Audio-Visual Voice Command Recognition in Noisy Conditions

Size: px
Start display at page:

Download "Audio-Visual Voice Command Recognition in Noisy Conditions"

Transcription

1 Audio-Viual Voice Command Recognition in Noiy Condition Joef Chaloupka, Jan Nouza, Jindrich Zdanky Laboratory of Computer Speech Proceing, Intitute of Information Technology and Electronic, Technical Univerity of Liberec, Czech Republic Abtract Thi paper preent an experiment of audio-viual voice command recognition from mall vocabulary in imulated noiy condition. Electric and electronic device hould be controlled by thee voice command mainly in home of motor-handicapped people and viual part of peech could improve recognition rate if a noie i relatively trong. Therefore the main aim of thi experiment were to find out how viual part of peech can improve reulting recognition rate and if it i poible to ue uccefully two-tream Hidden Markov Model (HMM) for audio-viual voice command recognition. Index Term: audio-viual peech recognition in noiy condition, voice control of electric and electronic home device 1. Introduction The main reearch area of our Laboratory of computer peech proceing i automatic continuou peech recognition mainly for Czech language. Czech language belong to the inflectional language therefore recognizer lexicon and correponding language model i larger and different than e.g. for Englih. We have developed our own on-line peech recognizer which ue a lexicon of 30,000 mot frequent Czech word and it cover 99% of Czech independent text. Thi recognizer i ued for continuou peech dictation or for automatic broadcat programme trancription ytem [1]. Our next activitie are focued on the creation of tool for motor-handicapped people. In 005, we have developed oftware for voice control of a PC by voice command the ytem MyVoice []. More than 50 motor-handicapped people are uing thi ytem at preent. Handicapped people have different electric and electronic device (TV, radio, HI- FI, DVD, light, heating, air-condition, roller blind etc.) at home but they cannot control thee device therefore a ytem for voice control of different electric and electronic device ha been created [3] for them and thi ytem i connected with program MyVoice. But the problem i that ome of thee device produce noie o the recognition rate i lower in noiy condition. It would be poible to ue ome method for filtration of noie or to ue more microphone and method for blind eparation but we wanted to ue method for audio-viual recognition becaue motor handicapped people it in front of monitor without movement and becaue viual part of a peech can improve recognition rate in noiy condition. Proceing of a viual peech ignal i time demanding but PC are relatively fat at preent or it i poible to ue cluter of PC therefore ome ytem for large-vocabulary audioviual peech recognition were developed [4] till thi time (008). Word recognition in ytem MyVoice i baed on HMM of Czech phoneme. What hould be done next i to create the Czech audio-viual databae for training the HMM of vieme. Creation of uch a databae i very time conuming and expenive therefore we have decided that a mall audio-viual databae with mall-vocabulary will be created and whole-word HMM will be trained from thi databae and thee audio-viual HMM will be ued a pecial module unit to oftware MyVoice. Vocabulary wa created from voice command for controlling of mot common home device - light, electric heating, air condition and TV. Device i witched on by one voice command and it i witched off by the ame voice command if it i pronounced for econd time therefore vocabulary ha only 0 word including voice command for controlling of TV. The main idea of thi work wa to find out how viual part of peech can improve recognition rate in noiy condition or if it i poible to ue viual peech recognition only from mall vocabulary. The firt tak wa audio and viual feature extraction for audio-viual voice command recognition:. Audio and Viual Feature Extraction.1. Audio Feature Extraction Extraction of audio feature i relatively well-olved tak in automatic audio peech recognition reearch area at preent therefore tandard method were ued in thi work too. The audio ignal wa pre-proceed and it wa divided into 33.3 m frame without overlap m frame wa elected becaue viual tream wa ampled at 30 frame (video image) per econd (fp) and we wanted to have the ame time length of audio and viual frame becaue of next audioviual feature fuion. 13 Mel-Frequency Ceptral Coefficient (MFCC) were elected a audio feature and delta (dynamic) and delta-delta (acceleration) feature were calculated from thee MFCC feature between adjacent frame o 39 audio feature were ued.... Viual Feature Extraction It i poible to divide viual feature to three group [5]: Appearance-baed viual feature, hape-baed viual feature or combination of both. It i neceary to find hape of lip in video image for extraction of hape viual feature and it can be a difficult tak therefore appearance-baed viual feature are ued more often. Appearance-baed viual feature are computed from Region of Interet (ROI) with the help of ome linear tranform like Dicrete Coine Tranform (DCT), Principal Component Analyi (PCA), Dicrete Wavelet Tranform (DWT) etc. DCT i mot popular becaue of the exitence of a fat algorithm for computation of thi tranform. We ued hape and DCT viual feature in our previou work [6] and utilization of DCT feature gave to u the bet reult therefore DCT feature were ued in thi work too. Copyright 008 AVISA Accepted after peer review of full paper September 008, Moreton Iland, Autralia

2 Figure 1: Principle of audio-viual voice command recog. A method for extraction of thee viual feature i decribed below. It i neceary to find ROI for the extraction of DCT viual feature in the firt tep:..1. Region of Interet A region of interet for viual feature extraction i a quare or rectangular area of video image which contain peaker mouth area. It i a very difficult tak to find directly peaker mouth in a real video image therefore human face i detected firt and the mouth i located in the bottom part of a detected face. We have ued a method baed on haar-like filter [7] together with color image egmentation. Some probable region are located in image by haar-like filter which were trained from face or non-face image but ome non-face object which have imilar tructure to human face are ometime elected. Therefore color image egmentation i ued in the econd tep. All pixel which have imilar color to human kin are et to value 1 other pixel have value 0. Color image egmentation method baed on threholding wa ued for thi purpoe. Threhold were et from our human kin image databae. More than 000 image of a human face are in thi databae where all pixel, which are not from human kin, were manually removed from thee image. So region from haar-like filter method are elected a human face if at leat 40% of kin-like pixel were found in thi region. An object of mouth i located in the bottom part of face by color image egmentation but threhold for thi method ha been et automatically by algorithm baed on etimation of image hitogram [8]. Centre of gravity of mouth object and width of mouth i computed next. ROI of dimenion of 18 x 18 pixel i then elected around the centre of gravity o that the width of mouth would be 100 pixel therefore the original image i reized according to the mouth width. We have only one human peaker in our video recording therefore the tak of identification who i peaking wa not olved in our work.... DCT Viual Feature The extraction of DCT viual feature i performed by dicrete coine tranform which i calculated from image of ROI. A color ROI image i tranformed to gray-level and hitogram flattening method i applied to thi image at firt and DCT coefficient are calculated from ROI after that. Viual feature are elected from DCT coefficient according to the highet energy, variance, or ome other trategie are ued, e.g. viual feature election i baed on mutual Figure : Normalization of DCT viual feature. information [9]. Viual DCT feature election baed on the highet energy wa ued in thi work becaue it i imple, fat, and it give good reult [6]. DCT viual feature are normalized after election. Normalization of DCT viual feature i very important becaue the reulting recognition rate i relatively low without normalization or it i impoible to train HMM. Our normalization i implemented a follow: Logarithmic calculation of DCT viual feature i ued in the firt tep and Feature Mean Subtraction (FMS) i applied on viual feature vector in the econd tep, ee fig.. Delta and delta-delta feature are computed from tatic DCT viual feature by caual difference y f (i, j) = x f (i, j) x f (i 1, j), where y f i delta (or delta-delta) feature, x f i tatic (or delta) feature, i i index of frame and j i index of feature in feature vector of a ingle frame. 3. Audio-Viual Integration Several different method and algorithm have been propoed for audio-viual peech data fuion, like direct integration, eparate integration, motor recoding fuion, dominant recoding fuion, etc. [5]. We have ued HTK toolkit [10] for recognition of iolated word by HMM technique o we wanted to try the poibility of feature fuion where twotream HMM are trained from audio and viual feature. Audio feature vector wa ued for the firt tream and viual feature vector for the econd tream. The output HMM tate probability b of two-tream HMM i the following: b T M ctm t 1 m1 exp 0.5 x P 1 det tm T 1 x xtm tmx xtm t Where x i feature vector (audio or viual), P i number of feature, x i feature mean vector, i covariance matrix, M i number of mixture component in one tate, c m i the weight of mixture component, T i number of tream (T = in our cae) and t i a tream weight coefficient. 4. Signal to Noie Ratio Etimation Signal to Noie Ratio (SNR) wa neceary to etimate in our audio peech ignal before experiment. SNR i calculated (1) 6

