Abstract: The one-class support vector machine “support vector
data description” (SVDD) is an ideal approach for anomaly or outlier
detection. However, for the applicability of SVDD in real-world
applications, the ease of use is crucial. The results of SVDD are
massively determined by the choice of the regularisation parameter C
and the kernel parameter of the widely used RBF kernel. While for
two-class SVMs the parameters can be tuned using cross-validation
based on the confusion matrix, for a one-class SVM this is not
possible, because only true positives and false negatives can occur
during training. This paper proposes an approach to find the optimal
set of parameters for SVDD solely based on a training set from
one class and without any user parameterisation. Results on artificial
and real data sets are presented, underpinning the usefulness of the
approach.
Abstract: In the automotive industry test drives are being conducted
during the development of new vehicle models or as a part of
quality assurance of series-production vehicles. The communication
on the in-vehicle network, data from external sensors, or internal
data from the electronic control units is recorded by automotive
data loggers during the test drives. The recordings are used for fault
analysis. Since the resulting data volume is tremendous, manually
analysing each recording in great detail is not feasible.
This paper proposes to use machine learning to support domainexperts
by preventing them from contemplating irrelevant data and
rather pointing them to the relevant parts in the recordings. The
underlying idea is to learn the normal behaviour from available
recordings, i.e. a training set, and then to autonomously detect
unexpected deviations and report them as anomalies.
The one-class support vector machine “support vector data description”
is utilised to calculate distances of feature vectors. SVDDSUBSEQ
is proposed as a novel approach, allowing to classify subsequences
in multivariate time series data. The approach allows to
detect unexpected faults without modelling effort as is shown with
experimental results on recordings from test drives.
Abstract: Nondestructive testing in engineering is an inverse
Cauchy problem for Laplace equation. In this paper the problem
of nondestructive testing is expressed by a Laplace-s equation with
third-kind boundary conditions. In order to find unknown values on
the boundary, the method of fundamental solution is introduced and
realized. Because of the ill-posedness of studied problems, the TSVD
regularization technique in combination with L-curve criteria and
Generalized Cross Validation criteria is employed. Numerical results
are shown that the TSVD method combined with L-curve criteria is
more efficient than the TSVD method combined with GCV criteria.
The abstract goes here.
Abstract: Multi-dimensional principal component analysis
(PCA) is the extension of the PCA, which is used widely as the
dimensionality reduction technique in multivariate data analysis, to
handle multi-dimensional data. To calculate the PCA the singular
value decomposition (SVD) is commonly employed by the reason of
its numerical stability. The multi-dimensional PCA can be calculated
by using the higher-order SVD (HOSVD), which is proposed by
Lathauwer et al., similarly with the case of ordinary PCA. In this
paper, we apply the multi-dimensional PCA to the multi-dimensional
medical data including the functional independence measure (FIM)
score, and describe the results of experimental analysis.
Abstract: Snake bite cases in Malaysia most often involve the
species Naja-naja and Calloselasma rhodostoma. In keeping with the
need for a rapid snake venom detection kit in a clinical setting, plate
and dot-ELISA test for the venoms of Naja-naja sumatrana,
Calloselasma rhodostoma and the cobra venom fraction V antigen
was developed. Polyclonal antibodies were raised and further used to
prepare the reagents for the dot-ELISA test kit which was tested in
mice, rabbit and virtual human models. The newly developed dot-
ELISA kit was able to detect a minimum venom concentration of
244ng/ml with cross reactivity of one antibody type. The dot-ELISA
system was sensitive and specific for all three snake venom types in
all tested animal models. The lowest minimum venom concentration
detectable was in the rabbit model, 244ng/ml of the cobra venom
fraction V antigen. The highest minimum venom concentration was
in mice, 1953ng/ml against a multitude of venoms. The developed
dot-ELISA system for the detection of three snake venom types was
successful with a sensitivity of 95.8% and specificity of 97.9%.
Abstract: Support Vector Domain Description (SVDD) is one of the best-known one-class support vector learning methods, in which one tries the strategy of using balls defined on the feature space in order to distinguish a set of normal data from all other possible abnormal objects. As all kernel-based learning algorithms its performance depends heavily on the proper choice of the kernel parameter. This paper proposes a new approach to select kernel's parameter based on maximizing the distance between both gravity centers of normal and abnormal classes, and at the same time minimizing the variance within each class. The performance of the proposed algorithm is evaluated on several benchmarks. The experimental results demonstrate the feasibility and the effectiveness of the presented method.
Abstract: Sparse representation has long been studied and several
dictionary learning methods have been proposed. The dictionary
learning methods are widely used because they are adaptive. In this
paper, a new dictionary learning method for audio is proposed. Signals
are at first decomposed into different degrees of Intrinsic Mode
Functions (IMF) using Empirical Mode Decomposition (EMD)
technique. Then these IMFs form a learned dictionary. To reduce the
size of the dictionary, the K-means method is applied to the dictionary
to generate a K-EMD dictionary. Compared to K-SVD algorithm, the
K-EMD dictionary decomposes audio signals into structured
components, thus the sparsity of the representation is increased by
34.4% and the SNR of the recovered audio signals is increased by
20.9%.
Abstract: A series of microarray experiments produces observations
of differential expression for thousands of genes across multiple
conditions.
Principal component analysis(PCA) has been widely used in
multivariate data analysis to reduce the dimensionality of the data in
order to simplify subsequent analysis and allow for summarization of
the data in a parsimonious manner. PCA, which can be implemented
via a singular value decomposition(SVD), is useful for analysis of
microarray data.
For application of PCA using SVD we use the DNA microarray
data for the small round blue cell tumors(SRBCT) of childhood
by Khan et al.(2001). To decide the number of components which
account for sufficient amount of information we draw scree plot.
