Abstract: This paper presents a new algorithm which yields a nonlinear state estimator called iterated unscented Kalman filter. This state estimator makes use of both statistical and analytical linearization techniques in different parts of the filtering process. It outperforms the other three nonlinear state estimators: unscented Kalman filter (UKF), extended Kalman filter (EKF) and iterated extended Kalman filter (IEKF) when there is severe nonlinearity in system equation and less nonlinearity in measurement equation. The algorithm performance has been verified by illustrating some simulation results.
Abstract: This paper addresses the problem of determining the current 3D location of a moving object and robustly tracking it from a sequence of camera images. The approach presented here uses a particle filter and does not perform any explicit triangulation. Only the color of the object to be tracked is required, but not any precisemotion model. The observation model we have developed avoids the color filtering of the entire image. That and the Monte Carlotechniques inside the particle filter provide real time performance.Experiments with two real cameras are presented and lessons learned are commented. The approach scales easily to more than two cameras and new sensor cues.
Abstract: Decision feedback equalizers are commonly employed to reduce the error caused by intersymbol interference. Here, an adaptive decision feedback equalizer is presented with a new adaptation algorithm. The algorithm follows a block-based approach of normalized least mean square (NLMS) algorithm with set-membership filtering and achieves a significantly less computational complexity over its conventional NLMS counterpart with set-membership filtering. It is shown in the results that the proposed algorithm yields similar type of bit error rate performance over a reasonable signal to noise ratio in comparison with the latter one.
Abstract: We have proposed an information filtering system
using index word selection from a document set based on the
topics included in a set of documents. This method narrows
down the particularly characteristic words in a document set
and the topics are obtained by Sparse Non-negative Matrix
Factorization. In information filtering, a document is often
represented with the vector in which the elements correspond
to the weight of the index words, and the dimension of the
vector becomes larger as the number of documents is
increased. Therefore, it is possible that useless words as index
words for the information filtering are included. In order to
address the problem, the dimension needs to be reduced. Our
proposal reduces the dimension by selecting index words
based on the topics included in a document set. We have
applied the Sparse Non-negative Matrix Factorization to the
document set to obtain these topics. The filtering is carried out
based on a centroid of the learning document set. The centroid
is regarded as the user-s interest. In addition, the centroid is
represented with a document vector whose elements consist of
the weight of the selected index words. Using the English test
collection MEDLINE, thus, we confirm the effectiveness of
our proposal. Hence, our proposed selection can confirm the
improvement of the recommendation accuracy from the other
previous methods when selecting the appropriate number of
index words. In addition, we discussed the selected index
words by our proposal and we found our proposal was able to
select the index words covered some minor topics included in
the document set.
Abstract: Efficient storage, transmission and use of video information are key requirements in many multimedia applications currently being addressed by MPEG-4. To fulfill these requirements, a new approach for representing video information which relies on an object-based representation, has been adopted. Therefore, objectbased watermarking schemes are needed for copyright protection. This paper proposes a novel blind object watermarking scheme for images and video using the in place lifting shape adaptive-discrete wavelet transform (SA-DWT). In order to make the watermark robust and transparent, the watermark is embedded in the average of wavelet blocks using the visual model based on the human visual system. Wavelet coefficients n least significant bits (LSBs) are adjusted in concert with the average. Simulation results shows that the proposed watermarking scheme is perceptually invisible and robust against many attacks such as lossy image/video compression (e.g. JPEG, JPEG2000 and MPEG-4), scaling, adding noise, filtering, etc.
Abstract: Skin color can provide a useful and robust cue
for human-related image analysis, such as face detection,
pornographic image filtering, hand detection and tracking,
people retrieval in databases and Internet, etc. The major
problem of such kinds of skin color detection algorithms is
that it is time consuming and hence cannot be applied to a real
time system. To overcome this problem, we introduce a new
fast technique for skin detection which can be applied in a real
time system. In this technique, instead of testing each image
pixel to label it as skin or non-skin (as in classic techniques),
we skip a set of pixels. The reason of the skipping process is
the high probability that neighbors of the skin color pixels are
also skin pixels, especially in adult images and vise versa. The
proposed method can rapidly detect skin and non-skin color
pixels, which in turn dramatically reduce the CPU time
required for the protection process. Since many fast detection
techniques are based on image resizing, we apply our
proposed pixel skipping technique with image resizing to
obtain better results. The performance evaluation of the
proposed skipping and hybrid techniques in terms of the
measured CPU time is presented. Experimental results
demonstrate that the proposed methods achieve better result
than the relevant classic method.
