Abstract: In this research study, an intelligent detection system
to support medical diagnosis and detection of abnormal lesions by
processing endoscopic images is presented. The images used in this
study have been obtained using the M2A Swallowable Imaging
Capsule - a patented, video color-imaging disposable capsule.
Schemes have been developed to extract texture features from the
fuzzy texture spectra in the chromatic and achromatic domains for a
selected region of interest from each color component histogram of
endoscopic images. The implementation of an advanced fuzzy
inference neural network which combines fuzzy systems and
artificial neural networks and the concept of fusion of multiple
classifiers dedicated to specific feature parameters have been also
adopted in this paper. The achieved high detection accuracy of the
proposed system has provided thus an indication that such intelligent
schemes could be used as a supplementary diagnostic tool in
endoscopy.
Abstract: Modeling product configurations needs large amounts of knowledge about technical and marketing restrictions on the product. Previous attempts to automate product configurations concentrate on representations and management of the knowledge for specific domains in fixed and isolated computing environments. Since the knowledge about product configurations is subject to continuous change and hard to express, these attempts often failed to efficiently manage and exchange the knowledge in collaborative product development. In this paper, XML Topic Map (XTM) is introduced to represent and exchange the knowledge about product configurations in collaborative product development. A product configuration model based on XTM along with its merger and inference facilities enables configuration engineers in collaborative product development to manage and exchange their knowledge efficiently. A prototype implementation is also presented to demonstrate the proposed model can be applied to engineering information systems to exchange the product configuration knowledge.
Abstract: This paper presents work characterizing finite element
performance boundaries within which live, interactive finite element
modeling is feasible on current and emerging systems. These results
are based on wide-ranging tests performed using a prototype finite
element program implemented specifically for this study, thereby enabling
the unified investigation of numerous direct and iterative solver
strategies and implementations in a variety of modeling contexts.
The results are intended to be useful for researchers interested in
interactive analysis by providing baseline performance estimates, to
give guidance in matching solution strategies to problem domains,
and to spur further work addressing the challenge of extending the
present boundaries.
Abstract: Deciding the numerous parameters involved in
designing a competent artificial neural network is a complicated task.
The existence of several options for selecting an appropriate
architecture for neural network adds to this complexity, especially
when different applications of heterogeneous natures are concerned.
Two completely different applications in engineering and medical
science were selected in the present study including prediction of
workpiece's surface roughness in ultrasonic-vibration assisted turning
and papilloma viruses oncogenicity. Several neural network
architectures with different parameters were developed for each
application and the results were compared. It was illustrated in this
paper that some applications such as the first one mentioned above
are apt to be modeled by a single network with sufficient accuracy,
whereas others such as the second application can be best modeled
by different expert networks for different ranges of output.
Development of knowledge about the essentials of neural networks
for different applications is regarded as the cornerstone of
multidisciplinary network design programs to be developed as a
means of reducing inconsistencies and the burden of the user
intervention.
Abstract: In today-s information age, numbers of organizations
are still arguing on capitalizing the values of Information Technology
(IT) and Knowledge Management (KM) to which individuals can
benefit from and effective communication among the individuals can
be established. IT exists in enabling positive improvement for
communication among knowledge workers (k-workers) with a
number of social network technology domains at workplace. The
acceptance of digital discourse in sharing of knowledge and
facilitating the knowledge and information flows at most of the
organizations indeed impose the culture of knowledge sharing in
Digital Social Networks (DSN). Therefore, this study examines
whether the k-workers with IT background would confer an effect on
the three knowledge characteristics -- conceptual, contextual, and
operational. Derived from these three knowledge characteristics, five
potential factors will be examined on the effects of knowledge
exchange via e-mail domain as the chosen query. It is expected, that
the results could provide such a parameter in exploring how DSN
contributes in supporting the k-workers- virtues, performance and
qualities as well as revealing the mutual point between IT and KM.
Abstract: This paper describes a practical approach to design
and develop a hybrid learning with acceleration feedback control
(HLC) scheme for input tracking and end-point vibration suppression
of flexible manipulator systems. Initially, a collocated proportionalderivative
(PD) control scheme using hub-angle and hub-velocity
feedback is developed for control of rigid-body motion of the system.
This is then extended to incorporate a further hybrid control scheme
of the collocated PD control and iterative learning control with
acceleration feedback using genetic algorithms (GAs) to optimize the
learning parameters. Experimental results of the response of the
manipulator with the control schemes are presented in the time and
frequency domains. The performance of the HLC is assessed in terms
of input tracking, level of vibration reduction at resonance modes and
robustness with various payloads.