3 from power of ignal P and from power of noie P n (which i added to ignal). N 1 i0 i P i0 SNR 10.log 10.log () N 1 Pn n i where N i the number of ample from ignal, [i] are ample from clear ignal (without noie), n[i] are ample from noie ignal which i included in original audio ignal x. Our hypothei wa that noie n i additive noie therefore x[i] = [i] + n[i]. P wa etimated from the power of audio ignal P x and from P n which wa computed from non-peech part of audio ignal - peech or non-peech detector wa ued for thi purpoe. N 1 N 1 N 1 i x i n i i0 i0 i0 P Px Pn (3) N N N A problem i that SNR () i computed from all peech ignal and dynamic change of peech ignal are not covered much [11] therefore egmental ignal to noie ratio SSNR give u a better reult: N 1 M 1 j i 1 i0 SSNR 10.log (4) N 1 F j0 n j i i0 where F i the number of frame from peech ignal and M i the length of one frame in ample. SSNR from audio ignal from our video databae wa about 1dB (SNR wa about 9dB), M wa et to 67 ample (33m for 8kHz ignal). 5. Noie Addition to Speech Signal Creation of a databae of audio recording with given SNR would be very difficult therefore noie i added artificially to audio ignal in tak of audio or audio-viual peech recognition in noie condition. An algorithm for noie addition to peech ignal wa developed for our next experiment. Additive noie ignal (babble, detroyer engine1, factory1, Volvo, pink and white noie) were ued from the NOISEX databae [1]. The algorithm wa the following: SSNR (SSNR e ) wa etimated from each audio ignal and noie ignal wa added according to given relative change of SSNR (SSNR). SSNR SSNR SSNR (5) w e where SNR w i new value of SSNR in audio ignal: SSNR P P x n w 10.log (6) Pn c. Pan P an i power of additive noie and c i gain coefficient: c P an P P x n SSNRw Pn P an Reulting audio ignal x n [i] i created from original ignal x[i] and from additive noie an[i]: x n (7) [ i] x[ i] an[ i]. c, 0 i N (8) 6. Experiment Our own audio-viual databae wa created for our experiment where 35 peaker narrated 0 word voice command for controlling of different home electric device. Human peaker were camera-canned from the front by imple web-camera. Parameter of video recording from thi databae are the following: Audio ample frequency i 8kHz (one ample 16bit.). Video frame rate i 30fp and ize of a ingle video image i 640 x 460 pixel. Audio and viual peech ignal from video recording wa proceed and parameterized and whole-word two-tream HMM were trained from parameterized ignal from 5 peaker. Video recording from additional 5 peaker were ued in reearch for finding of the weight for two-tream HMM, and video recording from thee lat 5 peaker were ued for voice command recognition in imulated noiy condition. 39 audio feature (13 MFCC + delta + delta-delta) and 15 viual feature (5 DCT + delta + delta-delta) were extracted from audio and viual ignal. 5 DCT viual feature were elected becaue the bet reult were obtained with thi number of feature in our previou experiment [6] of audio-viual iolated word recognition and the audioviual databae from thi work wa created in imilar condition to the previou one. Two-tream HMM had 14 tate and 1 mixture it would be neceary to have larger databae for more mixture. SSNR from audio ignal from our databae ha been counted about 1dB. The weight for audio and viual tream were found in the firt experiment. Additive noie wa added to audio ignal from the tet part of our databae, the weight for audio and viual tream in HMM were changed from 0 to 3 with tep 0.1 and the weight for given SSNR were choen according to the bet recognition rate. Figure 3: Recognition rate from audio-viual peech recognition for different audio and viual tream weight, where white noie wa added (SSNR 14 db). SSNR in audio ignal wa changed from 1dB to -4dB and the babble, detroyer engine1, factory1, Volvo (car), pink and white noie were ued a additive noie. The reult with detroyer engine1, factory1, and pink noie were relatively imilar to the reult with babble noie therefore only the reult with babble, Volvo and white noie are preented in table no. 1. and in fig Experiment with audio peech ignal recognition only (AASR) and video peech ignal recognition only (VASR) were made after that. One-tream HMM were trained from either audio or video feature and the recognition rate for VASR ha been 79% and 99% for AASR (SSNR 1dB). Trained two-tream HMM with the weight for given SSNR from the firt experiment were ued for voice command recognition in imulated noiy condition in the lat experiment where 0 word from the lat 5 peaker from our audio-viual databae were recognized, ee table no. 1. 7

4 7. Dicuion and Summary An addition of white noie to audio ignal had larget influence on rapid decline of recognition rate. On the other hand recognition rate from audio or audio-viual voice command recognition wa relatively high for low SSNR if car noie wa added to audio ignal. It i very intereting becaue the ame algorithm wa ued for addition of both noie type. Second intereting reult wa that recognition rate (67%) from audio-viual peech recognition experiment hould be lower than reult from viual peech recognition only (79%) if the weight of audio tream i 0. Reulting recognition rate wa expected 79%. Therefore next experiment were done where two-tream HMM were trained with audio weight = 0 and viual weight wa changed from 0.1 to 10 with tep of 0.1. The bet reult from thi experiment wa 69% for viual weight = 4.5 but it in t till 79%. Table 1. Reulting recognition rate [%] for audio only (AO) and audio-viual (AV) voice command recognition depending on different noie type, SSNR and audio (AW) and viual (VW) weight in AV. Figure 4: Recognition rate from audio, viual, audioviual (audio and viual weight = 1) and audio-viual (with different weight) peech recognition for different SSNR and for car noie. SNR [db] Noie Type White Noie Babble Noie Car Noie AO AV AW VW AO AV AW VW AO AV AW VW ,7, ,9, , ,6, ,9, , , ,6, , , ,8, ,5, , ,4, ,7, , ,, ,6 1, , ,, ,5, , ,1, , ,5, ,1, ,3, , ,1, ,, ,1, , ,3, , , ,4, ,5, , ,, ,8, , ,, ,8, , , , 1, , ,1, ,4, , ,1, ,, , , ,3, , , ,, , , ,1 1, , , ,1 1, , , ,, , , ,, , ,1 85 0,1 1,7 Figure 5: Recognition rate from audio, viual, audioviual (audio and viual weight = 1) and audio-viual (with different weight) peech recognition for different SSNR and for white noie. Maybe, ome pecial adjutment of HTK recognition or trained algorithm were created for fater calculation therefore it in t poible to get ame reult for viual and audio-viual (audio weight = 0) peech recognition. It i evident that audio weight (fig. 7) are different for different noie type for ame SSNR but the noie in the SmartRoom hould be very imilar a babble noie and reult from factory and detroyer engine were very imilar a reult with babble noie. Therefore HMM trained with weight from babble noie experiment were ued in our work where audioviual voice command recognition with mall vocabulary i ued a a pecial module in our ytem MyVoice []. Figure 6: Recognition rate from audio, viual, audioviual (audio and viual weight = 1) and audio-viual (with different weight) peech recognition for different SSNR and for babble noie. 8

