Abstract: This paper presents the methodology from machine
learning approaches for short-term rain forecasting system. Decision
Tree, Artificial Neural Network (ANN), and Support Vector Machine
(SVM) were applied to develop classification and prediction models
for rainfall forecasts. The goals of this presentation are to
demonstrate (1) how feature selection can be used to identify the
relationships between rainfall occurrences and other weather
conditions and (2) what models can be developed and deployed for
predicting the accurate rainfall estimates to support the decisions to
launch the cloud seeding operations in the northeastern part of
Thailand. Datasets collected during 2004-2006 from the
Chalermprakiat Royal Rain Making Research Center at Hua Hin,
Prachuap Khiri khan, the Chalermprakiat Royal Rain Making
Research Center at Pimai, Nakhon Ratchasima and Thai
Meteorological Department (TMD). A total of 179 records with 57
features was merged and matched by unique date. There are three
main parts in this work. Firstly, a decision tree induction algorithm
(C4.5) was used to classify the rain status into either rain or no-rain.
The overall accuracy of classification tree achieves 94.41% with the
five-fold cross validation. The C4.5 algorithm was also used to
classify the rain amount into three classes as no-rain (0-0.1 mm.),
few-rain (0.1- 10 mm.), and moderate-rain (>10 mm.) and the overall
accuracy of classification tree achieves 62.57%. Secondly, an ANN
was applied to predict the rainfall amount and the root mean square
error (RMSE) were used to measure the training and testing errors of
the ANN. It is found that the ANN yields a lower RMSE at 0.171 for
daily rainfall estimates, when compared to next-day and next-2-day
estimation. Thirdly, the ANN and SVM techniques were also used to
classify the rain amount into three classes as no-rain, few-rain, and
moderate-rain as above. The results achieved in 68.15% and 69.10%
of overall accuracy of same-day prediction for the ANN and SVM
models, respectively. The obtained results illustrated the comparison
of the predictive power of different methods for rainfall estimation.
Abstract: The purpose of our study was to compare spontaneous
re-epithelisation characteristics versus assisted re-epithelisation. In
order to assess re-epithelisation of the injured skin, we have imagined
and designed a burn wound model on Wistar rat skin. Our aim was to
create standardised, easy reproducible and quantifiable skin lesions
involving entire epidermis and superficial dermis. We then have
applied the above mentioned therapeutic strategies to compare
regeneration of epidermis and dermis, local and systemic parameter
changes in different conditions. We have enhanced the reepithelisation
process under a moist atmosphere of a polyurethane
wound dress modified with helium non-thermal plasma, and with the
aid of direct cold-plasma treatment respectively. We have followed
systemic parameters change: hematologic and biochemical
parameters, and local features: oxidative stress markers and histology
of skin in the above mentioned conditions. Re-epithelisation is just a
part of the skin regeneration process, which recruits cellular
components, with the aid of epidermal and dermal interaction via
signal molecules.
Abstract: This paper presents a novel template-based method to
detect objects of interest from real images by shape matching. To
locate a target object that has a similar shape to a given template
boundary, the proposed method integrates three components: contour
grouping, partial shape matching, and boundary verification. In the
first component, low-level image features, including edges and
corners, are grouped into a set of perceptually salient closed contours
using an extended ratio-contour algorithm. In the second component,
we develop a partial shape matching algorithm to identify the
fractions of detected contours that partly match given template
boundaries. Specifically, we represent template boundaries and
detected contours using landmarks, and apply a greedy algorithm to
search the matched landmark subsequences. For each matched
fraction between a template and a detected contour, we estimate an
affine transform that transforms the whole template into a hypothetic
boundary. In the third component, we provide an efficient algorithm
based on oriented edge lists to determine the target boundary from
the hypothetic boundaries by checking each of them against image
edges. We evaluate the proposed method on recognizing and
localizing 12 template leaves in a data set of real images with clutter
back-grounds, illumination variations, occlusions, and image noises.
The experiments demonstrate the high performance of our proposed
method1.
Abstract: This manuscript presents, palmprint recognition by
combining different texture extraction approaches with high accuracy.
