMARY GENERATION AND ENCODING + Zhu L, * Aggelos atsaggelos and + Bhavan Gandh (ICIP Draft v.2, -2-23) + Multmeda Communcaton Research Lab, Motorola Labs, Schaumburg * Department of Electrcal

More information

Adaptive Energy and Location Aware Routing in Wireless Sensor Network

Adaptive Energy and Location Aware Routing in Wireless Sensor Network Adaptve Energy and Locaton Aware Routng n Wreless Sensor Network Hong Fu 1,1, Xaomng Wang 1, Yngshu L 1 Department of Computer Scence, Shaanx Normal Unversty, X an, Chna, 71006 fuhong433@gmal.com {wangxmsnnu@hotmal.cn}

More information

Analysis of Continuous Beams in General

Analysis of Continuous Beams in General Analyss of Contnuous Beams n General Contnuous beams consdered here are prsmatc, rgdly connected to each beam segment and supported at varous ponts along the beam. onts are selected at ponts of support,

More information

A Post Randomization Framework for Privacy-Preserving Bayesian. Network Parameter Learning

A Post Randomization Framework for Privacy-Preserving Bayesian. Network Parameter Learning A Post Randomzaton Framework for Prvacy-Preservng Bayesan Network Parameter Learnng JIANJIE MA K.SIVAKUMAR School Electrcal Engneerng and Computer Scence, Washngton State Unversty Pullman, WA. 9964-75

More information

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach Angle Estmaton and Correcton of Hand Wrtten, Textual and Large areas of Non-Textual Document Images: A Novel Approach D.R.Ramesh Babu Pyush M Kumat Mahesh D Dhannawat PES Insttute of Technology Research

More information

Performance Evaluation of Information Retrieval Systems

Performance Evaluation of Information Retrieval Systems Why System Evaluaton? Performance Evaluaton of Informaton Retreval Systems Many sldes n ths secton are adapted from Prof. Joydeep Ghosh (UT ECE) who n turn adapted them from Prof. Dk Lee (Unv. of Scence

More information

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth

More information

Maintaining temporal validity of real-time data on non-continuously executing resources

Maintaining temporal validity of real-time data on non-continuously executing resources Mantanng temporal valdty of real-tme data on non-contnuously executng resources Tan Ba, Hong Lu and Juan Yang Hunan Insttute of Scence and Technology, College of Computer Scence, 44, Yueyang, Chna Wuhan

More information

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices Steps for Computng the Dssmlarty, Entropy, Herfndahl-Hrschman and Accessblty (Gravty wth Competton) Indces I. Dssmlarty Index Measurement: The followng formula can be used to measure the evenness between

More information

A Hybrid Genetic Algorithm for Routing Optimization in IP Networks Utilizing Bandwidth and Delay Metrics

A Hybrid Genetic Algorithm for Routing Optimization in IP Networks Utilizing Bandwidth and Delay Metrics A Hybrd Genetc Algorthm for Routng Optmzaton n IP Networks Utlzng Bandwdth and Delay Metrcs Anton Redl Insttute of Communcaton Networks, Munch Unversty of Technology, Arcsstr. 21, 80290 Munch, Germany

More information

X- Chart Using ANOM Approach

X- Chart Using ANOM Approach ISSN 1684-8403 Journal of Statstcs Volume 17, 010, pp. 3-3 Abstract X- Chart Usng ANOM Approach Gullapall Chakravarth 1 and Chaluvad Venkateswara Rao Control lmts for ndvdual measurements (X) chart are

More information

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems A Unfed Framework for Semantcs and Feature Based Relevance Feedback n Image Retreval Systems Ye Lu *, Chunhu Hu 2, Xngquan Zhu 3*, HongJang Zhang 2, Qang Yang * School of Computng Scence Smon Fraser Unversty

More information

The Codesign Challenge

The Codesign Challenge ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.

