High-Level Power Modeling of CPLDs and FPGAs

Size: px
Start display at page:

Download "High-Level Power Modeling of CPLDs and FPGAs"

Transcription

1 Hgh-Level Power Modelng of CPLs and FPGAs L Shang and Nraj K. Jha epartment of Electrcal Engneerng Prnceton Unversty {lshang, jha}@ee.prnceton.edu Abstract In ths paper, we present a hgh-level power modelng technque to estmate the power consumpton of reconfgurable devces such as complex programmable logc devces (CPLs and feld-programmable gate arrays (FPGAs. For smplcty of reference, we smply refer to these devces as FPGAs. Frst, we capture the relatonshp between FPGA power dsspaton and I/O sgnal statstcs. We then use an adaptve regresson method to model the FPGA power consumpton. Such a hgh-level model can be used n the nner loop of a system-level synthess tool to estmate the power consumed by dfferent FPGA resources for dfferent potental system-level synthess solutons. It can also be used to verfy the power budgets durng embedded system desgn. Wth our hgh-level power model, the FPGA power consumpton can be obtaned very qucly. Expermental results ndcate that the average relatve error s only 3.1% compared to low-level FPGA power smulaton methods. 1. Introducton Reconfgurable devces [1-5], such as CPLs and FPGAs, are parallel and general hardware platforms. For embedded systems produced n lmted quanttes, FPGAs are much more flexble and cost-effectve alternatves to applcaton-specfc ntegrated crcuts (ASICs. More mportantly, modern applcatons, such as multmeda and wreless communcaton, have dfferent objectves under dfferent operatng modes. A mult-mode system archtecture can be supported by FPGAs n a natural way wth the help of dynamc reconfguraton. Wth the success of battery-based personal computng devces and wreless communcaton systems, low power has become a ey ssue n embedded system desgn. Although ts flexblty maes FPGA a good soluton for portable applcatons, the power consumpton problem cannot be neglected. Frst, less effcent utlzaton of avalable resources maes an FPGA less power-effcent than an ASIC. Second, snce routng resources n an FGPA nclude many swtches, the nterconnect load capactance of an FPGA s 10X to 100X compared to the Acnowledgements: hs wor was supported by ARPA under contract no. AAB07-00-C-L516. capactance n an ASIC [12]. In order to effectvely use FPGAs n low power systems, effcent FPGA power estmaton methods are needed. However, the problem of FPGA power estmaton s not that well-studed. he rest of ths paper s organzed as follows. In Secton 2, we dscuss prevous wors on FPGA and ASIC power estmaton. In Secton 3, we ntroduce our hghlevel power model. In Secton 4, we dscuss hgh-level FPGA power modelng n detal. In Secton 5, we present an adaptve regresson-based hgh-level power modelng technque. We demonstrate the feasblty of our methods expermentally n Secton 6. Fnally, we conclude n Secton Related Wor Some power estmaton technques for ASICs have been presented n [6-10]. In [7], technques are presented for estmatng swtchng actvty and power consumpton n regster-transfer level (RL crcuts. A framewor for exact and approxmate swtchng actvty estmaton n a sequental crcut s provded n [8]. A looup table based ASIC power estmaton method s proposed n [9,10]. o crcumvent the problem of an exponentally ncreasng storage for table looup, a four-dmensonal table s used to model power consumpton. Wors n [11-14] address the power estmaton/ optmzaton problem n FPGAs. A power estmaton method, whch s based on power modelng of dfferent components n an FPGA, s proposed n [12]. In ths approach, the nternal structure of the FPGA needs to be fully explored. ue to the perphery effect and estmaton error n swtchng actvty and nterconnect capactance, the total power estmaton error may be up to 30%. he method n [14] characterzes the power dsspaton of FPGAs usng Manhattan dstances between confgurable logc blocs (CLBs to model the nterconnect power consumpton. he error s usually less than 5% when compared to actual power measurement. However, snce an teratve approach s used for updatng the values of unnown sgnal parameters, the teraton process may not converge. Both the above methods need nternal FPGA confguraton nformaton, and use nternal sgnals to model power consumpton. However, snce many new macro modules, such as Bloc RAM [1], embedded