The Region of Interest (ROI) is decomposed into different frequencytime
sub-bands by wavelet transform up-to two levels and only the
approximate image of two levels is selected, which is known as
Approximate Image ROI (AIROI). This AIROI has information of
principal lines of the palm. The Competitive Index is used as the
features of the palmprint, in which six Gabor filters of different
orientations convolve with the palmprint image to extract the orientation
information from the image. The winner-take-all strategy
is used to select dominant orientation for each pixel, which is
known as Competitive Index. Further, PCA is applied to select highly
uncorrelated Competitive Index features, to reduce the dimensions of
the feature vector, and to project the features on Eigen space. The
similarity of two palmprints is measured by the Euclidean distance
metrics. The algorithm is tested on Hong Kong PolyU palmprint
database. Different AIROI of different wavelet filter families are also
tested with the Competitive Index and PCA. AIROI of db7 wavelet
filter achievs Equal Error Rate (EER) of 0.0152% and Genuine
Acceptance Rate (GAR) of 99.67% on the palm database of Hong
Kong PolyU.
Abstract: Advertising is one of the important marketing
strategies and the choice of media is an important aspect of
effectiveness of advertising media. The two most popular advertising
media, TV and web media are highly effective in creating successful
advertisements as they influence the purchase decision of the
viewers. Although TV and web are electronic media, they are unique
in their features and traits of advertising. Hence, the present study
attempts to analyze the influence of these two media towards buying
behavior of the viewers. The two media are analyzed separately to
determine its level of influence towards buying behavior and finally a
comparative analysis of these media is attempted to find the
difference in their level of influence.
Abstract: Electrophysiological signals were recorded from primary cultures of dissociated rat cortical neurons coupled to Micro-Electrode Arrays (MEAs). The neuronal discharge patterns may change under varying physiological and pathological conditions. For this reason, we developed a new burst detection method able to identify bursts with peculiar features in different experimental conditions (i.e. spontaneous activity and under the effect of specific drugs). The main feature of our algorithm (i.e. Burst On Hurst), based on the auto-similarity or fractal property of the recorded signal, is the independence from the chosen spike detection method since it works directly on the raw data.
Abstract: Based on the Lagrangian for the Gross –Pitaevskii
equation as derived by H. Sakaguchi and B.A Malomed [5] we have
derived a double well model for the nonlinear optical lattice. This
model explains the various features of nonlinear optical lattices.
Further, from this model we obtain and simulate the probability for
tunneling from one well to another which agrees with experimental
results [4].
Abstract: In this paper a combined feature selection method is
proposed which takes advantages of sample domain filtering,
resampling and feature subset evaluation methods to reduce
dimensions of huge datasets and select reliable features. This method
utilizes both feature space and sample domain to improve the process
of feature selection and uses a combination of Chi squared with
Consistency attribute evaluation methods to seek reliable features.
This method consists of two phases. The first phase filters and
resamples the sample domain and the second phase adopts a hybrid
procedure to find the optimal feature space by applying Chi squared,
Consistency subset evaluation methods and genetic search.
Experiments on various sized datasets from UCI Repository of
Machine Learning databases show that the performance of five
classifiers (Naïve Bayes, Logistic, Multilayer Perceptron, Best First
Decision Tree and JRIP) improves simultaneously and the
classification error for these classifiers decreases considerably. The
experiments also show that this method outperforms other feature
selection methods.
Abstract: This paper introduces an automatic voice classification
system for the diagnosis of individual constitution based on Sasang
Constitutional Medicine (SCM) in Traditional Korean Medicine
(TKM). For the developing of this algorithm, we used the voices of
309 female speakers and extracted a total of 134 speech features from
the voice data consisting of 5 sustained vowels and one sentence. The
classification system, based on a rule-based algorithm that is derived
from a non parametric statistical method, presents 3 types of decisions:
reserved, positive and negative decisions. In conclusion, 71.5% of the
voice data were diagnosed by this system, of which 47.7% were
correct positive decisions and 69.7% were correct negative decisions.
Abstract: Dealing with hundreds of features in character
recognition systems is not unusual. This large number of features
leads to the increase of computational workload of recognition
process. There have been many methods which try to remove
unnecessary or redundant features and reduce feature dimensionality.
