Cooperative and Active Sensing in Mobile Sensor Networks for Scalar Field Mapping
|
|
- Reynold Golden
- 5 years ago
- Views:
Transcription
1 3 IEEE Intenatonal Confeence on Automaton Scence and Engneeng (CASE) TuBT. Coopeatve and Actve Sensng n Moble Senso Netwos fo Scala Feld Mappng Hung Manh La, Wehua Sheng and Jmng Chen Abstact Scala feld mappng has many applcatons ncludng envonmental montong, seach and escue, etc. In such applcatons thee s a need to acheve a cetan level of confdence egadng the estmates at each locaton. In ths pape, a coopeatve and actve sensng famewo s developed to enable scala feld mappng usng multple moble senso nodes. The coopeatve and actve contolle s desgned va the eal-tme feedbac of the sensng pefomance to stee the moble sensos to new locatons n ode to mpove the sensng qualty. Dung the movement of the moble sensos, the measuements fom each senso node and ts neghbos ae taen and fused wth the coespondng confdences usng dstbuted consensus fltes. As a esult an onlne map of the scala feld s bult wth a cetan level of confdence of the estmates. We conducted compute smulatons to valdate and evaluate ou poposed algothms Keywod: Actve sensng, Senso fuson, Senso netwos. I. INTRODUCTION Actve sensng n MSNs has ecently attacted much eseach nteest, especally n contol engneeng []. Some actve sensng algothms fo souce seeng and adaton mappng have been developed [] [5]. The poblem of souce seeng s fst addessed n [], and then t s thooughly studed n [3], [4] fo the case when dect gadent nfomaton of the measued quantty s unavalable. Also, the poblem of chemcal plume souce localzaton s addessed by constuctng a souce lelhood map based on Bayesan nfeence methods [3]. Moeove, localzaton of a adaton souce usng only adaton ntensty measuements has been done usng a hybd contol stategy [4]. Addtonally, actve sensng fo adaton mappng s developed n [5]. The contol algothm taes nto account sensng pefomance and dynamcs of the obseved pocess theefoe t can stee moble sensos to locatons whee they maxmze the nfomaton content of the measuement data. In ou pevous wo [6], [7], we have developed a coopeatve sensng algothm fo an MSN to buld the map of the scala feld. Based on ou algothm, all moble sensos can fom a quas lattce fomaton and collaboate togethe to estmate the value at each cell of the feld assocated wth Ths poject s suppoted by the Depatment of Defense unde DoD ARO DURIP gant 5568-CS-RIP, USA; and the Vetnamese Govenment unde the MOET (Mnsty of Educaton and Tanng) 3 pogam. Hung M. La s wth the Cente fo Advanced Infastuctue and Tanspotaton (CAIT), Rutges Unvesty, Pscataway, NJ 8854, USA, Emal: hung.la@utges.edu. Wehua Sheng s wth the School of Electcal and Compute Engneeng, Olahoma State Unvesty, Stllwate, OK 7478, USA, Emal: wehua.sheng@ostate.edu. Jmng Chen s wth the State Key Lab. of Industal Contol Technology, Depatment of Contol, Zhejang Unvesty, Hangzhou, P.R.Chna, 37,Emal: jmchen@eee.og. Confdence (Weght) x Numbe Cell Index of Cells Fg.. Low confdence cells The confdence at each cell of the scala feld. ts own confdence of estmaton. Howeve the coopeatve contolle does not nclude onlne feedbac of the estmate confdence. Hence, the sensng pefomance o the confdence does not satsfy the desed one. Ths could affect some scala feld mappng applcatons such as tempeatue feld mappng, seach and escue, whee a need exsts to acheve a cetan level of confdence egadng the estmates at each locaton. As we can see fom Fgue, usng the nomal coopeatve sensng algothm developed n ou pevous papes [6], [7], we fnd that some cells have vey low confdence. Ths means that we may mss mpotant nfomaton at these locatons (cells). Fo example, n seach and escue opeaton the MSN may mss the objects at the locatons whee the confdence of the estmate s not suffcent. Ths motvates us to develop a coopeatve and actve sensng algothm fo MSNs so that each senso only nteacts wth ts neghbos and uses the local obsevaton to automatcally adjust the confguaton of the MSNs such as elatve locaton among sensos, oentaton and focal length of the sensos (camea), etc. to adapt to the envonments and mpove the sensng pefomance. To acheve ths goal the contolle should be desgned va the eal-tme feedbac of the sensng pefomance. By ths way the contolle can stee the moble senso to move to the ght locatons of the feld n ode to mpove the sensng qualty. Fo smplcty, n ths wo we only focus on adjustng the elatve locaton among sensos. Specfcally, ou poblem focuses on how to contol the movement of the moble sensos to ensue quas /3/$3. 3 IEEE 83
2 unfom confdence on the estmates. Hee by quas unfom confdence we mean that the confdence s bounded by a lowe and uppe bound. hee c v s the small postve constant between and. The eason of ntoducng c v s to avod the vaance V (t) beng zeo when the dstance q (t) qc equals to zeo. II. SCALAR FIELD AND MEASUREMENT MODELING In ths secton we pesent the model of the scala feld and the measuement model of moble sensos. A. Model of the Scala Feld We model the scala feld of nteest as F = ΘΦ T, () hee Θ = [θ,θ,...,θ K ], and Φ = [φ,φ,...,φ K ]. φ j, j =,..., K, s a functon epesentng a densty dstbuton, and θ j s the weght of the densty dstbuton of the functonφ j. We can model the functon φ j as a b-vaate Gaussan dstbuton φ j = det(cj )(π) e (x µj x )C j (y µ j y )T,j [,,...,K]. hee [µ j x µj y ] s the mean of the dstbuton of functon φ j, and C j s covaance matx (postve defnte) and t s epesented by: [ (σ j C j = x ) c o ] j σj xy c j σj xy (σy) j, whee c j s a coelaton facto. B. Measuement Model We patton the scala feld F nto a gd of C cells. Each senso maes an obsevaton (measuement) of the scala feld at cell ( {,,...,C}) at tme step t based on the followng equaton m (t) = O (t)[f (t)+n (t)], () hee n (t) s the Gaussan nose wth zeo mean and vaance V (t) at tme step t. We assume that n s uncoelated nose whch satsfes { Cov(n (s),n V (t)) =, f s = t, othewse, hee Cov s the covaance. O (t) s the obsevablty of senso node at cell at tme step t, and t s defned as O (t) = {, f q (t) q c s, othewse, hee q R s the poston of senso node ; qc R s the locaton of cell at ts cente; and s s the sensng ange of senso node. Ths defnton tells us that f cell s nsde the sensng ange, s, of senso node then cell can be measued o obseved. Othewse the obsevablty s zeo. Each moble senso node maes an measuement at cell coespondng to ts poston. We assume that the vaance V (t) s elated to the dstance between the senso node and the locaton of the measuement accodng to: { q(t) q (t) = c +c v (, f q s (t) q ) c s, othewse, V (3) (4) III. DISTRIBUTED SENSOR FUSION ALGORITHM A. Oveall Appoach In ths secton we pesent a dstbuted senso fuson algothm to allow each senso