Abstract: A direct search approach to determine optimal reservoir operating is proposed with ant colony optimization for continuous domains (ACOR). The model is applied to a system of single reservoir to determine the optimum releases during 42 years of monthly steps. A disadvantage of ant colony based methods and the ACOR in particular, refers to great amount of computer run time consumption. In this study a highly effective procedure for decreasing run time has been developed. The results are compared to those of a GA based model.
Abstract: Semilinear elliptic equations are ubiquitous in natural sciences. They give rise to a variety of important phenomena in quantum mechanics, nonlinear optics, astrophysics, etc because they have rich multiple solutions. But the nontrivial solutions of semilinear equations are hard to be solved for the lack of stabilities, such as Lane-Emden equation, Henon equation and Chandrasekhar equation. In this paper, bifurcation method is applied to solving semilinear elliptic equations which are with homogeneous Dirichlet boundary conditions in 2D. Using this method, nontrivial numerical solutions will be computed and visualized in many different domains (such as square, disk, annulus, dumbbell, etc).
Abstract: This work concerns the evolution and the maintenance
of an ontological resource in relation with the evolution of the corpus
of texts from which it had been built.
The knowledge forming a text corpus, especially in dynamic domains,
is in continuous evolution. When a change in the corpus occurs, the
domain ontology must evolve accordingly. Most methods manage
ontology evolution independently from the corpus from which it is
built; in addition, they treat evolution just as a process of knowledge
addition, not considering other knowledge changes. We propose a
methodology for managing an evolving ontology from a text corpus
that evolves over time, while preserving the consistency and the
persistence of this ontology.
Our methodology is based on the changes made on the corpus to
reflect the evolution of the considered domain - augmented surgery
in our case. In this context, the results of text mining techniques,
as well as the ARCHONTE method slightly modified, are used to
support the evolution process.
Abstract: The present microfluidic study is emphasizing the flow behavior within a Y shape micro-bifurcation in two similar flow configurations. We report here a numerical and experimental investigation on the velocity profiles evolution and secondary flows, manifested at different Reynolds numbers (Re) and for two different boundary conditions. The experiments are performed using special designed setup based on optical microscopic devices. With this setup, direct visualizations and quantitative measurements of the path-lines are obtained. A Micro-PIV measurement system is used to obtain velocity profiles distributions in a spatial evolution in the main flows domains. The experimental data is compared with numerical simulations performed with commercial computational code FLUENT in a 3D geometry with the same dimensions as the experimental one. The numerical flow patterns are found to be in good agreement with the experimental manifestations.
Abstract: In the proposed method for Web page-ranking, a
novel theoretic model is introduced and tested by examples of order
relationships among IP addresses. Ranking is induced using a
convexity feature, which is learned according to these examples
using a self-organizing procedure. We consider the problem of selforganizing
learning from IP data to be represented by a semi-random
convex polygon procedure, in which the vertices correspond to IP
addresses. Based on recent developments in our regularization
theory for convex polygons and corresponding Euclidean distance
based methods for classification, we develop an algorithmic
framework for learning ranking functions based on a Computational
Geometric Theory. We show that our algorithm is generic, and
present experimental results explaining the potential of our approach.
In addition, we explain the generality of our approach by showing its
possible use as a visualization tool for data obtained from diverse
domains, such as Public Administration and Education.
Abstract: A concern that researchers usually face in different
applications of Artificial Neural Network (ANN) is determination of
the size of effective domain in time series. In this paper, trial and
error method was used on groundwater depth time series to determine
the size of effective domain in the series in an observation well in
Union County, New Jersey, U.S. different domains of 20, 40, 60, 80,
100, and 120 preceding day were examined and the 80 days was
considered as effective length of the domain. Data sets in different
domains were fed to a Feed Forward Back Propagation ANN with
one hidden layer and the groundwater depths were forecasted. Root
Mean Square Error (RMSE) and the correlation factor (R2) of
estimated and observed groundwater depths for all domains were
determined. In general, groundwater depth forecast improved, as
evidenced by lower RMSEs and higher R2s, when the domain length
increased from 20 to 120. However, 80 days was selected as the
effective domain because the improvement was less than 1% beyond
that. Forecasted ground water depths utilizing measured daily data
(set #1) and data averaged over the effective domain (set #2) were
compared. It was postulated that more accurate nature of measured
daily data was the reason for a better forecast with lower RMSE
(0.1027 m compared to 0.255 m) in set #1. However, the size of input
data in this set was 80 times the size of input data in set #2; a factor
that may increase the computational effort unpredictably. It was
concluded that 80 daily data may be successfully utilized to lower the
size of input data sets considerably, while maintaining the effective
information in the data set.