Besides because of the characteristics of Farsi scripts, it-s not
possible to apply other languages algorithms to Farsi directly. In this
paper some methods for feature subset selection using genetic
algorithms are applied on a Farsi optical character recognition (OCR)
system. Experimental results show that application of genetic
algorithms (GA) to feature subset selection in a Farsi OCR results in
lower computational complexity and enhanced recognition rate.
Abstract: E-learning refers to the specific kind of learning
experienced within the domain of educational technology, which can
be used in or out of the classroom. In this paper, we give an
overview of an e-learning platform 'An Innovative Interactive and
Online English Platform for Upper Primary Students' is an
interactive web-based application which will serve as an aid to the
primary school students in Mauritius. The objectives of this platform
are to offer quality learning resources for the English subject at our
primary level of education, encourage self-learning and hence
promote e-learning. The platform developed consists of several
interesting features, for example, the English Verb Conjugation tool,
Negative Form tool, Interrogative Form tool and Close Test
Generator. Thus, this learning platform will be useful at a time
where our country is looking for an alternative to private tuition and
also, looking forward to increase the pass rate.
Abstract: Aspect Oriented Programming promises many
advantages at programming level by incorporating the cross cutting
concerns into separate units, called aspects. Join Points are
distinguishing features of Aspect Oriented Programming as they
define the points where core requirements and crosscutting concerns
are (inter)connected. Currently, there is a problem of multiple
aspects- composition at the same join point, which introduces the
issues like ordering and controlling of these superimposed aspects.
Dynamic strategies are required to handle these issues as early as
possible. State chart is an effective modeling tool to capture dynamic
behavior at high level design. This paper provides methodology to
formulate the strategies for multiple aspect composition at high level,
which helps to better implement these strategies at coding level. It
also highlights the need of designing shared join point at high level,
by providing the solutions of these issues using state chart diagrams
in UML 2.0. High level design representation of shared join points
also helps to implement the designed strategy in systematic way.
Abstract: This paper proposes a new approach to perform the
problem of real-time face detection. The proposed method combines
primitive Haar-Like feature and variance value to construct a new
feature, so-called Variance based Haar-Like feature. Face in image
can be represented with a small quantity of features using this
new feature. We used SVM instead of AdaBoost for training and
classification. We made a database containing 5,000 face samples
and 10,000 non-face samples extracted from real images for learning
purposed. The 5,000 face samples contain many images which have
many differences of light conditions. And experiments showed that
face detection system using Variance based Haar-Like feature and
SVM can be much more efficient than face detection system using
primitive Haar-Like feature and AdaBoost. We tested our method on
two Face databases and one Non-Face database. We have obtained
96.17% of correct detection rate on YaleB face database, which is
higher 4.21% than that of using primitive Haar-Like feature and
AdaBoost.
Abstract: With the drastically growth in optical communication
technology, a lossless, low-crosstalk and multifunction optical switch
is most desirable for large-scale photonic network. To realize such a
switch, we have introduced the new architecture of optical switch
that embedded many functions on single device. The asymmetrical
architecture of OXADM consists of 3 parts; selective port, add/drop
operation, and path routing. Selective port permits only the interest
wavelength pass through and acts as a filter. While add and drop
function can be implemented in second part of OXADM architecture.
The signals can then be re-routed to any output port or/and perform
an accumulation function which multiplex all signals onto single path
and then exit to any interest output port. This will be done by path
routing operation. The unique features offered by OXADM has
extended its application to Fiber to-the Home Technology (FTTH),
here the OXADM is used as a wavelength management element in
Optical Line Terminal (OLT). Each port is assigned specifically with
the operating wavelengths and with the dynamic routing management
to ensure no traffic combustion occurs in OLT.
Abstract: In this paper we have proposed a novel dynamic least cost multicast routing protocol using hybrid genetic algorithm for IP networks. Our protocol finds the multicast tree with minimum cost subject to delay, degree, and bandwidth constraints. The proposed protocol has the following features: i. Heuristic local search function has been devised and embedded with normal genetic operation to increase the speed and to get the optimized tree, ii. It is efficient to handle the dynamic situation arises due to either change in the multicast group membership or node / link failure, iii. Two different crossover and mutation probabilities have been used for maintaining the diversity of solution and quick convergence. The simulation results have shown that our proposed protocol generates dynamic multicast tree with lower cost. Results have also shown that the proposed algorithm has better convergence rate, better dynamic request success rate and less execution time than other existing algorithms. Effects of degree and delay constraints have also been analyzed for the multicast tree interns of search success rate.