node to fnd out an estmate of the value at each cell of the scala feld based on ts own measuement and ts neghbo s measuements. Ou algothm has two phases. Fst, at tme step t, each senso node fnds an estmate of the value of the scala feld F. Second, each senso node fnds a fnal estmate of the value of the scala feldf at each cell dung ts movement. To acheve t, we use two consensus fltes. The consensus flte s to fnd out an estmate of the value of the feld F at each cell at tme step t. Snce each moble senso node maes ts own measuement at each cell wth ts own weght (confdence), the consensus flte s used to fnd out an ageement among these confdences. At each tme step t each moble senso node needs to fnd an estmate of the value of each cell based on consensus flte, and fnd an oveall confdence of ths estmate based on consensus flte. Ths pocess can be called the spatal estmaton phase. Then, dung the movement of each senso node, t wll have multple spatal estmates of each cell assocated wth the own confdences. Hence, these spatal estmates ae fused teatvely though the weghted aveage potocol, and ths pocess can be called the tempoal estmaton phase. B. Spatal Estmaton Phase In the spatal estmaton phase, the measuements of each senso node and ts neghbos at cell at tme steptae nputs of the consensus flte. Then, the output of ths consensus s the estmate of the value of the scala feld F at cell at tme step t. Also n ths phase, the confdences (weghts) of the measuements of each senso node and ts neghbos at cell at tme step t ae nputs of the consensus flte. Then, the output of ths consensus s the estmate of the confdence of the measuement of the scala feld at cell at tme step t. ) Consensus Flte : Dstbuted consensus [7], [8] s an mpotant computatonal tool to acheve coopeatve sensng. We consde dstbuted lnea teatons of the followng fom x (l+) = w(l)x (l)+ wj(l)x j(l), (5) j N (t) hee l s teaton ndex. The ntal condton fo the state s gven as x (l = ) = m (t). The weght, w (l), s the self weght o vetex weght of each senso to cell, and wj (l) s the edge weght between senso and senso j. Ou poblem hee s to estmate the value of the feld F at each cell at each tme step t. Snce each senso node maes the obsevaton at cell at tme step t based on ts own confdence (weght), the consensus should convege to the weghted aveage of all obsevatons (measuements) at 83
3 cell fom all senso nodes n the netwo. Ths weghted aveage s the estmate of the value at cell at tme step t, and t s computed as: n E = (t) = w (t)m (t) n = w. (6) (t) In ode to mae the consensus (5) convege to E n (6) we need to ensue that the sum of all weghts ncludng the vetex and edge weghts at each node satsfes the followng condton [6], [7]: w(l)+ wj(l) =. (7) j N (t) Fom Equaton (7) by assgnng the same value to all edge weghts we obtan: hee, w (l) s defned as wj (l) = w (l). (8) N (t) w (l) = cw (9) (t), V whee c w s a constant. If senso node does not obseve cell (O (t) = ) then the vetex weght w (l) s set to zeo. Theefoe we have the followng weght desgn c w wj V (l) = (t), f = j, w (l) N, f j,j N (t) (t), (), othewse. In ode to satsfy Equaton (7) we need the followng condton fo c w : < cw V <. () (t) Snce mn(v have: cv (t)) = ( when q s (t) q ) c =, we < cw c v < < c w < c v ( ( s () s) ). ) Consensus Flte : Snce each senso node has ts own confdence of the measuement of the value of the scala feld at each cell at each tme step t we need to fnd an ageement among the confdences of senso nodes. The consensus algothm s ntoduced to fnd the oveall confdence fom each tme step t. Ths oveall confdence s the estmated weght, W (t), of the weghted aveage potocol as shown n Equaton (7). Let y (l = ) be the confdence of the measuement of the value of the scala feld at cell at each tme step t fo senso node, o y (l = ) = w (t). Let y j (l = ) be the confdence of the measuement of the value of the scala feld at cell at each tme step t fo senso node j wth j N (t), o yj (l = ) = w jj (t). Then, we have the followng consensus flte y (l+) = w (l)y (l)+ j N (t) wj (l)y j (l), (3) In ths consensus flte, we use the Metopols weght [8] as wj(l) +max( N, f j,j N (t), N j(t) ) (t), = j N (t) w j (l), f = j,, othewse. (4) C. Tempoal Estmaton Phase Fom the consensus fltes and, to allow each senso node to on-lne estmate the value of the scala feld at each cell based on ts own measuement and ts neghbo s measuements, the tempoal estmate phase s used. Dung the movement of senso nodes, each senso obtan seveal spatal estmates (fom the spatal estmaton phase) of the value at cell assocated wth ts own confdence, hence the fnal estmate s teatvely updated based on these spatal estmates va the weghted aveage potocol. Fo detals, fst let l c be the teaton that both consensus flte and convege, then we have the estmates of cell : E (t) = x (l c); and W (t) = y (l c). We can fnd the fnal estmate of the value of the scala feld at cell based on followng equatons: - Update weght (confdence): W (t) = W (t )+W (t )+...+W () (5) - Update the fnal estmate (weghted aveage potocol): E (t = ) = E (t = ) = x (l c ) (6) E (t) = W (t )E (t )+W (t)e (t) W (7) (t )+W (t) IV. POTENTIAL CONTROLLER DESIGN FOR ACTIVE SENSING In ths secton we am to develop a potental contolle fo coopeatve and actve sensng, and the man dea of ou appoach s shown n Fgue. Ou pupose s usng the feedbac of the confdence of the estmate to adjust the movement of the sensos to adapt to the envonments so that they can mpove the sensng pefomance n a dstbuted fashon. Specfcally, the potental contolle s desgned to stee the moble sensos to the expected locatons n ode to acheve the quas unfomty of the confdence. Fst, we descbe the flocng contol algothm [9], [] whch s used to contol moble sensos to move togethe wthout collson. A. Flocng Contol We consde n moble senso nodes movng n two dmensonal Eucldean space. The dynamc equatons of each senso node ae descbed as: { q = p (8) ṗ = u, =,,...,n. hee (q, p ) R ae the poston and velocty of senso node, espectvely, and u s the contol nput of senso node. 833
