Abstract: In this work, we present a novel active learning approach
for learning a visual object detection system. Our system
is composed of an active learning mechanism as wrapper around
a sub-algorithm which implement an online boosting-based learning
object detector. In the core is a combination of a bootstrap procedure
and a semi automatic learning process based on the online boosting
procedure. The idea is to exploit the availability of classifier during
learning to automatically label training samples and increasingly
improves the classifier. This addresses the issue of reducing labeling
effort meanwhile obtain better performance. In addition, we propose
a verification process for further improvement of the classifier.
The idea is to allow re-update on seen data during learning for
stabilizing the detector. The main contribution of this empirical study
is a demonstration that active learning based on an online boosting
approach trained in this manner can achieve results comparable or
even outperform a framework trained in conventional manner using
much more labeling effort. Empirical experiments on challenging data
set for specific object deteciton problems show the effectiveness of
our approach.
Abstract: As the performance of the filtering system depends
upon the accuracy of the noise detection scheme, in this paper, we
present a new scheme for impulse noise detection based on two
levels of decision. In this scheme in the first stage we coarsely
identify the corrupted pixels and in the second stage we finally
decide whether the pixel under consideration is really corrupt or not.
The efficacy of the proposed filter has been confirmed by extensive
simulations.
Abstract: In this study, an investigation over digestive diseases has been done in which the sound acts as a detector medium. Pursue to the preprocessing the extracted signal in cepstrum domain is registered. After classification of digestive diseases, the system selects random samples based on their features and generates the interest nonstationary, long-term signals via inverse transform in cepstral domain which is presented in digital and sonic form as the output. This structure is updatable or on the other word, by receiving a new signal the corresponding disease classification is updated in the feature domain.
Abstract: Support Vector Machine (SVM) is a statistical
learning tool that was initially developed by Vapnik in 1979 and later
developed to a more complex concept of structural risk minimization
(SRM). SVM is playing an increasing role in applications to
detection problems in various engineering problems, notably in
statistical signal processing, pattern recognition, image analysis, and
communication systems. In this paper, SVM was applied to the
detection of SAR (synthetic aperture radar) images in the presence of
partially developed speckle noise. The simulation was done for single
look and multi-look speckle models to give a complete overlook and
insight to the new proposed model of the SVM-based detector. The
structure of the SVM was derived and applied to real SAR images
and its performance in terms of the mean square error (MSE) metric
was calculated. We showed that the SVM-detected SAR images have
a very low MSE and are of good quality. The quality of the
processed speckled images improved for the multi-look model.
Furthermore, the contrast of the SVM detected images was higher
than that of the original non-noisy images, indicating that the SVM
approach increased the distance between the pixel reflectivity levels
(the detection hypotheses) in the original images.
Abstract: Infrared focal plane arrays (IRFPA) sensors, due to
their high sensitivity, high frame frequency and simple structure, have
become the most prominently used detectors in military applications.
However, they suffer from a common problem called the fixed pattern
noise (FPN), which severely degrades image quality and limits the
infrared imaging applications. Therefore, it is necessary to perform
non-uniformity correction (NUC) on IR image. The algorithms of
non-uniformity correction are classified into two main categories, the
calibration-based and scene-based algorithms. There exist some
shortcomings in both algorithms, hence a novel non-uniformity
correction algorithm based on non-linear fit is proposed, which
combines the advantages of the two algorithms. Experimental results
show that the proposed algorithm acquires a good effect of NUC with
a lower non-uniformity ratio.
Abstract: For the past couple of decades Weak signal detection
is of crucial importance in various engineering and scientific
applications. It finds its application in areas like Wireless
communication, Radars, Aerospace engineering, Control systems and
many of those. Usually weak signal detection requires phase sensitive
detector and demodulation module to detect and analyze the signal.
