Wildfire Smoke Detection Using SpatioTemporal Bag-of-Features of Smoke

Size: px
Start display at page:

Download "Wildfire Smoke Detection Using SpatioTemporal Bag-of-Features of Smoke"

Transcription

1 Wldfre Smoke Detecton Usng SpatoTemporal Bag-of-Features of Smoke JunOh Park, ByoungChul Ko, Jae-Yeal Nam Dept. of Computer Engneerng Kemyung Unversty Daegu, Korea wnsdhd, nceko, Abstract Ths paper presents a wldfre smoke detecton method based on a spatotemporal bag-of-features (BoF) and a random forest classfer. Frst, canddate blocks are detected usng key-frame dfferences and non-parametrc color models to reduce the computaton tme. Subsequently, spatotemporal three-dmensonal (3D) volumes are bult by combnng the canddate blocks n the current key-frame and the correspondng blocks n prevous frames. A hstogram of gradent (HOG) s extracted as a spatal feature, and a hstogram of optcal flow (HOF) s extracted as a temporal feature based on the fact that the dffuson drecton of smoke s upward owng to thermal convecton. Usng these spatotemporal features, a codebook and a BoF hstogram are generated from tranng data. For smoke verfcaton, a random forest classfer s bult durng the tranng phase by usng the BoF hstogram. The random forest wth BoF hstogram can ncrease the detecton accuracy and allow smoke detecton to be carred out n near real-tme. 1. Introducton Wldfres rank among varous natural dsasters such as storms, droughts, floods, landsldes, and tsunams, resultng n not only extensve loss of lfe and property but also ecologcal problems. Therefore, an early warnng of wldfres s crucal to reduce the potental for casualtes and property damage. Recently, wth the rapd development of nformaton technology, automatc wldfre detecton has grown to become a new research feld. The conventonal approach has been to watch for a sgn of fre or smoke wth the naked eye. To overcome the lmtatons of tradtonal methods, nfrared (IR) sensors and lght detecton and rangng (LIDAR) systems are used to dentfy the heat flux of frelght and to measure the laser lght backscattered by smoke partcles. However, these optcal sensor-based wldfre detecton methods generate many false alarms due to atmospherc condtons, lght reflectons, and the vast dstance between the sensors and the burnng pont [1]. SooYeong Kwak Dept. Electronc and Control Engneerng, Hanbat Natonal Unversty Daejeon Korea sykwak@hanbat.ac.kr In general, a charge-coupled devce (CCD) camera for a wldfre detecton system s nstalled atop a mountan to montor a wde area and to provde more dependable fre detecton results than sensor-based methods: The equpment and management costs are lower. One camera covers a wde range. The response tme for fre and smoke detecton s shorter. The manager can confrm a fre and montor the status of the fre and smoke wthout vstng the locaton. However, methods based on CCD cameras stll have problems such as envronmental llumnaton, varatons n smoke color tones, and low qualty of mages of a wde outdoor area [2]. Wldfre detecton can be dvded nto two research categores: smoke detecton and flame detecton. Smoke detecton s partcularly mportant for early warnng systems, because smoke usually rses before flames arse. Therefore, our research focuses on daytme wldfre smoke detecton. The man smoke detecton methods are summarzed as follows: Krstnć et al. [2] proposed a pxel-level mage analyss and segmentaton of smoke-colored pxels for automatc forest fre detecton. They proved that good color space canddates for smoke detecton nclude HIS and ts dervatves as well as the RGB color space. They also proposed a performance evaluaton method to fnd an effcent combnaton of a color space and a pxel-level smoke segmentaton algorthm. Töreyn and Cetn [3] proposed a part-based smoke detecton algorthm usng four sub-algorthms: (1) slow-movng vdeo object detecton, (2) gray regon detecton, (3) rsng object detecton, and (4) shadow elmnaton. These four sub-algorthms detect the presence of smoke ndvdually, and the decsons of the sub-algorthms are combned by an adaptve weghted majorty algorthm. Ham et al. [4] proposed a wldfre smoke detecton algorthm usng fuzzy fnte automata (FFA) and temporal vsual features. For smoke verfcaton usng FFA, three two-dmensonal probablty densty functons are estmated from nformaton on ntensty, wavelet energy, and moton /12/$ /13/$ IEEE 200

2 Habboglu et al. [5] used background subtracton and color thresholds to fnd the smoke-colored slow-movng regons n vdeo. Canddate regons are dvded nto spatotemporal blocks and correlaton features are extracted from the blocks. Then, a bnary support vector machne (SVM) classfer wth spatotemporal correlaton descrptors s used to classfy smoke-colored and non-smoke-colored objects. Ko et al. [6] extracted spatotemporal characterstcs such as color, wavelet coeffcents, moton orentaton, and hstogram of orented gradents (HOG) from canddate smoke blocks and the precedng 100 assocated frames. The man dea of ths method s to tran two ndvdual random forests usng ndependent temporal and spatal feature vectors. Fnally, a canddate block s declared a smoke block f the average probablty of two random forests n the smoke class s maxmum. In ths study, we ntroduce a wldfre smoke detecton method based on a spatotemporal bag-of-features (BoF) and a random forest classfer. Frst, we detect canddate blocks from key-frames n vdeo and prepare spatotemporal 3D volumes by combnng the canddate blocks n the current key-frame wth the correspondng blocks n prevous frames. An HOG s extracted from the current block as a spatal feature, and a hstogram of optcal flow (HOF) s extracted as a temporal feature based on the fact that the dffuson drecton of smoke s upward owng to thermal convecton. Second, the random forest classfer, whch s an ensemble of decson trees, s bult durng the tranng phase by usng the BoF hstogram. The random forest wth the BoF hstogram can ncrease the detecton accuracy and allow smoke detecton to be carred out n near real-tme. The remander of ths paper s organzed as follows. Secton 2 descrbes the canddate smoke block detecton algorthm as the preprocessng step. Secton 3 ntroduces our smoke verfcaton method usng a spatotemporal BoF and random forests. Secton 4 presents an expermental evaluaton of the accuracy and applcablty of our proposed wldfre smoke detecton method. Secton 5 presents our conclusons and dscusses scope for future work. 2. Canddate smoke block detecton For real-tme processng, t s effcent to use canddate regons wthout usng every mage pxel. Therefore, we frst detect slow-movng regons by key-frame detecton, and then we confrm the canddate regons by usng a smoke color model. The nput vdeo sequences are dvded nto blocks accordng to the aspect rato n the MPEG standardzaton, and all subsequent procedures are appled to these unts. One of the man characterstcs of wldfre smoke s the relatvely low apparent spreadng speed, as the survellance cameras are nstalled at vast dstances. Thus, canddate smoke regons cannot be detected usng only a smple background subtracton model. To overcome the lmtatons of smple background subtracton, we select key-frames from a vdeo sequence used n [6] whenever the frame dfference exceeds a certan threshold. After detectng key-frames and ther movng blocks, the non-smoke-colored blocks must be fltered out to reduce the computaton tme for smoke verfcaton. In general, the smoke color s dstrbuted wdely n the RGB color space dependng on the burnng materal. On the other hand, smoke color n the HSI color space s dstrbuted wth a low level of saturaton (S), a hgh level of ntensty (I), and no hue (H) [4]. Thus, we remove non-smoke-colored blocks usng the probablty densty functon (PDF) of a smoke color model. The parameters of the PDFs are learned from tranng data. In contrast to typcal supervsed learnng n whch the underlyng dstrbuton functons are known, smoke color does not follow a known dstrbuton or parametrc denstes [8]. Therefore, we construct the PDF to have multmodal denstes, rather than unmodal denstes, by usng a non-parametrc method. In ths paper, we use a smoother kernel functon n the form of a Gaussan n order to obtan the followng smoother kernel densty model: 2 N 1 1 x x n p( x) d exp (1) N n1 (2h ) 2h where N s the number of data and h s the parameter that determnes the wdth of the effectve Gaussan wndow along each dmenson d. After PDF are generated, the lkelhood of the feature vector of block b s denoted by p( b Smoke), and can be estmated from the defned PDFs. These PDF are then used to confgure real canddate blocks. From the PDF, the lkelhood p( b Smoke) that a block ( b ) has the smoke color s obtaned by summng the probabltes for all pxels n b usng the followng formula: n 1 f p( b j Smoke ) T1 b (2) j1 0 otherwse If the result exceeds a pre-defned threshold, the block b s declared a canddate smoke block. Fgure 1 shows canddate smoke blocks after key-frame dfferencng and flterng of non-smoke-colored blocks. After detectng the canddate smoke blocks, the mage s 201

