Abstract: Text categorization is the problem of classifying text documents into a set of predefined classes. After a preprocessing step the documents are typically represented as large sparse vectors. When training classifiers on large collections of documents, both the time and memory restrictions can be quite prohibitive. This justifies the application of features selection methods to reduce the dimensionality of the document-representation vector. Four feature selection methods are evaluated: Random Selection, Information Gain (IG), Support Vector Machine (called SVM_FS) and Genetic Algorithm with SVM (GA_FS). We showed that the best results were obtained with SVM_FS and GA_FS methods for a relatively small dimension of the features vector comparative with the IG method that involves longer vectors, for quite similar classification accuracies. Also we present a novel method to better correlate SVM kernel-s parameters (Polynomial or Gaussian kernel).
Abstract: Schema matching plays a key role in many different
applications, such as schema integration, data integration, data
warehousing, data transformation, E-commerce, peer-to-peer data
management, ontology matching and integration, semantic Web,
semantic query processing, etc. Manual matching is expensive and
error-prone, so it is therefore important to develop techniques to
automate the schema matching process. In this paper, we present a
solution for XML schema automated matching problem which
produces semantic mappings between corresponding schema
elements of given source and target schemas. This solution
contributed in solving more comprehensively and efficiently XML
schema automated matching problem. Our solution based on
combining linguistic similarity, data type compatibility and structural
similarity of XML schema elements. After describing our solution,
we present experimental results that demonstrate the effectiveness of
this approach.
Abstract: Extraction of edge-end-pixels is an important step for the edge linking process to achieve edge-based image segmentation. This paper presents an algorithm to extract edge-end pixels together with their directional sensitivities as an augmentation to the currently available mathematical models. The algorithm is implemented in the Java environment because of its inherent compatibility with web interfaces since its main use is envisaged to be for remote image analysis on a virtual instrumentation platform.
Abstract: Detection, feature extraction and pose estimation of
people in images and video is made challenging by the variability of
human appearance, the complexity of natural scenes and the high
dimensionality of articulated body models and also the important
field in Image, Signal and Vision Computing in recent years. In this
paper, four types of people in 2D dimension image will be tested and
proposed. The system will extract the size and the advantage of them
(such as: tall fat, short fat, tall thin and short thin) from image. Fat
and thin, according to their result from the human body that has been
extract from image, will be obtained. Also the system extract every
size of human body such as length, width and shown them in output.
Abstract: The requirements analysis, modeling, and simulation have consistently been one of the main challenges during the development of complex systems. The scenarios and the state machines are two successful models to describe the behavior of an interactive system. The scenarios represent examples of system execution in the form of sequences of messages exchanged between objects and are a partial view of the system. In contrast, state machines can represent the overall system behavior. The automation of processing scenarios in the state machines provide some answers to various problems such as system behavior validation and scenarios consistency checking. In this paper, we propose a method for translating scenarios in state machines represented by Discreet EVent Specification and procedure to detect implied scenarios. Each induced DEVS model represents the behavior of an object of the system. The global system behavior is described by coupling the atomic DEVS models and validated through simulation. We improve the validation process with integrating formal methods to eliminate logical inconsistencies in the global model. For that end, we use the Z notation.
Abstract: This paper presents an application of power line
carrier (PLC) for electrical power telemetering. This system has a
special capability of transmitting the measured values to a centralized
computer via power lines. The PLC modem as a passive high-pass
filter is designed for transmitting and receiving information. Its
function is to send the information carrier together with transmitted
data by superimposing it on the 50 Hz power frequency signal. A
microcontroller is employed to function as the main processing of the
modem. It is programmed for PLC control and interfacing with other
devices. Each power meter, connected via a PLC modem, is assigned
with a unique identification number (address) for distinguishing each
device from one another.
Abstract: This research is intended to develop a raw material allocation model in timber processing industry in Perum Perhutani Unit I, Central Java, Indonesia. The model can be used to determine the quantity of allocation of timber between chain in the supply chain to select supplier considering factors that are log price and the distance. In determining the quantity of allocation of timber between chains in the supply chain, the model considers the optimal inventory in each chain. Whilst the optimal inventory is determined based on demand forecast, the capacity and safety stock. Problem solving allocation is conducted by developing linear programming model that aims to minimize the total cost of the purchase, transportation cost and storage costs at each chain. The results of numerical examples show that the proposed model can generate savings of the purchase cost of 20.84% and select suppliers with mileage closer.
Abstract: In this paper, the processing of sonar signals has been
carried out using Minimal Resource Allocation Network (MRAN)
and a Probabilistic Neural Network (PNN) in differentiation of
commonly encountered features in indoor environments. The
stability-plasticity behaviors of both networks have been
investigated. The experimental result shows that MRAN possesses
lower network complexity but experiences higher plasticity than
PNN. An enhanced version called parallel MRAN (pMRAN) is
proposed to solve this problem and is proven to be stable in
prediction and also outperformed the original MRAN.