Biplot, a graphic display associated with PCA, reveals important
features that exhibit relationship between variables and also the
relationship of variables with observations.
Abstract: In this paper, a novel contrast enhancement technique
for contrast enhancement of a low-contrast satellite image has been
proposed based on the singular value decomposition (SVD) and
discrete cosine transform (DCT). The singular value matrix
represents the intensity information of the given image and any
change on the singular values change the intensity of the input image.
The proposed technique converts the image into the SVD-DCT
domain and after normalizing the singular value matrix; the enhanced
image is reconstructed by using inverse DCT. The visual and
quantitative results suggest that the proposed SVD-DCT method
clearly shows the increased efficiency and flexibility of the proposed
method over the exiting methods such as Linear Contrast Stretching
technique, GHE technique, DWT-SVD technique, DWT technique,
Decorrelation Stretching technique, Gamma Correction method
based techniques.
Abstract: In this paper, we first give the representation of the general solution of the following least-squares problem (LSP): Given matrices X ∈ Rn×p, B ∈ Rp×p and A0 ∈ Rr×r, find a matrix A ∈ Rn×n such that XT AX − B = min, s. t. A([1, r]) = A0, where A([1, r]) is the r×r leading principal submatrix of the matrix A. We then consider a best approximation problem: given an n × n matrix A˜ with A˜([1, r]) = A0, find Aˆ ∈ SE such that A˜ − Aˆ = minA∈SE A˜ − A, where SE is the solution set of LSP. We show that the best approximation solution Aˆ is unique and derive an explicit formula for it. Keyw
Abstract: In this paper, a robust digital image watermarking
scheme for copyright protection applications using the singular value
decomposition (SVD) is proposed. In this scheme, an entropy
masking model has been applied on the host image for the texture
segmentation. Moreover, the local luminance and textures of the host
image are considered for watermark embedding procedure to
increase the robustness of the watermarking scheme. In contrast to all
existing SVD-based watermarking systems that have been designed
to embed visual watermarks, our system uses a pseudo-random
sequence as a watermark. We have tested the performance of our
method using a wide variety of image processing attacks on different
test images. A comparison is made between the results of our
proposed algorithm with those of a wavelet-based method to
demonstrate the superior performance of our algorithm.
Abstract: In digital signal processing it is important to
approximate multi-dimensional data by the method called rank
reduction, in which we reduce the rank of multi-dimensional data from
higher to lower. For 2-dimennsional data, singular value
decomposition (SVD) is one of the most known rank reduction
techniques. Additional, outer product expansion expanded from SVD
was proposed and implemented for multi-dimensional data, which has
been widely applied to image processing and pattern recognition.
However, the multi-dimensional outer product expansion has behavior
of great computation complex and has not orthogonally between the
expansion terms. Therefore we have proposed an alterative method,
Third-order Orthogonal Tensor Product Expansion short for 3-OTPE.
3-OTPE uses the power method instead of nonlinear optimization
method for decreasing at computing time. At the same time the group
of B. D. Lathauwer proposed Higher-Order SVD (HOSVD) that is
also developed with SVD extensions for multi-dimensional data.
3-OTPE and HOSVD are similarly on the rank reduction of
multi-dimensional data. Using these two methods we can obtain
computation results respectively, some ones are the same while some
ones are slight different. In this paper, we compare 3-OTPE to
HOSVD in accuracy of calculation and computing time of resolution,
and clarify the difference between these two methods.
Abstract: The current speech interfaces in many military
applications may be adequate for native speakers. However,
the recognition rate drops quite a lot for non-native speakers
(people with foreign accents). This is mainly because the nonnative
speakers have large temporal and intra-phoneme
variations when they pronounce the same words. This
problem is also complicated by the presence of large
environmental noise such as tank noise, helicopter noise, etc.
In this paper, we proposed a novel continuous acoustic feature
adaptation algorithm for on-line accent and environmental
adaptation. Implemented by incremental singular value
decomposition (SVD), the algorithm captures local acoustic
variation and runs in real-time. This feature-based adaptation
method is then integrated with conventional model-based
maximum likelihood linear regression (MLLR) algorithm.
Extensive experiments have been performed on the NATO
non-native speech corpus with baseline acoustic model trained
on native American English. The proposed feature-based
adaptation algorithm improved the average recognition
accuracy by 15%, while the MLLR model based adaptation
achieved 11% improvement. The corresponding word error
rate (WER) reduction was 25.8% and 2.73%, as compared to
that without adaptation. The combined adaptation achieved
overall recognition accuracy improvement of 29.5%, and
WER reduction of 31.8%, as compared to that without
adaptation.
Abstract: Artificial Neural Network (ANN) has been
extensively used for classification of heart sounds for its
discriminative training ability and easy implementation. However, it
suffers from overparameterization if the number of nodes is not
chosen properly. In such cases, when the dataset has redundancy
within it, ANN is trained along with this redundant information that
results in poor validation. Also a larger network means more
computational expense resulting more hardware and time related
cost. Therefore, an optimum design of neural network is needed
towards real-time detection of pathological patterns, if any from heart
sound signal. The aims of this work are to (i) select a set of input
features that are effective for identification of heart sound signals and
(ii) make certain optimum selection of nodes in the hidden layer for a
more effective ANN structure. Here, we present an optimization
technique that involves Singular Value Decomposition (SVD) and
QR factorization with column pivoting (QRcp) methodology to
optimize empirically chosen over-parameterized ANN structure.
Input nodes present in ANN structure is optimized by SVD followed
by QRcp while only SVD is required to prune undesirable hidden
nodes. The result is presented for classifying 12 common
pathological cases and normal heart sound.