More information

Support Vector Machines

Support Vector Machines Support Vector Machnes Decson surface s a hyperplane (lne n 2D) n feature space (smlar to the Perceptron) Arguably, the most mportant recent dscovery n machne learnng In a nutshell: map the data to a predetermned

More information

Fibre-Optic AWG-based Real-Time Networks

Fibre-Optic AWG-based Real-Time Networks Fbre-Optc AWG-based Real-Tme Networks Krstna Kunert, Annette Böhm, Magnus Jonsson, School of Informaton Scence, Computer and Electrcal Engneerng, Halmstad Unversty {Magnus.Jonsson, Krstna.Kunert}@de.hh.se

More information

DEAR: A DEVICE AND ENERGY AWARE ROUTING PROTOCOL FOR MOBILE AD HOC NETWORKS

DEAR: A DEVICE AND ENERGY AWARE ROUTING PROTOCOL FOR MOBILE AD HOC NETWORKS DEAR: A DEVICE AND ENERGY AWARE ROUTING PROTOCOL FOR MOBILE AD HOC NETWORKS Arun Avudanayagam Yuguang Fang Wenjng Lou Department of Electrcal and Computer Engneerng Unversty of Florda Ganesvlle, FL 3261

More information

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and

More information

Online Policies for Opportunistic Virtual MISO Routing in Wireless Ad Hoc Networks

Online Policies for Opportunistic Virtual MISO Routing in Wireless Ad Hoc Networks 12 IEEE Wreless Communcatons and Networkng Conference: Moble and Wreless Networks Onlne Polces for Opportunstc Vrtual MISO Routng n Wreless Ad Hoc Networks Crstano Tapparello, Stefano Tomasn and Mchele

More information

Wishing you all a Total Quality New Year!

Wishing you all a Total Quality New Year! Total Qualty Management and Sx Sgma Post Graduate Program 214-15 Sesson 4 Vnay Kumar Kalakband Assstant Professor Operatons & Systems Area 1 Wshng you all a Total Qualty New Year! Hope you acheve Sx sgma

More information

ARTICLE IN PRESS. Signal Processing: Image Communication

ARTICLE IN PRESS. Signal Processing: Image Communication Sgnal Processng: Image Communcaton 23 (2008) 754 768 Contents lsts avalable at ScenceDrect Sgnal Processng: Image Communcaton journal homepage: www.elsever.com/locate/mage Dstrbuted meda rate allocaton

More information

Overview. Basic Setup [9] Motivation and Tasks. Modularization 2008/2/20 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION

Overview. Basic Setup [9] Motivation and Tasks. Modularization 2008/2/20 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION Overvew 2 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION Introducton Mult- Smulator MASIM Theoretcal Work and Smulaton Results Concluson Jay Wagenpfel, Adran Trachte Motvaton and Tasks Basc Setup

More information

IJCTA Nov-Dec 2016 Available

IJCTA Nov-Dec 2016 Available Dr K Santh et al, Internatonal Journal of Computer Technology & Applcatons,Vol 7(6),773-779 Optmzed Route Technque for DSR Routng Protocol n MANET Dr.K.Santh, Assocate Professor, Dept. of Computer Scence,

More information

An efficient iterative source routing algorithm

An efficient iterative source routing algorithm An effcent teratve source routng algorthm Gang Cheng Ye Tan Nrwan Ansar Advanced Networng Lab Department of Electrcal Computer Engneerng New Jersey Insttute of Technology Newar NJ 7 {gc yt Ansar}@ntedu

More information

Learning-Based Top-N Selection Query Evaluation over Relational Databases

Learning-Based Top-N Selection Query Evaluation over Relational Databases Learnng-Based Top-N Selecton Query Evaluaton over Relatonal Databases Lang Zhu *, Wey Meng ** * School of Mathematcs and Computer Scence, Hebe Unversty, Baodng, Hebe 071002, Chna, zhu@mal.hbu.edu.cn **

More information

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 A mathematcal programmng approach to the analyss, desgn and