2 system bloc (ESB [2] and standard nterfaces etc., have been ntegrated nto FPGAs, fully explorng the nternal archtecture of an FPGA has become very challengng. Wth these nternal sgnal modelng approaches, dfferent modules may need ther own descrpton models. Hence, t becomes dffcult to construct a sngle fxed hgh-level power model template. 3. Overvew of Our Wor In ths paper, we propose a hgh-level FPGA power modelng approach wth the followng characterstcs. he model s based on nput and output sgnal statstcs to estmate the nternal power consumpton of FPGAs. Models for dfferently-confgured crcuts are based on the same power macromodel template. hus, the same modelng procedure s appled to dfferent crcuts, whether combnatonal or sequental. An adaptve regresson method s used to tacle the problem of based trang sequences. A good tradeoff between accuracy and effcency s acheved. here are two mportant concerns n hgh-level FPGA power modelng. Frst, hgh-level power estmators need to be more effcent than gate-level power estmators. he hgh-level power model we propose can be used n the nner loop of system-level synthess, puttng power estmaton n the crtcal path of synthess. hus, estmaton effcency s a must. We use a regresson functon to estmate the FPGA power consumpton. In our approach, spatal correlaton nformaton s utlzed to partton nput sgnals nto dfferent subsets. Statstcs for three nput sgnal parameters for each subset and one output sgnal parameter are used n our regresson method to construct the hgh-level power model. A shortcomng of hgh-level power estmaton methods n general s that a trang set of nput vectors wth gven statstcal dstrbutons s typcally used n developng the power macromodels. Hence, the macromodel s based towards the trang set. If the nput trace observed n practce has a dfferent statstcal dstrbuton than the trang set, the power estmaton result may not be accurate. urng normal operaton, there may be hundreds of dfferent typcal nput traces for dfferent applcatons. We cannot use a statc off-lne method to buld a power macromodel for each of these nput traces. In our approach, we use adaptve regresson methods to address ths problem. An adaptve regresson method has prevously been used for ASICs [19], but not for FPGAs. A low power CPL, called Coolrunner [15], s used for expermentally valdatng our technque. Coolrunner s an deal choce for battery-operated portable devces. rang sequences wth dfferent statstcal dstrbutons are generated for tmng and power smulaton. In order to capture the tmng nformaton for dfferent confguratons, we chose Scrocco [16], a real-delay tmng smulator. A low-level power smulator [17] s nvoed to estmate the power consumpton. Snce ths low-level power smulator captures all the nternal swtchng nformaton for ths devce, ts accuracy s comparable to physcal power measurements. hen wth all the collected nformaton, we use an adaptve regresson method to construct a hgh-level power model. Although our experments are based on the Coolrunner, our method s also sutable for other reconfgurable devces, ncludng other CPLs and FPGAs. here are two reasons for ths. Frst, our method does not need to explore the nternal structure of the reconfgurable devces. Only nput and output statstcal parameters are used to construct the hgh-level power model. Second, although the detaled nternal structures of dfferent reconfgurable devces are dfferent, most reconfgurable devces, ncludng CPLs and FPGAs, have the same macro structure: embedded logc blocs connected wth global and local nterconnecton resources. Netlst Synthess confguraton Real-delay smulaton models Adaptve hgh-level regresson power model Macromodel template analyss 1.Complexty analyss 2.Parameters selecton Real-delay smulator Statstcs analyzer Low-level power smulator Regresson analyss Statc hgh-level regresson power model Adaptve regresson analyss Statstcal parameters rang trace generator Parameter partton Parameter matrx Verfcaton model Gven nput trace Statstcs analyzer Fg.1: Hgh-level power modelng for FPGAs he adaptve regresson-based hgh-level power modelng flow s shown n Fg. 1. Frst, the macromodel template analyzer s nvoed to perform complexty analyss and other preprocessng steps. hen, trang sequences wth dfferent statstcal characterstcs are generated. hese sequences are used for real-delay tmng smulaton. Wth these results, the statstcs analyzer s nvoed to partton the nput sgnals nto subsets, and create a parameter matrx. A low-level power smulator tool s also nvoed to estmate FPGA power consumpton. he power results and parameter matrx form the nputs of the regresson analyss step. Usng feedbac from the verfcaton model, a statc hgh-level regresson power model s constructed. urng the power estmaton perod, the nput trace s analyzed to decde whether adaptve regresson analyss should be used. If

3 so, the nput trace s sampled, and the sampled data are sent to the low-level power estmator, whle the statc hgh-level regresson power model estmates the FPGA power consumpton wth the whole nput sequence. Adaptve regresson analyss s nvoed fnally to construct the adaptve hgh-level regresson power model. 4. Hgh-Level Power Modelng In ths secton, we gve detals of the consttuent parameters used n our power model. 4.1 Parttonng of nput sgnals In [10], smlar to our method, four nds of parameters are used to model the nput and output sgnal statstcs of ASICs. However, the method n [10] gnores the nature of the sgnals. In practcal crcuts, dfferent nput sgnals may or may not be correlated. For example, f the crcut nputs nclude both data and control sgnals, each may have a very dfferent statstcal dstrbuton. hus, one should avod usng one average statstcal parameter to cover both types of sgnals. In our nput sgnal parttonng approach, we study the spatal correlaton behavor between dfferent nput sgnals based on the nput traces wth dfferent statstcal dstrbutons. If the correlaton between two nput sgnals s less than a pre-defned correlaton threshold, we partton them to dfferent nput subsets, as shown n Fg. 2. hen, we use statstcal parameters to model the sgnals n each subset, as dscussed next. Input sgnals Subset Input sgnals partton Correlaton boundary Input sgnals Input sgnals Fg. 2: Input sgnals partton Input sgnals 4.1 Input subset sgnal probablty he FPGA power consumpton can vary sgnfcantly wth the statstcal dstrbuton of the nput data. Hence, whte nose nput sequence cannot be appled to model the power consumpton of FPGAs. In our approach, after spatal correlaton parttonng s done usng typcal nput traces, the average sgnal probablty for each nput sgnal subset s calculated and used n hgh-level power modelng. 4.2 Input subset sgnal transton densty For each nput subset, the average sgnal transton densty [10] s calculated to model the swtchng actvty for all the sgnals n the subset, whch s defned as: = subset N nn ( lm subset where nn ( swtches durng tme. sgnals n subset. (1 s the number of tmes nput sgnal n N subset s the number of nput 4.3 Input subset sgnal spatal correlaton he average nput subset parwse correlaton parameter [8] s defned as: prob{ n n = 1} SC = (, + 1 subset N subset + 1 where the parameters are self-evdent. 4.4 Output sgnal transton densty he last parameter s the average output sgnal transton densty. In order to construct a more accurate power macromodel, we use real-delay tmng smulaton and capture the transton densty of the output sgnals. hs allows us to capture output gltchng nformaton, whch also reflects the nternal FPGA gltchng behavor. 4.5 Regresson macromodelng functon Our hgh-level power model s based on the average nput subset sgnal probablty (P n, average nput subset sgnal transton densty ( n, average nput subset sgnal spatal correlaton (SC n, and average output sgnal transton densty ( out. Frst-order, quadratc and cubc regresson templates are three possble approaches to model the FPGA power, whch have dfferent executon complexty and accuracy. In the smplest model, a frstorder polynomal template s expressed as: Power where FPGA C n 1 = ( = 0 Pn C P Pn out out SCn c out c SCn SC (2 (3 are regresson coeffcents, and n s the total number of nput subsets. In order to acheve a good trade-off between effcency and accuracy, we desgn a hybrd model n our approach, whch s based on the senstvty of dfferent parameters. Frst, we evaluate the senstvty of FPGA power consumpton to the dfferent parameters. A low order term s chosen for parameters to whch the FPGA power s less senstve, whle a hgh order term s used for parameters to whch the FPGA power s more senstve. he pseudo-code of our algorthm s shown n Fg. 3. In ths algorthm, p denotes the total number of terms and q the total number of frst-order terms (e.g., s a frstorder term n Equaton (3. εthreshold s a predefned error threshold. he error mmzaton rato (EMR s defned as the error mmzed per term dvded by the error threshold:

4 εn 1 εn EMR = ε threshold 1. Create_canddate_term_pool( term1,term2,...,term p 2. Reg_fun_tem = Create_frst_order_template( term1,..., termq 3. Powerlow_level = Low_level_power_est( real_delay_smulaton 4. Powerhgh_level = Regresson_power_est( Reg_fun_tem 5. Error_calculaton( Powerlow_level,Powerhgh_level 6. Whle( ( error ε threshold terms termupperbound EMR EMR 7. erm_pr_sen_sortng( term_pool 8. new_term = term_pool.begn( 9. Reg_fun_tem Reg_template( Reg_fun_tem,new_term 10. Powerhgh_level = = Regresson_power_est( Reg_fun_tem 11. Error_calculaton( Powerlow_level,Powerhgh_level 12. terms EMR _ calculaton( 14. } output( Reg_fun_tem, error} (4 lowerbound Fg. 3: he power macromodelng algorthm In the frst step of the algorthm, a pool of terms s created, and the senstvty of FPGA power to each term s evaluated dynamcally n the followng teratons. hen, n Steps 2-5, the tal regresson model s constructed and the pertnent error compared to low-level power estmaton results s calculated. If the error s larger than ε threshold, a heurstc procedure s nvoed n Step 6. he prorty of terms n the pool s decded dynamcally accordng to ther senstvty (Step 7, and the term (quadratc or cubc wth the hghest prorty s chosen and ncluded n the macromodel (Steps 8 and 9. he error and EMR are evaluated (Steps 11 and 13. At the end of each teraton, three crtera are used to mae a decson on whether the heurstc procedure should be stopped. he three crtera are: frst, the error s less than a predefned error threshold, ε threshold, or second, the total number of terms has exceeded a predefned upper bound on the number of terms, or thrd, the EMR s less than a predefned threshold, EMR lowerbound. Snce dfferent crcuts mapped to an FPGA have dfferent power consumpton behavor, usng our algorthm, we can flexbly construct hgh-level power estmaton models wth dfferent complexty for them, achevng a good trade-off between effcency and accuracy. For our example crcuts, a typcal hgh-level power estmaton functon was found to be: Power FPGA n 1 = ( = 0 C P P SC Pn, SCn Pn, SCn SC out out Pn Havng derved a hgh-level power estmaton functon, we need to estmate the regresson coeffcents C. Hence, we generate dfferent random nput sequences wth dfferent values of P n, n, and SC n, coverng a wde range of nput statstcs. For each nput sequence, a lowerlevel power smulator and real-delay tmng smulator s nvoed to estmate the average FPGA power consumpton and average output sgnal transton densty out. hese results are used to calculate the regresson c P (5 { coeffcents as follows. We frst set up a matrx equaton based on the nputs: P x0, P1 x 1,... = Pr xr 2,... Pr xr 1,... where P l, l = 0,1,..., r 1, x0, s C0 x 1, s C xr 2, s Cs 1 x r 1, s Cs denotes the power smulaton results for the l th nput sequence, x j,, j = 0,..., r 1, = 1,..., s represents the th parameter s j th statstcal value, and C t, t = 0,1,..., s, s the regresson coeffcent we need to estmate. enote the matrx by [X]. If [X] [X] s of full ran, then [18]: Co C1... = Cs 1 Cs P 0 1 P 1 [ X ] [ X ] [ X ]... (7 P P r 2 r 1 o evaluate the accuracy of the macro-model, we defne relatve error as: ε = where r 1(( Pˆ P / P = 0 r P 2 s are the smulated power consumpton, and P s are the estmated values. 5. Adaptve Regresson-Based Power Estmaton he method and algorthm descrbed so far are based on statc macromodels, whch do not change from one desgn that uses the macro logc bloc to another. However, such a statc macromodel s based towards the set of trang patterns used. It s most accurate when the trang patterns reflect well the typcal nput sequences n a specfc desgn mplementaton. However, ths may not always be true. he macro logc bloc and ts hgh-level power model are lely to be stored n a desgn lbrary, whch s used for dfferent applcatons, n whch the data statstcs can vary dramatcally. On the other hand, snce low-level power estmaton s tme-consumng, as we mentoned earler, f the hgh-level power models are to be used n the nner loop of system-level synthess, only fast and relatvely accurate power estmaton s acceptable. We use an adaptve regresson modelng approach to tacle the above problem, as shown n Fg. 4. Frst, the real-delay tmng smulator s nvoed for the gven nput trace. We compute the relevant statstcs of the nput sequence n Step 2 to determne f the nput sequence under consderaton has smlar statstcal characterstcs as the trang set used to derve the statc hgh-level power model (Step 3. If so, statc regresson modelng s used (Step 4. Otherwse, we nvoe the adaptve regresson modelng engne n Step 5, where the nput sequence s sampled. A low-level power estmator s nvoed to estmate the FPGA power consumpton wth (6 (8