Abstract: Financial forecasting using machine learning techniques has received great efforts in the last decide . In this ongoing work, we show how machine learning of graphical models will be able to infer a visualized causal interactions between different banks in the Saudi equities market. One important discovery from such learned causal graphs is how companies influence each other and to what extend. In this work, a set of graphical models named Gaussian graphical models with developed ensemble penalized feature selection methods that combine ; filtering method, wrapper method and a regularizer will be shown. A comparison between these different developed ensemble combinations will also be shown. The best ensemble method will be used to infer the causal relationships between banks in Saudi equities market.
Abstract: Although e-mail is the most efficient and popular communication method, unwanted and mass unsolicited e-mails, also called spam mail, endanger the existence of the mail system. This paper proposes a new algorithm called Dynamic Weighted Majority Concept Drift Detection (DWM-CDD) for content-based filtering. The design purposes of DWM-CDD are first to accurate the performance of the previously proposed algorithms, and second to speed up the time to construct the model. The results show that DWM-CDD can detect both sudden and gradual changes quickly and accurately. Moreover, the time needed for model construction is less than previously proposed algorithms.
Abstract: Segmentation, filtering out of measurement errors and
identification of breakpoints are integral parts of any analysis of
microarray data for the detection of copy number variation (CNV).
Existing algorithms designed for these tasks have had some successes
in the past, but they tend to be O(N2) in either computation time or
memory requirement, or both, and the rapid advance of microarray
resolution has practically rendered such algorithms useless. Here we
propose an algorithm, SAD, that is much faster and much less thirsty
for memory – O(N) in both computation time and memory requirement
-- and offers higher accuracy. The two key ingredients of SAD are the
fundamental assumption in statistics that measurement errors are
normally distributed and the mathematical relation that the product of
two Gaussians is another Gaussian (function). We have produced a
computer program for analyzing CNV based on SAD. In addition to
being fast and small it offers two important features: quantitative
statistics for predictions and, with only two user-decided parameters,
ease of use. Its speed shows little dependence on genomic profile.
Running on an average modern computer, it completes CNV analyses
for a 262 thousand-probe array in ~1 second and a 1.8 million-probe
array in 9 seconds
Abstract: This study proposes a new recommender system based on the collaborative folksonomy. The purpose of the proposed system is to recommend Internet resources (such as books, articles, documents, pictures, audio and video) to users. The proposed method includes four steps: creating the user profile based on the tags, grouping the similar users into clusters using an agglomerative hierarchical clustering, finding similar resources based on the user-s past collections by using content-based filtering, and recommending similar items to the target user. This study examines the system-s performance for the dataset collected from “del.icio.us," which is a famous social bookmarking website. Experimental results show that the proposed tag-based collaborative and content-based filtering hybridized recommender system is promising and effectiveness in the folksonomy-based bookmarking website.
Abstract: In this paper we are to find the optimum multiwavelet for compression of electrocardiogram (ECG) signals and then, selecting it for using with SPIHT codec. At present, it is not well known which multiwavelet is the best choice for optimum compression of ECG. In this work, we examine different multiwavelets on 24 sets of ECG data with entirely different characteristics, selected from MIT-BIH database. For assessing the functionality of the different multiwavelets in compressing ECG signals, in addition to known factors such as Compression Ratio (CR), Percent Root Difference (PRD), Distortion (D), Root Mean Square Error (RMSE) in compression literature, we also employed the Cross Correlation (CC) criterion for studying the morphological relations between the reconstructed and the original ECG signal and Signal to reconstruction Noise Ratio (SNR). The simulation results show that the Cardinal Balanced Multiwavelet (cardbal2) by the means of identity (Id) prefiltering method to be the best effective transformation. After finding the most efficient multiwavelet, we apply SPIHT coding algorithm on the transformed signal by this multiwavelet.
Abstract: Image restoration involves elimination of noise. Filtering techniques were adopted so far to restore images since last five decades. In this paper, we consider the problem of image restoration degraded by a blur function and corrupted by random noise. A method for reducing additive noise in images by explicit analysis of local image statistics is introduced and compared to other noise reduction methods. The proposed method, which makes use of an a priori noise model, has been evaluated on various types of images. Bayesian based algorithms and technique of image processing have been described and substantiated with experimentation using MATLAB.
Abstract: Many factors affect the success of Machine Learning
(ML) on a given task. The representation and quality of the instance
data is first and foremost. If there is much irrelevant and redundant
information present or noisy and unreliable data, then knowledge
discovery during the training phase is more difficult. It is well known
that data preparation and filtering steps take considerable amount of
processing time in ML problems. Data pre-processing includes data
cleaning, normalization, transformation, feature extraction and
selection, etc. The product of data pre-processing is the final training
set. It would be nice if a single sequence of data pre-processing
algorithms had the best performance for each data set but this is not
happened. Thus, we present the most well know algorithms for each
step of data pre-processing so that one achieves the best performance
for their data set.
