Professional Documents
Culture Documents
Download textbook Bioinspired Computation In Artificial Systems International Work Conference On The Interplay Between Natural And Artificial Computation Iwinac 2015 Elche Spain June 1 5 2015 Proceedings Part Ii 1St Ed ebook all chapter pdf
Download textbook Bioinspired Computation In Artificial Systems International Work Conference On The Interplay Between Natural And Artificial Computation Iwinac 2015 Elche Spain June 1 5 2015 Proceedings Part Ii 1St Ed ebook all chapter pdf
https://textbookfull.com/product/artificial-intelligence-in-
education-17th-international-conference-aied-2015-madrid-spain-
june-22-26-2015-proceedings-1st-edition-cristina-conati/
Bioinspired Computation
in Artificial Systems
International Work-Conference on the Interplay
Between Natural and Artificial Computation, IWINAC 2015
Elche, Spain, June 1–5, 2015, Proceedings, Part II
123
Lecture Notes in Computer Science 9108
Commenced Publication in 1973
Founding and Former Series Editors:
Gerhard Goos, Juris Hartmanis, and Jan van Leeuwen
Editorial Board
David Hutchison
Lancaster University, Lancaster, UK
Takeo Kanade
Carnegie Mellon University, Pittsburgh, PA, USA
Josef Kittler
University of Surrey, Guildford, UK
Jon M. Kleinberg
Cornell University, Ithaca, NY, USA
Friedemann Mattern
ETH Zürich, Zürich, Switzerland
John C. Mitchell
Stanford University, Stanford, CA, USA
Moni Naor
Weizmann Institute of Science, Rehovot, Israel
C. Pandu Rangan
Indian Institute of Technology, Madras, India
Bernhard Steffen
TU Dortmund University, Dortmund, Germany
Demetri Terzopoulos
University of California, Los Angeles, CA, USA
Doug Tygar
University of California, Berkeley, CA, USA
Gerhard Weikum
Max Planck Institute for Informatics, Saarbrücken, Germany
More information about this series at http://www.springer.com/series/7407
José Manuel Ferrández Vicente
José Ramón Álvarez-Sánchez
Félix de la Paz López
Fco. Javier Toledo-Moreo
Hojjat Adeli (Eds.)
Bioinspired Computation
in Artificial Systems
International Work-Conference on the Interplay
Between Natural and Artificial Computation, IWINAC 2015,
Elche, Spain, June 1–5, 2015, Proceedings, Part II
ABC
Editors
José Manuel Ferrández Vicente Fco. Javier Toledo-Moreo
Universidad Politécnica de Cartagena Universidad Politécnica de Cartagena
Cartagena Cartagena
Spain Spain
An event of the nature of IWINAC 2015 cannot be organized without the collabo-
ration of a group of institutions and people who we would like to thank now, starting
with UNED and Universidad Politécnica de Cartagena. The collaboration of the UNED
Associated Center in Elche was crucial, as was the efficient work of the Local Orga-
nizing Committee, chaired by Eduardo Fernández with the close collaboration of the
Universidad Miguel Hernández de Elche. In addition to our universities, we received
financial support from the Spanish CYTED, Red Nacional en Computación Natural y
Artificial and Apliquem Microones 21 s.l.
We want to express our gratefulness to our invited speakers Prof. Hojjat Adeli, Ohio
State University (USA), Prof. Marc de Kamps, University of Leeds (UK), Prof. Richard
Duro, University of A Coruña (Spain), and Prof. Luis Miguel Martínez Otero, Univer-
sity Miguel Hernández (Spain) for accepting our invitation and for their magnificent
plenary talks.
We would also like to thank the authors for their interest in our call and the effort in
preparing the papers, condition sine qua non for these proceedings. We thank the Sci-
entific and Organizing Committees, in particular the members of these committees who
acted as effective and efficient referees and as promoters and managers of preorganized
sessions on autonomous and relevant topics under the IWINAC global scope.
Our sincere gratitude goes also to Springer and to Alfred Hofmann and his collab-
orators, Anna Kramer and Christine Reiss, for the continuous receptivity, help efforts,
and collaboration in all our joint editorial ventures on the interplay between neuro-
science and computation.
Finally, we want to express our special thanks to Viajes Hispania, our technical
secretariat, and to Chari García and Beatriz Baeza, for making this meeting possible,
and for arranging all the details that comprise the organization of this kind of event.
We want to dedicate these two volumes of the IWINAC proceedings to the memory of
Professor Mira, whose challenging and inquiring spirit is in all of us. We greatly miss
him.
