Abstract: This paper proposes an efficient method to classify
inverse synthetic aperture (ISAR) images. Because ISAR images can
be translated and rotated in the 2-dimensional image place, invariance
to the two factors is indispensable for successful classification. The
proposed method achieves invariance to translation and rotation of
ISAR images using a combination of two-dimensional Fourier
transform, polar mapping and correlation-based alignment of the
image. Classification is conducted using a simple matching score
classifier. In simulations using the real ISAR images of five scaled
models measured in a compact range, the proposed method yields
classification ratios higher than 97 %.
Abstract: In this paper, we proposed a method to classify each
type of natural rock texture. Our goal is to classify 26 classes of rock
textures. First, we extract five features of each class by using
principle component analysis combining with the use of applied
spatial frequency measurement. Next, the effective node number of
neural network was tested. We used the most effective neural
network in classification process. The results from this system yield
quite high in recognition rate. It is shown that high recognition rate
can be achieved in separation of 26 stone classes.
Abstract: Microarray data profiles gene expression on a whole
genome scale, therefore, it provides a good way to study associations
between gene expression and occurrence or progression of cancer.
More and more researchers realized that microarray data is helpful
to predict cancer sample. However, the high dimension of gene
expressions is much larger than the sample size, which makes this
task very difficult. Therefore, how to identify the significant genes
causing cancer becomes emergency and also a hot and hard research
topic. Many feature selection algorithms have been proposed in
the past focusing on improving cancer predictive accuracy at the
expense of ignoring the correlations between the features. In this
work, a novel framework (named by SGS) is presented for stable gene
selection and efficient cancer prediction . The proposed framework
first performs clustering algorithm to find the gene groups where
genes in each group have higher correlation coefficient, and then
selects the significant genes in each group with Bayesian Lasso and
important gene groups with group Lasso, and finally builds prediction
model based on the shrinkage gene space with efficient classification
algorithm (such as, SVM, 1NN, Regression and etc.). Experiment
results on real world data show that the proposed framework often
outperforms the existing feature selection and prediction methods,
say SAM, IG and Lasso-type prediction model.
Abstract: Spare parts inventory management is one of the major
areas of inventory research. Analysis of recent literature showed that
an approach integrating spare parts classification, demand
forecasting, and stock control policies is essential; however, adapting
this integrated approach is limited. This work presents an integrated
framework for spare part inventory management and an Excel based
application developed for the implementation of the proposed
framework. A multi-criteria analysis has been used for spare
classification. Forecasting of spare parts- intermittent demand has
been incorporated into the application using three different
forecasting models; namely, normal distribution, exponential
smoothing, and Croston method. The application is also capable of
running with different inventory control policies. To illustrate the
performance of the proposed framework and the developed
application; the framework is applied to different items at a service
organization. The results achieved are presented and possible areas
for future work are highlighted.
Abstract: The use of radar in Quantitative Precipitation Estimation (QPE) for radar-rainfall measurement is significantly beneficial. Radar has advantages in terms of high spatial and temporal condition in rainfall measurement and also forecasting. In Malaysia, radar application in QPE is still new and needs to be explored. This paper focuses on the Z/R derivation works of radarrainfall estimation based on rainfall classification. The works developed new Z/R relationships for Klang River Basin in Selangor area for three different general classes of rain events, namely low (10mm/hr, 30mm/hr) and also on more specific rain types during monsoon seasons. Looking at the high potential of Doppler radar in QPE, the newly formulated Z/R equations will be useful in improving the measurement of rainfall for any hydrological application, especially for flood forecasting.
Abstract: In this paper we introduce a novel kernel classifier
based on a iterative shrinkage algorithm developed for compressive
sensing. We have adopted Bregman iteration with soft and hard
shrinkage functions and generalized hinge loss for solving l1 norm
minimization problem for classification. Our experimental results
with face recognition and digit classification using SVM as the
benchmark have shown that our method has a close error rate
compared to SVM but do not perform better than SVM. We have
found that the soft shrinkage method give more accuracy and in some
situations more sparseness than hard shrinkage methods.