5 the sampled sequence (Step 6. he statc hgh-level power model s also used to estmate the power consumed by the FPGA for the whole nput trace (Step 7. Fnally, n Step 8, an adaptve regresson engne s nvoed to generate the adaptve hgh-level power model. Snce the length of the sampled sequences s much shorter than the whole typcal nput trace, the tme consumed n runnng the low-level power smulator s acceptable. By adaptng the statc hgh-level power model usng sampled vectors, we can acheve a good trade-off between accuracy and effcency. Netlst Synthess confguraton Real-delay smulaton models Statc hgh-level power model Step 7. All vectors Step 8. ynamc model adaptaton Power estmaton result Step 4. Gven nput trace Step 1. Real-delay smulator Step 2. Statstcs engne Step 3. Statstcs analyss Step 5. Vector par sam plng Step 6. Sampled vectors Low-level power smulator Regresson engne Fg. 4: Adaptve regresson method flow he method we use s smlar to the one used n [19] for ASICs. Let S be the set of all nput vector pars for a macro logc bloc such that S = N. We sample a subset s S, such that s = n. Let x be the power estmaton result obtaned from the statc hgh-level power model, and y be the power estmaton result obtaned from the low-level power smulator. A lnear functon of hgh-level power estmaton results,, s used to estmate the low-level power smulaton results,, as follows. y y = nα + β x whereα and β are constants. hus, mmzng y ~ get ~ α = y β x and ~ β = ( y y( x x 2 ( x x ( α βx 2 x (9 least-square-error, we (10 where y and x are the average of y and x. hen the modfed power estmate, P, s gven by [19] 1 ~ ~ P = ( y + ( N n α + β x N s (11 6. Expermental Results In ths secton, we present the expermental results to demonstrate the effcacy of our hgh-level power modelng approach. We should frst eep n mnd that FPGA and ASIC lbrares are dfferent. In an ASIC lbrary, f a component s presented as a hard core, t means that the layout and technology are fxed. When such a component s used n a system, wth the same nput sequence, the tmng and power behavor wll be the same. hs may not be true for a component from the FPGA lbrary. Snce FPGAs consttute a parallel hardware platform, multple tass may execute concurrently on the same devce. Combnatons of dfferent tass change the tas confguraton. For the same macro logc bloc, the power consumpton under dfferent confguratons may be dfferent,.e., power estmaton cannot be strctly modeled wth the same parameters or functons. herefore, for hgh-level power modelng, multple tass need to be consdered together, and macro logc bloc combnatons, whch occur wth a hgh probablty, need to be explored. he second pont s that the hgh-level power models we construct are sutable for both combnatonal and sequental logc. Although n sequental logc, the tal states are dffcult to ascertan, the estmaton error ntroduced by unnown tal states s mmzed n a long smulaton. A seres of experments was performed to verfy our hgh-level power estmaton model on a Sun Enterprse 4500 server wth 4 ggabyte memory. he example crcuts are ( 8-bt ALU wth control logc, ( 32-bt adder, ( FIR flter, (v IIR flter, (v Huffman encoder, (v ALU, controller and encoder, and (v ALU, controller and FIR flter. he results for these examples are shown n ables I and II. he crcuts are referred to as Crcut 1-7, respectvely. Ex. able I: Accuracy of the hgh-level power models erms Relatve error Max. error Offlne CPU tme(hrs Onlne CPU tme(sec Crcut % 1.7% Crcut % 4.4% Crcut % 3.4% Crcut % 4.1% Crcut % 7.9% Crcut % 6.7% Crcut % 5.5% In able I, for each example, we show fve results for statc regresson-based hgh-level power models: number of terms we use n the model, relatve error, maxmum error, tme used to construct the model, and tme used to estmate power consumpton. For these examples, the average relatve error s 1.7%.

6 able II: Accuracy of the adaptve regresson-based hgh-level power models Ex. erms Onlne Relatve Samplng CPU error rato tme(sec Crcut % 5% 5.8 Crcut % 5% 8.4 Crcut % 5% 5.5 Crcut % 5% 8.0 Crcut % 5% 6.9 Crcut % 5% 11.7 Crcut % 5% 8.7 In able II, we show results for adaptve regressonbased power models for nput traces wth very dfferent statstcal characterstcs than those used to derve the statc macromodel. he table ncludes the number of terms, relatve error, and the vector-pars samplng rato (.e., the percentage of vector pars from the nput trace that are sampled. Comparng these results wth those n able I, we note that adaptve modelng leads to relatve errors that are qute comparable to those from the statc macromodel. hus, t s ndeed able to adapt to dfferent nput traces wthout much loss n accuracy. For these examples, the average relatve error s only 3.1%. Fgure 5 demonstrates the agreement between hgh-level and low-level power estmaton for part of the expermental results. Fg. 5: Hgh-level vs. low-level power estmaton 7. Conclusons We have presented effcent adaptve regresson-based hgh-level power models to estmate FPGA power consumpton. For each FPGA confguraton, only four types of nput/output statstcs are needed, and only one compact functon s needed to estmate the power consumpton. hus, the memory space requred to store the hgh-level power model s also small. he methods and algorthms we use are general: ( the same power macromodel template can be used for all modeled crcuts. ( hey do not need to explore the nternal structure of the reconfgurable devces. ( In order to mprove on-lne power estmaton accuracy, we use adaptve regresson methods to lessen the problem of based trang sequences, and acheve a good trade-off between effcency and accuracy. References [1] Vrtex data sheet, [2] APEX data sheet, [3] FPSLIC, [4] S. rmberger,. Carberry, A. Johnson, and J. Wong, A tme-multplexed FPGA, n Proc. Feld-Programmable Custom Computng Machnes, pp , Apr [5] K. Compton and S. Hauc, Confgurable computng: A survey of systems and software, submtted to ACM Computng Surveys, [6] P. E. Landman and J. M. Rabaey, Archtectural power analyss: he dual bt type method, IEEE rans. VLSI Systems, vol. 3, pp , June [7] A. Raghunathan, S. ey, and N. K. Jha, Regster-transfer level estmaton technques for swtchng actvty and power consumpton, n Proc. Int. Conf. Computer-Aded esgn, pp , Nov [8] C-Y. su, J. Montero, M. Pedram, S. evadas, A. M. espan, and B. Ln, Power estmaton n sequental logc crcuts, IEEE rans. VLSI Systems, vol. 3, no. 3, pp , Sept [9] S. Gupta and F. N. Najm, Analytcal model for hgh level power modelng of combnatonal and sequental crcuts, n Proc. Alessandro Volta Memoral Wsp. Low Power esgn, pp , Mar [10] S. Gupta and F. Najm, Power modelng for hgh-level power estmaton, IEEE rans. VLSI systems, vol. 8, no. 1, pp , Feb [11] K. Roy, Power-dsspaton drven FPGA place and route under tmng constrants, IEEE rans. Crcuts & Systems, vol. 46, no. 5, pp , May [12] E. A. Kusse, Analyss and crcut desgn for low power programmable logc modules, Master s thess, ept. of Electrcal Engneerng and Computer Scence, Unversty of Calforna at Bereley, [13] V. George, H. Zhang and J. Rabaey, esgn of a low energy FPGA, n Proc. Int. Symp. Low Power Electroncs & esgn, pp , Aug [14]. Osmuls, J.. Muehrng, B. Veale, J. M. West, H. L, S. Vanchayobon, S. -H. Ko, J. K. Antono, and S. K. hall, A probablstc power predcton tool for the Xlnx 4000-seres FPGA, n Proc. 5 th Int. Wsp. Embedded/strbuted HPC Systems and Applcatons (EHPC 2000, IPPS 2000 Worshops, pp , May [15] CoolRunner, [16] Scrocco smulator, [17] Power estmator for CoolRunner, [18] R.H. Myerslasscal and Modern Regresson wth Applcaton, uxbury Press, BelmontA, 2 nd edton, [19] C.-. Hseh, Q. Wu.-S. ng, and M. Pedram, Statstcal samplng and regresson analyss for R-level power evaluaton, n Proc. Int. Conf. Computer-Aded esgn, pp , Nov