3 scanned to group the blocks nto clusters based on block connectvty. Once all of the N clusters have been determned, some clusters are removed f the number of blocks s less than three. 3. Smoke verfcaton usng spatotemporal BoF and random forest Ths secton presents our smoke verfcaton method usng spatotemporal features such as HOGs, HOFs, and bag-of-features. Fnally, a feature hstogram s estmated from the BoF, and the random forest classfer uses the feature hstogram to determne whether the canddate block represents real smoke Spatotemporal BoF In vdeo-based acton recognton, sparse spatotemporal features have recently shown good performance [9, 10, 11]. Fgure 1: Examples of canddate blocks detected by key-frame dfferencng and flterng of non-smoke-colored blocks. In ths study, we use canddate blocks that are selected from prevous steps nstead of nterest ponts. In a manner smlar to that for acton recognton, we frst prepare spatotemporal 3D volumes by combnng the canddate blocks wth t correspondng blocks n prevous frames, as shown n Fgure 2 (a). Each volume ( x, y, t ) has the same wdth and heght, wth canddate blocks (10, 10), and the tme duraton t s 100. From each volume, we compute the moton and appearance of local spatotemporal features as shown n Fgure 2 (b). For a spatal feature, an HOG s generated from the current block. Snce the dffuson drecton of smoke s upward owng to thermal convecton, the gradent dstrbuton of a smoke boundary has a dstngushable pattern. By usng ths characterstc, we extract an HOG as a spatal feature. In order to extract an HOG from a canddate block, gradent orentatons are estmated at each pxel and a hstogram of each orentaton n a canddate block s calculated n a manner smlar to that n [6]. For a temporal feature, an HOF s generated from 100 blocks wthn the same volume. Snce smoke usually drfts contnually upwards due to hot arflows, the orentaton of the moton s estmated from the 100 blocks n each volume. Then, two features are normalzed and concatenated nto one. After extractng a set of spatotemporal features from tranng data, we construct a spatotemporal BoF as shown n Fgures 2 (c) and (d). A BoF s desgned to depct each mage as an orderless collecton of local features. Vsual vocabulares (codebooks) are bult to descrbe a BoF usng tranng descrptors and k-means clusterng. Each cluster s treated as a vsual word (codeword) n the vsual vocabulary. By mappng the local features of an mage to the vsual vocabulary, we can descrbe the mage as a feature hstogram accordng to the presence (or count) of each vsual word [12]. Gven a random subset of volumes ncludng smoke and non-smoke regons from the tranng set, we learn the vsual vocabulary by performng k-means clusterng. In our experments, the sze of the vsual vocabulary was determned as k = 400. Fgure 2 (c) shows the process of codebook generaton Generaton of BoF hstogram Once the codebook of the BoF s bult, two knds of BoF hstograms of vsual words should be estmated usng the smoke and non-smoke classes. The BoF hstogram assgns each feature to the closest vsual word and computes the hstogram of vsual word occurrences over a space-tme volume [13]. To assgn a weght to the hstogram, bnary weghtng ndcates the presence or absence of a vsual word by values 1 or 0, respectvely. However, we adopt the soft-weghtng approach [14] to emphasze the sgnfcance of vsual words: nstead of searchng only for the nearest vsual word, we select the N nearest vsual words and assgn dfferent weghts accordng to the sum of dstances. Fgure 2 (d) shows an example of a BoF feature hstogram Smoke verfcaton usng random forest classfer In contrast to prevous heurstc methods and smple pattern classfers for smoke verfcaton, ths study uses a random forest classfer [15] to determne whether the canddate smoke clusters represent real smoke. A random forest s a decson tree ensemble classfer, wth each tree grown usng some types of randomzaton. Random forests have a capacty for processng large amounts of data wth hgh tranng speeds, based on a decson tree. The structure of each tree n the random forest s bnary and s created n a top down manner, as shown n Fgure 2 (e). In the tranng procedure, the random forest s started by choosng a random subset I from the local BoF tranng 202

4 Fgure 2: Flow dagram of BoF generaton and random forest learnng: (a) 3D volume generaton from canddate blocks, (b) spatotemporal feature extracton, (c) codebook generaton, (d) BoF hstogram generaton, and (e) random forest generaton. data I. At node n, the tranng data I n s teratvely splt nto left and rght subsets I and I by usng Equaton (3) l r wth the threshold t and splt functon f ( v ) for the feature vector v. The threshold t s randomly chosen n the range t mn f ( v ),max f ( v )) by the splt functon f v ) ( [6]. Il { In f ( v) t}, (3) Ir In \ Il. The overall procedure for tranng one decson tree of a random forest s summarzed below. 1. Choose the maxmum tree depth. 2. Grow each tree for an ndvdual random forest by the followng steps: a. Select n new bootstrap samples from the tranng set S n and grow an unpruned tree usng these n bootstrap samples. b. For each node, randomly select m varables at each nternal node and determne the best splt functon usng only these varables. c. Grow the tree wthn the maxmum tree depth. After the ndvdual decson trees are traned, the ensemble of trees s assembled nto a random forest classfer as shown n Fgure 2 (e). The number of trees T s set to 100, whch has been shown emprcally to yeld good results and computaton tmes comparable wth those for related methods. After the random forest classfer has been learned, the BoF hstogram of the test blocks s created and s used as nput to the traned random forests. The fnal class dstrbuton s generated by arthmetc averagng of each ( dstrbuton of all trees, L = ( l 1, l 2,, l T ), usng Equaton (4). In Equaton (4), T s the number of trees, and we choose c as the fnal class of an nput mage f p( c L) has the maxmum value. T 1 P( c L) P( c lt) (4) T t1 4. Experment We performed experments usng the KMU Fre & Smoke Database ( whch ncludes 38 dverse fre vdeos, such as Indoor-outdoor flame, Indoor-outdoor smoke, Wldfre smoke, and Smoke & fre lke movng object. The frame rates of the vdeo data vared from 15 to 30 Hz, whle the sze of each nput mage was pxels. To perform the tranng, 517 blocks were randomly selected from ten vdeos: 130 blocks of dense smoke, 131 blocks of tenuous smoke, 120 blocks of tenuous smoke-colored clouds and fog, and 136 blocks of dense smoke-lke clouds and fog. The tranng vdeo sequences conssted of fve vdeos that ncluded wldfre smoke and fve vdeos that ncluded smoke-colored clouds and fog. In ths study, we used three crtera for performance evaluaton: average true postve rate (ATPR), average false postve rate (AFPR), and average mss rate (AMR). We compared the performance of the proposed algorthm wth that of prevous algorthms. Among the exstng methods, those of Töreyn and Cetn [3] and Ham et al. [4] 203