Abstract: In the last few years, the Semantic Web gained scientific acceptance as a means of relationships identification in knowledge base, widely known by semantic association. Query about complex relationships between entities is a strong requirement for many applications in analytical domains. In bioinformatics for example, it is critical to extract exchanges between proteins. Currently, the widely known result of such queries is to provide paths between connected entities from data graph. However, they do not always give good results while facing the user need by the best association or a set of limited best association, because they only consider all existing paths but ignore the path evaluation. In this paper, we present an approach for supporting association discovery queries. Our proposal includes (i) a query language PmSPRQL which provides a multiparadigm query expressions for association extraction and (ii) some quantification measures making easy the process of association ranking. The originality of our proposal is demonstrated by a performance evaluation of our approach on real world datasets.
Abstract: Meshing is the process of discretizing problem
domain into many sub domains before the numerical calculation can
be performed. One of the most popular meshes among many types of meshes is tetrahedral mesh, due to their flexibility to fit into almost
any domain shape. In both 2D and 3D domains, triangular and tetrahedral meshes can be generated by using Delaunay triangulation.
The quality of mesh is an important factor in performing any Computational Fluid Dynamics (CFD) simulations as the results is
highly affected by the mesh quality. Many efforts had been done in
order to improve the quality of the mesh. The paper describes a mesh
generation routine which has been developed capable of generating
high quality tetrahedral cells in arbitrary complex geometry. A few
test cases in CFD problems are used for testing the mesh generator.
The result of the mesh is compared with the one generated by a
commercial software. The results show that no sliver exists for the
meshes generated, and the overall quality is acceptable since the percentage of the bad tetrahedral is relatively small. The boundary
recovery was also successfully done where all the missing faces are
rebuilt.
Abstract: Although the usefulness of fuzzy databases has been
pointed out in several works, they are not fully developed in numerous
domains. A task that is mostly disregarded and which is the topic
of this paper is the determination of suitable inequalities for fuzzy
sets in fuzzy query languages. This paper examines which kinds
of fuzzy inequalities exist at all. Afterwards, different procedures
are presented that appear theoretically appropriate. By being applied
to various examples, their strengths and weaknesses are revealed.
Furthermore, an algorithm for an efficient computation of the selected
fuzzy inequality is shown.
Abstract: Discourse pronominal anaphora resolution must be part of any efficient information processing systems, since the reference of a pronoun is dependent on an antecedent located in the discourse. Contrary to knowledge-poor approaches, this paper shows that syntax-semantic relations are basic in pronominal anaphora resolution. The identification of quantified expressions to which pronouns can be anaphorically related provides further evidence that pronominal anaphora is based on domains of interpretation where asymmetric agreement holds.
Abstract: We provide a maximum norm analysis of a finite
element Schwarz alternating method for a nonlinear elliptic boundary
value problem of the form -Δu = f(u), on two overlapping sub
domains with non matching grids. We consider a domain which is
the union of two overlapping sub domains where each sub domain
has its own independently generated grid. The two meshes being
mutually independent on the overlap region, a triangle belonging to
one triangulation does not necessarily belong to the other one. Under
a Lipschitz assumption on the nonlinearity, we establish, on each sub
domain, an optimal L∞ error estimate between the discrete Schwarz
sequence and the exact solution of the boundary value problem.
Abstract: Timetabling problems are often hard and timeconsuming
to solve. Most of the methods of solving them concern
only one problem instance or class. This paper describes a universal
method for solving large, highly constrained timetabling problems
from different domains. The solution is based on evolutionary
algorithm-s framework and operates on two levels – first-level
evolutionary algorithm tries to find a solution basing on given set of
operating parameters, second-level algorithm is used to establish
those parameters. Tabu search is employed to speed up the solution
finding process on first level. The method has been used to solve
three different timetabling problems with promising results.
Abstract: How to coordinate the behaviors of the agents through
learning is a challenging problem within multi-agent domains.
Because of its complexity, recent work has focused on how
coordinated strategies can be learned. Here we are interested in using
reinforcement learning techniques to learn the coordinated actions of a
group of agents, without requiring explicit communication among
them. However, traditional reinforcement learning methods are based
on the assumption that the environment can be modeled as Markov
Decision Process, which usually cannot be satisfied when multiple
agents coexist in the same environment. Moreover, to effectively
coordinate each agent-s behavior so as to achieve the goal, it-s
necessary to augment the state of each agent with the information
about other existing agents. Whereas, as the number of agents in a
multiagent environment increases, the state space of each agent grows
exponentially, which will cause the combinational explosion problem.
Profit sharing is one of the reinforcement learning methods that allow
agents to learn effective behaviors from their experiences even within
non-Markovian environments. In this paper, to remedy the drawback
of the original profit sharing approach that needs much memory to
store each state-action pair during the learning process, we firstly
address a kind of on-line rational profit sharing algorithm. Then, we
integrate the advantages of modular learning architecture with on-line
rational profit sharing algorithm, and propose a new modular
reinforcement learning model. The effectiveness of the technique is
demonstrated using the pursuit problem.