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

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,

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

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

Determining the Optimal Bandwidth Based on Multi-criterion Fusion Proceedngs of 01 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 5 (01) (01) IACSIT Press, Sngapore Determnng the Optmal Bandwdth Based on Mult-crteron Fuson Ha-L Lang 1+, Xan-Mn

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

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

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

Configuration Management in Multi-Context Reconfigurable Systems for Simultaneous Performance and Power Optimizations*

Configuration Management in Multi-Context Reconfigurable Systems for Simultaneous Performance and Power Optimizations* Confguraton Management n Mult-Context Reconfgurable Systems for Smultaneous Performance and Power Optmzatons* Rafael Maestre, Mlagros Fernandez Departamento de Arqutectura de Computadores y Automátca Unversdad

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

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching A Fast Vsual Trackng Algorthm Based on Crcle Pxels Matchng Zhqang Hou hou_zhq@sohu.com Chongzhao Han czhan@mal.xjtu.edu.cn Ln Zheng Abstract: A fast vsual trackng algorthm based on crcle pxels matchng

More information

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

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation 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 An Iteratve Soluton Approach to Process Plant Layout usng Mxed

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

An Image Fusion Approach Based on Segmentation Region

An Image Fusion Approach Based on Segmentation Region Rong Wang, L-Qun Gao, Shu Yang, Yu-Hua Cha, and Yan-Chun Lu An Image Fuson Approach Based On Segmentaton Regon An Image Fuson Approach Based on Segmentaton Regon Rong Wang, L-Qun Gao, Shu Yang 3, Yu-Hua

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

Air Transport Demand. Ta-Hui Yang Associate Professor Department of Logistics Management National Kaohsiung First Univ. of Sci. & Tech.

Air Transport Demand. Ta-Hui Yang Associate Professor Department of Logistics Management National Kaohsiung First Univ. of Sci. & Tech. Ar Transport Demand Ta-Hu Yang Assocate Professor Department of Logstcs Management Natonal Kaohsung Frst Unv. of Sc. & Tech. 1 Ar Transport Demand Demand for ar transport between two ctes or two regons

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

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

Load Balancing for Hex-Cell Interconnection Network

Load Balancing for Hex-Cell Interconnection Network Int. J. Communcatons, Network and System Scences,,, - Publshed Onlne Aprl n ScRes. http://www.scrp.org/journal/jcns http://dx.do.org/./jcns.. Load Balancng for Hex-Cell Interconnecton Network Saher Manaseer,

More information

Repeater Insertion for Two-Terminal Nets in Three-Dimensional Integrated Circuits

Repeater Insertion for Two-Terminal Nets in Three-Dimensional Integrated Circuits Repeater Inserton for Two-Termnal Nets n Three-Dmensonal Integrated Crcuts Hu Xu, Vasls F. Pavlds, and Govann De Mchel LSI - EPFL, CH-5, Swtzerland, {hu.xu,vasleos.pavlds,govann.demchel}@epfl.ch Abstract.

More information

Outline. Digital Systems. C.2: Gates, Truth Tables and Logic Equations. Truth Tables. Logic Gates 9/8/2011

Outline. Digital Systems. C.2: Gates, Truth Tables and Logic Equations. Truth Tables. Logic Gates 9/8/2011 9/8/2 2 Outlne Appendx C: The Bascs of Logc Desgn TDT4255 Computer Desgn Case Study: TDT4255 Communcaton Module Lecture 2 Magnus Jahre 3 4 Dgtal Systems C.2: Gates, Truth Tables and Logc Equatons All sgnals

More information

NAG Fortran Library Chapter Introduction. G10 Smoothing in Statistics

NAG Fortran Library Chapter Introduction. G10 Smoothing in Statistics Introducton G10 NAG Fortran Lbrary Chapter Introducton G10 Smoothng n Statstcs Contents 1 Scope of the Chapter... 2 2 Background to the Problems... 2 2.1 Smoothng Methods... 2 2.2 Smoothng Splnes and Regresson

More information

AADL : about scheduling analysis

AADL : about scheduling analysis AADL : about schedulng analyss Schedulng analyss, what s t? Embedded real-tme crtcal systems have temporal constrants to meet (e.g. deadlne). Many systems are bult wth operatng systems provdng multtaskng

More information

Review of approximation techniques

Review of approximation techniques CHAPTER 2 Revew of appromaton technques 2. Introducton Optmzaton problems n engneerng desgn are characterzed by the followng assocated features: the objectve functon and constrants are mplct functons evaluated

More information

A Power Optimization Toolbox for Logic Synthesis and Mapping

A Power Optimization Toolbox for Logic Synthesis and Mapping A Power Optmzaton Toolbox for Logc Synthess and Mappng Alan Mshchenko Robert Brayton Stephen Jang Kevn Chung Department of EECS, Unversty of Calforna, Berkeley LogcMll Technology Qualcom Innovatons {alanm,

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

Mathematics 256 a course in differential equations for engineering students

Mathematics 256 a course in differential equations for engineering students Mathematcs 56 a course n dfferental equatons for engneerng students Chapter 5. More effcent methods of numercal soluton Euler s method s qute neffcent. Because the error s essentally proportonal to the

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

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

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

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

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters Proper Choce of Data Used for the Estmaton of Datum Transformaton Parameters Hakan S. KUTOGLU, Turkey Key words: Coordnate systems; transformaton; estmaton, relablty. SUMMARY Advances n technologes and

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

Fusion Performance Model for Distributed Tracking and Classification

Fusion Performance Model for Distributed Tracking and Classification Fuson Performance Model for Dstrbuted rackng and Classfcaton K.C. Chang and Yng Song Dept. of SEOR, School of I&E George Mason Unversty FAIRFAX, VA kchang@gmu.edu Martn Lggns Verdan Systems Dvson, Inc.