This article gives you a preamble to intrusion detection system which
can effectively detect a weak signal from a multiplexed signal. By
carefully inspecting and analyzing the respective signal, this
system can successfully indicate any peripheral intrusion. Intrusion
detection system (IDS) is a comprehensive and easy approach
towards detecting and analyzing any signal that is weakened and
garbled due to low signal to noise ratio (SNR). This approach
finds significant importance in applications like peripheral security
systems.
Abstract: The submitted paper deals with the problems of
trapping and enriching the gases and aerosols of the substances to be
determined in the ambient atmosphere. Further, the paper is focused
on the working principle of the miniaturized portable continuous
concentrator we have designed and the possibilities of its
application in air sampling and accumulation of organic and
inorganic substances with which the air is contaminated. The stress is
laid on trapping vapours and aerosols of solid substances with the
comparatively low vapour tension such as explosive compounds.
Abstract: Taking into account the link between the efficiency of
a detector and the complexity of a stealth mechanism, we propose in
this paper a new formalism for stealth using graph theory.
Abstract: Five vegetables (spinach, lettuce, cabbage, tomato, and onion) were freshly harvested from the Alau Dam and Gongulong agricultural areas for the determination of some organochlorine pesticide residues (o, p-DDE, p,p’-DDD, o,p’-DDD, p,p’-DDT, α-BHC, γ-BHC, metoxichlor, lindane, endosulfan dieldrin, and aldrin.) Soil samples were also collected at different depths for the determination of the above pesticides. Samples collection and preparation were conducted using standard procedures. The concentrations of all the pesticides in the soil and vegetable samples were determined using GC/MS SHIMADZU (GC-17A) equipped with electron capture detector (ECD). The highest concentration was that of p,p’-DDD (132.4±13.45µg/g) which was observed in the leaf of cabbage, while the lowest concentration was that of p,p’-DDT (2.34µg/g) was observed in the root of spinach. Similar trends were observed at the Gongulong agricultural area, with p,p’-DDD having the highest concentration of 153.23µg/g in the leaf of cabbage, while the lowest concentration was that of p,p’-DDT (12.45µg/g) which was observed in the root of spinach. α-BHC, γ-BHC, Methoxychlor, and lindane were detected in all the vegetable samples studied. The concentrations of all the pesticides in the soil samples were observed to be higher at a depth of 21-30cm, while the lowest concentrations were observed at a depth of 0-10cm. The concentrations of all the pesticides in the vegetables and soil samples from the two agricultural sites were observed to be at alarming levels, much higher than the maximum residue limits (MRLs) and acceptable daily intake values (ADIs) .The levels of the pesticides observed in the vegetables and soil samples investigated, are of such a magnitude that calls for special attention and laws to regulate the use and circulation of such chemicals. Routine monitoring of pesticide residues in these study areas is necessary for the prevention, control and reduction of environmental pollution, so as to minimize health risks.
Abstract: A challenging problem in radar signal processing is to
achieve reliable target detection in the presence of interferences. In
this paper, we propose a novel algorithm for automatic censoring of
radar interfering targets in log-normal clutter. The proposed
algorithm, termed the forward automatic censored cell averaging
detector (F-ACCAD), consists of two steps: removing the corrupted
reference cells (censoring) and the actual detection. Both steps are
performed dynamically by using a suitable set of ranked cells to
estimate the unknown background level and set the adaptive
thresholds accordingly. The F-ACCAD algorithm does not require
any prior information about the clutter parameters nor does it require
the number of interfering targets. The effectiveness of the F-ACCAD
algorithm is assessed by computing, using Monte Carlo simulations,
the probability of censoring and the probability of detection in
different background environments.