Abstract: Olomouc is a unique and complex landmark with
widespread forestation and land use. This research work was
conducted to assess important and complex land use change
trajectories in Olomouc region. Multi-temporal satellite data from
1991, 2001 and 2013 were used to extract land use/cover types by
object oriented classification method. To achieve the objectives, three
different aspects were used: (1) Calculate the quantity of each
transition; (2) Allocate location based landscape pattern (3) Compare
land use/cover evaluation procedure. Land cover change trajectories
shows that 16.69% agriculture, 54.33% forest and 21.98% other areas
(settlement, pasture and water-body) were stable in all three decade.
Approximately 30% of the study area maintained as a same land cove
type from 1991 to 2013. Here broad scale of political and socioeconomic
factors was also affect the rate and direction of landscape
changes. Distance from the settlements was the most important
predictor of land cover change trajectories. This showed that most of
landscape trajectories were caused by socio-economic activities and
mainly led to virtuous change on the ecological environment.
Abstract: The main goal of data mining is to extract accurate, comprehensible and interesting knowledge from databases that may be considered as large search spaces. In this paper, a new, efficient type of Genetic Algorithm (GA) called uniform two-level GA is proposed as a search strategy to discover truly interesting, high-level prediction rules, a difficult problem and relatively little researched, rather than discovering classification knowledge as usual in the literatures. The proposed method uses the advantage of uniform population method and addresses the task of generalized rule induction that can be regarded as a generalization of the task of classification. Although the task of generalized rule induction requires a lot of computations, which is usually not satisfied with the normal algorithms, it was demonstrated that this method increased the performance of GAs and rapidly found interesting rules.
Abstract: The distinction among urban, periurban and rural areas represents a classical example of uncertainty in land classification. Satellite images, geostatistical analysis and all kinds of spatial data are very useful in urban sprawl studies, but it is important to define precise rules in combining great amounts of data to build complex knowledge about territory. Rough Set theory may be a useful method to employ in this field. It represents a different mathematical approach to uncertainty by capturing the indiscernibility. Two different phenomena can be indiscernible in some contexts and classified in the same way when combining available information about them. This approach has been applied in a case of study, comparing the results achieved with both Map Algebra technique and Spatial Rough Set. The study case area, Potenza Province, is particularly suitable for the application of this theory, because it includes 100 municipalities with different number of inhabitants and morphologic features.
Abstract: Discovering new biological knowledge from the highthroughput biological data is a major challenge to bioinformatics today. To address this challenge, we developed a new approach for protein classification. Proteins that are evolutionarily- and thereby functionally- related are said to belong to the same classification. Identifying protein classification is of fundamental importance to document the diversity of the known protein universe. It also provides a means to determine the functional roles of newly discovered protein sequences. Our goal is to predict the functional classification of novel protein sequences based on a set of features extracted from each protein sequence. The proposed technique used datasets extracted from the Structural Classification of Proteins (SCOP) database. A set of spectral domain features based on Fast Fourier Transform (FFT) is used. The proposed classifier uses multilayer back propagation (MLBP) neural network for protein classification. The maximum classification accuracy is about 91% when applying the classifier to the full four levels of the SCOP database. However, it reaches a maximum of 96% when limiting the classification to the family level. The classification results reveal that spectral domain contains information that can be used for classification with high accuracy. In addition, the results emphasize that sequence similarity measures are of great importance especially at the family level.