Abstract: Process-oriented software development is a new
software development paradigm in which software design is modeled
by a business process which is in turn translated into a process
execution language for execution. The building blocks of this
paradigm are software units that are composed together to work
according to the flow of the business process. This new paradigm
still exhibits the characteristic of the applications built with the
traditional software component technology. This paper discusses an
approach to apply a traditional technique for software component
fabrication to the design of process-oriented software units, called
process components. These process components result from
decomposing a business process of a particular application domain
into subprocesses, and these process components can be reused to
design the business processes of other application domains. The
decomposition considers five managerial goals, namely cost
effectiveness, ease of assembly, customization, reusability, and
maintainability. The paper presents how to design or decompose
process components from a business process model and measure
some technical features of the design that would affect the
managerial goals. A comparison between the measurement values
from different designs can tell which process component design is
more appropriate for the managerial goals that have been set. The
proposed approach can be applied in Web Services environment
which accommodates process-oriented software development.
Abstract: The increasing complexity of software development based on peer to peer networks makes necessary the creation of new frameworks in order to simplify the developer-s task. Additionally, some applications, e.g. fire detection or security alarms may require real-time constraints and the high level definition of these features eases the application development. In this paper, a service model based on a component model with real-time features is proposed. The high-level model will abstract developers from implementation tasks, such as discovery, communication, security or real-time requirements. The model is oriented to deploy services on small mobile devices, such as sensors, mobile phones and PDAs, where the computation is light-weight. Services can be composed among them by means of the port concept to form complex ad-hoc systems and their implementation is carried out using a component language called UM-RTCOM. In order to apply our proposals a fire detection application is described.
Abstract: In this paper a new method for increasing the speed of
SAGCM-APD is proposed. Utilizing carrier rate equations in
different regions of the structure, a circuit model for the structure is
obtained. In this research, in addition to frequency response, the
effect of added new charge layer on some transient parameters like
slew-rate, rising and falling times have been considered. Finally, by
trading-off among some physical parameters such as different layers
widths and droppings, a noticeable decrease in breakdown voltage
has been achieved. The results of simulation, illustrate some features
of proposed structure improvement in comparison with conventional
SAGCM-APD structures.
Abstract: In this paper we analyze the core issues affecting
software architecture in enterprise projects where a large number of
people at different backgrounds are involved and complex business,
management and technical problems exist. We first give general
features of typical enterprise projects and then present foundations of
software architectures. The detailed analysis of core issues affecting
software architecture in software development phases is given. We
focus on three main areas in each development phase: people,
process, and management related issues, structural (product) issues,
and technology related issues. After we point out core issues and
problems in these main areas, we give recommendations for
designing good architecture. We observed these core issues and the
importance of following the best software development practices and
also developed some novel practices in many big enterprise
commercial and military projects in about 10 years of experience.
Abstract: In current common research reports, salient regions
are usually defined as those regions that could present the main
meaningful or semantic contents. However, there are no uniform
saliency metrics that could describe the saliency of implicit image
regions. Most common metrics take those regions as salient regions,
which have many abrupt changes or some unpredictable
characteristics. But, this metric will fail to detect those salient useful
regions with flat textures. In fact, according to human semantic
perceptions, color and texture distinctions are the main characteristics
that could distinct different regions. Thus, we present a novel saliency
metric coupled with color and texture features, and its corresponding
salient region extraction methods. In order to evaluate the
corresponding saliency values of implicit regions in one image, three
main colors and multi-resolution Gabor features are respectively used
for color and texture features. For each region, its saliency value is
actually to evaluate the total sum of its Euclidean distances for other
regions in the color and texture spaces. A special synthesized image
and several practical images with main salient regions are used to
evaluate the performance of the proposed saliency metric and other
several common metrics, i.e., scale saliency, wavelet transform
modulus maxima point density, and important index based metrics.
Experiment results verified that the proposed saliency metric could
achieve more robust performance than those common saliency
metrics.