More information

CPE 628 Chapter 2 Design for Testability. Dr. Rhonda Kay Gaede UAH. UAH Chapter Introduction

CPE 628 Chapter 2 Design for Testability. Dr. Rhonda Kay Gaede UAH. UAH Chapter Introduction Chapter 2 Desgn for Testablty Dr Rhonda Kay Gaede UAH 2 Introducton Dffcultes n and the states of sequental crcuts led to provdng drect access for storage elements, whereby selected storage elements are

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

Study of Data Stream Clustering Based on Bio-inspired Model

Study of Data Stream Clustering Based on Bio-inspired Model , pp.412-418 http://dx.do.org/10.14257/astl.2014.53.86 Study of Data Stream lusterng Based on Bo-nspred Model Yngme L, Mn L, Jngbo Shao, Gaoyang Wang ollege of omputer Scence and Informaton Engneerng,

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

3. CR parameters and Multi-Objective Fitness Function

3. CR parameters and Multi-Objective Fitness Function 3 CR parameters and Mult-objectve Ftness Functon 41 3. CR parameters and Mult-Objectve Ftness Functon 3.1. Introducton Cogntve rados dynamcally confgure the wreless communcaton system, whch takes beneft

More information

Conditional Speculative Decimal Addition*

Conditional Speculative Decimal Addition* Condtonal Speculatve Decmal Addton Alvaro Vazquez and Elsardo Antelo Dep. of Electronc and Computer Engneerng Unv. of Santago de Compostela, Span Ths work was supported n part by Xunta de Galca under grant

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

Modeling Multiple Input Switching of CMOS Gates in DSM Technology Using HDMR

Modeling Multiple Input Switching of CMOS Gates in DSM Technology Using HDMR 1 Modelng Multple Input Swtchng of CMOS Gates n DSM Technology Usng HDMR Jayashree Srdharan and Tom Chen Dept. of Electrcal and Computer Engneerng Colorado State Unversty, Fort Collns, CO, 8523, USA (jaya@engr.colostate.edu,

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

Application of Improved Fish Swarm Algorithm in Cloud Computing Resource Scheduling

Application of Improved Fish Swarm Algorithm in Cloud Computing Resource Scheduling , pp.40-45 http://dx.do.org/10.14257/astl.2017.143.08 Applcaton of Improved Fsh Swarm Algorthm n Cloud Computng Resource Schedulng Yu Lu, Fangtao Lu School of Informaton Engneerng, Chongqng Vocatonal Insttute

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

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010 Smulaton: Solvng Dynamc Models ABE 5646 Week Chapter 2, Sprng 200 Week Descrpton Readng Materal Mar 5- Mar 9 Evaluatng [Crop] Models Comparng a model wth data - Graphcal, errors - Measures of agreement

More information

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Proceedngs of the Wnter Smulaton Conference M E Kuhl, N M Steger, F B Armstrong, and J A Jones, eds A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Mark W Brantley Chun-Hung

More information

A RECONFIGURABLE ARCHITECTURE FOR MULTI-GIGABIT SPEED CONTENT-BASED ROUTING. James Moscola, Young H. Cho, John W. Lockwood

A RECONFIGURABLE ARCHITECTURE FOR MULTI-GIGABIT SPEED CONTENT-BASED ROUTING. James Moscola, Young H. Cho, John W. Lockwood A RECONFIGURABLE ARCHITECTURE FOR MULTI-GIGABIT SPEED CONTENT-BASED ROUTING James Moscola, Young H. Cho, John W. Lockwood Dept. of Computer Scence and Engneerng Washngton Unversty, St. Lous, MO {jmm5,

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

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

Projection-Based Performance Modeling for Inter/Intra-Die Variations

Projection-Based Performance Modeling for Inter/Intra-Die Variations Proecton-Based Performance Modelng for Inter/Intra-De Varatons Xn L, Jayong Le 2, Lawrence. Plegg and Andrze Strowas Dept. of Electrcal & Computer Engneerng Carnege Mellon Unversty Pttsburgh, PA 523, USA

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

Six-Band HDTV Camera System for Color Reproduction Based on Spectral Information

Six-Band HDTV Camera System for Color Reproduction Based on Spectral Information IS&T's 23 PICS Conference Sx-Band HDTV Camera System for Color Reproducton Based on Spectral Informaton Kenro Ohsawa )4), Hroyuk Fukuda ), Takeyuk Ajto 2),Yasuhro Komya 2), Hdeak Hanesh 3), Masahro Yamaguch

More information

Explicit Formulas and Efficient Algorithm for Moment Computation of Coupled RC Trees with Lumped and Distributed Elements

Explicit Formulas and Efficient Algorithm for Moment Computation of Coupled RC Trees with Lumped and Distributed Elements Explct Formulas and Effcent Algorthm for Moment Computaton of Coupled RC Trees wth Lumped and Dstrbuted Elements Qngan Yu and Ernest S.Kuh Electroncs Research Lab. Unv. of Calforna at Berkeley Berkeley

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

Wavefront Reconstructor

Wavefront Reconstructor A Dstrbuted Smplex B-Splne Based Wavefront Reconstructor Coen de Vsser and Mchel Verhaegen 14-12-201212 2012 Delft Unversty of Technology Contents Introducton Wavefront reconstructon usng Smplex B-Splnes