5 Fgure 3: Comparson between results of proposed method and two related methods performed well usng the same ten test vdeos contanng fve smoke samples and fve smoke-colored samples. Fgure 3 shows the comparson of the results of the three methods. Note that the proposed method outperformed the methods of Ko et al., Töreyn et al. and Ham et al., wth an ATPR of 95.1% versus 94.2%, 75.6% and 81.0%, an AFPR of 2.3% versus 6.3%, 7.5% and 14.5%, and an AMR of 4.1% versus 1.5%, 16.9% and 4.5%, respectvely. In partcular, the method of Töreyn and Cetn produced a hgher AMR, snce t detected canddate smoke regons n every frame by usng the frame dfference. However, snce wldfre smoke, especally that n vdeos 1, 3, and 4, appears to move very slowly due to the vast dstances between the camera and the locatons of the smoke, many true smoke regons were mssed. The method of Ham et al. exhbted hgher AFPR of 14.5% for test vdeos. The man reason for the hgher error was that smoke was confused wth movng smoke-colored objects and swayng trees. Smlarly, the method of Töreyn and Cetn gave several false alarms for vdeo 6 because movng clouds were confused wth fre-smoke. However, by usng spatotemporal features wth a random forest classfer, our method reduced the false alarms caused by movements of smoke-colored clouds. Moreover, snce a BoF represents vdeos as a collecton of local propertes calculated from a set of 3D volumes, our method can dstngush real smoke from a smoke-colored cloud n dynamc moton. Fgure 4 shows the results of smoke detecton obtaned wth our proposed method usng a set of ten tests. As shown n Fgure 4, our proposed method detected smoke correctly and elmnated false alarms for test vdeos contanng smoke and non-smoke objects wth dfferent speeds and colors. Fgure 4: Smoke detecton results obtaned usng the proposed algorthm 5. Concluson Ths paper ntroduced a wldfre smoke detecton method based on a spatotemporal BoF and a random forest classfer. After canddate blocks are detected, we frst prepare the spatotemporal 3D volumes by combnng the canddate blocks wth t correspondng blocks n prevous frames. An HOG s extracted from the current block as a spatal feature, and an HOF s extracted as a temporal feature based on the fact that the dffuson drecton of smoke s upward owng to thermal convecton. For classfcaton, the random forests that comprse the ensemble of decson trees are bult durng the tranng phase by usng the BoF hstogram. Compared wth related methods, our algorthm can ndeed provde mproved smoke detecton performance. In future work, n order to mprove the detecton performance especally reduce the AMR, we shall optmze the parameters of the BoF and random forest, such as the codebook sze, 3D volume length, tree depth, and number of trees. Acknowledgement Ths research was partally supported by Basc Scence Research Program through the Natonal Research Foundaton of Korea (NRF) funded by the Mnstry of Educaton, Scence and Technology ( ) and t was also fnancally supported by the Mnstry of Educaton, Scence Technology (MEST) and Natonal Research Foundaton of Korea(NRF) through the Human Resource 204

6 Tranng Project for Regonal Innovaton ( A ) References [1] B. C. Ko and S. Y. Kwak. A survey of computer vson-based natural dsaster warnng systems. Optcal Engneerng, 57(1): , [2] D. Krstnć, D. Stpančev, and T. Jakovčevć. Hstogram-based smoke segmentaton n forest fre detecton system. Informaton Technology and Control, 38(3): , [3] B. U. Töreyn and A. E. Cetn. Wldfre detecton usng LMS based actve learnng. IEEE Internatonal Conference on Acoustcs, Speech and Sgnal Processng, , [4] S. J. Ham, B. C. Ko, and J. Y. Nam. Vson based forest smoke detecton usng analyzng of temporal patterns of smoke and ther probablty models. Image Processng: Machne Vson Applcatons IV, 7877:1 6, [5] Y. H. Habboglu, O. Gunay, and A. E. Cetn. Real-tme wldfre detecton usng correlaton descrptors. 19th European Sgnal Processng Conference, , [6] B. C. Ko, J. Y. Kwak, and J. Y. Nam. Wldfre smoke detecton usng temporal-spatal features and random forest classfers. Optcal Engneerng, 51(1): , [7] Q. Tan and S. Zhang. Descrptve vsual words and vsual phrases for mage applcatons. ACM Multmeda, 19 24, [8] B. C. Ko, J. W. Gm, and J. Y. Nam. Automatc whte blood cell segmentaton usng stepwse mergng rules and gradent vector flow snake. Mcron, 42: , [9] M. Marszalek, C. Schmd, and B. Rozenfeld. Learnng realstc human actons from moves. IEEE Conference on Computer Vson and Pattern Recognton, 1 8, [10] P. Dollar, V. Rabaud, G. Cottrell, and S. Belonge. Behavor recognton va sparse spato-temporal features. IEEE Internatonal Workshop on Vsual Survellance and Performance Evaluaton of Trackng and Survellance, 65 72, [11] J. C. Nebles, H. Wang, and L. Fe-Fe. Unsupervsed learnng of human acton categores usng spato-temporal words. Brtsh Machne Vson Conference, 1 11, [12] Y. G. Jang C. W. Ngo, and J. Yang. Towards optmal bag-of-features for object categorzaton and semantc vdeo retreval. 6th ACM Internatonal Conference on Image and Vdeo Retreval, , [13] I. Laptev, M. Marszalek, C. Schmd, and B. Rozenfeld. Learnng realstc human actons from moves. IEEE Internatonal Conference on Computer Vson and Pattern Recognton, 1 8, [14] A. Agarwal and B. Trggs. Hyperfetures-multlevel local codng for vsual recognton. IEEE Internatonal Conference on Computer Vson and Pattern Recognton, 30 43, [15] L. Breman. Random forests. Machne Learnng, 45:5 32, [16] Actual Author Name..". The frobncatable foo flter, Face and Gesture apper ID 324. [17] Authors. Frobncaton tutoral, Some URL al tr.pdf. 205

The Development of Web Log Mining Based on Improve-K-Means Clustering Analysis

The Development of Web Log Mining Based on Improve-K-Means Clustering Analysis The Development of Web Log Mnng Based on Improve-K-Means Clusterng Analyss TngZhong Wang * College of Informaton Technology, Luoyang Normal Unversty, Luoyang, 471022, Chna wangtngzhong2@sna.cn Abstract.

More information

Vision Mouse. Saurabh Sarkar a* University of Cincinnati, Cincinnati, USA ABSTRACT 1. INTRODUCTION

Vision Mouse. Saurabh Sarkar a* University of Cincinnati, Cincinnati, USA ABSTRACT 1. INTRODUCTION Vson Mouse Saurabh Sarkar a* a Unversty of Cncnnat, Cncnnat, USA ABSTRACT The report dscusses a vson based approach towards trackng of eyes and fngers. The report descrbes the process of locatng the possble

More information

An interactive system for structure-based ASCII art creation

An interactive system for structure-based ASCII art creation An nteractve system for structure-based ASCII art creaton Katsunor Myake Henry Johan Tomoyuk Nshta The Unversty of Tokyo Nanyang Technologcal Unversty Abstract Non-Photorealstc Renderng (NPR), whose am

More information

MACHINE VISION SYSTEM FOR SPECULAR SURFACE INSPECTION: USE OF SIMULATION PROCESS AS A TOOL FOR DESIGN AND OPTIMIZATION

MACHINE VISION SYSTEM FOR SPECULAR SURFACE INSPECTION: USE OF SIMULATION PROCESS AS A TOOL FOR DESIGN AND OPTIMIZATION MACHINE VISION SYSTEM FOR SPECULAR SURFACE INSPECTION: USE OF SIMULATION PROCESS AS A TOOL FOR DESIGN AND OPTIMIZATION R. SEULIN, F. MERIENNE and P. GORRIA Laboratore Le2, CNRS FRE2309, EA 242, Unversté

More information

Face Verification Problem. Face Recognition Problem. Application: Access Control. Biometric Authentication. Face Verification (1:1 matching)