More information

LECTURE : MANIFOLD LEARNING

LECTURE : MANIFOLD LEARNING LECTURE : MANIFOLD LEARNING Rta Osadchy Some sldes are due to L.Saul, V. C. Raykar, N. Verma Topcs PCA MDS IsoMap LLE EgenMaps Done! Dmensonalty Reducton Data representaton Inputs are real-valued vectors

More information

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance Tsnghua Unversty at TAC 2009: Summarzng Mult-documents by Informaton Dstance Chong Long, Mnle Huang, Xaoyan Zhu State Key Laboratory of Intellgent Technology and Systems, Tsnghua Natonal Laboratory for

More information

Collaboratively Regularized Nearest Points for Set Based Recognition

Collaboratively Regularized Nearest Points for Set Based Recognition Academc Center for Computng and Meda Studes, Kyoto Unversty Collaboratvely Regularzed Nearest Ponts for Set Based Recognton Yang Wu, Mchhko Mnoh, Masayuk Mukunok Kyoto Unversty 9/1/013 BMVC 013 @ Brstol,

More information

Application of Clustering Algorithm in Big Data Sample Set Optimization

Application of Clustering Algorithm in Big Data Sample Set Optimization Applcaton of Clusterng Algorthm n Bg Data Sample Set Optmzaton Yutang Lu 1, Qn Zhang 2 1 Department of Basc Subjects, Henan Insttute of Technology, Xnxang 453002, Chna 2 School of Mathematcs and Informaton

More information

A Statistical Model Selection Strategy Applied to Neural Networks

A Statistical Model Selection Strategy Applied to Neural Networks A Statstcal Model Selecton Strategy Appled to Neural Networks Joaquín Pzarro Elsa Guerrero Pedro L. Galndo joaqun.pzarro@uca.es elsa.guerrero@uca.es pedro.galndo@uca.es Dpto Lenguajes y Sstemas Informátcos

More information

Query Clustering Using a Hybrid Query Similarity Measure

Query Clustering Using a Hybrid Query Similarity Measure Query clusterng usng a hybrd query smlarty measure Fu. L., Goh, D.H., & Foo, S. (2004). WSEAS Transacton on Computers, 3(3), 700-705. Query Clusterng Usng a Hybrd Query Smlarty Measure Ln Fu, Don Hoe-Lan

More information

DECA: distributed energy conservation algorithm for process reconstruction with bounded relative error in wireless sensor networks

DECA: distributed energy conservation algorithm for process reconstruction with bounded relative error in wireless sensor networks da Rocha Henrques et al. EURASIP Journal on Wreless Communcatons and Networkng (2016) 2016:163 DOI 10.1186/s13638-016-0662-9 RESEARCH Open Access DECA: dstrbuted energy conservaton algorthm for process

More information

Avoiding congestion through dynamic load control

Avoiding congestion through dynamic load control Avodng congeston through dynamc load control Vasl Hnatyshn, Adarshpal S. Seth Department of Computer and Informaton Scences, Unversty of Delaware, Newark, DE 976 ABSTRACT The current best effort approach

More information

Incremental Learning with Support Vector Machines and Fuzzy Set Theory

Incremental Learning with Support Vector Machines and Fuzzy Set Theory The 25th Workshop on Combnatoral Mathematcs and Computaton Theory Incremental Learnng wth Support Vector Machnes and Fuzzy Set Theory Yu-Mng Chuang 1 and Cha-Hwa Ln 2* 1 Department of Computer Scence and

More information

12/2/2009. Announcements. Parametric / Non-parametric. Case-Based Reasoning. Nearest-Neighbor on Images. Nearest-Neighbor Classification

12/2/2009. Announcements. Parametric / Non-parametric. Case-Based Reasoning. Nearest-Neighbor on Images. Nearest-Neighbor Classification Introducton to Artfcal Intellgence V22.0472-001 Fall 2009 Lecture 24: Nearest-Neghbors & Support Vector Machnes Rob Fergus Dept of Computer Scence, Courant Insttute, NYU Sldes from Danel Yeung, John DeNero