4 Desed Confdence of Estmates + - Potental Contolle (u ) Potental Contolle Enhanced wth Attactve and Repulsve Foces Cuent Confdence of Estmates Moble Senso Scala Feld Fg.. Dagam of coopeatve and actve sensng based on the flocng contolle enhanced wth attactve and epulsve foces va confdence feedbac. The geomety of the MSN s modeled by an -lattce [9] that meets the followng condton: q j q = d,j N (t), (9) hee d s a postve constant ndcatng the dstance between senso node and ts neghbo j. Howeve, at sngula confguaton (q = q j ) the collectve potental used to constuct the geomety of flocs s not dffeentable. Theefoe, the set of algebac constants n (9) s ewtten n tem of σ - nom [9] as follows: q j q σ = d,j N (t), hee the constant d = d σ wth d = / c, whee c s the scalng facto. The σ - nom,. σ, of a vecto s a map R m = R + defned as z σ = ǫ [ +ǫ z ] wth ǫ >. Unle the Eucldean nom z, whch s not dffeentable at z =, the σ - nom z σ, s dffeentable evey whee. The flocng contol algothm whch conssts of the fomaton contol tem and the leade tacng contol tem s pesented as u = f +f t. The fomaton contolle [9] s used to contol the netwo to fom a quas lattce fomaton, and t s desgned based on a pawse attactve/epulsve foce. f = c φ ( q j q σ )n j +c a j (q)(p j p ), j N j N () whee c and c ae postve constants. Moe detals of how to compute f please see [9]. The leade tacng contolle s used to contol each moble senso to tac the vtual leade. The tajectoy of the vtual leade s planned so that the MSN can cove the ente scala feld. Ths contolle s pesented as f t = c t (q q t ) c t (p p t ) () heec t andct ae postve constant, andq t andp t ae poston and velocty of the vtual leade, espectvely. B. Desgn of Attactve Foce In ths subsecton, we ntoduce the attactve foce tem to ncease the confdence level. The attactve foce wll stee the moble sensos to the cells whch have low confdence. In ode to do ths, fst let qc be the locaton of the cell that has confdence lowe than the lowe bound, o O L (t), hee O L (t) s the subset of cells coveed by moble senso at tme t, whch have confdence lowe than the lowe bound. O L(t) Oc (t), hee Oc (t) s the set of cells coveed by moble senso at tme t, and t s defned as O(t) c = { ϑ O : qc q,ϑ s O = {,,...,} }. () At each tme t, the moble senso may have seveal cells whch have confdence lowe than the desed one. In ode to stee the moble senso to go to these low confdence cells, the vtual attactve foce ae geneated at these cells. If the cell has lowe confdence the bgge attactve foce s geneated. To expess the detals of the attactve foce desgn, fst let W L d be a lowe bound of the desed confdence of the estmates of all cells n the scala feld, and W L d s a vecto of C dmenson. Let L W (t) = WL d W(t) be the dffeence between the cuent confdence and the lowe bound (see Fgue 3), L W (t) = [ W (t), W (t),..., C W (t)]. Based on ths feedbac, L W (t), we can desgn a attactve foce as shown n Equaton (3). f att = O L (t) C att φ att ( qc q σ )n att, (3) hee, C att = c W (t) a +( W (t)), W (t) L W (t), and c a s a postve constant. C att s used to contol the ampltude of the attactve foce. Namely, f cell has low confdence o W (t) s lage, the the ampltude of the attactve foce s bg n ode to attact the moble senso to go to close ths cell. The attactve foce functon φ att ( qc q σ ) s desgned as: φ att ( q c q σ ) = ρ h ( q c q σ s O L (t). qc ) q σ + q c q σ hee, s = s σ ( s s sensng ange as defned befoe). Smla to [9], the bump functon ρ h ( q c q σ ) wth h s (,) s defned as,f q c q σ [,h) ρ h ( q c q s qc q σ σ s ) = [ + cos(π( s h h ))] (4) f q c q σ [h,] s, othewse. The vecto along the lne connectng qc ( OL (t)) and q s defned as: n att = (q c q )/ +ǫ qc q, O L (t). (5) hee, ǫ s small postve constant. C. Desgn of Repulsve Foce Based on the attactve foce desgn n the pevous subsecton, the confdence level can be nceased, howeve some cells may have too hgh confdence. Ths s unnecessay snce ths needs moe measuements, and causes moe enegy consumpton. Theefoe, t s desable f we can mantan 834
5 Confdence (Weght) Confdence of Estmates Uppe Bound Lowe Bound Fnally, the potental contolle fo the coopeatve and actve sensng s pesented as follows: u = f ep +f att +f +f t. (8) Cell Index Fg. 3. Illustaton of confdence feedbac fo quas unfomty of the confdence. The uppe bound and lowe bound ae used to ceate a quas unfom of the confdence. both lowe and uppe bound of the confdence pefomance, o a quas unfom confdence (see Fgue 3). Hence, we ntoduce a epulsve foce tem to the Potental Contolle n ode to stee the moble sensos to move away fom the cells whch have too hgh confdence. Let qc be the locaton of the cell that has confdence hghe than the uppe bound (see Fgue 3). Fo these cells we wll ceate the vtual epulsve foce to stee the moble sensos to move away. To expess the detals of the epulsve foce desgn, fst let W H d be a uppe bound of the desed confdence of the estmates of all cells n the scala feld, andw H d s a vecto of C dmenson. Let H W (t) = WH d W(t) be the dffeence between the cuent confdence and the uppe bound (see Fgue 3), H W (t) = [ W (t), W (t),..., C W (t)]. Based on ths feedbac, H W (t), we can desgn a epulsve foce as shown n Equaton 6. = f ep O H (t) C ep φ ep ( qc q σ )n ep, (6) hee, C ep = c W (t) +( W (t)), W (t) H W (t), hee c s a postve constance. O H (t) s the subset of cells coveed by moble senso at tme t, whch have confdence hghe than the uppe bound. Obvously,O H(t) Oc (t). Cep s used to contol the ampltude of the epulsve foce. Namely, f cell has hgh confdence, o W (t) s lage, the the ampltude of the epulsve foce s bg n ode to push the moble senso to move away fom ths cell futhe. The epulsve foce functon φ ep ( qc q σ ) s desgned as: φ ep ( qc q σ ) = ρ h ( q c q σ ) s qc q σ s ( ) +( q c q σ s ), O H (t). The bump functon ρ h ( q c q σ ) s defned as (4), but t s s now appled fo the hgh confdence cells o O H (t). The vecto along the lne connectng qc ( OH (t)) and q s defned as: n ep = (q c q )/ +ǫ qc q, O H (t). (7) V. SIMULATION RESULTS In ths secton, we test ou coopeatve and actve sensng algothm and compae t wth the nomal coopeatve sensng algothm [6], [7] n tems of the sensng pefomance. We model the envonment (scala feld F ) as multple vaate Gaussan dstbutons. The scala vecto Θ can be abtaly selected, fo example Θ = [ ], coespondng to fou multple vaate Gaussan dstbutons (K = 4), and each one s epesented as: φ = det(c )(π) e (x )C (y )T. [ ] hee we can select: C =, wth the coelaton facto c =.333. Fo the functons φ,φ 3,φ 4 : the means (µ x,µ y ) ae (, ), (4.3, [ 3.5), (3, -3), espectvely; ] the matx C = C 3 = C 4 = ; the coelaton facto c = c 3 = c = c. We set the lowe bound of the confdence level s 5, and the hghe bound of the confdence level s.9 5. The feld F has a sze of 9, and t s pattoned nto cells. The snapshots of multple senso nodes fomng a floc and buldng the map of the unnown scala feld ae shown n Fgue 4. The fnal confdence of the estmate n one dmenson at each cell of the feld F s shown n Fgue 5. In ths fgue we compaed thee methods togethe. Namely, Fgue 5 (a) shows the confdence of nomal coopeatve sensng (Potental Contolle wthout attactve and epulsve foces). Fgue 5 (b) shows the confdence of actve sensng wth the Potental Contolle wth attactve foce only. Fgue 5 (c) shows the confdence of actve sensng wth Potental Contolle wth both attactve and epulsve foces. Fom these esults, we can see that by usng both attactve and epulsve foce contolles we have bette unfomty of the confdence pefomance. Ths ndcates that all the cells of the scala feld ae obseved wth a cetan level of confdence. To see the advantages of the actve sensng we compae t wth the nomal sensng n tem of mappng eo as shown n Fgue 6. We can see that the eo between the ognal map and the bult map ove cells s small when applyng the actve sensng (see Fgue 6 (b)), but t s bgge when applyng the nomal sensng (see Fgue 6 (a)). VI. CONCLUSION Ths pape pesented coopeatve and actve sensng algothms fo moble senso netwos to buld the map of an unnown scala feld. The poposed dstbuted senso fuson algothm conssts of two dffeent dstbuted consensus 835
