Abstract: A simple adaptive voice activity detector (VAD) is
implemented using Gabor and gammatone atomic decomposition of
speech for high Gaussian noise environments. Matching pursuit is
used for atomic decomposition, and is shown to achieve optimal
speech detection capability at high data compression rates for low
signal to noise ratios. The most active dictionary elements found by
matching pursuit are used for the signal reconstruction so that the
algorithm adapts to the individual speakers dominant time-frequency
characteristics. Speech has a high peak to average ratio enabling
matching pursuit greedy heuristic of highest inner products to isolate
high energy speech components in high noise environments. Gabor
and gammatone atoms are both investigated with identical
logarithmically spaced center frequencies, and similar bandwidths.
The algorithm performs equally well for both Gabor and gammatone
atoms with no significant statistical differences. The algorithm
achieves 70% accuracy at a 0 dB SNR, 90% accuracy at a 5 dB SNR
and 98% accuracy at a 20dB SNR using 30d B SNR as a reference
for voice activity.
Abstract: In this work, we explore the capability of the mean
shift algorithm as a powerful preprocessing tool for improving the
quality of spatial data, acquired from airborne scanners, from densely
built urban areas. On one hand, high resolution image data corrupted
by noise caused by lossy compression techniques are appropriately
smoothed while at the same time preserving the optical edges and, on
the other, low resolution LiDAR data in the form of normalized
Digital Surface Map (nDSM) is upsampled through the joint mean
shift algorithm. Experiments on both the edge-preserving smoothing
and upsampling capabilities using synthetic RGB-z data show that the
mean shift algorithm is superior to bilateral filtering as well as to
other classical smoothing and upsampling algorithms. Application of
the proposed methodology for 3D reconstruction of buildings of a
pilot region of Athens, Greece results in a significant visual
improvement of the 3D building block model.
Abstract: In more complex systems, such as automotive
gearbox, a rigorous treatment of the data is necessary because there
are several moving parts (gears, bearings, shafts, etc.), and in this
way, there are several possible sources of errors and also noise. The
basic objective of this work is the detection of damage in automotive
gearbox. The detection methods used are the wavelet method, the
bispectrum; advanced filtering techniques (selective filtering) of
vibrational signals and mathematical morphology. Gearbox vibration
tests were performed (gearboxes in good condition and with defects)
of a production line of a large vehicle assembler. The vibration
signals are obtained using five accelerometers in different positions
of the sample. The results obtained using the kurtosis, bispectrum,
wavelet and mathematical morphology showed that it is possible to
identify the existence of defects in automotive gearboxes.
Abstract: This paper presents the development of a robot car
that can track the motion of an object by detecting its color through
an Android device. The employed computer vision algorithm uses the
OpenCV library, which is embedded into an Android application of a
smartphone, for manipulating the captured image of the object. The
captured image of the object is subjected to color conversion and is
transformed to a binary image for further processing after color
filtering. The desired object is clearly determined after removing
pixel noise by applying image morphology operations and contour
definition. Finally, the area and the center of the object are
determined so that object’s motion to be tracked. The smartphone
application has been placed on a robot car and transmits by Bluetooth
to an Arduino assembly the motion directives so that to follow
objects of a specified color. The experimental evaluation of the
proposed algorithm shows reliable color detection and smooth
tracking characteristics.
Abstract: Image enhancement is a challenging issue in many applications. In the last two decades, there are various filters developed. This paper proposes a novel method which removes Gaussian noise from the gray scale images. The proposed technique is compared with Enhanced Fuzzy Peer Group Filter (EFPGF) for various noise levels. Experimental results proved that the proposed filter achieves better Peak-Signal-to-Noise-Ratio PSNR than the existing techniques. The proposed technique achieves 1.736dB gain in PSNR than the EFPGF technique.
Abstract: We have conducted the optimal synthesis of rootmean-
squared objective filter to estimate the state vector in the case if
within the observation channel with memory the anomalous noises
with unknown mathematical expectation are complement in the
function of the regular noises. The synthesis has been carried out for
linear stochastic systems of continuous - time.