More information

Cost-efficient deployment of distributed software services

Cost-efficient deployment of distributed software services 1/30 Cost-effcent deployment of dstrbuted software servces csorba@tem.ntnu.no 2/30 Short ntroducton & contents Cost-effcent deployment of dstrbuted software servces Cost functons Bo-nspred decentralzed

More information

Connection-information-based connection rerouting for connection-oriented mobile communication networks

Connection-information-based connection rerouting for connection-oriented mobile communication networks Dstrb. Syst. Engng 5 (1998) 47 65. Prnted n the UK PII: S0967-1846(98)90513-7 Connecton-nformaton-based connecton reroutng for connecton-orented moble communcaton networks Mnho Song, Yanghee Cho and Chongsang

More information

FAHP and Modified GRA Based Network Selection in Heterogeneous Wireless Networks

FAHP and Modified GRA Based Network Selection in Heterogeneous Wireless Networks 2017 2nd Internatonal Semnar on Appled Physcs, Optoelectroncs and Photoncs (APOP 2017) ISBN: 978-1-60595-522-3 FAHP and Modfed GRA Based Network Selecton n Heterogeneous Wreless Networks Xaohan DU, Zhqng

More information

Biostatistics 615/815

Biostatistics 615/815 The E-M Algorthm Bostatstcs 615/815 Lecture 17 Last Lecture: The Smplex Method General method for optmzaton Makes few assumptons about functon Crawls towards mnmum Some recommendatons Multple startng ponts

More information

Machine Learning: Algorithms and Applications

Machine Learning: Algorithms and Applications 14/05/1 Machne Learnng: Algorthms and Applcatons Florano Zn Free Unversty of Bozen-Bolzano Faculty of Computer Scence Academc Year 011-01 Lecture 10: 14 May 01 Unsupervsed Learnng cont Sldes courtesy of

More information

CS 534: Computer Vision Model Fitting

CS 534: Computer Vision Model Fitting CS 534: Computer Vson Model Fttng Sprng 004 Ahmed Elgammal Dept of Computer Scence CS 534 Model Fttng - 1 Outlnes Model fttng s mportant Least-squares fttng Maxmum lkelhood estmaton MAP estmaton Robust

More information

Classification Based Mode Decisions for Video over Networks

Classification Based Mode Decisions for Video over Networks Classfcaton Based Mode Decsons for Vdeo over Networks Deepak S. Turaga and Tsuhan Chen Advanced Multmeda Processng Lab Tranng data for Inter-Intra Decson Inter-Intra Decson Regons pdf 6 5 6 5 Energy 4

More information

Positive Semi-definite Programming Localization in Wireless Sensor Networks

Positive Semi-definite Programming Localization in Wireless Sensor Networks Postve Sem-defnte Programmng Localzaton n Wreless Sensor etworks Shengdong Xe 1,, Jn Wang, Aqun Hu 1, Yunl Gu, Jang Xu, 1 School of Informaton Scence and Engneerng, Southeast Unversty, 10096, anjng Computer

More information

Feature Reduction and Selection

Feature Reduction and Selection Feature Reducton and Selecton Dr. Shuang LIANG School of Software Engneerng TongJ Unversty Fall, 2012 Today s Topcs Introducton Problems of Dmensonalty Feature Reducton Statstc methods Prncpal Components

More information

CS246: Mining Massive Datasets Jure Leskovec, Stanford University

CS246: Mining Massive Datasets Jure Leskovec, Stanford University CS46: Mnng Massve Datasets Jure Leskovec, Stanford Unversty http://cs46.stanford.edu /19/013 Jure Leskovec, Stanford CS46: Mnng Massve Datasets, http://cs46.stanford.edu Perceptron: y = sgn( x Ho to fnd