6 Fg. 4. Snapshots of buldng the map of the scala feld F usng the dstbuted fuson algothm and the coopeatve and actve sensng algothm (8). 3 x 5 3 x 5 3 x Confdence (Weght).5 Confdence (Weght).5 Confdence (Weght) Numbe of Cells Numbe of Cells (a) Cell Index (b) Cell Index (c) Numbe of Cells Cell Index Fg. 5. Confdence ove the cells n one dmenson: (a) fo nomal coopeatve sensng [6], [7]; (b) fo actve sensng wth Potental Contolle usng only attactve foce; (c) fo actve sensng wth Potental Contolle usng both attactve and epulsve foces (8) x Numbe of Cells Cell Index (a) x Numbe of Cells Cell Index Fg. 6. Eo between the ognal map and the bult map n one dmenson ove cells: (a) fo the nomal sensng [6], [7]; (b) fo the actve sensng. fltes whch can fnd an ageement on the estmates and an ageement on the confdence among senso nodes. Each senso node coopeates wth neghbong sensos to estmate the value of the feld at each cell. The fnal estmates of the values of the scala feld ae updated on-lne based on the weghted aveage potocol. Moe mpotantly, the moble sensos can automatcally adjust the movement to acheve quas unfom confdence though a potental feld based feedbac contol algothm. Smulaton esults ae collected to demonstate the poposed algothms. REFERENCES [] T. H. Chung, V. Gupta, J. W. Budc, and R. M. Muay. On a decentalzed actve sensng stategy usng moble senso platfoms (b) n a netwo. the 43th IEEE Conf. on Decson and Contol, pages 94 99, 4. [] C. Zhang, D. Anold, N. Ghods, A. Sanosan, and M. Kstc. Souce seeng wth nonholonomc uncycle wthout poston measument pat : Tunng of fowad velocty. IEEE Conf. on Decson and Contol, pages , 6. [3] S. Pang and J. A. Faell. Chemcal plume souce localzaton. IEEE Tans. on Systems, Man, and Cybenetcs Pat B, 36(5):68 8, 6. [4] C. G. Mayhew, R. G. Sanfelce, and A. R. Teel. Robust souce-seeng hybd contolles fo autonomous vehcles. Amecan Contol Conf., pages 85 9, 7. [5] H. G. Tanne R. A. Cotez and R. Luma. Dstbuted obotc adaton mappng. Expemental Robotcs The Eleventh Int.l Symposum, volume 54 of Spnge tacts n advanced obotcs, Spnge, pages 47 56, 9. [6] H. M. La and W. Sheng. Coopeatve sensng n moble senso netwos based on dstbuted consensus. the Sgnal and Data Pocessng of Small Tagets Conf., Poc. of SPIE,. [7] H. M. La and W. Sheng. Dstbuted senso fuson fo scala feld mappng usng moble senso netwos. IEEE Tans. on Cybenetcs, 43(): , Ap. 3. [8] L. Xao, S. Boy, and S. Lall. A scheme fo obust dstbuted senso fuson based on aveage consensus. Intenatonal Confeence on Infomaton Pocessng n Senso Netwos, pages 63 7, 5. [9] R. Olfat-Sabe. Flocng fo mult-agent dynamc systems: Algothms and theoy. IEEE Tansactons on Automatc Contol, 5(3):4 4, 6. [] H. M. La and W. Sheng. Flocng contol of a moble senso netwo to tac and obseve a movng taget. Poc. of the 9 IEEE Int. Conf. on Robotcs and Automaton (ICRA 9), Kobe, Japan, pages ,
On Maneuvering Target Tracking with Online Observed Colored Glint Noise Parameter Estimation
Wold Academy of Scence, Engneeng and Technology 6 7 On Maneuveng Taget Tacng wth Onlne Obseved Coloed Glnt Nose Paamete Estmaton M. A. Masnad-Sha, and S. A. Banan Abstact In ths pape a compehensve algothm
More informationMultistage Median Ranked Set Sampling for Estimating the Population Median
Jounal of Mathematcs and Statstcs 3 (: 58-64 007 ISSN 549-3644 007 Scence Publcatons Multstage Medan Ranked Set Samplng fo Estmatng the Populaton Medan Abdul Azz Jeman Ame Al-Oma and Kamaulzaman Ibahm
More informationPotential Fields in Cooperative Motion Control and Formations
Pepaed by F.L. Lews and E. Stngu Updated: Satuday, Febuay 0, 03 Potental Felds n Coopeatve Moton Contol and Fomatons Add dscusson. Refe to efs.. Potental Felds Equaton Chapte Secton The potental s a scala
More informationDistinct 8-QAM+ Perfect Arrays Fanxin Zeng 1, a, Zhenyu Zhang 2,1, b, Linjie Qian 1, c
nd Intenatonal Confeence on Electcal Compute Engneeng and Electoncs (ICECEE 15) Dstnct 8-QAM+ Pefect Aays Fanxn Zeng 1 a Zhenyu Zhang 1 b Lnje Qan 1 c 1 Chongqng Key Laboatoy of Emegency Communcaton Chongqng
More informationA NOVEL DWELLING TIME DESIGN METHOD FOR LOW PROBABILITY OF INTERCEPT IN A COMPLEX RADAR NETWORK
Z. Zhang et al., Int. J. of Desgn & Natue and Ecodynamcs. Vol. 0, No. 4 (205) 30 39 A NOVEL DWELLING TIME DESIGN METHOD FOR LOW PROBABILITY OF INTERCEPT IN A COMPLEX RADAR NETWORK Z. ZHANG,2,3, J. ZHU
More informationSet of square-integrable function 2 L : function space F
Set of squae-ntegable functon L : functon space F Motvaton: In ou pevous dscussons we have seen that fo fee patcles wave equatons (Helmholt o Schödnge) can be expessed n tems of egenvalue equatons. H E,
More information3. A Review of Some Existing AW (BT, CT) Algorithms
3. A Revew of Some Exstng AW (BT, CT) Algothms In ths secton, some typcal ant-wndp algothms wll be descbed. As the soltons fo bmpless and condtoned tansfe ae smla to those fo ant-wndp, the pesented algothms
More information24-2: Electric Potential Energy. 24-1: What is physics
D. Iyad SAADEDDIN Chapte 4: Electc Potental Electc potental Enegy and Electc potental Calculatng the E-potental fom E-feld fo dffeent chage dstbutons Calculatng the E-feld fom E-potental Potental of a
More information8 Baire Category Theorem and Uniform Boundedness
8 Bae Categoy Theoem and Unfom Boundedness Pncple 8.1 Bae s Categoy Theoem Valdty of many esults n analyss depends on the completeness popety. Ths popety addesses the nadequacy of the system of atonal
More informationScalars and Vectors Scalar
Scalas and ectos Scala A phscal quantt that s completel chaacteed b a eal numbe (o b ts numecal value) s called a scala. In othe wods a scala possesses onl a magntude. Mass denst volume tempeatue tme eneg
More informationCS649 Sensor Networks IP Track Lecture 3: Target/Source Localization in Sensor Networks
C649 enso etwoks IP Tack Lectue 3: Taget/ouce Localaton n enso etwoks I-Jeng Wang http://hng.cs.jhu.edu/wsn06/ png 006 C 649 Taget/ouce Localaton n Weless enso etwoks Basc Poblem tatement: Collaboatve