5 Figure 7: Selected audio weight for AV ASR in different noiy condition. Human peaker i camera canned, SSNR i evaluated from audio ignal and applicable two-tream HMM are elected according to SSNR. Parameterization of one econd of audioviual peech ignal take about 1.5 econd (PC 3.4GHz) therefore it i poible to ue our audio-viual voice command recognizer in real condition. Utilization of two-tream HMM i poible only for mall vocabulary becaue we need everal HMM for ingle word (for different SSNR). Therefore it i better to ue ome another audio-viual fuion method for audio-viual peech recognition with large vocabulary. Experiment with car noie wa developed becaue we have wanted to know what influence ha a car noie on audio-viual peech recognition and the reult will be ued in our next work. 8. Acknowledgement The reearch wa upported partly by the Grant Agency of the Czech Academy of Science (grant no.1qs ) and partly by the internal grant provided by the Faculty of Mechatronic at the Technical Univerity of Liberec. 9. Reference [1] Nouza, J., Zdanky, J., Cerva, P. and Kolorenc J., Continual On-line Monitoring of Czech Spoken Broadcat Program, In: ICSLP 006, USA, pp , ISSN , 006 [] Nouza, J., Nouza, T. and Cerva, P., A Multi-Functional Voice- Control Aid for Diabled Peron, Proc. of Specom 005, Greece, pp , ISBN x, 005 [3] Nouza, J., Chaloupka, J., Zdanky, J., Silovky, J., Kroul, M. and Mader, Z., Voice Controlled Center for Home of Motor- Handicapped Peron, In: Speech and Computer International Conference, Ruia, pp , ISBN X, 007 [4] Potamiano, G., Neti, C., Iyengar, G. and Helmuth, E., Largevocabulary audio-viual peech recognition by machine and human, Proc. Europeech, Aalborg, 001. [5] Potamiano, G., Neti, C., Gravier,G., Garg, A. and Andrew, W., "Recent Advance in the Automatic Recognition of Audio- Viual Speech", Proc of the IEEE, Vol. 91, Iue 9, pp , ISSN , 003 [6] Chaloupka, J., Fat Method for Extraction of the Viual Speech Feature for Audio-Viual Speech Recognition, In: Specom 005, Greece, pp , ISBN x, 005 [7] Hong, K., Min, J., Lee, W. and Kim, J., Real Time Face Detection and Recognition Sytem Uing Haar-Like Feature/HMM in Ubiquitou Network Environment, In Lecture Note in Computer Science, Springer Berlin, Volume 3480, pp , ISBN , 005 [8] Chaloupka, J., Automatic Lip Reading for Audio-Viual Speech Proceing and Recognition, In: Proc. of ICSLP 004, Korea, pp , ISSN x, 004 [9] Scanlon, P., Potamiano, G., Libal, V. and CHU, S., M., Mutual Information Baed Viual Feature Selection for Lipreading In ICSLP 004, Korea, ISSN x, 004 [10] Steve, Y., Odel, J., OLLASON, D., Valtchev, V. and Woodland, P., The HTK Book, verion.1., In Cambr. Univ., UK, 1997 [11] Martin, R., An efficient algorithm to etimate the intantaneou SNR of peech ignal, In Europeech 1993, Germany, pp , 1993 [1] Varga, A., P., Steenekan, H., J., M., Tomlinon, M. and Jone, D., The noiex-9 tudy on the effect of additive noie on automatic peech recognition, Tech. Rep., DRA Speech Reearch Unit, 199 9

6 30

/06/$ IEEE 364

/06/$ IEEE 364 006 IEEE International ympoium on ignal Proceing and Information Technology oie Variance Etimation In ignal Proceing David Makovoz IPAC, California Intitute of Technology, MC-0, Paadena, CA, 95 davidm@ipac.caltech.edu;

More information

Modeling of underwater vehicle s dynamics

Modeling of underwater vehicle s dynamics Proceeding of the 11th WEA International Conference on YTEM, Agio Nikolao, Crete Iland, Greece, July 23-25, 2007 44 Modeling of underwater vehicle dynamic ANDRZEJ ZAK Department of Radiolocation and Hydrolocation

More information

Building a Compact On-line MRF Recognizer for Large Character Set using Structured Dictionary Representation and Vector Quantization Technique

Building a Compact On-line MRF Recognizer for Large Character Set using Structured Dictionary Representation and Vector Quantization Technique 202 International Conference on Frontier in Handwriting Recognition Building a Compact On-line MRF Recognizer for Large Character Set uing Structured Dictionary Repreentation and Vector Quantization Technique

More information

Laboratory Exercise 6

Laboratory Exercise 6 Laboratory Exercie 6 Adder, Subtractor, and Multiplier The purpoe of thi exercie i to examine arithmetic circuit that add, ubtract, and multiply number. Each type of circuit will be implemented in two

More information

Comparison of Methods for Horizon Line Detection in Sea Images

Comparison of Methods for Horizon Line Detection in Sea Images Comparion of Method for Horizon Line Detection in Sea Image Tzvika Libe Evgeny Gerhikov and Samuel Koolapov Department of Electrical Engineering Braude Academic College of Engineering Karmiel 2982 Irael

More information

Trainable Context Model for Multiscale Segmentation

Trainable Context Model for Multiscale Segmentation Trainable Context Model for Multicale Segmentation Hui Cheng and Charle A. Bouman School of Electrical and Computer Engineering Purdue Univerity Wet Lafayette, IN 47907-1285 {hui, bouman}@ ecn.purdue.edu

More information

Compressed Sensing Image Processing Based on Stagewise Orthogonal Matching Pursuit

Compressed Sensing Image Processing Based on Stagewise Orthogonal Matching Pursuit Senor & randucer, Vol. 8, Iue 0, October 204, pp. 34-40 Senor & randucer 204 by IFSA Publihing, S. L. http://www.enorportal.com Compreed Sening Image Proceing Baed on Stagewie Orthogonal Matching Puruit

More information

Key Terms - MinMin, MaxMin, Sufferage, Task Scheduling, Standard Deviation, Load Balancing.