Abstract: Motor imagery classification provides an important basis for designing Brain Machine Interfaces [BMI]. A BMI captures and decodes brain EEG signals and transforms human thought into actions. The ability of an individual to control his EEG through imaginary mental tasks enables him to control devices through the BMI. This paper presents a method to design a four state BMI using EEG signals recorded from the C3 and C4 locations. Principle features extracted through principle component analysis of the segmented EEG are analyzed using two novel classification algorithms using Elman recurrent neural network and functional link neural network. Performance of both classifiers is evaluated using a particle swarm optimization training algorithm; results are also compared with the conventional back propagation training algorithm. EEG motor imagery recorded from two subjects is used in the offline analysis. From overall classification performance it is observed that the BP algorithm has higher average classification of 93.5%, while the PSO algorithm has better training time and maximum classification. The proposed methods promises to provide a useful alternative general procedure for motor imagery classification
Abstract: The paper describes a new approach for fingerprint
classification, based on the distribution of local features (minute
details or minutiae) of the fingerprints. The main advantage is that
fingerprint classification provides an indexing scheme to facilitate
efficient matching in a large fingerprint database. A set of rules based
on heuristic approach has been proposed. The area around the core
point is treated as the area of interest for extracting the minutiae
features as there are substantial variations around the core point as
compared to the areas away from the core point. The core point in a
fingerprint has been located at a point where there is maximum
curvature. The experimental results report an overall average
accuracy of 86.57 % in fingerprint classification.
Abstract: In this article a modification of the algorithm of the fuzzy ART network, aiming at returning it supervised is carried out. It consists of the search for the comparison, training and vigilance parameters giving the minimum quadratic distances between the output of the training base and those obtained by the network. The same process is applied for the determination of the parameters of the fuzzy ARTMAP giving the most powerful network. The modification consist in making learn the fuzzy ARTMAP a base of examples not only once as it is of use, but as many time as its architecture is in evolution or than the objective error is not reached . In this way, we don-t worry about the values to impose on the eight (08) parameters of the network. To evaluate each one of these three networks modified, a comparison of their performances is carried out. As application we carried out a classification of the image of Algiers-s bay taken by SPOT XS. We use as criterion of evaluation the training duration, the mean square error (MSE) in step control and the rate of good classification per class. The results of this study presented as curves, tables and images show that modified fuzzy ARTMAP presents the best compromise quality/computing time.
Abstract: Sparse representation which can represent high dimensional
data effectively has been successfully used in computer vision
and pattern recognition problems. However, it doesn-t consider the
label information of data samples. To overcome this limitation,
we develop a novel dimensionality reduction algorithm namely
dscriminatively regularized sparse subspace learning(DR-SSL) in this
paper. The proposed DR-SSL algorithm can not only make use of
the sparse representation to model the data, but also can effective
employ the label information to guide the procedure of dimensionality
reduction. In addition,the presented algorithm can effectively deal
with the out-of-sample problem.The experiments on gene-expression
data sets show that the proposed algorithm is an effective tool for
dimensionality reduction and gene-expression data classification.
Abstract: In this paper, we present a novel statistical approach to
corpus-based speech synthesis. Classically, phonetic information is
defined and considered as acoustic reference to be respected. In this
way, many studies were elaborated for acoustical unit classification.
This type of classification allows separating units according to their
symbolic characteristics. Indeed, target cost and concatenation cost
were classically defined for unit selection.
In Corpus-Based Speech Synthesis System, when using large text
corpora, cost functions were limited to a juxtaposition of symbolic
criteria and the acoustic information of units is not exploited in the
definition of the target cost.
In this manuscript, we token in our consideration the unit phonetic
information corresponding to acoustic information. This would be realized
by defining a probabilistic linguistic Bi-grams model basically
used for unit selection. The selected units would be extracted from
the English TIMIT corpora.
Abstract: The ElectroEncephaloGram (EEG) is useful for
clinical diagnosis and biomedical research. EEG signals often
contain strong ElectroOculoGram (EOG) artifacts produced
by eye movements and eye blinks especially in EEG recorded
from frontal channels. These artifacts obscure the underlying
brain activity, making its visual or automated inspection
difficult. The goal of ocular artifact removal is to remove
ocular artifacts from the recorded EEG, leaving the underlying
background signals due to brain activity. In recent times,
Independent Component Analysis (ICA) algorithms have
demonstrated superior potential in obtaining the least
dependent source components. In this paper, the independent
components are obtained by using the JADE algorithm (best
separating algorithm) and are classified into either artifact
component or neural component. Neural Network is used for
the classification of the obtained independent components.