More information4 Recursive Linear Predictor
4 Recusve Lnea Pedcto The man objectve of ths chapte s to desgn a lnea pedcto wthout havng a po knowledge about the coelaton popetes of the nput sgnal. In the conventonal lnea pedcto the known coelaton
More informationTian Zheng Department of Statistics Columbia University
Haplotype Tansmsson Assocaton (HTA) An "Impotance" Measue fo Selectng Genetc Makes Tan Zheng Depatment of Statstcs Columba Unvesty Ths s a jont wok wth Pofesso Shaw-Hwa Lo n the Depatment of Statstcs at
More informationVibration Input Identification using Dynamic Strain Measurement
Vbaton Input Identfcaton usng Dynamc Stan Measuement Takum ITOFUJI 1 ;TakuyaYOSHIMURA ; 1, Tokyo Metopoltan Unvesty, Japan ABSTRACT Tansfe Path Analyss (TPA) has been conducted n ode to mpove the nose
More informationPhysics 11b Lecture #2. Electric Field Electric Flux Gauss s Law
Physcs 11b Lectue # Electc Feld Electc Flux Gauss s Law What We Dd Last Tme Electc chage = How object esponds to electc foce Comes n postve and negatve flavos Conseved Electc foce Coulomb s Law F Same
More informationAPPLICATIONS OF SEMIGENERALIZED -CLOSED SETS
Intenatonal Jounal of Mathematcal Engneeng Scence ISSN : 22776982 Volume Issue 4 (Apl 202) http://www.mes.com/ https://stes.google.com/ste/mesounal/ APPLICATIONS OF SEMIGENERALIZED CLOSED SETS G.SHANMUGAM,
More informationLife-long Informative Paths for Sensing Unknown Environments
Lfe-long Infomatve Paths fo Sensng Unknown Envonments Danel E. Solteo Mac Schwage Danela Rus Abstact In ths pape, we have a team of obots n a dynamc unknown envonment and we would lke them to have accuate
More informationRigid Bodies: Equivalent Systems of Forces
Engneeng Statcs, ENGR 2301 Chapte 3 Rgd Bodes: Equvalent Sstems of oces Intoducton Teatment of a bod as a sngle patcle s not alwas possble. In geneal, the se of the bod and the specfc ponts of applcaton
More informationCorrespondence Analysis & Related Methods
Coespondence Analyss & Related Methods Ineta contbutons n weghted PCA PCA s a method of data vsualzaton whch epesents the tue postons of ponts n a map whch comes closest to all the ponts, closest n sense
More informationMachine Learning 4771
Machne Leanng 4771 Instucto: Tony Jebaa Topc 6 Revew: Suppot Vecto Machnes Pmal & Dual Soluton Non-sepaable SVMs Kenels SVM Demo Revew: SVM Suppot vecto machnes ae (n the smplest case) lnea classfes that
More informationChapter 23: Electric Potential
Chapte 23: Electc Potental Electc Potental Enegy It tuns out (won t show ths) that the tostatc foce, qq 1 2 F ˆ = k, s consevatve. 2 Recall, fo any consevatve foce, t s always possble to wte the wok done
More informationFormation Control with Leadership Alternation for Obstacle Avoidance
Pepnts of the 8th IFAC Wold Congess Mlano (Italy) August 8 - Septembe, Fomaton Contol wth Leadeshp Altenaton fo Obstacle Avodance Jose M. V. Vlca Maco H. Tea Vald Gass J. Depatment of Electcal Engneeng,
More informationChapter Fifiteen. Surfaces Revisited
Chapte Ffteen ufaces Revsted 15.1 Vecto Descpton of ufaces We look now at the vey specal case of functons : D R 3, whee D R s a nce subset of the plane. We suppose s a nce functon. As the pont ( s, t)
More informationN = N t ; t 0. N is the number of claims paid by the
Iulan MICEA, Ph Mhaela COVIG, Ph Canddate epatment of Mathematcs The Buchaest Academy of Economc Studes an CECHIN-CISTA Uncedt Tac Bank, Lugoj SOME APPOXIMATIONS USE IN THE ISK POCESS OF INSUANCE COMPANY
More informationA Brief Guide to Recognizing and Coping With Failures of the Classical Regression Assumptions
A Bef Gude to Recognzng and Copng Wth Falues of the Classcal Regesson Assumptons Model: Y 1 k X 1 X fxed n epeated samples IID 0, I. Specfcaton Poblems A. Unnecessay explanatoy vaables 1. OLS s no longe
More informationAdvanced Robust PDC Fuzzy Control of Nonlinear Systems
Advanced obust PDC Fuzzy Contol of Nonlnea Systems M Polanský Abstact hs pape ntoduces a new method called APDC (Advanced obust Paallel Dstbuted Compensaton) fo automatc contol of nonlnea systems hs method
More informationA. Thicknesses and Densities
10 Lab0 The Eath s Shells A. Thcknesses and Denstes Any theoy of the nteo of the Eath must be consstent wth the fact that ts aggegate densty s 5.5 g/cm (ecall we calculated ths densty last tme). In othe
More informationObserver Design for Takagi-Sugeno Descriptor System with Lipschitz Constraints
Intenatonal Jounal of Instumentaton and Contol Systems (IJICS) Vol., No., Apl Obseve Desgn fo akag-sugeno Descpto System wth Lpschtz Constants Klan Ilhem,Jab Dalel, Bel Hadj Al Saloua and Abdelkm Mohamed
More informationCOMPLEMENTARY ENERGY METHOD FOR CURVED COMPOSITE BEAMS
ultscence - XXX. mcocd Intenatonal ultdscplnay Scentfc Confeence Unvesty of skolc Hungay - pl 06 ISBN 978-963-358-3- COPLEENTRY ENERGY ETHOD FOR CURVED COPOSITE BES Ákos József Lengyel István Ecsed ssstant
More informationEngineering Mechanics. Force resultants, Torques, Scalar Products, Equivalent Force systems
Engneeng echancs oce esultants, Toques, Scala oducts, Equvalent oce sstems Tata cgaw-hll Companes, 008 Resultant of Two oces foce: acton of one bod on anothe; chaacteed b ts pont of applcaton, magntude,
More informationPHYS 705: Classical Mechanics. Derivation of Lagrange Equations from D Alembert s Principle
1 PHYS 705: Classcal Mechancs Devaton of Lagange Equatons fom D Alembet s Pncple 2 D Alembet s Pncple Followng a smla agument fo the vtual dsplacement to be consstent wth constants,.e, (no vtual wok fo
More informationContact, information, consultations
ontact, nfomaton, consultatons hemsty A Bldg; oom 07 phone: 058-347-769 cellula: 664 66 97 E-mal: wojtek_c@pg.gda.pl Offce hous: Fday, 9-0 a.m. A quote of the week (o camel of the week): hee s no expedence
More informationExact Simplification of Support Vector Solutions
Jounal of Machne Leanng Reseach 2 (200) 293-297 Submtted 3/0; Publshed 2/0 Exact Smplfcaton of Suppot Vecto Solutons Tom Downs TD@ITEE.UQ.EDU.AU School of Infomaton Technology and Electcal Engneeng Unvesty
More informationClosed-loop adaptive optics using a CMOS image quality metric sensor
Closed-loop adaptve optcs usng a CMOS mage qualty metc senso Chueh Tng, Mchael Gles, Adtya Rayankula, and Pual Futh Klpsch School of Electcal and Compute Engneeng ew Mexco State Unvesty Las Cuces, ew Mexco
More informationEfficiency of the principal component Liu-type estimator in logistic
Effcency of the pncpal component Lu-type estmato n logstc egesson model Jbo Wu and Yasn Asa 2 School of Mathematcs and Fnance, Chongqng Unvesty of Ats and Scences, Chongqng, Chna 2 Depatment of Mathematcs-Compute