Key Terms - MinMin, MaxMin, Sufferage, Task Scheduling, Standard Deviation, Load Balancing. Volume 3, Iue 11, November 2013 ISSN: 2277 128X International Journal of Advanced Reearch in Computer Science and Software Engineering Reearch Paper Available online at: www.ijarce.com Tak Aignment in

More information

Universität Augsburg. Institut für Informatik. Approximating Optimal Visual Sensor Placement. E. Hörster, R. Lienhart.

Universität Augsburg. Institut für Informatik. Approximating Optimal Visual Sensor Placement. E. Hörster, R. Lienhart. Univerität Augburg à ÊÇÅÍÆ ËÀǼ Approximating Optimal Viual Senor Placement E. Hörter, R. Lienhart Report 2006-01 Januar 2006 Intitut für Informatik D-86135 Augburg Copyright c E. Hörter, R. Lienhart Intitut

More information

Video sequence. Audio sequence

Video sequence. Audio sequence 1 Dynamic Bayeian Network for Audio-Viual Speech Recognition Ara V. Nefian, Luhong Liang, Xiaobo i, Xiaoxing Liu and Kevin Murphy Abtract The ue of viual feature in audio-viual peech recognition (AVSR)

More information

Advanced Encryption Standard and Modes of Operation

Advanced Encryption Standard and Modes of Operation Advanced Encryption Standard and Mode of Operation G. Bertoni L. Breveglieri Foundation of Cryptography - AES pp. 1 / 50 AES Advanced Encryption Standard (AES) i a ymmetric cryptographic algorithm AES

More information

Image authentication and tamper detection using fragile watermarking in spatial domain

Image authentication and tamper detection using fragile watermarking in spatial domain International Journal of Advanced Reearch in Computer Engineering & Technology (IJARCET) Volume 6, Iue 7, July 2017, ISSN: 2278 1323 Image authentication and tamper detection uing fragile watermarking

More information

Gray-level histogram. Intensity (grey-level) transformation, or mapping. Use of intensity transformations:

Gray-level histogram. Intensity (grey-level) transformation, or mapping. Use of intensity transformations: Faculty of Informatic Eötvö Loránd Univerity Budapet, Hungary Lecture : Intenity Tranformation Image enhancement by point proceing Spatial domain and frequency domain method Baic Algorithm for Digital

More information

Analyzing Hydra Historical Statistics Part 2

Analyzing Hydra Historical Statistics Part 2 Analyzing Hydra Hitorical Statitic Part Fabio Maimo Ottaviani EPV Technologie White paper 5 hnode HSM Hitorical Record The hnode i the hierarchical data torage management node and ha to perform all the

More information

[N309] Feedforward Active Noise Control Systems with Online Secondary Path Modeling. Muhammad Tahir Akhtar, Masahide Abe, and Masayuki Kawamata

[N309] Feedforward Active Noise Control Systems with Online Secondary Path Modeling. Muhammad Tahir Akhtar, Masahide Abe, and Masayuki Kawamata he 32nd International Congre and Expoition on Noie Control Engineering Jeju International Convention Center, Seogwipo, Korea, Augut 25-28, 2003 [N309] Feedforward Active Noie Control Sytem with Online

More information

Routing Definition 4.1

Routing Definition 4.1 4 Routing So far, we have only looked at network without dealing with the iue of how to end information in them from one node to another The problem of ending information in a network i known a routing

More information

Planning of scooping position and approach path for loading operation by wheel loader

Planning of scooping position and approach path for loading operation by wheel loader 22 nd International Sympoium on Automation and Robotic in Contruction ISARC 25 - September 11-14, 25, Ferrara (Italy) 1 Planning of cooping poition and approach path for loading operation by wheel loader

More information

Multi-Target Tracking In Clutter

Multi-Target Tracking In Clutter Multi-Target Tracking In Clutter John N. Sander-Reed, Mary Jo Duncan, W.B. Boucher, W. Michael Dimmler, Shawn O Keefe ABSTRACT A high frame rate (0 Hz), multi-target, video tracker ha been developed and

More information

Performance of a Robust Filter-based Approach for Contour Detection in Wireless Sensor Networks

Performance of a Robust Filter-based Approach for Contour Detection in Wireless Sensor Networks Performance of a Robut Filter-baed Approach for Contour Detection in Wirele Senor Network Hadi Alati, William A. Armtrong, Jr., and Ai Naipuri Department of Electrical and Computer Engineering The Univerity

More information

Distributed Packet Processing Architecture with Reconfigurable Hardware Accelerators for 100Gbps Forwarding Performance on Virtualized Edge Router

Distributed Packet Processing Architecture with Reconfigurable Hardware Accelerators for 100Gbps Forwarding Performance on Virtualized Edge Router Ditributed Packet Proceing Architecture with Reconfigurable Hardware Accelerator for 100Gbp Forwarding Performance on Virtualized Edge Router Satohi Nihiyama, Hitohi Kaneko, and Ichiro Kudo Abtract To

More information

ES205 Analysis and Design of Engineering Systems: Lab 1: An Introductory Tutorial: Getting Started with SIMULINK

ES205 Analysis and Design of Engineering Systems: Lab 1: An Introductory Tutorial: Getting Started with SIMULINK ES05 Analyi and Deign of Engineering Sytem: Lab : An Introductory Tutorial: Getting Started with SIMULINK What i SIMULINK? SIMULINK i a oftware package for modeling, imulating, and analyzing dynamic ytem.

More information

The Implementation of an Adaptive Mechanism in the RTP Packet in Mobile Video Transmission

The Implementation of an Adaptive Mechanism in the RTP Packet in Mobile Video Transmission 2011 International Conference on Information Management and Engineering (ICIME 2011) IPCSIT vol. 52 (2012) (2012) IACSIT Pre, Singapore DOI: 10.7763/IPCSIT.2012.V52.91 The Implementation of an Adaptive

More information

AUTOMATIC TEST CASE GENERATION USING UML MODELS

AUTOMATIC TEST CASE GENERATION USING UML MODELS Volume-2, Iue-6, June-2014 AUTOMATIC TEST CASE GENERATION USING UML MODELS 1 SAGARKUMAR P. JAIN, 2 KHUSHBOO S. LALWANI, 3 NIKITA K. MAHAJAN, 4 BHAGYASHREE J. GADEKAR 1,2,3,4 Department of Computer Engineering,

More information

DAROS: Distributed User-Server Assignment And Replication For Online Social Networking Applications

DAROS: Distributed User-Server Assignment And Replication For Online Social Networking Applications DAROS: Ditributed Uer-Server Aignment And Replication For Online Social Networking Application Thuan Duong-Ba School of EECS Oregon State Univerity Corvalli, OR 97330, USA Email: duongba@eec.oregontate.edu

More information

MAT 155: Describing, Exploring, and Comparing Data Page 1 of NotesCh2-3.doc

MAT 155: Describing, Exploring, and Comparing Data Page 1 of NotesCh2-3.doc MAT 155: Decribing, Exploring, and Comparing Data Page 1 of 8 001-oteCh-3.doc ote for Chapter Summarizing and Graphing Data Chapter 3 Decribing, Exploring, and Comparing Data Frequency Ditribution, Graphic

More information

Research on Star Image Noise Filtering Based on Diffusion Model of Regularization Influence Function

Research on Star Image Noise Filtering Based on Diffusion Model of Regularization Influence Function 016 Sith International Conference on Intrumentation & Meaurement Computer Communication and Control Reearch on Star Image Noie Filtering Baed on Diffuion Model of Regularization Influence Function SunJianming