Neural Network requires input features that exactly represent
the true character of the input signals so that the neural
network could classify the signals based on those key
characters that differentiate between various signals. In this
work, Auto Regressive (AR) coefficients are used as the input
features for classification. Two neural network approaches
are used to learn classification rules from EEG data. First, a
Polynomial Neural Network (PNN) trained by GMDH (Group
Method of Data Handling) algorithm is used and secondly,
feed-forward neural network classifier trained by a standard
back-propagation algorithm is used for classification and the
results show that JADE-FNN performs better than JADEPNN.
Abstract: Results of Chilean wine classification based on the
information provided by an electronic nose are reported in this paper.
The classification scheme consists of two parts; in the first stage,
Principal Component Analysis is used as feature extraction method to
reduce the dimensionality of the original information. Then, Radial
Basis Functions Neural Networks is used as pattern recognition
technique to perform the classification. The objective of this study is
to classify different Cabernet Sauvignon, Merlot and Carménère wine
samples from different years, valleys and vineyards of Chile.
Abstract: Text categorization (the assignment of texts in natural language into predefined categories) is an important and extensively studied problem in Machine Learning. Currently, popular techniques developed to deal with this task include many preprocessing and learning algorithms, many of which in turn require tuning nontrivial internal parameters. Although partial studies are available, many authors fail to report values of the parameters they use in their experiments, or reasons why these values were used instead of others. The goal of this work then is to create a more thorough comparison of preprocessing parameters and their mutual influence, and report interesting observations and results.
Abstract: The evaluation and measurement of human body
dimensions are achieved by physical anthropometry. This research
was conducted in view of the importance of anthropometric indices
of the face in forensic medicine, surgery, and medical imaging. The
main goal of this research is to optimization of facial feature point by
establishing a mathematical relationship among facial features and
used optimize feature points for age classification. Since selected
facial feature points are located to the area of mouth, nose, eyes and
eyebrow on facial images, all desire facial feature points are extracted
accurately. According this proposes method; sixteen Euclidean
distances are calculated from the eighteen selected facial feature
points vertically as well as horizontally. The mathematical
relationships among horizontal and vertical distances are established.
Moreover, it is also discovered that distances of the facial feature
follows a constant ratio due to age progression. The distances
between the specified features points increase with respect the age
progression of a human from his or her childhood but the ratio of the
distances does not change (d = 1 .618 ) . Finally, according to the
proposed mathematical relationship four independent feature
distances related to eight feature points are selected from sixteen
distances and eighteen feature point-s respectively. These four feature
distances are used for classification of age using Support Vector
Machine (SVM)-Sequential Minimal Optimization (SMO) algorithm
and shown around 96 % accuracy. Experiment result shows the
proposed system is effective and accurate for age classification.
Abstract: This research paper deals with the implementation of face recognition using neural network (recognition classifier) on low-resolution images. The proposed system contains two parts, preprocessing and face classification. The preprocessing part converts original images into blurry image using average filter and equalizes the histogram of those image (lighting normalization). The bi-cubic interpolation function is applied onto equalized image to get resized image. The resized image is actually low-resolution image providing faster processing for training and testing. The preprocessed image becomes the input to neural network classifier, which uses back-propagation algorithm to recognize the familiar faces. The crux of proposed algorithm is its beauty to use single neural network as classifier, which produces straightforward approach towards face recognition. The single neural network consists of three layers with Log sigmoid, Hyperbolic tangent sigmoid and Linear transfer function respectively. The training function, which is incorporated in our work, is Gradient descent with momentum (adaptive learning rate) back propagation. The proposed algorithm was trained on ORL (Olivetti Research Laboratory) database with 5 training images. The empirical results provide the accuracy of 94.50%, 93.00% and 90.25% for 20, 30 and 40 subjects respectively, with time delay of 0.0934 sec per image.