More informationDirichlet Mixture Priors: Inference and Adjustment
Dchlet Mxtue Pos: Infeence and Adustment Xugang Ye (Wokng wth Stephen Altschul and Y Kuo Yu) Natonal Cante fo Botechnology Infomaton Motvaton Real-wold obects Independent obsevatons Categocal data () (2)
More informationUNIT10 PLANE OF REGRESSION
UIT0 PLAE OF REGRESSIO Plane of Regesson Stuctue 0. Intoducton Ojectves 0. Yule s otaton 0. Plane of Regesson fo thee Vaales 0.4 Popetes of Resduals 0.5 Vaance of the Resduals 0.6 Summay 0.7 Solutons /
More informationExperimental study on parameter choices in norm-r support vector regression machines with noisy input
Soft Comput 006) 0: 9 3 DOI 0.007/s00500-005-0474-z ORIGINAL PAPER S. Wang J. Zhu F. L. Chung Hu Dewen Expemental study on paamete choces n nom- suppot vecto egesson machnes wth nosy nput Publshed onlne:
More informationGenerating Functions, Weighted and Non-Weighted Sums for Powers of Second-Order Recurrence Sequences
Geneatng Functons, Weghted and Non-Weghted Sums fo Powes of Second-Ode Recuence Sequences Pantelmon Stăncă Aubun Unvesty Montgomey, Depatment of Mathematcs Montgomey, AL 3614-403, USA e-mal: stanca@studel.aum.edu
More informationKhintchine-Type Inequalities and Their Applications in Optimization
Khntchne-Type Inequaltes and The Applcatons n Optmzaton Anthony Man-Cho So Depatment of Systems Engneeng & Engneeng Management The Chnese Unvesty of Hong Kong ISDS-Kolloquum Unvestaet Wen 29 June 2009
More informationCEEP-BIT WORKING PAPER SERIES. Efficiency evaluation of multistage supply chain with data envelopment analysis models
CEEP-BIT WORKING PPER SERIES Effcency evaluaton of multstage supply chan wth data envelopment analyss models Ke Wang Wokng Pape 48 http://ceep.bt.edu.cn/englsh/publcatons/wp/ndex.htm Cente fo Enegy and
More informationA Study about One-Dimensional Steady State. Heat Transfer in Cylindrical and. Spherical Coordinates
Appled Mathematcal Scences, Vol. 7, 03, no. 5, 67-633 HIKARI Ltd, www.m-hka.com http://dx.do.og/0.988/ams.03.38448 A Study about One-Dmensonal Steady State Heat ansfe n ylndcal and Sphecal oodnates Lesson
More informationP 365. r r r )...(1 365
SCIENCE WORLD JOURNAL VOL (NO4) 008 www.scecncewoldounal.og ISSN 597-64 SHORT COMMUNICATION ANALYSING THE APPROXIMATION MODEL TO BIRTHDAY PROBLEM *CHOJI, D.N. & DEME, A.C. Depatment of Mathematcs Unvesty
More informationThermodynamics of solids 4. Statistical thermodynamics and the 3 rd law. Kwangheon Park Kyung Hee University Department of Nuclear Engineering
Themodynamcs of solds 4. Statstcal themodynamcs and the 3 d law Kwangheon Pak Kyung Hee Unvesty Depatment of Nuclea Engneeng 4.1. Intoducton to statstcal themodynamcs Classcal themodynamcs Statstcal themodynamcs
More informationStellar Astrophysics. dt dr. GM r. The current model for treating convection in stellar interiors is called mixing length theory:
Stella Astophyscs Ovevew of last lectue: We connected the mean molecula weght to the mass factons X, Y and Z: 1 1 1 = X + Y + μ 1 4 n 1 (1 + 1) = X μ 1 1 A n Z (1 + ) + Y + 4 1+ z A Z We ntoduced the pessue
More informationAmplifier Constant Gain and Noise
Amplfe Constant Gan and ose by Manfed Thumm and Wene Wesbeck Foschungszentum Kalsuhe n de Helmholtz - Gemenschaft Unvestät Kalsuhe (TH) Reseach Unvesty founded 85 Ccles of Constant Gan (I) If s taken to
More informationThe Greatest Deviation Correlation Coefficient and its Geometrical Interpretation
By Rudy A. Gdeon The Unvesty of Montana The Geatest Devaton Coelaton Coeffcent and ts Geometcal Intepetaton The Geatest Devaton Coelaton Coeffcent (GDCC) was ntoduced by Gdeon and Hollste (987). The GDCC
More informationEnergy in Closed Systems
Enegy n Closed Systems Anamta Palt palt.anamta@gmal.com Abstact The wtng ndcates a beakdown of the classcal laws. We consde consevaton of enegy wth a many body system n elaton to the nvese squae law and
More informationRemember: When an object falls due to gravity its potential energy decreases.
Chapte 5: lectc Potental As mentoned seveal tmes dung the uate Newton s law o gavty and Coulomb s law ae dentcal n the mathematcal om. So, most thngs that ae tue o gavty ae also tue o electostatcs! Hee
More informationTest 1 phy What mass of a material with density ρ is required to make a hollow spherical shell having inner radius r i and outer radius r o?
Test 1 phy 0 1. a) What s the pupose of measuement? b) Wte all fou condtons, whch must be satsfed by a scala poduct. (Use dffeent symbols to dstngush opeatons on ectos fom opeatons on numbes.) c) What
More informationModeling and Adaptive Control of a Coordinate Measuring Machine
Modelng and Adaptve Contol of a Coodnate Measung Machne Â. Yudun Obak, Membe, IEEE Abstact Although tadtonal measung nstuments can povde excellent solutons fo the measuement of length, heght, nsde and
More informationVParC: A Compression Scheme for Numeric Data in Column-Oriented Databases
The Intenatonal Aab Jounal of Infomaton Technology VPaC: A Compesson Scheme fo Numec Data n Column-Oented Databases Ke Yan, Hong Zhu, and Kevn Lü School of Compute Scence and Technology, Huazhong Unvesty
More informationThe Forming Theory and the NC Machining for The Rotary Burs with the Spectral Edge Distribution
oden Appled Scence The Fomn Theoy and the NC achnn fo The Rotay us wth the Spectal Ede Dstbuton Huan Lu Depatment of echancal Enneen, Zhejan Unvesty of Scence and Technoloy Hanzhou, c.y. chan, 310023,
More informationBudding yeast colony growth study based on circular granular cell
Jounal of Physcs: Confeence Sees PAPER OPEN ACCESS Buddng yeast colony gowth study based on ccula ganula cell To cte ths atcle: Dev Apant et al 2016 J. Phys.: Conf. Se. 739 012026 Vew the atcle onlne fo
More informationPhysics Exam 3
Physcs 114 1 Exam 3 The numbe of ponts fo each secton s noted n backets, []. Choose a total of 35 ponts that wll be gaded that s you may dop (not answe) a total of 5 ponts. Clealy mak on the cove of you
More informationSOME NEW SELF-DUAL [96, 48, 16] CODES WITH AN AUTOMORPHISM OF ORDER 15. KEYWORDS: automorphisms, construction, self-dual codes
Факултет по математика и информатика, том ХVІ С, 014 SOME NEW SELF-DUAL [96, 48, 16] CODES WITH AN AUTOMORPHISM OF ORDER 15 NIKOLAY I. YANKOV ABSTRACT: A new method fo constuctng bnay self-dual codes wth
More informationVISUALIZATION OF THE ABSTRACT THEORIES IN DSP COURSE BASED ON CDIO CONCEPT
VISUALIZATION OF THE ABSTRACT THEORIES IN DSP COURSE BASED ON CDIO CONCEPT Wang L-uan, L Jan, Zhen Xao-qong Chengdu Unvesty of Infomaton Technology ABSTRACT The pape analyzes the chaactestcs of many fomulas
More informationV. Principles of Irreversible Thermodynamics. s = S - S 0 (7.3) s = = - g i, k. "Flux": = da i. "Force": = -Â g a ik k = X i. Â J i X i (7.