More information

Analysis of the results of analytical and simulation With the network model and dynamic priority Unchecked Buffer

Analysis of the results of analytical and simulation With the network model and dynamic priority Unchecked Buffer International Reearch Journal of Applied and Baic Science 218 Available online at www.irjab.com ISSN 2251-838X / Vol, 12 (1): 49-53 Science Explorer Publication Analyi of the reult of analytical and imulation

More information

Computer Arithmetic Homework Solutions. 1 An adder for graphics. 2 Partitioned adder. 3 HDL implementation of a partitioned adder

Computer Arithmetic Homework Solutions. 1 An adder for graphics. 2 Partitioned adder. 3 HDL implementation of a partitioned adder Computer Arithmetic Homework 3 2016 2017 Solution 1 An adder for graphic In a normal ripple carry addition of two poitive number, the carry i the ignal for a reult exceeding the maximum. We ue thi ignal

More information

Digifort Standard. Architecture

Digifort Standard. Architecture Digifort Standard Intermediate olution for intalling up to 32 camera The Standard verion provide the ideal reource for local and remote monitoring of up to 32 camera per erver and a the intermediate verion

More information

Aalborg Universitet. Published in: Proceedings of the Working Conference on Advanced Visual Interfaces

Aalborg Universitet. Published in: Proceedings of the Working Conference on Advanced Visual Interfaces Aalborg Univeritet Software-Baed Adjutment of Mobile Autotereocopic Graphic Uing Static Parallax Barrier Paprocki, Martin Marko; Krog, Kim Srirat; Kritofferen, Morten Bak; Krau, Martin Publihed in: Proceeding

More information

Laboratory Exercise 6

Laboratory Exercise 6 Laboratory Exercie 6 Adder, Subtractor, and Multiplier The purpoe of thi exercie i to examine arithmetic circuit that add, ubtract, and multiply number. Each circuit will be decribed in Verilog and implemented

More information

A User-Attention Based Focus Detection Framework and Its Applications

A User-Attention Based Focus Detection Framework and Its Applications A Uer-Attention Baed Focu Detection Framework and It Application Chia-Chiang Ho, Wen-Huang Cheng, Ting-Jian Pan, Ja-Ling Wu Communication and Multimedia Laboratory, Department of Computer Science and Information

More information

Keywords Cloud Computing, Service Level Agreements (SLA), CloudSim, Monitoring & Controlling SLA Agent, JADE

Keywords Cloud Computing, Service Level Agreements (SLA), CloudSim, Monitoring & Controlling SLA Agent, JADE Volume 5, Iue 8, Augut 2015 ISSN: 2277 128X International Journal of Advanced Reearch in Computer Science and Software Engineering Reearch Paper Available online at: www.ijarce.com Verification of Agent

More information

Finite Elements Method in Split Hopkinson Pressure Bar developing process

Finite Elements Method in Split Hopkinson Pressure Bar developing process 6th WSEAS International Conference on SYSTEM SCIENCE and SIMULATION in ENGINEERING, Venice, Italy, November 1-3, 007 63 Finite Element Method in Split Hopkinon Preure Bar developing proce ROTARIU ADRIAN

More information

ANALYSIS OF THE FIRST LAYER IN WEIGHTLESS NEURAL NETWORKS FOR 3_DIMENSIONAL PATTERN RECOGNITION

ANALYSIS OF THE FIRST LAYER IN WEIGHTLESS NEURAL NETWORKS FOR 3_DIMENSIONAL PATTERN RECOGNITION ANALYSIS OF THE FIRST LAYER IN WEIGHTLESS NEURAL NETWORKS FOR 3_DIMENSIONAL PATTERN RECOGNITION A. Váque-Nava * Ecuela de Ingeniería. CENTRO UNIVERSITARIO MEXICO. DIVISION DE ESTUDIOS SUPERIORES J. Figueroa

More information

Performance Evaluation of an Advanced Local Search Evolutionary Algorithm

Performance Evaluation of an Advanced Local Search Evolutionary Algorithm Anne Auger and Nikolau Hanen Performance Evaluation of an Advanced Local Search Evolutionary Algorithm Proceeding of the IEEE Congre on Evolutionary Computation, CEC 2005 c IEEE Performance Evaluation

More information

IMPROVED JPEG DECOMPRESSION OF DOCUMENT IMAGES BASED ON IMAGE SEGMENTATION. Tak-Shing Wong, Charles A. Bouman, and Ilya Pollak

IMPROVED JPEG DECOMPRESSION OF DOCUMENT IMAGES BASED ON IMAGE SEGMENTATION. Tak-Shing Wong, Charles A. Bouman, and Ilya Pollak IMPROVED DECOMPRESSION OF DOCUMENT IMAGES BASED ON IMAGE SEGMENTATION Tak-Shing Wong, Charle A. Bouman, and Ilya Pollak School of Electrical and Computer Engineering Purdue Univerity ABSTRACT We propoe

More information

Z-transformation in simulation of continuous system

Z-transformation in simulation of continuous system Z-tranformation in imulation of continuou tem Mirolav Kašpar, Alexandr Štefek Univerit of defence Abtract Motl ued method for continuou tem imulation i uing algorithm for numeric olving of differential

More information

Edits in Xylia Validity Preserving Editing of XML Documents

Edits in Xylia Validity Preserving Editing of XML Documents dit in Xylia Validity Preerving diting of XML Document Pouria Shaker, Theodore S. Norvell, and Denni K. Peter Faculty of ngineering and Applied Science, Memorial Univerity of Newfoundland, St. John, NFLD,

More information

On successive packing approach to multidimensional (M-D) interleaving

On successive packing approach to multidimensional (M-D) interleaving On ucceive packing approach to multidimenional (M-D) interleaving Xi Min Zhang Yun Q. hi ankar Bau Abtract We propoe an interleaving cheme for multidimenional (M-D) interleaving. To achieved by uing a

More information

3D MODELLING WITH LINEAR APPROACHES USING GEOMETRIC PRIMITIVES

3D MODELLING WITH LINEAR APPROACHES USING GEOMETRIC PRIMITIVES MAKARA, TEKNOLOGI, VOL. 9, NO., APRIL 5: 3-35 3D MODELLING WITH LINEAR APPROACHES USING GEOMETRIC PRIMITIVES Mochammad Zulianyah Informatic Engineering, Faculty of Engineering, ARS International Univerity,

More information

Topics. Lecture 37: Global Optimization. Issues. A Simple Example: Copy Propagation X := 3 B > 0 Y := 0 X := 4 Y := Z + W A := 2 * 3X

Topics. Lecture 37: Global Optimization. Issues. A Simple Example: Copy Propagation X := 3 B > 0 Y := 0 X := 4 Y := Z + W A := 2 * 3X Lecture 37: Global Optimization [Adapted from note by R. Bodik and G. Necula] Topic Global optimization refer to program optimization that encompa multiple baic block in a function. (I have ued the term

More information

A reduced reference image quality metric based on feature fusion and neural networks

A reduced reference image quality metric based on feature fusion and neural networks Univerity of Wollongong Reearch Online Faculty of Engineering and Information Science - Paper: Part A Faculty of Engineering and Information Science 2011 A reduced reference image quality metric baed on