Abstract: Unlike general-purpose processors, digital signal
processors (DSP processors) are strongly application-dependent. To
meet the needs for diverse applications, a wide variety of DSP
processors based on different architectures ranging from the
traditional to VLIW have been introduced to the market over the
years. The functionality, performance, and cost of these processors
vary over a wide range. In order to select a processor that meets the
design criteria for an application, processor performance is usually
the major concern for digital signal processing (DSP) application
developers. Performance data are also essential for the designers of
DSP processors to improve their design. Consequently, several DSP
performance benchmarks have been proposed over the past decade or
so. However, none of these benchmarks seem to have included recent
new DSP applications.
In this paper, we use a new benchmark that we recently developed
to compare the performance of popular DSP processors from Texas
Instruments and StarCore. The new benchmark is based on the
Selectable Mode Vocoder (SMV), a speech-coding program from the
recent third generation (3G) wireless voice applications. All
benchmark kernels are compiled by the compilers of the respective
DSP processors and run on their simulators. Weighted arithmetic
mean of clock cycles and arithmetic mean of code size are used to
compare the performance of five DSP processors.
In addition, we studied how the performance of a processor is
affected by code structure, features of processor architecture and
optimization of compiler. The extensive experimental data gathered,
analyzed, and presented in this paper should be helpful for DSP
processor and compiler designers to meet their specific design goals.
Abstract: Attempts to add fibre and polyphenols (PPs) into
popular beverages present challenges related to the properties of
finished products such as smoothies. Consumer acceptability,
viscosity and phenolic composition of smoothies containing high
levels of fruit fibre (2.5-7.5 g per 300 mL serve) and PPs (250-750
mg per 300 mL serve) were examined. The changes in total
extractable PP, vitamin C content, and colour of selected smoothies
over a storage stability trial (4°C, 14 days) were compared. A set of
acidic aqueous model beverages were prepared to further examine
the effect of two different heat treatments on the stability and
extractability of PPs. Results show that overall consumer
acceptability of high fibre and PP smoothies was low, with average
hedonic scores ranging from 3.9 to 6.4 (on a 1-9 scale). Flavour,
texture and overall acceptability decreased as fibre and polyphenol
contents increased, with fibre content exerting a stronger effect.
Higher fibre content resulted in greater viscosity, with an elevated PP
content increasing viscosity only slightly. The presence of fibre also
aided the stability and extractability of PPs after heating. A reduction
of extractable PPs, vitamin C content and colour intensity of
smoothies was observed after a 14-day storage period at 4°C. Two
heat treatments (75°C for 45 min or 85°C for 1 min) that are
normally used for beverage production, did not cause significant
reduction of total extracted PPs. It is clear that high levels of added
fibre and PPs greatly influence the consumer appeal of smoothies,
suggesting the need to develop novel formulation and processing
methods if a satisfactory functional beverage is to be developed
incorporating these ingredients.
Abstract: It is estimated that the total cost of abnormal
conditions to US process industries is around $20 billion dollars in
annual losses. The hydrotreatment (HDT) of diesel fuel in petroleum
refineries is a conversion process that leads to high profitable
economical returns. However, this is a difficult process to control
because it is operated continuously, with high hydrogen pressures
and it is also subject to disturbances in feed properties and catalyst
performance. So, the automatic detection of fault and diagnosis plays
an important role in this context. In this work, a hybrid approach
based on neural networks together with a pos-processing
classification algorithm is used to detect faults in a simulated HDT
unit. Nine classes (8 faults and the normal operation) were correctly
classified using the proposed approach in a maximum time of 5
minutes, based on on-line data process measurements.
Abstract: The efficient operation of any biological treatment
process requires pre-treatment of incompatible pollutants such as
acids, bases, oil, toxic substances, etc. which hamper the treatment
of other major components which are otherwise degradable. The
pre-treatment of alkaline waste-waters, generated from various
industries like textile, paper & pulp, potato-processing industries,
etc., having a pH of 10 or higher, is essential. The pre-treatment,
i.e., neutralization of such alkaline waste-waters can be achieved by
chemical as well as biological means. However, the biological pretreatment
offers better package over the chemical means by being
safe and economical. The biological pre-treatment can be
accomplished by using a blend of microorganisms able to withstand
such harsh alkaline conditions. In the present study, for the proper
pre-treatment of alkaline waste-waters, a package of alkalophilic
bacteria is formulated to neutralise the alkaline pH of the industrial
waste-waters. The developed microbial package is cost-effective as
well as environmental friendly.
Abstract: Over the past few years, XML (eXtensible Mark-up
Language) has emerged as the standard for information
representation and data exchange over the Internet. This paper
provides a kick-start for new researches venturing in XML databases
field. We survey the storage representation for XML document,
review the XML query processing and optimization techniques with
respect to the particular storage instance. Various optimization
technologies have been developed to solve the query retrieval and
updating problems. Towards the later year, most researchers
proposed hybrid optimization techniques. Hybrid system opens the
possibility of covering each technology-s weakness by its strengths.