Abstract: Mostly the systems are dealing with time varying
signals. The Power efficiency can be achieved by adapting the system
activity according to the input signal variations. In this context
an adaptive rate filtering technique, based on the level crossing sampling
is devised. It adapts the sampling frequency and the filter order
by following the input signal local variations. Thus, it correlates the
processing activity with the signal variations. Interpolation is required
in the proposed technique. A drastic reduction in the interpolation
error is achieved by employing the symmetry during the interpolation
process. Processing error of the proposed technique is
calculated. The computational complexity of the proposed filtering
technique is deduced and compared to the classical one. Results
promise a significant gain of the computational efficiency and hence
of the power consumption.
Abstract: In this paper a simple watermarking method for
color images is proposed. The proposed method is based on
watermark embedding for the histograms of the HSV planes
using visual cryptography watermarking. The method has
been proved to be robust for various image processing
operations such as filtering, compression, additive noise, and
various geometrical attacks such as rotation, scaling, cropping,
flipping, and shearing.
Abstract: In this paper, the application of the Mode Matching
(MM) method in the case of photonic crystal waveguide
discontinuities is presented. The structure under consideration is
divided into a number of cells, which supports a number of guided
and evanescent modes. These modes can be calculated numerically
by an alternative formulation of the plane wave expansion method
for each frequency. A matrix equation is then formed relating the
modal amplitudes at the beginning and at the end of the structure.
The theory is highly efficient and accurate and can be applied to
study the transmission sensitivity of photonic crystal devices due to
fabrication tolerances. The accuracy of the MM method is compared
to the Finite Difference Frequency Domain (FDFD) and the Adjoint
Variable Method (AVM) and good agreement is observed.
Abstract: Question answering (QA) aims at retrieving precise information from a large collection of documents. Most of the Question Answering systems composed of three main modules: question processing, document processing and answer processing. Question processing module plays an important role in QA systems to reformulate questions. Moreover answer processing module is an emerging topic in QA systems, where these systems are often required to rank and validate candidate answers. These techniques aiming at finding short and precise answers are often based on the semantic relations and co-occurrence keywords. This paper discussed about a new model for question answering which improved two main modules, question processing and answer processing which both affect on the evaluation of the system operations. There are two important components which are the bases of the question processing. First component is question classification that specifies types of question and answer. Second one is reformulation which converts the user's question into an understandable question by QA system in a specific domain. The objective of an Answer Validation task is thus to judge the correctness of an answer returned by a QA system, according to the text snippet given to support it. For validating answers we apply candidate answer filtering, candidate answer ranking and also it has a final validation section by user voting. Also this paper described new architecture of question and answer processing modules with modeling, implementing and evaluating the system. The system differs from most question answering systems in its answer validation model. This module makes it more suitable to find exact answer. Results show that, from total 50 asked questions, evaluation of the model, show 92% improving the decision of the system.
Abstract: In this paper we propose a method for recognition of
adult video based on support vector machine (SVM). Different kernel
features are proposed to classify adult videos. SVM has an advantage
that it is insensitive to the relative number of training example in
positive (adult video) and negative (non adult video) classes. This
advantage is illustrated by comparing performance between different
SVM kernels for the identification of adult video.
Abstract: We describe a new filtering approach in the wavelet domain for image denoising and compression, based on the projections of details subbands coefficients (resultants of the splitting procedure, typical in wavelet domain) onto the approximation subband coefficients (much less noisy). The new algorithm is called Projection Onto Approximation Coefficients (POAC). As a result of this approach, only the approximation subband coefficients and three scalars are stored and/or transmitted to the channel. Besides, with the elimination of the details subbands coefficients, we obtain a bigger compression rate. Experimental results demonstrate that our approach compares favorably to more typical methods of denoising and compression in wavelet domain.
Abstract: Image retrieval is a topic where scientific interest is currently high. The important steps associated with image retrieval system are the extraction of discriminative features and a feasible similarity metric for retrieving the database images that are similar in content with the search image. Gabor filtering is a widely adopted technique for feature extraction from the texture images. The recently proposed sparsity promoting l1-norm minimization technique finds the sparsest solution of an under-determined system of linear equations. In the present paper, the l1-norm minimization technique as a similarity metric is used in image retrieval. It is demonstrated through simulation results that the l1-norm minimization technique provides a promising alternative to existing similarity metrics. In particular, the cases where the l1-norm minimization technique works better than the Euclidean distance metric are singled out.