More information

Markov Random Fields in Image Segmentation

Markov Random Fields in Image Segmentation Preented at SSIP 2011, Szeged, Hungary Markov Random Field in Image Segmentation Zoltan Kato Image Proceing & Computer Graphic Dept. Univerity of Szeged Hungary Zoltan Kato: Markov Random Field in Image

More information

A Multi-objective Genetic Algorithm for Reliability Optimization Problem

A Multi-objective Genetic Algorithm for Reliability Optimization Problem International Journal of Performability Engineering, Vol. 5, No. 3, April 2009, pp. 227-234. RAMS Conultant Printed in India A Multi-objective Genetic Algorithm for Reliability Optimization Problem AMAR

More information

An Approach to a Test Oracle for XML Query Testing

An Approach to a Test Oracle for XML Query Testing An Approach to a Tet Oracle for XML Query Teting Dae S. Kim-Park, Claudio de la Riva, Javier Tuya Univerity of Oviedo Computing Department Campu of Vieque, /n, 33204 (SPAIN) kim_park@li.uniovi.e, claudio@uniovi.e,

More information

Karen L. Collins. Wesleyan University. Middletown, CT and. Mark Hovey MIT. Cambridge, MA Abstract

Karen L. Collins. Wesleyan University. Middletown, CT and. Mark Hovey MIT. Cambridge, MA Abstract Mot Graph are Edge-Cordial Karen L. Collin Dept. of Mathematic Weleyan Univerity Middletown, CT 6457 and Mark Hovey Dept. of Mathematic MIT Cambridge, MA 239 Abtract We extend the definition of edge-cordial

More information

A New Approach to Pipeline FFT Processor

A New Approach to Pipeline FFT Processor A ew Approach to Pipeline FFT Proceor Shouheng He and Mat Torkelon Department of Applied Electronic, Lund Univerity S- Lund, SWEDE email: he@tde.lth.e; torkel@tde.lth.e Abtract A new VLSI architecture

More information

A NEW APPROACH IN MEASURING OF THE ROUGHNESS FOR SURFACE CONSTITUTED WITH MACHINING PROCESS BY MATERIAL REMOVAL

A NEW APPROACH IN MEASURING OF THE ROUGHNESS FOR SURFACE CONSTITUTED WITH MACHINING PROCESS BY MATERIAL REMOVAL International Journal of Mechanical and Production Engineering Reearch and Development (IJMPERD) ISSN 49-689 Vol. 3, Iue, Mar 3, 4-5 TJPRC Pvt. Ltd. A NEW APPROACH IN MEASURING OF THE ROUGHNESS FOR SURFACE

More information

SLA Adaptation for Service Overlay Networks

SLA Adaptation for Service Overlay Networks SLA Adaptation for Service Overlay Network Con Tran 1, Zbigniew Dziong 1, and Michal Pióro 2 1 Department of Electrical Engineering, École de Technologie Supérieure, Univerity of Quebec, Montréal, Canada

More information

Motivation: Level Sets. Input Data Noisy. Easy Case Use Marching Cubes. Intensity Varies. Non-uniform Exposure. Roger Crawfis

Motivation: Level Sets. Input Data Noisy. Easy Case Use Marching Cubes. Intensity Varies. Non-uniform Exposure. Roger Crawfis Level Set Motivation: Roger Crawfi Slide collected from: Fan Ding, Charle Dyer, Donald Tanguay and Roger Crawfi 4/24/2003 R. Crawfi, Ohio State Univ. 109 Eay Cae Ue Marching Cube Input Data Noiy 4/24/2003

More information

A study on turbo decoding iterative algorithms

A study on turbo decoding iterative algorithms Buletinul Ştiinţific al Univerităţii "Politehnica" din Timişoara Seria ELECTRONICĂ şi TELECOMUNICAŢII TRANSACTIONS on ELECTRONICS and COMMUNICATIONS Tom 49(63, Facicola 2, 2004 A tudy on turbo decoding

More information

(12) Patent Application Publication (10) Pub. No.: US 2003/ A1

(12) Patent Application Publication (10) Pub. No.: US 2003/ A1 US 2003O196031A1 (19) United State (12) Patent Application Publication (10) Pub. No.: US 2003/0196031 A1 Chen (43) Pub. Date: Oct. 16, 2003 (54) STORAGE CONTROLLER WITH THE DISK Related U.S. Application

More information

An Active Stereo Vision System Based on Neural Pathways of Human Binocular Motor System

An Active Stereo Vision System Based on Neural Pathways of Human Binocular Motor System Journal of Bionic Engineering 4 (2007) 185 192 An Active Stereo Viion Sytem Baed on Neural Pathway of Human Binocular Motor Sytem Yu-zhang Gu 1, Makoto Sato 2, Xiao-lin Zhang 2 1. Department of Advanced

More information

Laboratory Exercise 2

Laboratory Exercise 2 Laoratory Exercie Numer and Diplay Thi i an exercie in deigning cominational circuit that can perform inary-to-decimal numer converion and inary-coded-decimal (BCD) addition. Part I We wih to diplay on

More information

A PROBABILISTIC NOTION OF CAMERA GEOMETRY: CALIBRATED VS. UNCALIBRATED

A PROBABILISTIC NOTION OF CAMERA GEOMETRY: CALIBRATED VS. UNCALIBRATED A PROBABILISTIC NOTION OF CAMERA GEOMETRY: CALIBRATED VS. UNCALIBRATED Jutin Domke and Yianni Aloimono Computational Viion Laboratory, Center for Automation Reearch Univerity of Maryland College Park,

More information

Motion Control (wheeled robots)

Motion Control (wheeled robots) 3 Motion Control (wheeled robot) Requirement for Motion Control Kinematic / dynamic model of the robot Model of the interaction between the wheel and the ground Definition of required motion -> peed control,

More information

LinkGuide: Towards a Better Collection of Hyperlinks in a Website Homepage

LinkGuide: Towards a Better Collection of Hyperlinks in a Website Homepage Proceeding of the World Congre on Engineering 2007 Vol I LinkGuide: Toward a Better Collection of Hyperlink in a Webite Homepage A. Ammari and V. Zharkova chool of Informatic, Univerity of Bradford anammari@bradford.ac.uk,

More information

A METHOD OF REAL-TIME NURBS INTERPOLATION WITH CONFINED CHORD ERROR FOR CNC SYSTEMS

A METHOD OF REAL-TIME NURBS INTERPOLATION WITH CONFINED CHORD ERROR FOR CNC SYSTEMS Vietnam Journal of Science and Technology 55 (5) (017) 650-657 DOI: 10.1565/55-518/55/5/906 A METHOD OF REAL-TIME NURBS INTERPOLATION WITH CONFINED CHORD ERROR FOR CNC SYSTEMS Nguyen Huu Quang *, Banh

More information

Development of an atmospheric climate model with self-adapting grid and physics

Development of an atmospheric climate model with self-adapting grid and physics Intitute of Phyic Publihing Journal of Phyic: Conference Serie 16 (2005) 353 357 doi:10.1088/1742-6596/16/1/049 SciDAC 2005 Development of an atmopheric climate model with elf-adapting grid and phyic Joyce

More information

Using Mouse Feedback in Computer Assisted Transcription of Handwritten Text Images