More information

A Saturation Binary Neural Network for Crossbar Switching Problem

A Saturation Binary Neural Network for Crossbar Switching Problem A Saturaton Bnary Neural Network for Crossbar Swtchng Problem Cu Zhang 1, L-Qng Zhao 2, and Rong-Long Wang 2 1 Department of Autocontrol, Laonng Insttute of Scence and Technology, Benx, Chna bxlkyzhangcu@163.com

More information

Decision Strategies for Rating Objects in Knowledge-Shared Research Networks

Decision Strategies for Rating Objects in Knowledge-Shared Research Networks Decson Strateges for Ratng Objects n Knowledge-Shared Research etwors ALEXADRA GRACHAROVA *, HAS-JOACHM ER **, HASSA OUR ELD ** OM SUUROE ***, HARR ARAKSE *** * nsttute of Control and System Research,

More information

SVM-based Learning for Multiple Model Estimation

SVM-based Learning for Multiple Model Estimation SVM-based Learnng for Multple Model Estmaton Vladmr Cherkassky and Yunqan Ma Department of Electrcal and Computer Engneerng Unversty of Mnnesota Mnneapols, MN 55455 {cherkass,myq}@ece.umn.edu Abstract:

More information

High-Boost Mesh Filtering for 3-D Shape Enhancement

High-Boost Mesh Filtering for 3-D Shape Enhancement Hgh-Boost Mesh Flterng for 3-D Shape Enhancement Hrokazu Yagou Λ Alexander Belyaev y Damng We z Λ y z ; ; Shape Modelng Laboratory, Unversty of Azu, Azu-Wakamatsu 965-8580 Japan y Computer Graphcs Group,

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

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

A Similarity-Based Prognostics Approach for Remaining Useful Life Estimation of Engineered Systems

A Similarity-Based Prognostics Approach for Remaining Useful Life Estimation of Engineered Systems 2008 INTERNATIONAL CONFERENCE ON PROGNOSTICS AND HEALTH MANAGEMENT A Smlarty-Based Prognostcs Approach for Remanng Useful Lfe Estmaton of Engneered Systems Tany Wang, Janbo Yu, Davd Segel, and Jay Lee

More information

Range images. Range image registration. Examples of sampling patterns. Range images and range surfaces

Range images. Range image registration. Examples of sampling patterns. Range images and range surfaces Range mages For many structured lght scanners, the range data forms a hghly regular pattern known as a range mage. he samplng pattern s determned by the specfc scanner. Range mage regstraton 1 Examples

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

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

Motivation. EE 457 Unit 4. Throughput vs. Latency. Performance Depends on View Point?! Computer System Performance. An individual user wants to:

Motivation. EE 457 Unit 4. Throughput vs. Latency. Performance Depends on View Point?! Computer System Performance. An individual user wants to: 4.1 4.2 Motvaton EE 457 Unt 4 Computer System Performance An ndvdual user wants to: Mnmze sngle program executon tme A datacenter owner wants to: Maxmze number of Mnmze ( ) http://e-tellgentnternetmarketng.com/webste/frustrated-computer-user-2/

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

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

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision SLAM Summer School 2006 Practcal 2: SLAM usng Monocular Vson Javer Cvera, Unversty of Zaragoza Andrew J. Davson, Imperal College London J.M.M Montel, Unversty of Zaragoza. josemar@unzar.es, jcvera@unzar.es,

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

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

Simple March Tests for PSF Detection in RAM

Simple March Tests for PSF Detection in RAM Smple March Tests for PSF Detecton n RAM Ireneusz Mroze Balysto Techncal Unversty Computer Scence Department Wejsa 45A, 5-35 Balysto POLAND mroze@.pb.balysto.pl Eugena Buslowsa Balysto Techncal Unversty

More information

IMPACT OF RADIO MAP SIMULATION ON POSITIONING IN INDOOR ENVIRONTMENT USING FINGER PRINTING ALGORITHMS

IMPACT OF RADIO MAP SIMULATION ON POSITIONING IN INDOOR ENVIRONTMENT USING FINGER PRINTING ALGORITHMS IMPACT OF RADIO MAP SIMULATION ON POSITIONING IN INDOOR ENVIRONTMENT USING FINGER PRINTING ALGORITHMS Jura Macha and Peter Brda Unversty of Zlna, Faculty of Electrcal Engneerng, Department of Telecommuncatons

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

Newton-Raphson division module via truncated multipliers

Newton-Raphson division module via truncated multipliers Newton-Raphson dvson module va truncated multplers Alexandar Tzakov Department of Electrcal and Computer Engneerng Illnos Insttute of Technology Chcago,IL 60616, USA Abstract Reducton n area and power

More information

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z.

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z. TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS Muradalyev AZ Azerbajan Scentfc-Research and Desgn-Prospectng Insttute of Energetc AZ1012, Ave HZardab-94 E-mal:aydn_murad@yahoocom Importance 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

APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET

APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET Jae-young Lee, Shahram Payandeh, and Ljljana Trajovć School of Engneerng Scence Smon Fraser Unversty 8888 Unversty

More information

Relevance Assignment and Fusion of Multiple Learning Methods Applied to Remote Sensing Image Analysis

Relevance Assignment and Fusion of Multiple Learning Methods Applied to Remote Sensing Image Analysis Assgnment and Fuson of Multple Learnng Methods Appled to Remote Sensng Image Analyss Peter Bajcsy, We-Wen Feng and Praveen Kumar Natonal Center for Supercomputng Applcaton (NCSA), Unversty of Illnos at

More information

Run-Time Energy Estimation in System-On-a-Chip Designs *

Run-Time Energy Estimation in System-On-a-Chip Designs * Run-Tme Energy Estmaton n System-On-a-Chp Desgns * J. Had, G. Kaefer, Ch. Steger, R. Wess Insttute for Techncal Informatcs Graz Unversty of Technology Graz, Austra Abstract - In ths paper, a co-processor

More information

Categories and Subject Descriptors B.7.2 [Integrated Circuits]: Design Aids Verification. General Terms Algorithms

Categories and Subject Descriptors B.7.2 [Integrated Circuits]: Design Aids Verification. General Terms Algorithms 3. Fndng Determnstc Soluton from Underdetermned Equaton: Large-Scale Performance Modelng by Least Angle Regresson Xn L ECE Department, Carnege Mellon Unversty Forbs Avenue, Pttsburgh, PA 3 xnl@ece.cmu.edu

