Computational Intelligence - February 2014 - 8

Outstanding Organization Award
Honda Research Institute Europe,
GERMANY
For contributions to the field of computational
intelligence in science and innovation.
The Honda Research Institute
Europe (HRI-EU)
has been founded
in 2003 with the mission to conduct
fundamental and applied research in
intelligent systems.
Together with sister institutes in
Japan and in the United States the
aim was to explore the future of computer science.
Almost ten years later, the importance of information and communication technology in the automotive
industry is growing rapidly.
At HRI ideas are the products; ideas
that lead to innovations. Science without innovation neglects opportunities
and innovation without science remains
shallow and superficial. Innovation
Through Science is part of the HRI
philosophy and enables HRI to remain
focused on its role in Honda and in the
society at large.
Research in Intelligent Systems is at
the center of the Honda Research
Institute Europe. Intelligent systems
will shape the future in a variety of
for ms, ranging from accident-free
mobility to cognitive robotics and from
smart process management to the efficient use of resources. Intelligence is
necessary to handle complexity in
products and in processes.
Currently, the researchers at HRIEU are organized in four competence
groups with the topics: "Cognitive Systems and Representation", "System
Architecture and Embodiment", "Sensory Processing and Learning" and
"Complex System Optimization and
Analysis". Among others, the institute
has contributed to neural computation,
visual scene analysis, humanoid robotics, artificial life, systems engineering,
evolutionary optimization and learning,
natural computation and speech and
signal processing. In these areas,

researchers at HRI-EU have published
more than 700 scientific papers with
more than 7300 citations. For additional information, see http://www.
honda-ri.de.
HRI-EU has filed 118 patent families in eight countries all focusing on
using new insights from computational intelligence for improving technical processes.
The Honda Research Institute
Europe has been engaged in academic
teaching and in the education of students in particular PhD students since
its foundation. PhD projects are carried
out as collaboration projects with Universities on research subjects of mutual
interest. The students that are supported
by HRI-EU are part of the HRI European Graduate Network, which fosters
communication between "HRI" students during their time at HRI-EU
and beyond.
Outstanding Ph.D.
Dissertation Award
Jing Liang (J.J.
Liang) for her thesis entitled "Novel
Par ticle Swar m
Optimizers with
Hybrid, Dynamic
and Adaptive
Neighborhood
Structures" presented for the degree of
Doctor of Philosophy in the Nanyang
Technological University, Singapore,
March 2009.
Supervisor: P.N. Suganthan, Nanyang
Technological University, SINGAPORE
Abstract-Many real world problems can be formulated as optimization
problems with various parameters to be
optimized. Some problems only have
one objective to be optimized, some
may have multiple objectives to be
optimized at the same time and some
need to be optimized subjecting to one
or more constraints. Thus numerous
optimization algorithms have been proposed to solve these problems. Particle
Swarm Optimizer (PSO) is a relatively
new optimization algorithm which has
shown its strength in the optimization

IEEE ComputatIonal IntEllIgEnCE magazInE | FEbruary 2014

world. This thesis presents two PSO
variants, Comprehensive Learning Particle Swarm Optimizer (CLPSO) and
Dynamic Multi-Swarm Particle Swarm
Optimizer (DMS-PSO), which have
good global search ability and can solve
complex multi-modal problems for single objective optimization. The latter
one is extended to solve constrained
optimization and multi-objective optimization problems successfully with a
novel constraint-handling mechanism
and a novel updating criterion respectively. Subsequently, DMS-PSO is
applied to determine the Bragg wavelengths of the sensors in an FBG sensor
network and a tree search structure is
designed to improve the accuracy and
reduce the computation cost.
Outstanding Chapter Award
IEEE CIS UKRI Chapter, UK
For promoting and supporting the dissemination of computational intelligence within
the UKRI Section.
IEEE Transactions on Neural Networks Outstanding Paper Award
Long Cheng, Zeng-Guang Hou,
Yingzi Lin, Min Tan, Wenjun Chris
Zhang, Fang-Xiang Wu for their paper
entitled "Recurrent Neural Network
for Non-Smooth Convex Optimization Problems with Application to the
Identification of Genetic Regulatory
Networks", vol. 22, no. 5, pp. 714-726,
May 2011.
Digital Object Identifier: 10.1109/
TNN.2011.2109735
Abstract-A recurrent neural network is proposed for solving the nonsmooth convex optimization problem
with the convex inequality and linear
equality constraints. Since the objective
function and inequality constraints may
not be smooth, the Clarke's generalized gradients of the objective function
and inequality constraints are employed
to describe the dynamics of the proposed neural network. It is proved that
the equilibrium point set of the proposed neural network is equivalent to
the optimal solution of the original
optimization problem by using the
Lagrangian saddle-point theorem.

http://www http://www.honda-ri.de

Table of Contents for the Digital Edition of Computational Intelligence - February 2014