Face Verification Problem. Face Recognition Problem. Application: Access Control. Biometric Authentication. Face Verification (1:1 matching) Face Recognton Problem Face Verfcaton Problem Face Verfcaton (1:1 matchng) Querymage face query Face Recognton (1:N matchng) database Applcaton: Access Control www.vsage.com www.vsoncs.com Bometrc Authentcaton

More information

An Interest-Oriented Network Evolution Mechanism for Online Communities

An Interest-Oriented Network Evolution Mechanism for Online Communities An Interest-Orented Network Evoluton Mechansm for Onlne Communtes Cahong Sun and Xaopng Yang School of Informaton, Renmn Unversty of Chna, Bejng 100872, P.R. Chna {chsun,yang}@ruc.edu.cn Abstract. Onlne

More information

What is Candidate Sampling

What is Candidate Sampling What s Canddate Samplng Say we have a multclass or mult label problem where each tranng example ( x, T ) conssts of a context x a small (mult)set of target classes T out of a large unverse L of possble

More information

A Multi-mode Image Tracking System Based on Distributed Fusion

A Multi-mode Image Tracking System Based on Distributed Fusion A Mult-mode Image Tracng System Based on Dstrbuted Fuson Ln zheng Chongzhao Han Dongguang Zuo Hongsen Yan School of Electroncs & nformaton engneerng, X an Jaotong Unversty X an, Shaanx, Chna Lnzheng@malst.xjtu.edu.cn

More information

A Suspect Vehicle Tracking System Based on Video

A Suspect Vehicle Tracking System Based on Video 3rd Internatonal Conference on Multmeda Technology ICMT 2013) A Suspect Vehcle Trackng System Based on Vdeo Yad Chen 1, Tuo Wang Abstract. Vdeo survellance systems are wdely used n securty feld. The large

More information

Forecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network

Forecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network 700 Proceedngs of the 8th Internatonal Conference on Innovaton & Management Forecastng the Demand of Emergency Supples: Based on the CBR Theory and BP Neural Network Fu Deqang, Lu Yun, L Changbng School

More information

Forecasting the Direction and Strength of Stock Market Movement

Forecasting the Direction and Strength of Stock Market Movement Forecastng the Drecton and Strength of Stock Market Movement Jngwe Chen Mng Chen Nan Ye cjngwe@stanford.edu mchen5@stanford.edu nanye@stanford.edu Abstract - Stock market s one of the most complcated systems

More information

Vehicle Detection and Tracking in Video from Moving Airborne Platform

Vehicle Detection and Tracking in Video from Moving Airborne Platform Journal of Computatonal Informaton Systems 10: 12 (2014) 4965 4972 Avalable at http://www.jofcs.com Vehcle Detecton and Trackng n Vdeo from Movng Arborne Platform Lye ZHANG 1,2,, Hua WANG 3, L LI 2 1 School

More information

ECE544NA Final Project: Robust Machine Learning Hardware via Classifier Ensemble

ECE544NA Final Project: Robust Machine Learning Hardware via Classifier Ensemble 1 ECE544NA Fnal Project: Robust Machne Learnng Hardware va Classfer Ensemble Sa Zhang, szhang12@llnos.edu Dept. of Electr. & Comput. Eng., Unv. of Illnos at Urbana-Champagn, Urbana, IL, USA Abstract In

More information

Detecting Global Motion Patterns in Complex Videos

Detecting Global Motion Patterns in Complex Videos Detectng Global Moton Patterns n Complex Vdeos Mn Hu, Saad Al, Mubarak Shah Computer Vson Lab, Unversty of Central Florda {mhu,sal,shah}@eecs.ucf.edu Abstract Learnng domnant moton patterns or actvtes

More information

Logistic Regression. Lecture 4: More classifiers and classes. Logistic regression. Adaboost. Optimization. Multiple class classification

Logistic Regression. Lecture 4: More classifiers and classes. Logistic regression. Adaboost. Optimization. Multiple class classification Lecture 4: More classfers and classes C4B Machne Learnng Hlary 20 A. Zsserman Logstc regresson Loss functons revsted Adaboost Loss functons revsted Optmzaton Multple class classfcaton Logstc Regresson

More information

benefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ).

benefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ). REVIEW OF RISK MANAGEMENT CONCEPTS LOSS DISTRIBUTIONS AND INSURANCE Loss and nsurance: When someone s subject to the rsk of ncurrng a fnancal loss, the loss s generally modeled usng a random varable or

More information

Module 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur

Module 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur Module LOSSLESS IMAGE COMPRESSION SYSTEMS Lesson 3 Lossless Compresson: Huffman Codng Instructonal Objectves At the end of ths lesson, the students should be able to:. Defne and measure source entropy..

More information

Gender Classification for Real-Time Audience Analysis System

Gender Classification for Real-Time Audience Analysis System Gender Classfcaton for Real-Tme Audence Analyss System Vladmr Khryashchev, Lev Shmaglt, Andrey Shemyakov, Anton Lebedev Yaroslavl State Unversty Yaroslavl, Russa vhr@yandex.ru, shmaglt_lev@yahoo.com, andrey.shemakov@gmal.com,

More information

A machine vision approach for detecting and inspecting circular parts

A machine vision approach for detecting and inspecting circular parts A machne vson approach for detectng and nspectng crcular parts Du-Mng Tsa Machne Vson Lab. Department of Industral Engneerng and Management Yuan-Ze Unversty, Chung-L, Tawan, R.O.C. E-mal: edmtsa@saturn.yzu.edu.tw

More information

Human Tracking by Fast Mean Shift Mode Seeking

Human Tracking by Fast Mean Shift Mode Seeking JOURAL OF MULTIMEDIA, VOL. 1, O. 1, APRIL 2006 1 Human Trackng by Fast Mean Shft Mode Seekng [10 font sze blank 1] [10 font sze blank 2] C. Belezna Advanced Computer Vson GmbH - ACV, Venna, Austra Emal:

More information

Feature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College

Feature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College Feature selecton for ntruson detecton Slobodan Petrovć NISlab, Gjøvk Unversty College Contents The feature selecton problem Intruson detecton Traffc features relevant for IDS The CFS measure The mrmr measure

More information

Eye Center Localization on a Facial Image Based on Multi-Block Local Binary Patterns

Eye Center Localization on a Facial Image Based on Multi-Block Local Binary Patterns Eye Center Localzaton on a Facal Image Based on Mult-Bloc Local Bnary Patterns Anatoly tn, Vladmr Khryashchev, Olga Stepanova Yaroslavl State Unversty Yaroslavl, Russa anatolyntnyar@gmal.com, vhr@yandex.ru,

More information

APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT

APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT Toshhko Oda (1), Kochro Iwaoka (2) (1), (2) Infrastructure Systems Busness Unt, Panasonc System Networks Co., Ltd. Saedo-cho

More information

Recurrence. 1 Definitions and main statements

Recurrence. 1 Definitions and main statements Recurrence 1 Defntons and man statements Let X n, n = 0, 1, 2,... be a MC wth the state space S = (1, 2,...), transton probabltes p j = P {X n+1 = j X n = }, and the transton matrx P = (p j ),j S def.