This paper reviews the advantages and limitations of optimization
techniques.
Abstract: The structure of retinal vessels is a prominent feature,
that reveals information on the state of disease that are reflected in
the form of measurable abnormalities in thickness and colour.
Vascular structures of retina, for implementation of clinical diabetic
retinopathy decision making system is presented in this paper.
Retinal Vascular structure is with thin blood vessel, whose accuracy
is highly dependent upon the vessel segmentation. In this paper the
blood vessel thickness is automatically detected using preprocessing
techniques and vessel segmentation algorithm. First the capture
image is binarized to get the blood vessel structure clearly, then it is
skeletonised to get the overall structure of all the terminal and
branching nodes of the blood vessels. By identifying the terminal
node and the branching points automatically, the main and branching
blood vessel thickness is estimated. Results are presented and
compared with those provided by clinical classification on 50 vessels
collected from Bejan Singh Eye hospital..
Abstract: This paper describes text mining technique for automatically extracting association rules from collections of textual documents. The technique called, Extracting Association Rules from Text (EART). It depends on keyword features for discover association rules amongst keywords labeling the documents. In this work, the EART system ignores the order in which the words occur, but instead focusing on the words and their statistical distributions in documents. The main contributions of the technique are that it integrates XML technology with Information Retrieval scheme (TFIDF) (for keyword/feature selection that automatically selects the most discriminative keywords for use in association rules generation) and use Data Mining technique for association rules discovery. It consists of three phases: Text Preprocessing phase (transformation, filtration, stemming and indexing of the documents), Association Rule Mining (ARM) phase (applying our designed algorithm for Generating Association Rules based on Weighting scheme GARW) and Visualization phase (visualization of results). Experiments applied on WebPages news documents related to the outbreak of the bird flu disease. The extracted association rules contain important features and describe the informative news included in the documents collection. The performance of the EART system compared with another system that uses the Apriori algorithm throughout the execution time and evaluating extracted association rules.
Abstract: An important step in studying the statistics of
fingerprint minutia features is to reliably extract minutia features from
the fingerprint images. A new reliable method of computation for
minutiae feature extraction from fingerprint images is presented. A
fingerprint image is treated as a textured image. An orientation flow
field of the ridges is computed for the fingerprint image. To
accurately locate ridges, a new ridge orientation based computation
method is proposed. After ridge segmentation a new method of
computation is proposed for smoothing the ridges. The ridge skeleton
image is obtained and then smoothed using morphological operators
to detect the features. A post processing stage eliminates a large
number of false features from the detected set of minutiae features.
The detected features are observed to be reliable and accurate.
Abstract: A complex valued neural network is a neural network
which consists of complex valued input and/or weights and/or thresholds
and/or activation functions. Complex-valued neural networks
have been widening the scope of applications not only in electronics
and informatics, but also in social systems. One of the most important
applications of the complex valued neural network is in signal
processing. In Neural networks, generalized mean neuron model
(GMN) is often discussed and studied. The GMN includes a new
aggregation function based on the concept of generalized mean of all
the inputs to the neuron. This paper aims to present exhaustive results
of using Generalized Mean Neuron model in a complex-valued neural
network model that uses the back-propagation algorithm (called
-Complex-BP-) for learning. Our experiments results demonstrate the
effectiveness of a Generalized Mean Neuron Model in a complex
plane for signal processing over a real valued neural network. We
have studied and stated various observations like effect of learning
rates, ranges of the initial weights randomly selected, error functions
used and number of iterations for the convergence of error required on
a Generalized Mean neural network model. Some inherent properties
of this complex back propagation algorithm are also studied and
discussed.
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 medical ultrasound 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 clinical ultrasound images and its performance in terms of the mean square error (MSE) metric was calculated. We showed that the SVM-detected ultrasound 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 (detection hypotheses) in the original images.
Abstract: Image convolution similar to the receptive fields
found in mammalian visual pathways has long been used in
conventional image processing in the form of Gabor masks.
However, no VLSI implementation of parallel, multi-layered pulsed
processing has been brought forward which would emulate this
property. We present a technical realization of such a pulsed image
processing scheme. The discussed IC also serves as a general testbed
for VLSI-based pulsed information processing, which is of interest
especially with regard to the robustness of representing an analog
signal in the phase or duration of a pulsed, quasi-digital signal, as
well as the possibility of direct digital manipulation of such an
analog signal. The network connectivity and processing properties
are reconfigurable so as to allow adaptation to various processing
tasks.
Abstract: This paper deals with the localization of the wideband sources. We develop a new approach for estimating the wide band sources parameters. This method is based on the high order statistics of the recorded data in order to eliminate the Gaussian components from the signals received on the various hydrophones.In fact the noise of sea bottom is regarded as being Gaussian. Thanks to the coherent signal subspace algorithm based on the cumulant matrix of the received data instead of the cross-spectral matrix the wideband correlated sources are perfectly located in the very noisy environment. We demonstrate the performance of the proposed algorithm on the real data recorded during an underwater acoustics experiments.