Using Mouse Feedback in Computer Assisted Transcription of Handwritten Text Images 2009 10th International Conference on Document Analyi and Recognition Uing Moue Feedback in Computer Aited Trancription of Handwritten Text Image Verónica Romero, Alejandro H. Toelli, Enrique Vidal Intituto

More information

The norm Package. November 15, Title Analysis of multivariate normal datasets with missing values

The norm Package. November 15, Title Analysis of multivariate normal datasets with missing values The norm Package November 15, 2003 Verion 1.0-9 Date 2002/05/06 Title Analyi of multivariate normal dataet with miing value Author Ported to R by Alvaro A. Novo . Original by Joeph

More information

How to Select Measurement Points in Access Point Localization

How to Select Measurement Points in Access Point Localization Proceeding of the International MultiConference of Engineer and Computer Scientit 205 Vol II, IMECS 205, March 8-20, 205, Hong Kong How to Select Meaurement Point in Acce Point Localization Xiaoling Yang,

More information

Minimum congestion spanning trees in bipartite and random graphs

Minimum congestion spanning trees in bipartite and random graphs Minimum congetion panning tree in bipartite and random graph M.I. Otrovkii Department of Mathematic and Computer Science St. John Univerity 8000 Utopia Parkway Queen, NY 11439, USA e-mail: otrovm@tjohn.edu

More information

CENTER-POINT MODEL OF DEFORMABLE SURFACE

CENTER-POINT MODEL OF DEFORMABLE SURFACE CENTER-POINT MODEL OF DEFORMABLE SURFACE Piotr M. Szczypinki Iintitute of Electronic, Technical Univerity of Lodz, Poland Abtract: Key word: Center-point model of deformable urface for egmentation of 3D

More information

The Association of System Performance Professionals

The Association of System Performance Professionals The Aociation of Sytem Performance Profeional The Computer Meaurement Group, commonly called CMG, i a not for profit, worldwide organization of data proceing profeional committed to the meaurement and

More information

A TOPSIS based Method for Gene Selection for Cancer Classification

A TOPSIS based Method for Gene Selection for Cancer Classification Volume 67 No17, April 2013 A TOPSIS baed Method for Gene Selection for Cancer Claification IMAbd-El Fattah,WIKhedr, KMSallam, 1 Department of Statitic, 3 Department of Deciion upport, 2 Department of information

More information

An Improved Implementation of Elliptic Curve Digital Signature by Using Sparse Elements

An Improved Implementation of Elliptic Curve Digital Signature by Using Sparse Elements The International Arab Journal of Information Technology, Vol. 1, No., July 004 0 An Improved Implementation of Elliptic Curve Digital Signature by Uing Spare Element Eam Al-Daoud Computer Science Department,

More information

Optimal Gossip with Direct Addressing

Optimal Gossip with Direct Addressing Optimal Goip with Direct Addreing Bernhard Haeupler Microoft Reearch 1065 La Avenida, Mountain View Mountain View, CA 94043 haeupler@c.cmu.edu Dahlia Malkhi Microoft Reearch 1065 La Avenida, Mountain View

More information

Computer Aided Drafting, Design and Manufacturing Volume 25, Number 3, September 2015, Page 10

Computer Aided Drafting, Design and Manufacturing Volume 25, Number 3, September 2015, Page 10 Computer Aided Drafting, Deign and Manufacturing Volume 5, umber 3, September 015, Page 10 CADDM Reearch of atural Geture Recognition and Interactive Technology Compatible with YCbCr and SV Color Space

More information

Combining Web Usage Mining and Fuzzy Inference for Website Personalization

Combining Web Usage Mining and Fuzzy Inference for Website Personalization Combining Web Uage Mining and Fuzzy Inference for Webite Peronalization Olfa Naraoui and Chritopher Petene Dept. of Electrical and Computer Engineering 206 Engineering Science Bldg. The Univerity of Memphi

More information

Laboratory Exercise 6

Laboratory Exercise 6 Laboratory Exercie 6 Adder, Subtractor, and Multiplier a a The purpoe of thi exercie i to examine arithmetic circuit that add, ubtract, and multiply number. Each b c circuit will be decribed in Verilog

More information

Quadrilaterals. Learning Objectives. Pre-Activity

Quadrilaterals. Learning Objectives. Pre-Activity Section 3.4 Pre-Activity Preparation Quadrilateral Intereting geometric hape and pattern are all around u when we tart looking for them. Examine a row of fencing or the tiling deign at the wimming pool.

More information

1 The secretary problem

1 The secretary problem Thi i new material: if you ee error, pleae email jtyu at tanford dot edu 1 The ecretary problem We will tart by analyzing the expected runtime of an algorithm, a you will be expected to do on your homework.

More information

Tracking High Speed Skater by Using Multiple Model

Tracking High Speed Skater by Using Multiple Model Vol. 2, No. 26 Tracing High Speed Sater by Uing Multiple Model Guojun Liu & Xianglong Tang School of Computer Science & Engineering Harbin Intitute of Technology Harbin 5000, China E-mail: hitliu@hit.edu.cn

More information

Floating Point CORDIC Based Power Operation

Floating Point CORDIC Based Power Operation Floating Point CORDIC Baed Power Operation Kazumi Malhan, Padmaja AVL Electrical and Computer Engineering Department School of Engineering and Computer Science Oakland Univerity, Rocheter, MI e-mail: kmalhan@oakland.edu,

More information

A SIMPLE IMPERATIVE LANGUAGE THE STORE FUNCTION NON-TERMINATING COMMANDS

A SIMPLE IMPERATIVE LANGUAGE THE STORE FUNCTION NON-TERMINATING COMMANDS A SIMPLE IMPERATIVE LANGUAGE Eventually we will preent the emantic of a full-blown language, with declaration, type and looping. However, there are many complication, o we will build up lowly. Our firt

More information

Anisotropic filtering on normal field and curvature tensor field using optimal estimation theory

Anisotropic filtering on normal field and curvature tensor field using optimal estimation theory Aniotropic filtering on normal field and curvature tenor field uing optimal etimation theory Min Liu Yuhen Liu and Karthik Ramani Purdue Univerity, Wet Lafayette, Indiana, USA Email: {liu66 liu28 ramani}@purdue.edu

More information

xy-monotone path existence queries in a rectilinear environment

xy-monotone path existence queries in a rectilinear environment CCCG 2012, Charlottetown, P.E.I., Augut 8 10, 2012 xy-monotone path exitence querie in a rectilinear environment Gregory Bint Anil Mahehwari Michiel Smid Abtract Given a planar environment coniting of

More information

Analysis of slope stability

Analysis of slope stability Engineering manual No. 8 Updated: 02/2016 Analyi of lope tability Program: Slope tability File: Demo_manual_08.gt In thi engineering manual, we are going to how you how to verify the lope tability for

More information

Kinematics Programming for Cooperating Robotic Systems

Kinematics Programming for Cooperating Robotic Systems Kinematic Programming for Cooperating Robotic Sytem Critiane P. Tonetto, Carlo R. Rocha, Henrique Sima, Altamir Dia Federal Univerity of Santa Catarina, Mechanical Engineering Department, P.O. Box 476,

More information

On combining Learning Vector Quantization and the Bayesian classifiers for natural textured images