Abstract: A cyclostationary Gaussian linearization method is
formulated for investigating the time average response of nonlinear
system under sinusoidal signal and white noise excitation. The
quantitative measure of cyclostationary mean, variance, spectrum of
mean amplitude, and mean power spectral density of noise are
analyzed. The qualitative response behavior of stochastic jump and
bifurcation are investigated. The validity of the present approach in
predicting the quantitative and qualitative statistical responses is
supported by utilizing Monte Carlo simulations. The present analysis
without imposing restrictive analytical conditions can be directly
derived by solving non-linear algebraic equations. The analytical
solution gives reliable quantitative and qualitative prediction of mean
and noise response for the Duffing system subjected to both sinusoidal
signal and white noise excitation.
Abstract: Subspace channel estimation methods have been
studied widely, where the subspace of the covariance matrix is
decomposed to separate the signal subspace from noise subspace. The
decomposition is normally done by using either the eigenvalue
decomposition (EVD) or the singular value decomposition (SVD) of
the auto-correlation matrix (ACM). However, the subspace
decomposition process is computationally expensive. This paper
considers the estimation of the multipath slow frequency hopping
(FH) channel using noise space based method. In particular, an
efficient method is proposed to estimate the multipath time delays by
applying multiple signal classification (MUSIC) algorithm which is
based on the null space extracted by the rank revealing LU (RRLU)
factorization. As a result, precise information is provided by the
RRLU about the numerical null space and the rank, (i.e., important
tool in linear algebra). The simulation results demonstrate the
effectiveness of the proposed novel method by approximately
decreasing the computational complexity to the half as compared
with RRQR methods keeping the same performance.
Abstract: This paper provides a quantitative measure of the
time-varying multiunit neuronal spiking activity using an entropy
based approach. To verify the status embedded in the neuronal activity
of a population of neurons, the discrete wavelet transform (DWT) is
used to isolate the inherent spiking activity of MUA. Due to the
de-correlating property of DWT, the spiking activity would be
preserved while reducing the non-spiking component. By evaluating
the entropy of the wavelet coefficients of the de-noised MUA, a
multiresolution Shannon entropy (MRSE) of the MUA signal is
developed. The proposed entropy was tested in the analysis of both
simulated noisy MUA and actual MUA recorded from cortex in rodent
model. Simulation and experimental results demonstrate that the
dynamics of a population can be quantified by using the proposed
entropy.
Abstract: This paper presents a novel integrated hybrid
approach for fault diagnosis (FD) of nonlinear systems. Unlike most
FD techniques, the proposed solution simultaneously accomplishes
fault detection, isolation, and identification (FDII) within a unified
diagnostic module. At the core of this solution is a bank of adaptive
neural parameter estimators (NPE) associated with a set of singleparameter
fault models. The NPEs continuously estimate unknown
fault parameters (FP) that are indicators of faults in the system. Two
NPE structures including series-parallel and parallel are developed
with their exclusive set of desirable attributes. The parallel scheme is
extremely robust to measurement noise and possesses a simpler, yet
more solid, fault isolation logic. On the contrary, the series-parallel
scheme displays short FD delays and is robust to closed-loop system
transients due to changes in control commands. Finally, a fault
tolerant observer (FTO) is designed to extend the capability of the
NPEs to systems with partial-state measurement.
Abstract: In this paper, we introduced a gradient-based inverse
solver to obtain the missing boundary conditions based on the
readings of internal thermocouples. The results show that the method
is very sensitive to measurement errors, and becomes unstable when
small time steps are used. The artificial neural networks are shown to
be capable of capturing the whole thermal history on the run-out
table, but are not very effective in restoring the detailed behavior of
the boundary conditions. Also, they behave poorly in nonlinear cases
and where the boundary condition profile is different.