More information

Realistic Image Synthesis

Realistic Image Synthesis Realstc Image Synthess - Combned Samplng and Path Tracng - Phlpp Slusallek Karol Myszkowsk Vncent Pegoraro Overvew: Today Combned Samplng (Multple Importance Samplng) Renderng and Measurng Equaton Random

More information

How To Understand The Results Of The German Meris Cloud And Water Vapour Product

How To Understand The Results Of The German Meris Cloud And Water Vapour Product Ttel: Project: Doc. No.: MERIS level 3 cloud and water vapour products MAPP MAPP-ATBD-ClWVL3 Issue: 1 Revson: 0 Date: 9.12.1998 Functon Name Organsaton Sgnature Date Author: Bennartz FUB Preusker FUB Schüller

More information

A hybrid global optimization algorithm based on parallel chaos optimization and outlook algorithm

A hybrid global optimization algorithm based on parallel chaos optimization and outlook algorithm Avalable onlne www.ocpr.com Journal of Chemcal and Pharmaceutcal Research, 2014, 6(7):1884-1889 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCPRC5 A hybrd global optmzaton algorthm based on parallel

More information

Human behaviour analysis and event recognition at a point of sale

Human behaviour analysis and event recognition at a point of sale Human behavour analyss and event recognton at a pont of sale R. Scre MIRANE S.A.S. Cenon, France scre@labr.fr H. Ncolas LaBRI, Unversty of Bordeaux Talence, France ncolas@labr.fr Abstract Ths paper presents

More information

Texture Analysis and Modified Level Set Method for Automatic Detection of Bone Boundaries in Hand Radiographs

Texture Analysis and Modified Level Set Method for Automatic Detection of Bone Boundaries in Hand Radiographs Texture Analyss and Modfed Level Set Method for Automatc Detecton of Bone Boundares n Hand Radographs Syaful Anam Graduate School of Scence and Engneerng Yamaguch Unversty Yamaguch, Japan Department of

More information

Single and multiple stage classifiers implementing logistic discrimination

Single and multiple stage classifiers implementing logistic discrimination Sngle and multple stage classfers mplementng logstc dscrmnaton Hélo Radke Bttencourt 1 Dens Alter de Olvera Moraes 2 Vctor Haertel 2 1 Pontfíca Unversdade Católca do Ro Grande do Sul - PUCRS Av. Ipranga,

More information

Conversion between the vector and raster data structures using Fuzzy Geographical Entities

Conversion between the vector and raster data structures using Fuzzy Geographical Entities Converson between the vector and raster data structures usng Fuzzy Geographcal Enttes Cdála Fonte Department of Mathematcs Faculty of Scences and Technology Unversty of Combra, Apartado 38, 3 454 Combra,

More information

A Hierarchical Anomaly Network Intrusion Detection System using Neural Network Classification

A Hierarchical Anomaly Network Intrusion Detection System using Neural Network Classification IDC IDC A Herarchcal Anomaly Network Intruson Detecton System usng Neural Network Classfcaton ZHENG ZHANG, JUN LI, C. N. MANIKOPOULOS, JAY JORGENSON and JOSE UCLES ECE Department, New Jersey Inst. of Tech.,

More information

Product Quality and Safety Incident Information Tracking Based on Web

Product Quality and Safety Incident Information Tracking Based on Web Product Qualty and Safety Incdent Informaton Trackng Based on Web News 1 Yuexang Yang, 2 Correspondng Author Yyang Wang, 2 Shan Yu, 2 Jng Q, 1 Hual Ca 1 Chna Natonal Insttute of Standardzaton, Beng 100088,

More information

THE APPLICATION OF DATA MINING TECHNIQUES AND MULTIPLE CLASSIFIERS TO MARKETING DECISION

THE APPLICATION OF DATA MINING TECHNIQUES AND MULTIPLE CLASSIFIERS TO MARKETING DECISION Internatonal Journal of Electronc Busness Management, Vol. 3, No. 4, pp. 30-30 (2005) 30 THE APPLICATION OF DATA MINING TECHNIQUES AND MULTIPLE CLASSIFIERS TO MARKETING DECISION Yu-Mn Chang *, Yu-Cheh

More information

VEHICLE DETECTION BY USING REAR PARTS AND TRACKING SYSTEM

VEHICLE DETECTION BY USING REAR PARTS AND TRACKING SYSTEM IJRET: Internatonal Journal of Research n Engneerng and Technology eissn: 2319-1163 pissn: 2321-7308 VEHICLE DETECTION BY USING REAR PARTS AND TRACKING SYSTEM Yogn Ashokrao Kanhegaonkar 1, Jagtap Rupal

More information

Can Auto Liability Insurance Purchases Signal Risk Attitude?

Can Auto Liability Insurance Purchases Signal Risk Attitude? Internatonal Journal of Busness and Economcs, 2011, Vol. 10, No. 2, 159-164 Can Auto Lablty Insurance Purchases Sgnal Rsk Atttude? Chu-Shu L Department of Internatonal Busness, Asa Unversty, Tawan Sheng-Chang

More information

IMPACT ANALYSIS OF A CELLULAR PHONE

IMPACT ANALYSIS OF A CELLULAR PHONE 4 th ASA & μeta Internatonal Conference IMPACT AALYSIS OF A CELLULAR PHOE We Lu, 2 Hongy L Bejng FEAonlne Engneerng Co.,Ltd. Bejng, Chna ABSTRACT Drop test smulaton plays an mportant role n nvestgatng

More information

A Secure Password-Authenticated Key Agreement Using Smart Cards

A Secure Password-Authenticated Key Agreement Using Smart Cards A Secure Password-Authentcated Key Agreement Usng Smart Cards Ka Chan 1, Wen-Chung Kuo 2 and Jn-Chou Cheng 3 1 Department of Computer and Informaton Scence, R.O.C. Mltary Academy, Kaohsung 83059, Tawan,

More information

How To Create An Emoton Recognzer

How To Create An Emoton Recognzer Recognzng Low/Hgh Anger n Speech for Call Centers FU-MING LEE*, LI-HUA LI, RU-YI HUANG Department of Informaton Management Chaoyang Unversty of Technology 168 Jfong E. Rd., Wufong Townshp Tachung County,

More information

An Enhanced Super-Resolution System with Improved Image Registration, Automatic Image Selection, and Image Enhancement

An Enhanced Super-Resolution System with Improved Image Registration, Automatic Image Selection, and Image Enhancement An Enhanced Super-Resoluton System wth Improved Image Regstraton, Automatc Image Selecton, and Image Enhancement Yu-Chuan Kuo ( ), Chen-Yu Chen ( ), and Chou-Shann Fuh ( ) Department of Computer Scence

More information

Improved SVM in Cloud Computing Information Mining

Improved SVM in Cloud Computing Information Mining Internatonal Journal of Grd Dstrbuton Computng Vol.8, No.1 (015), pp.33-40 http://dx.do.org/10.1457/jgdc.015.8.1.04 Improved n Cloud Computng Informaton Mnng Lvshuhong (ZhengDe polytechnc college JangSu

More information

CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK. Sample Stability Protocol

CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK. Sample Stability Protocol CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK Sample Stablty Protocol Background The Cholesterol Reference Method Laboratory Network (CRMLN) developed certfcaton protocols for total cholesterol, HDL

More information

Forensic Handwritten Document Retrieval System

Forensic Handwritten Document Retrieval System Forensc Handwrtten Document Retreval System Sargur N SRIHARI and Zhxn SHI + Center of Excellence for Document Analyss and Recognton (CEDAR), Unversty at Buffalo, State Unversty of New York, Buffalo, USA

More information

Damage detection in composite laminates using coin-tap method

Damage detection in composite laminates using coin-tap method Damage detecton n composte lamnates usng con-tap method S.J. Km Korea Aerospace Research Insttute, 45 Eoeun-Dong, Youseong-Gu, 35-333 Daejeon, Republc of Korea yaeln@kar.re.kr 45 The con-tap test has the

More information

Bag-of-Words models. Lecture 9. Slides from: S. Lazebnik, A. Torralba, L. Fei-Fei, D. Lowe, C. Szurka