Abstract: This paper presents a robust method to detect obstacles in stereo images using shadow removal technique and color information. Stereo vision based obstacle detection is an algorithm that aims to detect and compute obstacle depth using stereo matching and disparity map. The proposed advanced method is divided into three phases, the first phase is detecting obstacles and removing shadows, the second one is matching and the last phase is depth computing. We propose a robust method for detecting obstacles in stereo images using a shadow removal technique based on color information in HIS space, at the first phase. In this paper we use Normalized Cross Correlation (NCC) function matching with a 5 × 5 window and prepare an empty matching table τ and start growing disparity components by drawing a seed s from S which is computed using canny edge detector, and adding it to τ. In this way we achieve higher performance than the previous works [2,17]. A fast stereo matching algorithm is proposed that visits only a small fraction of disparity space in order to find a semi-dense disparity map. It works by growing from a small set of correspondence seeds. The obstacle identified in phase one which appears in the disparity map of phase two enters to the third phase of depth computing. Finally, experimental results are presented to show the effectiveness of the proposed method.
Abstract: Decision fusion is one of hot research topics in
classification area, which aims to achieve the best possible
performance for the task at hand. In this paper, we
investigate the usefulness of this concept to improve change
detection accuracy in remote sensing. Thereby, outputs of
two fuzzy change detectors based respectively on
simultaneous and comparative analysis of multitemporal
data are fused by using fuzzy integral operators. This
method fuses the objective evidences produced by the
change detectors with respect to fuzzy measures that express
the difference of performance between them. The proposed
fusion framework is evaluated in comparison with some
ordinary fuzzy aggregation operators. Experiments carried
out on two SPOT images showed that the fuzzy integral was
the best performing. It improves the change detection
accuracy while attempting to equalize the accuracy rate in
both change and no change classes.
Abstract: Reservoirs with high pressures and temperatures
(HPHT) that were considered to be atypical in the past are now
frequent targets for exploration. For downhole oilfield drilling tools
and components, the temperature and pressure affect the mechanical
strength. To address this issue, a finite element analysis (FEA) for
206.84 MPa (30 ksi) pressure and 165°C has been performed on the
pressure housing of the measurement-while-drilling/logging-whiledrilling
(MWD/LWD) density tool.
The density tool is a MWD/LWD sensor that measures the density
of the formation. One of the components of the density tool is the
pressure housing that is positioned in the tool. The FEA results are
compared with the experimental test performed on the pressure
housing of the density tool. Past results show a close match between
the numerical results and the experimental test. This FEA model can
be used for extreme HPHT and ultra HPHT analyses, and/or optimal
design changes.
Abstract: This paper proposes a smart design strategy for a sequential detector to reliably detect the primary user-s signal, especially in fast fading environments. We study the computation of the log-likelihood ratio for coping with a fast changing received signal and noise sample variances, which are considered random variables. First, we analyze the detectability of the conventional generalized log-likelihood ratio (GLLR) scheme when considering fast changing statistics of unknown parameters caused by fast fading effects. Secondly, we propose an efficient sensing algorithm for performing the sequential probability ratio test in a robust and efficient manner when the channel statistics are unknown. Finally, the proposed scheme is compared to the conventional method with simulation results with respect to the average number of samples required to reach a detection decision.
Abstract: The dynamical contouring error is a critical element for the accuracy of machine tools. The contouring error is defined as the difference between the processing actual path and commanded path, which is implemented by following the command curves from feeding driving system in machine tools. The contouring error is resulted from various factors, such as the external loads, friction, inertia moment, feed rate, speed control, servo control, and etc. Thus, the study proposes a 2D compensating system for the contouring accuracy of machine tools. Optical method is adopted by using stable frequency laser diode and the high precision position sensor detector (PSD) to performno-contact measurement. Results show the related accuracy of position sensor detector (PSD) of 2D contouring accuracy compensating system was ±1.5 μm for a calculated range of ±3 mm, and improvement accuracy is over 80% at high-speed feed rate.