GA and PSO are more effective in finding a detailed
representation of the time-varying boundary conditions, as well as in
nonlinear cases. However, their convergence takes longer. A
variation of the basic PSO, called CRPSO, showed the best
performance among the three versions. Also, PSO proved to be
effective in handling noisy data, especially when its performance
parameters were tuned. An increase in the self-confidence parameter
was also found to be effective, as it increased the global search
capabilities of the algorithm. RPSO was the most effective variation
in dealing with noise, closely followed by CRPSO. The latter
variation is recommended for inverse heat conduction problems, as it
combines the efficiency and effectiveness required by these
problems.
Abstract: For optimal unbiased filter as mean-square and in the
case of functioning anomalous noises in the observation memory
channel, we have proved insensitivity of filter to inaccurate
knowledge of the anomalous noise intensity matrix and its
equivalence to truncated filter plotted only by non anomalous
components of an observation vector.
Abstract: A model was constructed to predict the amount of
solar radiation that will make contact with the surface of the earth in
a given location an hour into the future. This project was supported
by the Southern Company to determine at what specific times during
a given day of the year solar panels could be relied upon to produce
energy in sufficient quantities. Due to their ability as universal
function approximators, an artificial neural network was used to
estimate the nonlinear pattern of solar radiation, which utilized
measurements of weather conditions collected at the Griffin, Georgia
weather station as inputs. A number of network configurations and
training strategies were utilized, though a multilayer perceptron with
a variety of hidden nodes trained with the resilient propagation
algorithm consistently yielded the most accurate predictions. In
addition, a modeled direct normal irradiance field and adjacent
weather station data were used to bolster prediction accuracy. In later
trials, the solar radiation field was preprocessed with a discrete
wavelet transform with the aim of removing noise from the
measurements. The current model provides predictions of solar
radiation with a mean square error of 0.0042, though ongoing efforts
are being made to further improve the model’s accuracy.
Abstract: The detection of moving objects from a video image
sequences is very important for object tracking, activity recognition,
and behavior understanding in video surveillance.
The most used approach for moving objects detection / tracking is
background subtraction algorithms. Many approaches have been
suggested for background subtraction. But, these are illumination
change sensitive and the solutions proposed to bypass this problem
are time consuming.
In this paper, we propose a robust yet computationally efficient
background subtraction approach and, mainly, focus on the ability to
detect moving objects on dynamic scenes, for possible applications in
complex and restricted access areas monitoring, where moving and
motionless persons must be reliably detected. It consists of three
main phases, establishing illumination changes invariance,
background/foreground modeling and morphological analysis for
noise removing.
We handle illumination changes using Contrast Limited Histogram
Equalization (CLAHE), which limits the intensity of each pixel to
user determined maximum. Thus, it mitigates the degradation due to
scene illumination changes and improves the visibility of the video
signal. Initially, the background and foreground images are extracted
from the video sequence. Then, the background and foreground
images are separately enhanced by applying CLAHE.
In order to form multi-modal backgrounds we model each channel
of a pixel as a mixture of K Gaussians (K=5) using Gaussian Mixture
Model (GMM). Finally, we post process the resulting binary
foreground mask using morphological erosion and dilation
transformations to remove possible noise.
For experimental test, we used a standard dataset to challenge the
efficiency and accuracy of the proposed method on a diverse set of
dynamic scenes.
Abstract: The present work analyses different parameters of end
milling to minimize the surface roughness for AISI D2 steel. D2 Steel
is generally used for stamping or forming dies, punches, forming
rolls, knives, slitters, shear blades, tools, scrap choppers, tyre
shredders etc. Surface roughness is one of the main indices that
determines the quality of machined products and is influenced by
various cutting parameters. In machining operations, achieving
desired surface quality by optimization of machining parameters, is a
challenging job. In case of mating components the surface roughness
become more essential and is influenced by the cutting parameters,
because, these quality structures are highly correlated and are
expected to be influenced directly or indirectly by the direct effect of
process parameters or their interactive effects (i.e. on process
environment). In this work, the effects of selected process parameters
on surface roughness and subsequent setting of parameters with the
levels have been accomplished by Taguchi’s parameter design
approach. The experiments have been performed as per the
combination of levels of different process parameters suggested by
L9 orthogonal array. Experimental investigation of the end milling of
AISI D2 steel with carbide tool by varying feed, speed and depth of
cut and the surface roughness has been measured using surface
roughness tester. Analyses of variance have been performed for mean
and signal-to-noise ratio to estimate the contribution of the different
process parameters on the process.