Bag-of-Words models. Lecture 9. Slides from: S. Lazebnik, A. Torralba, L. Fei-Fei, D. Lowe, C. Szurka Bag-of-Words models Lecture 9 Sldes from: S. Lazebnk, A. Torralba, L. Fe-Fe, D. Lowe, C. Szurka Bag-of-features models Overvew: Bag-of-features models Orgns and motvaton Image representaton Dscrmnatve

More information

On-Line Fault Detection in Wind Turbine Transmission System using Adaptive Filter and Robust Statistical Features

On-Line Fault Detection in Wind Turbine Transmission System using Adaptive Filter and Robust Statistical Features On-Lne Fault Detecton n Wnd Turbne Transmsson System usng Adaptve Flter and Robust Statstcal Features Ruoyu L Remote Dagnostcs Center SKF USA Inc. 3443 N. Sam Houston Pkwy., Houston TX 77086 Emal: ruoyu.l@skf.com

More information

Statistical Methods to Develop Rating Models

Statistical Methods to Develop Rating Models Statstcal Methods to Develop Ratng Models [Evelyn Hayden and Danel Porath, Österrechsche Natonalbank and Unversty of Appled Scences at Manz] Source: The Basel II Rsk Parameters Estmaton, Valdaton, and

More information

Searching for Interacting Features for Spam Filtering

Searching for Interacting Features for Spam Filtering Searchng for Interactng Features for Spam Flterng Chuanlang Chen 1, Yun-Chao Gong 2, Rongfang Be 1,, and X. Z. Gao 3 1 Department of Computer Scence, Bejng Normal Unversty, Bejng 100875, Chna 2 Software

More information

Risk-based Fatigue Estimate of Deep Water Risers -- Course Project for EM388F: Fracture Mechanics, Spring 2008

Risk-based Fatigue Estimate of Deep Water Risers -- Course Project for EM388F: Fracture Mechanics, Spring 2008 Rsk-based Fatgue Estmate of Deep Water Rsers -- Course Project for EM388F: Fracture Mechancs, Sprng 2008 Chen Sh Department of Cvl, Archtectural, and Envronmental Engneerng The Unversty of Texas at Austn

More information

Parallel Numerical Simulation of Visual Neurons for Analysis of Optical Illusion

Parallel Numerical Simulation of Visual Neurons for Analysis of Optical Illusion 212 Thrd Internatonal Conference on Networkng and Computng Parallel Numercal Smulaton of Vsual Neurons for Analyss of Optcal Illuson Akra Egashra, Shunj Satoh, Hdetsugu Ire and Tsutomu Yoshnaga Graduate

More information

An Evaluation of the Extended Logistic, Simple Logistic, and Gompertz Models for Forecasting Short Lifecycle Products and Services

An Evaluation of the Extended Logistic, Simple Logistic, and Gompertz Models for Forecasting Short Lifecycle Products and Services An Evaluaton of the Extended Logstc, Smple Logstc, and Gompertz Models for Forecastng Short Lfecycle Products and Servces Charles V. Trappey a,1, Hsn-yng Wu b a Professor (Management Scence), Natonal Chao

More information

An Alternative Way to Measure Private Equity Performance

An Alternative Way to Measure Private Equity Performance An Alternatve Way to Measure Prvate Equty Performance Peter Todd Parlux Investment Technology LLC Summary Internal Rate of Return (IRR) s probably the most common way to measure the performance of prvate

More information

Document Clustering Analysis Based on Hybrid PSO+K-means Algorithm

Document Clustering Analysis Based on Hybrid PSO+K-means Algorithm Document Clusterng Analyss Based on Hybrd PSO+K-means Algorthm Xaohu Cu, Thomas E. Potok Appled Software Engneerng Research Group, Computatonal Scences and Engneerng Dvson, Oak Rdge Natonal Laboratory,

More information

Who are you with and Where are you going?

Who are you with and Where are you going? Who are you wth and Where are you gong? Kota Yamaguch Alexander C. Berg Lus E. Ortz Tamara L. Berg Stony Brook Unversty Stony Brook Unversty, NY 11794, USA {kyamagu, aberg, leortz, tlberg}@cs.stonybrook.edu

More information

"Research Note" APPLICATION OF CHARGE SIMULATION METHOD TO ELECTRIC FIELD CALCULATION IN THE POWER CABLES *

Research Note APPLICATION OF CHARGE SIMULATION METHOD TO ELECTRIC FIELD CALCULATION IN THE POWER CABLES * Iranan Journal of Scence & Technology, Transacton B, Engneerng, ol. 30, No. B6, 789-794 rnted n The Islamc Republc of Iran, 006 Shraz Unversty "Research Note" ALICATION OF CHARGE SIMULATION METHOD TO ELECTRIC

More information

Traffic State Estimation in the Traffic Management Center of Berlin

Traffic State Estimation in the Traffic Management Center of Berlin Traffc State Estmaton n the Traffc Management Center of Berln Authors: Peter Vortsch, PTV AG, Stumpfstrasse, D-763 Karlsruhe, Germany phone ++49/72/965/35, emal peter.vortsch@ptv.de Peter Möhl, PTV AG,

More information

Calculating the high frequency transmission line parameters of power cables

Calculating the high frequency transmission line parameters of power cables < ' Calculatng the hgh frequency transmsson lne parameters of power cables Authors: Dr. John Dcknson, Laboratory Servces Manager, N 0 RW E B Communcatons Mr. Peter J. Ncholson, Project Assgnment Manager,

More information

NEURO-FUZZY INFERENCE SYSTEM FOR E-COMMERCE WEBSITE EVALUATION

NEURO-FUZZY INFERENCE SYSTEM FOR E-COMMERCE WEBSITE EVALUATION NEURO-FUZZY INFERENE SYSTEM FOR E-OMMERE WEBSITE EVALUATION Huan Lu, School of Software, Harbn Unversty of Scence and Technology, Harbn, hna Faculty of Appled Mathematcs and omputer Scence, Belarusan State

More information

A DATA MINING APPLICATION IN A STUDENT DATABASE

A DATA MINING APPLICATION IN A STUDENT DATABASE JOURNAL OF AERONAUTICS AND SPACE TECHNOLOGIES JULY 005 VOLUME NUMBER (53-57) A DATA MINING APPLICATION IN A STUDENT DATABASE Şenol Zafer ERDOĞAN Maltepe Ünversty Faculty of Engneerng Büyükbakkalköy-Istanbul

More information

CONSISTENT VEHICLES TRACKING BY USING A COOPERATIVE DISTRIBUTED VIDEO SURVEILLANCESYSTEM

CONSISTENT VEHICLES TRACKING BY USING A COOPERATIVE DISTRIBUTED VIDEO SURVEILLANCESYSTEM Internatonal Research Journal of Appled and Basc Scences 2013 Avalable onlne at www.rjabs.com ISSN 2251-838X / Vol, 4 (12):3658-3663 Scence Explorer Publcatons CONSISTENT VEHICLES TRACKING BY USING A COOPERATIVE

More information

Hallucinating Multiple Occluded CCTV Face Images of Different Resolutions

Hallucinating Multiple Occluded CCTV Face Images of Different Resolutions In Proc. IEEE Internatonal Conference on Advanced Vdeo and Sgnal based Survellance (AVSS 05), September 2005 Hallucnatng Multple Occluded CCTV Face Images of Dfferent Resolutons Ku Ja Shaogang Gong Computer

More information

Statistical Approach for Offline Handwritten Signature Verification

Statistical Approach for Offline Handwritten Signature Verification Journal of Computer Scence 4 (3): 181-185, 2008 ISSN 1549-3636 2008 Scence Publcatons Statstcal Approach for Offlne Handwrtten Sgnature Verfcaton 2 Debnath Bhattacharyya, 1 Samr Kumar Bandyopadhyay, 2

More information

Vehicle Detection, Classification and Position Estimation based on Monocular Video Data during Night-time