More information

Sensor-aware Adaptive Pull-Push Query Processing for Sensor Networks

Sensor-aware Adaptive Pull-Push Query Processing for Sensor Networks Sensor-aware Adaptve Pull-Push Query Processng for Sensor Networks Raja Bose Unversty of Florda Ganesvlle, FL 326 U.S.A. rbose@cse.ufl.edu Abdelsalam Helal Unversty of Florda Ganesvlle, FL 326 U.S.A. helal@cse.ufl.edu

More information

Ad Hoc Networks 11 (2013) Contents lists available at SciVerse ScienceDirect. Ad Hoc Networks

Ad Hoc Networks 11 (2013) Contents lists available at SciVerse ScienceDirect. Ad Hoc Networks Ad Hoc Networks 11 (213) 1136 1149 Contents lsts avalable at ScVerse ScenceDrect Ad Hoc Networks journal homepage: www.elsever.com/locate/adhoc Generc predcton asssted sngle-copy routng n underwater delay

More information

Using Particle Swarm Optimization for Enhancing the Hierarchical Cell Relay Routing Protocol

Using Particle Swarm Optimization for Enhancing the Hierarchical Cell Relay Routing Protocol 2012 Thrd Internatonal Conference on Networkng and Computng Usng Partcle Swarm Optmzaton for Enhancng the Herarchcal Cell Relay Routng Protocol Hung-Y Ch Department of Electrcal Engneerng Natonal Sun Yat-Sen

More information

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr)

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr) Helsnk Unversty Of Technology, Systems Analyss Laboratory Mat-2.08 Independent research projects n appled mathematcs (3 cr) "! #$&% Antt Laukkanen 506 R ajlaukka@cc.hut.f 2 Introducton...3 2 Multattrbute

More information

AN INDEXING METHOD FOR SUPPORTING SPATIAL QUERIES IN STRUCTURED PEER-TO-PEER SYSTEMS

AN INDEXING METHOD FOR SUPPORTING SPATIAL QUERIES IN STRUCTURED PEER-TO-PEER SYSTEMS AN INDEXING METHOD FOR SUPPORTING SPATIAL QUERIES IN STRUCTURED PEER-TO-PEER SYSTEMS Lngku Meng a, Wenun Xe a, *, Dan Lu a, b a School of Remote Sensng and Informaton Engneerng, Wuhan Unversty, Wuhan 4379,

More information

An Efficient Genetic Algorithm with Fuzzy c-means Clustering for Traveling Salesman Problem

An Efficient Genetic Algorithm with Fuzzy c-means Clustering for Traveling Salesman Problem An Effcent Genetc Algorthm wth Fuzzy c-means Clusterng for Travelng Salesman Problem Jong-Won Yoon and Sung-Bae Cho Dept. of Computer Scence Yonse Unversty Seoul, Korea jwyoon@sclab.yonse.ac.r, sbcho@cs.yonse.ac.r

More information

Bayesian Model for Mobility Prediction to Support Routing in Mobile Ad-Hoc Networks

Bayesian Model for Mobility Prediction to Support Routing in Mobile Ad-Hoc Networks Bayesan Model for Moblty Predcton to Support Routng n Moble Ad-Hoc Networks Tran The Son, Hoa Le Mnh, Graham Sexton, Nauman Aslam, Zabh Ghassemlooy Northumbra Communcatons Research Laboratory (NCRLab Faculty

More information

S1 Note. Basis functions.

S1 Note. Basis functions. S1 Note. Bass functons. Contents Types of bass functons...1 The Fourer bass...2 B-splne bass...3 Power and type I error rates wth dfferent numbers of bass functons...4 Table S1. Smulaton results of type

More information

Delay Variation Optimized Traffic Allocation Based on Network Calculus for Multi-path Routing in Wireless Mesh Networks

Delay Variation Optimized Traffic Allocation Based on Network Calculus for Multi-path Routing in Wireless Mesh Networks Appl. Math. Inf. Sc. 7, No. 2L, 467-474 2013) 467 Appled Mathematcs & Informaton Scences An Internatonal Journal http://dx.do.org/10.12785/ams/072l13 Delay Varaton Optmzed Traffc Allocaton Based on Network

More information