Abstract: Quantification of cardiac function is performed by
calculating blood volume and ejection fraction in routine clinical
practice. However, these works have been performed by manual
contouring, which requires computational costs and varies on the
observer. In this paper, an automatic left ventricle segmentation
algorithm on cardiac magnetic resonance images (MRI) is presented.
Using knowledge on cardiac MRI, a K-mean clustering technique is
applied to segment blood region on a coil-sensitivity corrected image.
Then, a graph searching technique is used to correct segmentation
errors from coil distortion and noises. Finally, blood volume and
ejection fraction are calculated. Using cardiac MRI from 15 subjects,
the presented algorithm is tested and compared with manual
contouring by experts to show outstanding performance.
Abstract: We propose a code acquisition scheme called improved
multiple-shift (IMS) for optical code division multiple access
systems, where the optical orthogonal code is used instead of the
pseudo noise code. Although the IMS algorithm has a similar process
to that of the conventional MS algorithm, it has a better code
acquisition performance than the conventional MS algorithm. We
analyze the code acquisition performance of the IMS algorithm and
compare the code acquisition performances of the MS and the IMS
algorithms in single-user and multi-user environments.
Abstract: Mechanical stress has a strong effect on the magnitude
of the Barkhausen-noise in structural steels. Because the
measurements are performed at the surface of the material, for a
sample sheet, the full effect can be described by a biaxial stress field.
The measured Barkhausen-noise is dependent on the orientation of
the exciting magnetic field relative to the axis of the stress tensor.
The sample inhomogenities including the residual stress also
modifies the angular dependence of the measured Barkhausen-noise.
We have developed a laboratory device with a cross like specimen
for bi-axial bending. The measuring head allowed performing
excitations in two orthogonal directions. We could excite the two
directions independently or simultaneously with different amplitudes.
The simultaneous excitation of the two coils could be performed in
phase or with a 90 degree phase shift. In principle this allows to
measure the Barkhausen-noise at an arbitrary direction without
moving the head, or to measure the Barkhausen-noise induced by a
rotating magnetic field if a linear superposition of the two fields can
be assumed.
Abstract: The performance and analysis of speech recognition
system is illustrated in this paper. An approach to recognize the
English word corresponding to digit (0-9) spoken by 2 different
speakers is captured in noise free environment. For feature extraction,
speech Mel frequency cepstral coefficients (MFCC) has been used
which gives a set of feature vectors from recorded speech samples.
Neural network model is used to enhance the recognition
performance. Feed forward neural network with back propagation
algorithm model is used. However other speech recognition
techniques such as HMM, DTW exist. All experiments are carried
out on Matlab.
Abstract: The ultrasound imaging is very popular to diagnosis
the disease because of its non-invasive nature. The ultrasound
imaging slowly produces low quality images due to the presence of
spackle noise and wave interferences. There are several algorithms to
be proposed for the segmentation of ultrasound carotid artery images
but it requires a certain limit of user interaction. The pixel in an
image is highly correlated so the spatial information of surrounding
pixels may be considered in the process of image segmentation which
improves the results further. When data is highly correlated, one pixel
may belong to more than one cluster with different degree of
membership. There is an important step to computerize the evaluation
of arterial disease severity using segmentation of carotid artery lumen
in 2D and 3D ultrasonography and in finding vulnerable
atherosclerotic plaques susceptible to rupture which can cause stroke.