Welcome to Scribd. Sign in or start your free trial to enjoy unlimited e-books, audiobooks & documents.Find out more
Download
Standard view
Full view
of .
Look up keyword
Like this
1Activity
0 of .
Results for:
No results containing your search query
P. 1
NCCT-2011 IEEE Matlab Project Abstracts, 2011-12

NCCT-2011 IEEE Matlab Project Abstracts, 2011-12

Ratings: (0)|Views: 107|Likes:
Published by ncctstudentproject

More info:

Published by: ncctstudentproject on Sep 02, 2011
Copyright:Attribution Non-commercial

Availability:

Read on Scribd mobile: iPhone, iPad and Android.
download as PDF, TXT or read online from Scribd
See more
See less

09/02/2011

pdf

text

original

 
NCCT
 
Promise for the Best Projects
 
IEEE PROJECTS 2011-12
 
MATLAB PROJECTS
 
NCCTNCCTNCCTNCCT
,
2823 5816, 93801 02891, 98411 93224
  www.ncct.in, www.ieeeprojects.net, ncctchennai@gmail.com
#109, 2
nd
Floor, Nungambakkam High Road, Nungambakkam, Chennai – 600 034Near Ganpat Hotel, Above IOB, Next to ICICI
 
AN ALGORITHM FOR INTELLIGIBILITY PREDICTION OFTIME-FREQUENCY WEIGHTED NOISY SPEECH
 
 Audio, Speech, and Language Processing, IEEE Transactions on
ABSTRACT
 In the development process of noise-reduction algorithms, an objectivemachine-driven intelligibility measure which shows high correlation withspeech intelligibility is of great interest. Besides reducing time andcosts compared to real listening experiments, an objective intelligibilitymeasure could also help provide answers on how to improve theintelligibility of noisy unprocessed speech.In this paper, a short-time objective intelligibility measure (STOI) ispresented, which shows high correlation with the intelligibility of noisyand time–frequency weighted noisy speech (e.g., resulting from noisereduction) of three different listening experiments.In general, STOI showed better correlation with speech intelligibilitycompared to five other reference objective intelligibility models. Incontrast to other conventional intelligibility models which tend to rely onglobal statistics across entire sentences, STOI is based on shorter timesegments (386 ms).Experiments indeed show that it is beneficial to take segment lengths of this order into account. In addition, a free Matlab implementation isprovided.
 
NCCT
 
Promise for the Best Projects
 
IEEE PROJECTS 2011-12
 
MATLAB PROJECTS
 
NCCTNCCTNCCTNCCT
,
2823 5816, 93801 02891, 98411 93224
  www.ncct.in, www.ieeeprojects.net, ncctchennai@gmail.com
#109, 2
nd
Floor, Nungambakkam High Road, Nungambakkam, Chennai – 600 034Near Ganpat Hotel, Above IOB, Next to ICICI
 
ADAPTIVE MULTISCALE COMPLEXITY ANALYSIS OFFETAL HEART RATE
 
Biomedical Engineering, IEEE Transactions on
ABSTRACT
 Per partum fetal asphyxia is a major cause of neonatal morbidity andmortality. Fetal heart rate monitoring plays an important role in earlydetection of acidosis, an indicator for asphyxia.This problem is addressed in this paper by introducing a novelcomplexity analysis of fetal heart rate data, based on producing acollection of piecewise linear approximations of varying dimensionsfrom which a measure of complexity is extracted.This procedure specifically accounts for the highly non-stationarycontext of labor by being adaptive and multiscale. Using a referencedataset, made of real per partum fetal heart rate data, collected in situand carefully constituted by obstetricians, the behavior of the proposedapproach is analyzed and illustrated.Its performance is evaluated in terms of the rate of correct acidosisdetection versus the rate of false detection, as well as how early thedetection is made. Computational cost is also discussed. The resultsare shown to be extremely promising and further potential uses of thetool are discussed
 
NCCT
 
Promise for the Best Projects
 
IEEE PROJECTS 2011-12
 
MATLAB PROJECTS
 
NCCTNCCTNCCTNCCT
,
2823 5816, 93801 02891, 98411 93224
  www.ncct.in, www.ieeeprojects.net, ncctchennai@gmail.com
#109, 2
nd
Floor, Nungambakkam High Road, Nungambakkam, Chennai – 600 034Near Ganpat Hotel, Above IOB, Next to ICICI
 
TISSUE-SPECIFIC COMPARTMENTAL ANALYSIS FORDYNAMIC CONTRAST-ENHANCED MR IMAGING OFCOMPLEX TUMORS
 
Medical Imaging, IEEE Transactions on
ABSTRACT
 Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI)provides a noninvasive method for evaluating tumor vasculaturepatterns based on contrast accumulation and washout. However, due tolimited imaging resolution and tumor tissue heterogeneity, tracer concentrations at many pixels often represent a mixture of more thanone distinct compartment.This pixel-wise partial volume effect (PVE) would have profound impacton the accuracy of pharmacokinetics studies using existingcompartmental modeling (CM) methods. We therefore propose aconvex analysis of mixtures (CAM) algorithm to explicitly mitigate PVEby expressing the kinetics in each pixel as a nonnegative combinationof underlying compartments and subsequently identifying pure volumepixels at the corners of the clustered pixel time series scatter plotsimplex.The algorithm is supported theoretically by a well-groundedmathematical framework and practically by plug-in noise filtering andnormalization preprocessing. We demonstrate the principle andfeasibility of the CAM-CM approach on realistic synthetic data involvingtwo functional tissue compartments, and compare the accuracy of parameter estimates obtained with and without PVE elimination usingCAM or other relevant techniques.Experimental results show that CAM-CM achieves a significantimprovement in the accuracy of kinetic parameter estimation.

You're Reading a Free Preview

Download
scribd
/*********** DO NOT ALTER ANYTHING BELOW THIS LINE ! ************/ var s_code=s.t();if(s_code)document.write(s_code)//-->