Themodynamcs and Knetcs of Solds 71 V. Pncples of Ievesble Themodynamcs 5. Onsage s Teatment s = S - S 0 = s( a 1, a 2,...) a n = A g - A n (7.6) Equlbum themodynamcs detemnes the paametes of an equlbum
More informationGroupoid and Topological Quotient Group
lobal Jounal of Pue and Appled Mathematcs SSN 0973-768 Volume 3 Numbe 7 07 pp 373-39 Reseach nda Publcatons http://wwwpublcatoncom oupod and Topolocal Quotent oup Mohammad Qasm Manna Depatment of Mathematcs
More informationCSJM University Class: B.Sc.-II Sub:Physics Paper-II Title: Electromagnetics Unit-1: Electrostatics Lecture: 1 to 4
CSJM Unvesty Class: B.Sc.-II Sub:Physcs Pape-II Ttle: Electomagnetcs Unt-: Electostatcs Lectue: to 4 Electostatcs: It deals the study of behavo of statc o statonay Chages. Electc Chage: It s popety by
More informationState Estimation. Ali Abur Northeastern University, USA. Nov. 01, 2017 Fall 2017 CURENT Course Lecture Notes
State Estmaton Al Abu Notheasten Unvesty, USA Nov. 0, 07 Fall 07 CURENT Couse Lectue Notes Opeatng States of a Powe System Al Abu NORMAL STATE SECURE o INSECURE RESTORATIVE STATE EMERGENCY STATE PARTIAL
More informationPart V: Velocity and Acceleration Analysis of Mechanisms
Pat V: Velocty an Acceleaton Analyss of Mechansms Ths secton wll evew the most common an cuently pactce methos fo completng the knematcs analyss of mechansms; escbng moton though velocty an acceleaton.
More informationPhysics 202, Lecture 2. Announcements
Physcs 202, Lectue 2 Today s Topcs Announcements Electc Felds Moe on the Electc Foce (Coulomb s Law The Electc Feld Moton of Chaged Patcles n an Electc Feld Announcements Homewok Assgnment #1: WebAssgn
More informationMultipole Radiation. March 17, 2014
Multpole Radaton Mach 7, 04 Zones We wll see that the poblem of hamonc adaton dvdes nto thee appoxmate egons, dependng on the elatve magntudes of the dstance of the obsevaton pont,, and the wavelength,
More informationALL QUESTIONS ARE WORTH 20 POINTS. WORK OUT FIVE PROBLEMS.
GNRAL PHYSICS PH -3A (D. S. Mov) Test (/3/) key STUDNT NAM: STUDNT d #: -------------------------------------------------------------------------------------------------------------------------------------------
More information3.1 Electrostatic Potential Energy and Potential Difference
3. lectostatc Potental negy and Potental Dffeence RMMR fom mechancs: - The potental enegy can be defned fo a system only f consevatve foces act between ts consttuents. - Consevatve foces may depend only
More informationDynamic State Feedback Control of Robotic Formation System
so he 00 EEE/RSJ ntenatonal Confeence on ntellgent Robots and Systems Octobe 8-, 00, ape, awan Dynamc State Feedback Contol of Robotc Fomaton System Chh-Fu Chang, Membe, EEE and L-Chen Fu, Fellow, EEE
More informationPHY126 Summer Session I, 2008
PHY6 Summe Sesson I, 8 Most of nfomaton s avalable at: http://nngoup.phscs.sunsb.edu/~chak/phy6-8 ncludng the sllabus and lectue sldes. Read sllabus and watch fo mpotant announcements. Homewok assgnment
More informationIntegral Vector Operations and Related Theorems Applications in Mechanics and E&M
Dola Bagayoko (0) Integal Vecto Opeatons and elated Theoems Applcatons n Mechancs and E&M Ι Basc Defnton Please efe to you calculus evewed below. Ι, ΙΙ, andιιι notes and textbooks fo detals on the concepts
More informationApproximate Abundance Histograms and Their Use for Genome Size Estimation
J. Hlaváčová (Ed.): ITAT 2017 Poceedngs, pp. 27 34 CEUR Wokshop Poceedngs Vol. 1885, ISSN 1613-0073, c 2017 M. Lpovský, T. Vnař, B. Bejová Appoxmate Abundance Hstogams and The Use fo Genome Sze Estmaton
More informationan application to HRQoL
AlmaMate Studoum Unvesty of Bologna A flexle IRT Model fo health questonnae: an applcaton to HRQoL Seena Boccol Gula Cavn Depatment of Statstcal Scence, Unvesty of Bologna 9 th Intenatonal Confeence on
More informationConsequences of Long Term Transients in Large Area High Density Plasma Processing: A 3-Dimensional Computational Investigation*
ISPC 2003 June 22-27, 2003 Consequences of Long Tem Tansents n Lage Aea Hgh Densty Plasma Pocessng: A 3-Dmensonal Computatonal Investgaton* Pamod Subamonum** and Mak J Kushne*** **Dept of Chemcal and Bomolecula
More informationPhysics 2A Chapter 11 - Universal Gravitation Fall 2017
Physcs A Chapte - Unvesal Gavtaton Fall 07 hese notes ae ve pages. A quck summay: he text boxes n the notes contan the esults that wll compse the toolbox o Chapte. hee ae thee sectons: the law o gavtaton,
More informationCombining IMM Method with Particle Filters for 3D Maneuvering Target Tracking
Combnng IMM Method wth Patcle Fltes fo D Maneuveng Taget Tacng Pe Hu Foo Depatment of Physcs Natonal Unvesty of Sngapoe Sngapoe g657@nus.edu.sg Abstact - The Inteactng Multple Model (IMM) algothm s a wdely
More informationPARAMETER ESTIMATION FOR TWO WEIBULL POPULATIONS UNDER JOINT TYPE II CENSORED SCHEME
Sept 04 Vol 5 No 04 Intenatonal Jounal of Engneeng Appled Scences 0-04 EAAS & ARF All ghts eseed wwweaas-ounalog ISSN305-869 PARAMETER ESTIMATION FOR TWO WEIBULL POPULATIONS UNDER JOINT TYPE II CENSORED
More informationComparison of three Approximate kinematic Models for Space Object Tracking
Compason of thee Appoxmate nematc Models fo Space Object acng Xn an, Genshe Chen Intellgent Fuson echnology Inc. 7 Goldenod Lane, Sute Gemantown MD, 87 USA {xtan, gchen}@ntfusontech.com E Blasch Infomaton
More information4 SingularValue Decomposition (SVD)
/6/00 Z:\ jeh\self\boo Kannan\Jan-5-00\4 SVD 4 SngulaValue Decomposton (SVD) Chapte 4 Pat SVD he sngula value decomposton of a matx s the factozaton of nto the poduct of thee matces = UDV whee the columns
More informationTheo K. Dijkstra. Faculty of Economics and Business, University of Groningen, Nettelbosje 2, 9747 AE Groningen THE NETHERLANDS
RESEARCH ESSAY COSISE PARIAL LEAS SQUARES PAH MODELIG heo K. Djksta Faculty of Economcs and Busness, Unvesty of Gonngen, ettelbosje, 9747 AE Gonngen HE EHERLADS {t.k.djksta@ug.nl} Jög Hensele Faculty of
More information1. A body will remain in a state of rest, or of uniform motion in a straight line unless it
Pncples of Dnamcs: Newton's Laws of moton. : Foce Analss 1. A bod wll eman n a state of est, o of unfom moton n a staght lne unless t s acted b etenal foces to change ts state.. The ate of change of momentum
More informationOptimization Methods: Linear Programming- Revised Simplex Method. Module 3 Lecture Notes 5. Revised Simplex Method, Duality and Sensitivity analysis
Optmzaton Meods: Lnea Pogammng- Revsed Smple Meod Module Lectue Notes Revsed Smple Meod, Dualty and Senstvty analyss Intoducton In e pevous class, e smple meod was dscussed whee e smple tableau at each
More informationConstraint Score: A New Filter Method for Feature Selection with Pairwise Constraints
onstant Scoe: A New Flte ethod fo Featue Selecton wth Pawse onstants Daoqang Zhang, Songcan hen and Zh-Hua Zhou Depatment of ompute Scence and Engneeng Nanjng Unvesty of Aeonautcs and Astonautcs, Nanjng
More informationIf there are k binding constraints at x then re-label these constraints so that they are the first k constraints.