More information

APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET

APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET APPLICATION OF PREDICTION-BASED PARTICLE FILTERS FOR TELEOPERATIONS OVER THE INTERNET Jae-young Lee, Shahram Payandeh, and Ljljana Trajovć School of Engneerng Scence Smon Fraser Unversty 8888 Unversty

More information

Solving two-person zero-sum game by Matlab

Solving two-person zero-sum game by Matlab Appled Mechancs and Materals Onlne: 2011-02-02 ISSN: 1662-7482, Vols. 50-51, pp 262-265 do:10.4028/www.scentfc.net/amm.50-51.262 2011 Trans Tech Publcatons, Swtzerland Solvng two-person zero-sum game by

More information

A Simple and Efficient Goal Programming Model for Computing of Fuzzy Linear Regression Parameters with Considering Outliers

A Simple and Efficient Goal Programming Model for Computing of Fuzzy Linear Regression Parameters with Considering Outliers 62626262621 Journal of Uncertan Systems Vol.5, No.1, pp.62-71, 211 Onlne at: www.us.org.u A Smple and Effcent Goal Programmng Model for Computng of Fuzzy Lnear Regresson Parameters wth Consderng Outlers

More information

TN348: Openlab Module - Colocalization

TN348: Openlab Module - Colocalization TN348: Openlab Module - Colocalzaton Topc The Colocalzaton module provdes the faclty to vsualze and quantfy colocalzaton between pars of mages. The Colocalzaton wndow contans a prevew of the two mages

More information

The Research of Support Vector Machine in Agricultural Data Classification

The Research of Support Vector Machine in Agricultural Data Classification The Research of Support Vector Machne n Agrcultural Data Classfcaton Le Sh, Qguo Duan, Xnmng Ma, Me Weng College of Informaton and Management Scence, HeNan Agrcultural Unversty, Zhengzhou 45000 Chna Zhengzhou

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

Unsupervised Learning and Clustering

Unsupervised Learning and Clustering Unsupervsed Learnng and Clusterng Why consder unlabeled samples?. Collectng and labelng large set of samples s costly Gettng recorded speech s free, labelng s tme consumng 2. Classfer could be desgned

More information

2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements

2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements Module 3: Element Propertes Lecture : Lagrange and Serendpty Elements 5 In last lecture note, the nterpolaton functons are derved on the bass of assumed polynomal from Pascal s trangle for the fled varable.

More information

Reducing Frame Rate for Object Tracking

Reducing Frame Rate for Object Tracking Reducng Frame Rate for Object Trackng Pavel Korshunov 1 and We Tsang Oo 2 1 Natonal Unversty of Sngapore, Sngapore 11977, pavelkor@comp.nus.edu.sg 2 Natonal Unversty of Sngapore, Sngapore 11977, oowt@comp.nus.edu.sg

More information

Design of Structure Optimization with APDL

Design of Structure Optimization with APDL Desgn of Structure Optmzaton wth APDL Yanyun School of Cvl Engneerng and Archtecture, East Chna Jaotong Unversty Nanchang 330013 Chna Abstract In ths paper, the desgn process of structure optmzaton wth

More information

ALGORITHM FOR H.264/AVC

ALGORITHM FOR H.264/AVC ISSN 1392 124X INFORMATION TECHNOLOGY AND CONTROL, 2010 Vol. 38, No. ISSN 1392 124X INFORMATION TECHNOLOGY AND CONTROL, 2011, Vol.40, No.3 1, 5 7 A NOVEL Novel Varance-Based VARIANCE-BASED Intra-FrameINTRA-FRAME

More information

Convolutional interleaver for unequal error protection of turbo codes

Convolutional interleaver for unequal error protection of turbo codes Convolutonal nterleaver for unequal error protecton of turbo codes Sna Vaf, Tadeusz Wysock, Ian Burnett Unversty of Wollongong, SW 2522, Australa E-mal:{sv39,wysock,an_burnett}@uow.edu.au Abstract: Ths

More information

SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB

SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB SURFACE PROFILE EVALUATION BY FRACTAL DIMENSION AND STATISTIC TOOLS USING MATLAB V. Hotař, A. Hotař Techncal Unversty of Lberec, Department of Glass Producng Machnes and Robotcs, Department of Materal

More information

Sorting Review. Sorting. Comparison Sorting. CSE 680 Prof. Roger Crawfis. Assumptions

Sorting Review. Sorting. Comparison Sorting. CSE 680 Prof. Roger Crawfis. Assumptions Sortng Revew Introducton to Algorthms Qucksort CSE 680 Prof. Roger Crawfs Inserton Sort T(n) = Θ(n 2 ) In-place Merge Sort T(n) = Θ(n lg(n)) Not n-place Selecton Sort (from homework) T(n) = Θ(n 2 ) In-place

More information

How Accurately Can We Model Timing In A Placement Engine?

How Accurately Can We Model Timing In A Placement Engine? How Accurately Can We Model Tmng In A Placement Engne? Amt Chowdhary, Karth Raagopal, Satsh Venatesan, Tung Cao, Vladmr Tourn, Yegna Parasuram, Bll Halpn Intel Corporaton Serra Desgn Automaton Synplcty,

More information

Parameter estimation for incomplete bivariate longitudinal data in clinical trials

Parameter estimation for incomplete bivariate longitudinal data in clinical trials Parameter estmaton for ncomplete bvarate longtudnal data n clncal trals Naum M. Khutoryansky Novo Nordsk Pharmaceutcals, Inc., Prnceton, NJ ABSTRACT Bvarate models are useful when analyzng longtudnal data

More information

Reliability and Energy-aware Cache Reconfiguration for Embedded Systems

Reliability and Energy-aware Cache Reconfiguration for Embedded Systems Relablty and Energy-aware Cache Reconfguraton for Embedded Systems Yuanwen Huang and Prabhat Mshra Department of Computer and Informaton Scence and Engneerng Unversty of Florda, Ganesvlle FL 326-62, USA

More information