Abstract: Although silicon photonic devices provide a significantly larger bandwidth and dissipate a substantially less power than the electronic devices, they suffer from a large size due to the fundamental diffraction limit and the weak optical response of Si. A potential solution is to exploit Si plasmonics, which may not only miniaturize the photonic device far beyond the diffraction limit, but also enhance the optical response in Si due to the electromagnetic field confinement. In this paper, we discuss and summarize the recently developed metal-insulator-Si-insulator-metal nanoplasmonic waveguide as well as various passive and active plasmonic components based on this waveguide, including coupler, bend, power splitter, ring resonator, MZI, modulator, detector, etc. All these plasmonic components are CMOS compatible and could be integrated with electronic and conventional dielectric photonic devices on the same SOI chip. More potential plasmonic devices as well as plasmonic nanocircuits with complex functionalities are also addressed.
Abstract: Cosmic showers, during the transit through space, produce
sub - products as a result of interactions with the intergalactic
or interstellar medium which after entering earth generate secondary
particles called Extensive Air Shower (EAS). Detection and analysis
of High Energy Particle Showers involve a plethora of theoretical and
experimental works with a host of constraints resulting in inaccuracies
in measurements. Therefore, there exist a necessity to develop a
readily available system based on soft-computational approaches
which can be used for EAS analysis. This is due to the fact that soft
computational tools such as Artificial Neural Network (ANN)s can be
trained as classifiers to adapt and learn the surrounding variations. But
single classifiers fail to reach optimality of decision making in many
situations for which Multiple Classifier System (MCS) are preferred
to enhance the ability of the system to make decisions adjusting
to finer variations. This work describes the formation of an MCS
using Multi Layer Perceptron (MLP), Recurrent Neural Network
(RNN) and Probabilistic Neural Network (PNN) with data inputs
from correlation mapping Self Organizing Map (SOM) blocks and
the output optimized by another SOM. The results show that the setup
can be adopted for real time practical applications for prediction
of primary energy and location of EAS from density values captured
using detectors in a circular grid.
Abstract: In this paper, we consider a multi user multiple input
multiple output (MU-MIMO) based cooperative reporting system for
cognitive radio network. In the reporting network, the secondary
users forward the primary user data to the common fusion center
(FC). The FC is equipped with linear equalizers and an energy
detector to make the decision about the spectrum. The primary user
data are considered to be a digital video broadcasting - terrestrial
(DVB-T) signal. The sensing channel and the reporting channel are
assumed to be an additive white Gaussian noise and an independent
identically distributed Raleigh fading respectively. We analyzed the
detection probability of MU-MIMO system with linear equalizers and
arrived at the closed form expression for average detection
probability. Also the system performance is investigated under
various MIMO scenarios through Monte Carlo simulations.
Abstract: Loop detectors report traffic characteristics in real
time. They are at the core of traffic control process. Intuitively,
one would expect that as density of detection increases, so would
the quality of estimates derived from detector data. However, as
detector deployment increases, the associated operating and
maintenance cost increases. Thus, traffic agencies often need to
decide where to add new detectors and which detectors should
continue receiving maintenance, given their resource constraints.
This paper evaluates the effect of detector spacing on freeway
travel time estimation. A freeway section (Interstate-15) in Salt
Lake City metropolitan region is examined. The research reveals
that travel time accuracy does not necessarily deteriorate with
increased detector spacing. Rather, the actual location of detectors
has far greater influence on the quality of travel time estimates.
The study presents an innovative computational approach that
delivers optimal detector locations through a process that relies on
Genetic Algorithm formulation.
Abstract: For gamma radiation detection, assemblies having
scintillation crystals and a photomultiplier tube, also there is a
preamplifier connected to the detector because the signals from
photomultiplier tube are of small amplitude. After pre-amplification
the signals are sent to the amplifier and then to the multichannel
analyser. The multichannel analyser sorts all incoming electrical
signals according to their amplitudes and sorts the detected photons
in channels covering small energy intervals. The energy range of
each channel depends on the gain settings of the multichannel
analyser and the high voltage across the photomultiplier tube. The
exit spectrum data of the two main isotopes studied ,putting data in
biomass program ,process it by Matlab program to get the solid
holdup image (solid spherical nuclear fuel)