Vehicle Detection, Classification and Position Estimation based on Monocular Video Data during Night-time Vehcle Detecton, Classfcaton and Poston Estmaton based on Monocular Vdeo Data durng Nght-tme Jonas Frl, Marko H. Hoerter, Martn Lauer and Chrstoph Stller Keywords: Automotve Lghtng, Lght-based Drver Assstance,

More information

FREQUENCY OF OCCURRENCE OF CERTAIN CHEMICAL CLASSES OF GSR FROM VARIOUS AMMUNITION TYPES

FREQUENCY OF OCCURRENCE OF CERTAIN CHEMICAL CLASSES OF GSR FROM VARIOUS AMMUNITION TYPES FREQUENCY OF OCCURRENCE OF CERTAIN CHEMICAL CLASSES OF GSR FROM VARIOUS AMMUNITION TYPES Zuzanna BRO EK-MUCHA, Grzegorz ZADORA, 2 Insttute of Forensc Research, Cracow, Poland 2 Faculty of Chemstry, Jagellonan

More information

Performance Analysis and Coding Strategy of ECOC SVMs

Performance Analysis and Coding Strategy of ECOC SVMs Internatonal Journal of Grd and Dstrbuted Computng Vol.7, No. (04), pp.67-76 http://dx.do.org/0.457/jgdc.04.7..07 Performance Analyss and Codng Strategy of ECOC SVMs Zhgang Yan, and Yuanxuan Yang, School

More information

Adaptive Fractal Image Coding in the Frequency Domain

Adaptive Fractal Image Coding in the Frequency Domain PROCEEDINGS OF INTERNATIONAL WORKSHOP ON IMAGE PROCESSING: THEORY, METHODOLOGY, SYSTEMS AND APPLICATIONS 2-22 JUNE,1994 BUDAPEST,HUNGARY Adaptve Fractal Image Codng n the Frequency Doman K AI UWE BARTHEL

More information

Biometric Signature Processing & Recognition Using Radial Basis Function Network

Biometric Signature Processing & Recognition Using Radial Basis Function Network Bometrc Sgnature Processng & Recognton Usng Radal Bass Functon Network Ankt Chadha, Neha Satam, and Vbha Wal Abstract- Automatc recognton of sgnature s a challengng problem whch has receved much attenton

More information

Faraday's Law of Induction

Faraday's Law of Induction Introducton Faraday's Law o Inducton In ths lab, you wll study Faraday's Law o nducton usng a wand wth col whch swngs through a magnetc eld. You wll also examne converson o mechanc energy nto electrc energy

More information

Descriptive Models. Cluster Analysis. Example. General Applications of Clustering. Examples of Clustering Applications

Descriptive Models. Cluster Analysis. Example. General Applications of Clustering. Examples of Clustering Applications CMSC828G Prncples of Data Mnng Lecture #9 Today s Readng: HMS, chapter 9 Today s Lecture: Descrptve Modelng Clusterng Algorthms Descrptve Models model presents the man features of the data, a global summary

More information

Institute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic

Institute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic Lagrange Multplers as Quanttatve Indcators n Economcs Ivan Mezník Insttute of Informatcs, Faculty of Busness and Management, Brno Unversty of TechnologCzech Republc Abstract The quanttatve role of Lagrange

More information

Automated information technology for ionosphere monitoring of low-orbit navigation satellite signals

Automated information technology for ionosphere monitoring of low-orbit navigation satellite signals Automated nformaton technology for onosphere montorng of low-orbt navgaton satellte sgnals Alexander Romanov, Sergey Trusov and Alexey Romanov Federal State Untary Enterprse Russan Insttute of Space Devce

More information

Properties of Indoor Received Signal Strength for WLAN Location Fingerprinting

Properties of Indoor Received Signal Strength for WLAN Location Fingerprinting Propertes of Indoor Receved Sgnal Strength for WLAN Locaton Fngerprntng Kamol Kaemarungs and Prashant Krshnamurthy Telecommuncatons Program, School of Informaton Scences, Unversty of Pttsburgh E-mal: kakst2,prashk@ptt.edu

More information

The Journal of Systems and Software

The Journal of Systems and Software The Journal of Systems and Software 82 (2009) 241 252 Contents lsts avalable at ScenceDrect The Journal of Systems and Software journal homepage: www. elsever. com/ locate/ jss A study of project selecton

More information

INVESTIGATION OF VEHICULAR USERS FAIRNESS IN CDMA-HDR NETWORKS

INVESTIGATION OF VEHICULAR USERS FAIRNESS IN CDMA-HDR NETWORKS 21 22 September 2007, BULGARIA 119 Proceedngs of the Internatonal Conference on Informaton Technologes (InfoTech-2007) 21 st 22 nd September 2007, Bulgara vol. 2 INVESTIGATION OF VEHICULAR USERS FAIRNESS

More information

Lecture 2: Single Layer Perceptrons Kevin Swingler

Lecture 2: Single Layer Perceptrons Kevin Swingler Lecture 2: Sngle Layer Perceptrons Kevn Sngler kms@cs.str.ac.uk Recap: McCulloch-Ptts Neuron Ths vastly smplfed model of real neurons s also knon as a Threshold Logc Unt: W 2 A Y 3 n W n. A set of synapses

More information

A Multi-Camera System on PC-Cluster for Real-time 3-D Tracking

A Multi-Camera System on PC-Cluster for Real-time 3-D Tracking The 23 rd Conference of the Mechancal Engneerng Network of Thaland November 4 7, 2009, Chang Ma A Mult-Camera System on PC-Cluster for Real-tme 3-D Trackng Vboon Sangveraphunsr*, Krtsana Uttamang, and

More information

The OC Curve of Attribute Acceptance Plans

The OC Curve of Attribute Acceptance Plans The OC Curve of Attrbute Acceptance Plans The Operatng Characterstc (OC) curve descrbes the probablty of acceptng a lot as a functon of the lot s qualty. Fgure 1 shows a typcal OC Curve. 10 8 6 4 1 3 4

More information

Calculation of Sampling Weights

Calculation of Sampling Weights Perre Foy Statstcs Canada 4 Calculaton of Samplng Weghts 4.1 OVERVIEW The basc sample desgn used n TIMSS Populatons 1 and 2 was a two-stage stratfed cluster desgn. 1 The frst stage conssted of a sample

More information

Characterization of Assembly. Variation Analysis Methods. A Thesis. Presented to the. Department of Mechanical Engineering. Brigham Young University

Characterization of Assembly. Variation Analysis Methods. A Thesis. Presented to the. Department of Mechanical Engineering. Brigham Young University Characterzaton of Assembly Varaton Analyss Methods A Thess Presented to the Department of Mechancal Engneerng Brgham Young Unversty In Partal Fulfllment of the Requrements for the Degree Master of Scence

More information

PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 12

PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 12 14 The Ch-squared dstrbuton PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 1 If a normal varable X, havng mean µ and varance σ, s standardsed, the new varable Z has a mean 0 and varance 1. When ths standardsed

More information

L10: Linear discriminants analysis

L10: Linear discriminants analysis L0: Lnear dscrmnants analyss Lnear dscrmnant analyss, two classes Lnear dscrmnant analyss, C classes LDA vs. PCA Lmtatons of LDA Varants of LDA Other dmensonalty reducton methods CSCE 666 Pattern Analyss

More information

Data Broadcast on a Multi-System Heterogeneous Overlayed Wireless Network *

Data Broadcast on a Multi-System Heterogeneous Overlayed Wireless Network * JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 24, 819-840 (2008) Data Broadcast on a Mult-System Heterogeneous Overlayed Wreless Network * Department of Computer Scence Natonal Chao Tung Unversty Hsnchu,