General Chairman
José Manuel Ferrández Vicente Universidad Politécnica de Cartagena, Spain
Organizing Committee
Honorary Chairs
Rodolfo Llinás New York University, USA
Hojjat Adeli Ohio State University, USA
Zhou Changjiu Singapore Polytechnic, Singapore
Invited Speakers
Hojjat Adeli Ohio State University, USA
Marc de Kamps University of Leeds, UK
Richard Duro University of A Coruña, Spain
Luis Miguel Martínez Otero University Miguel Hernández, Spain
X Organization
Field Editors
Diego Andina Spain
Jorge Azorín-López Spain
Rafael Berenguer Vidal Spain
Germán
Castellanos-Dominguez Spain
Miguel Cazorla Spain
Antonio Fernández-Caballero Spain
José Garcia-Rodriguez Spain
Pascual González Spain
Álvar Ginés Legaz Aparicio Spain
Javier de Lope Asiaín Spain
Miguel Ángel López Gordo Spain
Darío Maravall
Gómez-Allende Spain
Rafael Martínez Tomás Spain
Elena Navarro Spain
Pablo Padilla de la Torre Spain
Daniel Ruiz Fernández Spain
Antonio J. Tallón-Ballesteros Spain
Hujun Yin UK
1 Introduction
Constraint programming is an efficient technology for solving constraint satisfac-
tion and optimization problems. Under this framework, problems are formulated
2 Related Work
argue that initial choices are often more important, suggesting to perform an a
priori sampling phase for a better initial selection. In this paper, we focus on
online control, based on the work done in [1] we employ an online method to
adapt the enumeration strategies during solving time. The goal is to replace the
strategies depending on the performance exhibited along the solving process. In
this way, the most promising ones are used on each part of the search process. In
this context, two approaches have been proposed to online control, one based on
genetic algorithms [5] and a second one based on particle swarm optimization [6].
The performance information gathered in this phase via the indicators is used
as input data of the optimizer, which attempt to determine the most successful
weight set for the WSM. This tuning process is very important as the correct
configuration of the WSM may have essential effects on the ability of the solver
to properly solve specific CSPs. Parameter (weights) tuning is hard to achieve
as parameters are problem-dependent and their best configuration is not stable
along the search [12]. As previously mentioned, we are in the presence of an
hyper-optimization problem, which in practice is the optimization of the process
(the optimal configuration of the WSM) for solving an optimization (satisfaction)
problem. In Section 3.1, we present the approach used to optimize the WSM.
As previously mentioned, to determine the most successful weight set for perfor-
mance indicators, the WSM must be finely tuned by an optimizer. To this end we
propose the use of a bat algorithm, which is a recent metaheuristic [19] inspired
on the echolocation behavior of bats. Bats and particularly micro-bats are able
to identify objects in their surrounding areas by emitting pulses of sound and
retrieving the corresponding produced echoes. This advanced capability allows
bats even to distinguish obstacles from preys, being able to hunt in complete
darkness. The bat algorithm as been developed following three rules: (1) It is
assumed that all bats use echolocation to determine distances, and all of them
are able to distinguish food, prey, and background barriers. (2) A bat bi searches
for a prey with a position xi and a velocity vi . The pulses of sound emitted have
the following features: a frequency fmin , (or varying λ), a varying wavelength λ
(or frequency f ), loudness A0 , and a rate of pulse emission r ∈ [0, 1]. All sound
features can be automatically adjusted depending on their target proximity. (3)
Although the loudness can vary in many ways, it is assumed that the loudness
varies from a large (positive) A0 to a minimum constant value Amin .
Algorithm 1 illustrates the pseudo-code for bat optimization. At the begin-
ning, a population of m bats is initialized with position xi and velocity vi . Then,
the frequency fi at position xi is set followed by pulse rates and loudness. Then,
a while loop encloses a set of actions to be performed t times until the fixed
number T of iterations if reached. The first action to be done between the loop
is the movement of bats according to Eq. 2, 3, and 4.
1: while t < T do
2: for all bi do
3: Generate new solutions through Eq.(2), (3) and (4).
4: if rand > ri then
5: Select a solution among the best solutions.
6: Generate a local solution around the best solution.
7: end if
8: if rand < Ai and f (xi ) < f (x̂) then
9: Accept the new solutions.
10: Increase ri and reduce Ai .
11: end if
12: end for
13: end while
14: Rank the bats and f ind the current best x̂.
4 Experimental Results
Ordering Heuristics
Id Variable Value Id Variable Value Id Variable Value
S1 First S9 First S17 First
S2 MRV S10 MRV S18 MRV
S3 AMRV S11 AMRV S19 AMRV
S4 O S12 O S20 O
Min Mid Max
S5 S S13 S S21 S
S6 L S14 L S22 L
S7 MC S15 MC S23 MC
S8 MR S16 MR S24 MR
§ 5. Arms.
We shall not, of course, study Assyrian arms from the military
point of view. That question has been treated with all the care it
deserves by Rawlinson and Layard.[431] From the stone axes and
arrow-heads that have been found in the oldest Chaldæan tombs, to
the fine weapons and defensive armour in iron and bronze, used by
the soldiers of Nineveh in its greatest years, by the cavalry, the
infantry, and the chariot-men of Sargon and Sennacherib, the
progress is great and must have required many long centuries of
patient industry. In Assyria no trade can have occupied more hands
or given rise to more invention than that of the armourer. For two
centuries the Assyrian legions found no worthy rivals on the
battlefields of Asia; and, although their superiority was mainly due, of
course, to qualities of physical vigour and moral energy developed
by discipline, their unvarying success was in some degree the result
of their better arms. Without dwelling upon this point we may just
observe that when war is the chief occupation of a race, its arms are
sure to be carried to an extreme degree of luxury and perfection.
Some idea of their elaboration in the case of Assyria may be gained
from the reliefs and from the original fragments that have come down
to us.