Mathematcal Foundatons -1- Constaned Optmzaton Constaned Optmzaton Ma{ f ( ) X} whee X {, h ( ), 1,, m} Necessay condtons fo to be a soluton to ths mamzaton poblem Mathematcally, f ag Ma{ f ( ) X}, then
More informationSome Approximate Analytical Steady-State Solutions for Cylindrical Fin
Some Appoxmate Analytcal Steady-State Solutons fo Cylndcal Fn ANITA BRUVERE ANDRIS BUIIS Insttute of Mathematcs and Compute Scence Unvesty of Latva Rana ulv 9 Rga LV459 LATVIA Astact: - In ths pape we
More informationBackward Haplotype Transmission Association (BHTA) Algorithm. Tian Zheng Department of Statistics Columbia University. February 5 th, 2002
Backwad Haplotype Tansmsson Assocaton (BHTA) Algothm A Fast ult-pont Sceenng ethod fo Complex Tats Tan Zheng Depatment of Statstcs Columba Unvesty Febuay 5 th, 2002 Ths s a jont wok wth Pofesso Shaw-Hwa
More informationRe-Ranking Retrieval Model Based on Two-Level Similarity Relation Matrices
Intenatonal Jounal of Softwae Engneeng and Its Applcatons, pp. 349-360 http://dx.do.og/10.1457/sea.015.9.1.31 Re-Rankng Reteval Model Based on Two-Level Smlaty Relaton Matces Hee-Ju Eun Depatment of Compute
More informationState Feedback Controller Design via Takagi- Sugeno Fuzzy Model : LMI Approach
State Feedback Contolle Desgn va akag- Sugeno Fuzzy Model : LMI Appoach F. Khabe, K. Zeha, and A. Hamzaou Abstact In ths pape, we ntoduce a obust state feedback contolle desgn usng Lnea Matx Inequaltes
More informationChapter 8. Linear Momentum, Impulse, and Collisions
Chapte 8 Lnea oentu, Ipulse, and Collsons 8. Lnea oentu and Ipulse The lnea oentu p of a patcle of ass ovng wth velocty v s defned as: p " v ote that p s a vecto that ponts n the sae decton as the velocty
More informationUnconventional double-current circuit accuracy measures and application in twoparameter
th IMEKO TC Wokshop on Techncal Dagnostcs dvanced measuement tools n techncal dagnostcs fo systems elablty and safety June 6-7 Wasaw Poland nconventonal double-cuent ccut accuacy measues and applcaton
More informationA Method of Reliability Target Setting for Electric Power Distribution Systems Using Data Envelopment Analysis
27 กก ก 9 2-3 2554 ก ก ก A Method of Relablty aget Settng fo Electc Powe Dstbuton Systems Usng Data Envelopment Analyss ก 2 ก ก ก ก ก 0900 2 ก ก ก ก ก 0900 E-mal: penjan262@hotmal.com Penjan Sng-o Psut
More informationStable Model Predictive Control Based on TS Fuzzy Model with Application to Boiler-turbine Coordinated System
5th IEEE Confeence on Decson and Contol and Euopean Contol Confeence (CDC-ECC) Olando, FL, USA, Decembe -5, Stable Model Pedctve Contol Based on S Fuy Model wth Applcaton to Bole-tubne Coodnated System
More informationPhysics Exam II Chapters 25-29
Physcs 114 1 Exam II Chaptes 5-9 Answe 8 of the followng 9 questons o poblems. Each one s weghted equally. Clealy mak on you blue book whch numbe you do not want gaded. If you ae not sue whch one you do
More informationON THE FRESNEL SINE INTEGRAL AND THE CONVOLUTION
IJMMS 3:37, 37 333 PII. S16117131151 http://jmms.hndaw.com Hndaw Publshng Cop. ON THE FRESNEL SINE INTEGRAL AND THE CONVOLUTION ADEM KILIÇMAN Receved 19 Novembe and n evsed fom 7 Mach 3 The Fesnel sne
More informationResearch Article A Robust Longitudinal Control Strategy for Safer and Comfortable Automotive Driving
Reseach Jounal of Appled Scences, Engneeng and Technology 7(3): 506-5033, 014 DOI:10.1906/jaset.7.896 ISSN: 040-7459; e-issn: 040-7467 014 Mawell Scentfc Publcaton Cop. Submtted: Febuay 18, 014 Accepted:
More informationPHYS Week 5. Reading Journals today from tables. WebAssign due Wed nite
PHYS 015 -- Week 5 Readng Jounals today fom tables WebAssgn due Wed nte Fo exclusve use n PHYS 015. Not fo e-dstbuton. Some mateals Copyght Unvesty of Coloado, Cengage,, Peason J. Maps. Fundamental Tools
More informationAdaptive Flocking Control for Dynamic Target Tracking in Mobile Sensor Networks
The 29 IEEE/RSJ Internatonal Conference on Intellgent Robots and Systems October -5, 29 St. Lous, USA Adaptve Flockng Control for Dynamc Target Trackng n Moble Sensor Networks Hung Manh La and Wehua Sheng
More information2/24/2014. The point mass. Impulse for a single collision The impulse of a force is a vector. The Center of Mass. System of particles
/4/04 Chapte 7 Lnea oentu Lnea oentu of a Sngle Patcle Lnea oentu: p υ It s a easue of the patcle s oton It s a vecto, sla to the veloct p υ p υ p υ z z p It also depends on the ass of the object, sla
More informationNew Condition of Stabilization of Uncertain Continuous Takagi-Sugeno Fuzzy System based on Fuzzy Lyapunov Function
I.J. Intellgent Systems and Applcatons 4 9-5 Publshed Onlne Apl n MCS (http://www.mecs-pess.og/) DOI:.585/sa..4. New Condton of Stablzaton of Uncetan Contnuous aag-sugeno Fuzzy System based on Fuzzy Lyapunov
More informationCovariance Bounds Analysis during Intermittent Measurement for EKF-based SLAM
Intenatonal ounal o Integated Engneeng, Vol. 4 No. 3 () p. 9-5 Covaance Bounds Analyss dung Intemttent Measuement o EKF-based SLAM amzah Ahmad,*, ou Nameawa Faculty o Electcal & Electoncs, Unvesty Malaysa
More informationAN EXACT METHOD FOR BERTH ALLOCATION AT RAW MATERIAL DOCKS
AN EXACT METHOD FOR BERTH ALLOCATION AT RAW MATERIAL DOCKS Shaohua L, a, Lxn Tang b, Jyn Lu c a Key Laboatoy of Pocess Industy Automaton, Mnsty of Educaton, Chna b Depatment of Systems Engneeng, Notheasten
More informationEE 5337 Computational Electromagnetics (CEM)
7//28 Instucto D. Raymond Rumpf (95) 747 6958 cumpf@utep.edu EE 5337 Computatonal Electomagnetcs (CEM) Lectue #6 TMM Extas Lectue 6These notes may contan copyghted mateal obtaned unde fa use ules. Dstbuton
More information