More information

Using Supervised Clustering Technique to Classify Received Messages in 137 Call Center of Tehran City Council

Using Supervised Clustering Technique to Classify Received Messages in 137 Call Center of Tehran City Council Usng Supervsed Clusterng Technque to Classfy Receved Messages n 137 Call Center of Tehran Cty Councl Mahdyeh Haghr 1*, Hamd Hassanpour 2 (1) Informaton Technology engneerng/e-commerce, Shraz Unversty (2)

More information

Cluster Analysis of Data Points using Partitioning and Probabilistic Model-based Algorithms

Cluster Analysis of Data Points using Partitioning and Probabilistic Model-based Algorithms Internatonal Journal of Appled Informaton Systems (IJAIS) ISSN : 2249-0868 Foundaton of Computer Scence FCS, New York, USA Volume 7 No.7, August 2014 www.jas.org Cluster Analyss of Data Ponts usng Parttonng

More information

3D SURFACE RECONSTRUCTION AND ANALYSIS IN AUTOMATED APPLE STEM END/CALYX IDENTIFICATION

3D SURFACE RECONSTRUCTION AND ANALYSIS IN AUTOMATED APPLE STEM END/CALYX IDENTIFICATION 3D SURFACE RECONSTRUCTION AND ANALYSIS IN AUTOMATED APPLE STEM END/CALYX IDENTIFICATION L. Jang, B. Zhu, X. Cheng, Y. Luo, Y. Tao ABSTRACT. Machne vson methods are wdely used n apple defect detecton and

More information

Disagreement-Based Multi-System Tracking

Disagreement-Based Multi-System Tracking Dsagreement-Based Mult-System Trackng Quannan L 1, Xnggang Wang 2, We Wang 3, Yuan Jang 3, Zh-Hua Zhou 3, Zhuowen Tu 1 1 Lab of Neuro Imagng, Unversty of Calforna, Los Angeles 2 Huazhong Unversty of Scence

More information

Fast Fuzzy Clustering of Web Page Collections

Fast Fuzzy Clustering of Web Page Collections Fast Fuzzy Clusterng of Web Page Collectons Chrstan Borgelt and Andreas Nürnberger Dept. of Knowledge Processng and Language Engneerng Otto-von-Guercke-Unversty of Magdeburg Unverstätsplatz, D-396 Magdeburg,

More information

RESEARCH ON DUAL-SHAKER SINE VIBRATION CONTROL. Yaoqi FENG 1, Hanping QIU 1. China Academy of Space Technology (CAST) yaoqi.feng@yahoo.

RESEARCH ON DUAL-SHAKER SINE VIBRATION CONTROL. Yaoqi FENG 1, Hanping QIU 1. China Academy of Space Technology (CAST) yaoqi.feng@yahoo. ICSV4 Carns Australa 9- July, 007 RESEARCH ON DUAL-SHAKER SINE VIBRATION CONTROL Yaoq FENG, Hanpng QIU Dynamc Test Laboratory, BISEE Chna Academy of Space Technology (CAST) yaoq.feng@yahoo.com Abstract

More information

Master s Thesis. Configuring robust virtual wireless sensor networks for Internet of Things inspired by brain functional networks

Master s Thesis. Configuring robust virtual wireless sensor networks for Internet of Things inspired by brain functional networks Master s Thess Ttle Confgurng robust vrtual wreless sensor networks for Internet of Thngs nspred by bran functonal networks Supervsor Professor Masayuk Murata Author Shnya Toyonaga February 10th, 2014

More information

Support Vector Machines

Support Vector Machines Support Vector Machnes Max Wellng Department of Computer Scence Unversty of Toronto 10 Kng s College Road Toronto, M5S 3G5 Canada wellng@cs.toronto.edu Abstract Ths s a note to explan support vector machnes.

More information

Detecting Credit Card Fraud using Periodic Features

Detecting Credit Card Fraud using Periodic Features Detectng Credt Card Fraud usng Perodc Features Alejandro Correa Bahnsen, Djamla Aouada, Aleksandar Stojanovc and Björn Ottersten Interdscplnary Centre for Securty, Relablty and Trust Unversty of Luxembourg,

More information

Assessing Student Learning Through Keyword Density Analysis of Online Class Messages

Assessing Student Learning Through Keyword Density Analysis of Online Class Messages Assessng Student Learnng Through Keyword Densty Analyss of Onlne Class Messages Xn Chen New Jersey Insttute of Technology xc7@njt.edu Brook Wu New Jersey Insttute of Technology wu@njt.edu ABSTRACT Ths

More information

Frequency Selective IQ Phase and IQ Amplitude Imbalance Adjustments for OFDM Direct Conversion Transmitters

Frequency Selective IQ Phase and IQ Amplitude Imbalance Adjustments for OFDM Direct Conversion Transmitters Frequency Selectve IQ Phase and IQ Ampltude Imbalance Adjustments for OFDM Drect Converson ransmtters Edmund Coersmeer, Ernst Zelnsk Noka, Meesmannstrasse 103, 44807 Bochum, Germany edmund.coersmeer@noka.com,

More information

Automated Mobile ph Reader on a Camera Phone

Automated Mobile ph Reader on a Camera Phone Automated Moble ph Reader on a Camera Phone B.Y. Loh, N.K. Vuong, S. Chan and C.. Lau AbstractA robust classfcaton algorthm that apples color scence and mage processng technques s developed to automatcally

More information

Performance Analysis of Energy Consumption of Smartphone Running Mobile Hotspot Application

Performance Analysis of Energy Consumption of Smartphone Running Mobile Hotspot Application Internatonal Journal of mart Grd and lean Energy Performance Analyss of Energy onsumpton of martphone Runnng Moble Hotspot Applcaton Yun on hung a chool of Electronc Engneerng, oongsl Unversty, 511 angdo-dong,

More information

Vibration Analysis using Time Domain Methods for the Detection of small Roller Bearing Defects

Vibration Analysis using Time Domain Methods for the Detection of small Roller Bearing Defects SIRM 9-8th Internatonal Conference on Vbratons n Rotatng Machnes, Venna, Austra, 3-5 February 9 Vbraton Analyss usng Tme Doman Methods for the Detecton of small Roller Bearng Defects Tahsn Doguer Insttut

More information

Liptracking and MPEG4 Animation with Feedback Control

Liptracking and MPEG4 Animation with Feedback Control Lptrackng and MPEG4 Anmaton wth Feedback Control Brce Beaumesnl, Franck Luthon, Marc Chaumont To cte ths verson: Brce Beaumesnl, Franck Luthon, Marc Chaumont. Lptrackng and MPEG4 Anmaton wth Feedback Control.

More information

Optical Measurement of the Speed of Sound in Air Over the Temperature Range 300-650 K

Optical Measurement of the Speed of Sound in Air Over the Temperature Range 300-650 K NASA/CR-2000-210114 ICASE Report No. 2000-20 Optcal Measurement of the Speed of Sound n Ar Over the Temperature Range 300-650 K Roger C. Hart ICASE, Hampton, Vrgna R. Jeffrey Balla and G.C. Herrng NASA

More information

Brigid Mullany, Ph.D University of North Carolina, Charlotte

Brigid Mullany, Ph.D University of North Carolina, Charlotte Evaluaton And Comparson Of The Dfferent Standards Used To Defne The Postonal Accuracy And Repeatablty Of Numercally Controlled Machnng Center Axes Brgd Mullany, Ph.D Unversty of North Carolna, Charlotte

More information

A spam filtering model based on immune mechanism

A spam filtering model based on immune mechanism Avalable onlne www.jocpr.com Journal of Chemcal and Pharmaceutcal Research, 2014, 6(7):2533-2540 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCPRC5 A spam flterng model based on mmune mechansm Ya-png

More information