On combining Learning Vector Quantization and the Bayesian classifiers for natural textured images On combining Learning Vector Quantization and the Bayeian claifier for natural textured image María Guiarro Dept. Ingeniería del Software e Inteligencia Artificial Facultad Informática Univeridad Complutene

More information

A System Dynamics Model for Transient Availability Modeling of Repairable Redundant Systems

A System Dynamics Model for Transient Availability Modeling of Repairable Redundant Systems International Journal of Performability Engineering Vol., No. 3, May 05, pp. 03-. RAMS Conultant Printed in India A Sytem Dynamic Model for Tranient Availability Modeling of Repairable Redundant Sytem

More information

else end while End References

else end while End References 621-630. [RM89] [SK76] Roenfeld, A. and Melter, R. A., Digital geometry, The Mathematical Intelligencer, vol. 11, No. 3, 1989, pp. 69-72. Sklanky, J. and Kibler, D. F., A theory of nonuniformly digitized

More information

UC Berkeley International Conference on GIScience Short Paper Proceedings

UC Berkeley International Conference on GIScience Short Paper Proceedings UC Berkeley International Conference on GIScience Short Paper Proceeding Title A novel method for probabilitic coverage etimation of enor network baed on 3D vector repreentation in complex urban environment

More information

Increasing Throughput and Reducing Delay in Wireless Sensor Networks Using Interference Alignment

Increasing Throughput and Reducing Delay in Wireless Sensor Networks Using Interference Alignment Int. J. Communication, Network and Sytem Science, 0, 5, 90-97 http://dx.doi.org/0.436/ijcn.0.50 Publihed Online February 0 (http://www.scirp.org/journal/ijcn) Increaing Throughput and Reducing Delay in

More information

Keywords: Defect detection, linear phased array transducer, parameter optimization, phased array ultrasonic B-mode imaging testing.

Keywords: Defect detection, linear phased array transducer, parameter optimization, phased array ultrasonic B-mode imaging testing. Send Order for Reprint to reprint@benthamcience.ae 488 The Open Automation and Control Sytem Journal, 2014, 6, 488-492 Open Acce Parameter Optimization of Linear Phaed Array Tranducer for Defect Detection

More information

Modelling the impact of cyber attacks on the traffic control centre of an urban automobile transport system by means of enhanced cybersecurity

Modelling the impact of cyber attacks on the traffic control centre of an urban automobile transport system by means of enhanced cybersecurity Modelling the impact of cyber attack on the traffic control centre of an urban automobile tranport ytem by mean of enhanced cyberecurity Yoana Ivanova 1,* 1 Bulgarian Academy of Science, Intitute of ICT,

More information

Reporting Checklist for Nature Neuroscience

Reporting Checklist for Nature Neuroscience Correponding Author: Manucript Number: Manucript Type: Jeremy Elman NNBC48172A Brief Communication Reporting Checklit for Nature Neurocience # Figure: 2 # Figure: 5 # Table: 6 # Video: 0 Thi checklit i

More information

Laboratory Exercise 6

Laboratory Exercise 6 Laboratory Exercie 6 Adder, Subtractor, and Multiplier The purpoe of thi exercie i to examine arithmetic circuit that add, ubtract, and multiply number. Each circuit will be decribed in VHL and implemented

More information

USING ARTIFICIAL NEURAL NETWORKS TO APPROXIMATE A DISCRETE EVENT STOCHASTIC SIMULATION MODEL

USING ARTIFICIAL NEURAL NETWORKS TO APPROXIMATE A DISCRETE EVENT STOCHASTIC SIMULATION MODEL USING ARTIFICIAL NEURAL NETWORKS TO APPROXIMATE A DISCRETE EVENT STOCHASTIC SIMULATION MODEL Robert A. Kilmer Department of Sytem Engineering Unite State Military Acaemy Wet Point, NY 1996 Alice E. Smith

More information

Tracking Articulator Movements Using Orientation Measurements

Tracking Articulator Movements Using Orientation Measurements Tracking Articulator Movement Uing Orientation Meaurement An Ji, Michael T. Johnon, and Jeffrey Berry Marquette Univerity Department of Electrical and Computer Engineering Speech and Signal Proceing Laboratory

More information

REMOTE SENSING AND IMAGING IN A RECONFIGURABLE COMPUTING ENVIRONMENT

REMOTE SENSING AND IMAGING IN A RECONFIGURABLE COMPUTING ENVIRONMENT REMOTE SENSING AND IMAGING IN A RECONFIGURABLE COMPUTING ENVIRONMENT By VIKAS AGGARWAL A THESIS PRESENTED TO THE GRADUATE SCHOOL OF THE UNIVERSITY OF FLORIDA IN PARTIAL FULFILLMENT OF THE REQUIREMENTS

More information

New DSP to measure acoustic efficiency of road barriers. Part 2: Sound Insulation Index

New DSP to measure acoustic efficiency of road barriers. Part 2: Sound Insulation Index New DSP to meaure acoutic efficiency of road barrier. Part 2: Sound Inulation Index LAMBERTO TRONCHIN 1, KRISTIAN FABBRI 1, JELENA VASILJEVIC 2 1 DIENCA CIARM, Univerity of Bologna, Italy 2 Univerity of

More information

ML85C. Data Sheet. Press fit monitoring module. Special features. Block. diagram PLC. B en

ML85C. Data Sheet. Press fit monitoring module. Special features. Block. diagram PLC. B en ML85C Pre fit monitoring module Special feature Data Sheet Meaurement and evaluation ytem for force/diplacement coure in fitting procee Graphical repreentation of the procee with zoom function Immediate

More information

Representations and Transformations. Objectives

Representations and Transformations. Objectives Repreentation and Tranformation Objective Derive homogeneou coordinate tranformation matrice Introduce tandard tranformation - Rotation - Tranlation - Scaling - Shear Scalar, Point, Vector Three baic element

More information

Today s Outline. CS 561, Lecture 23. Negative Weights. Shortest Paths Problem. The presence of a negative cycle might mean that there is

Today s Outline. CS 561, Lecture 23. Negative Weights. Shortest Paths Problem. The presence of a negative cycle might mean that there is Today Outline CS 56, Lecture Jared Saia Univerity of New Mexico The path that can be trodden i not the enduring and unchanging Path. The name that can be named i not the enduring and unchanging Name. -

More information

Software Shaders in Interactive Environments Using Relief Impostors

Software Shaders in Interactive Environments Using Relief Impostors Software Shader in Interactive Environment Uing Relief Impotor ESTEBAN WALTER GONZALEZ CLUA BRUNO FEIJÓ MARCELO DREUX, FRANCISCO FONSECA ICAD/IGame/ViionLab, Department of Computer Science, PUC-Rio {eteban,

More information

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and Thi article appeared in a journal publihed by Elevier. The attached copy i furnihed to the author for internal non-commercial reearch and education ue, including for intruction at the author intitution

More information

Map-based Adaptive Foothold Planning for Unstructured Terrain Walking

Map-based Adaptive Foothold Planning for Unstructured Terrain Walking 21 IEEE International Conference on Robotic and Automation Anchorage Convention Ditrict May 3-8, 21, Anchorage, Alaka, USA Map-baed Adaptive Foothold Planning for Untructured Terrain Walking Dominik Belter,

More information