Handwritten Numeral recognition plays a vital role in postal automation
services especially in countries like India where multiple languages and
scripts are used Discrete Hidden Markov Model (HMM) and hybrid of Neural
Network (NN) and HMM are popular methods in handwritten word recognition
system. The hybrid system gives better recognition result due to better
discrimination capability of the NN. A major problem in handwriting recognition
is the huge variability and distortions of patterns.

We investigate the self-organising behaviour of Digital Ecosystems, because a
primary motivation for our research is to exploit the self-organising
properties of biological ecosystems. We extended a definition for the
complexity, grounded in the biological sciences, providing a measure of the
information in an organism's genome. Next, we extended a definition for the
stability, originating from the computer sciences, based upon convergence to an
equilibrium distribution.

The nature and source of evolutionary trends in complexity is difficult to
assess from the fossil record, and the driven vs. passive nature of such trends
has been debated for decades. There are also questions about how effectively
artificial life software can evolve increasing levels of complexity. We extend
our previous work demonstrating an evolutionary increase in an information
theoretic measure of neural complexity in an artificial life system
(Polyworld), and introduce a new technique for distinguishing driven from
passive trends in complexity.

We study the sequences generated by neuronal recurrence equations of the form
$x(n) = {\bf 1}[\sum_{j=1}^{h} a_{j} x(n-j)- \theta]$. From a neuronal
recurrence equation of memory size $h$ which describes a cycle of length
$\rho(m) \times lcm(p_0, p_1,..., p_{-1+\rho(m)})$, we construct a set of
$\rho(m)$ neuronal recurrence equations whose dynamics describe respectively
the transient of length $O(\rho(m) \times lcm(p_0, ..., p_{d}))$ and the cycle
of length $O(\rho(m) \times lcm(p_{d+1}, ..., p_{-1+\rho(m)}))$ if $0 \leq d
\leq -2+\rho(m)$ and 1 if $d=\rho(m)-1$.

We present a novel distributed evolutionary algorithm, KaFFPaE, to solve the
Graph Partitioning Problem, which makes use of KaFFPa (Karlsruhe Fast Flow
Partitioner). The use of our multilevel graph partitioner KaFFPa provides new
effective crossover and mutation operators. By combining these with a scalable
communication protocol we obtain a system that is able to improve the best
known partitioning results for many inputs in a very short amount of time.

Biclustering is a two way clustering approach involving simultaneous
clustering along two dimensions of the data matrix. Finding biclusters of web
objects (i.e. web users and web pages) is an emerging topic in the context of
web usage mining. It overcomes the problem associated with traditional
clustering methods by allowing automatic discovery of browsing pattern based on
a subset of attributes. A coherent bicluster of clickstream data is a local
browsing pattern such that users in bicluster exhibit correlated browsing
pattern through a subset of pages of a web site.

A schema is a naturally defined subset of the space of fixed-length binary
strings. The Holland Schema Theorem gives a lower bound on the expected
fraction of a population in a schema after one generation of a simple genetic
algorithm. This paper gives formulas for the exact expected fraction of a
population in a schema after one generation of the simple genetic algorithm.
Holland's schema theorem has three parts, one for selection, one for crossover,
and one for mutation. The selection part is exact, whereas the crossover and
mutation parts are approximations.

In this paper, we present an empirical study on convergence nature of
Differential Evolution (DE) variants to solve unconstrained global optimization
problems. The aim is to identify the competitive nature of DE variants in
solving the problem at their hand and compare. We have chosen fourteen
benchmark functions grouped by feature: unimodal and separable, unimodal and
nonseparable, multimodal and separable, and multimodal and nonseparable.
Fourteen variants of DE were implemented and tested on fourteen benchmark
problems for dimensions of 30.

Genetic Programming (GP) has found various applications. Understanding this
type of algorithm from a theoretical point of view is a challenging task. The
first results on the computational complexity of GP have been obtained for
problems with isolated program semantics. With this paper, we push forward the
computational complexity analysis of GP on a problem with dependent program
semantics. We study the well-known sorting problem in this context and analyze
rigorously how GP can deal with different measures of sortedness.

Bankruptcy prediction is very important for all the organization since it
affects the economy and rise many social problems with high costs. There are
large number of techniques have been developed to predict the bankruptcy, which
helps the decision makers such as investors and financial analysts. One of the
bankruptcy prediction models is the hybrid model using Fuzzy C-means clustering
and MARS, which uses static ratios taken from the bank financial statements for
prediction, which has its own theoretical advantages.

In this paper I present a novel type of Topology and Weight Evolving
Artificial Neural Network (TWEANN) system called Monolithic Discover & eXplore
Neural Network (DXNN), a monolithic variant of the standard DXNN which utilized
explicit modularity.

This paper details the application of a genetic programming framework for
classification of decision tree of Soil data to classify soil texture. The
database contains measurements of soil profile data. We have applied GATree for
generating classification decision tree. GATree is a decision tree builder that
is based on Genetic Algorithms (GAs). The idea behind it is rather simple but
powerful. Instead of using statistic metrics that are biased towards specific
trees we use a more flexible, global metric of tree quality that try to
optimize accuracy and size.

Web page categorization is one of the challenging tasks in the world of ever
increasing web technologies. There are many ways of categorization of web pages
based on different approach and features. This paper proposes a new dimension
in the way of categorization of web pages using artificial neural network (ANN)
through extracting the features automatically. Here eight major categories of
web pages have been selected for categorization; these are business & economy,
education, government, entertainment, sports, news & media, job search, and
science.

In recent years, many neural network models have been proposed for pattern
classification, function approximation and regression problems. This paper
presents an approach for classifying patterns from simplified NNs. Although the
predictive accuracy of ANNs is often higher than that of other methods or human
experts, it is often said that ANNs are practically "black boxes", due to the
complexity of the networks. In this paper, we have an attempted to open up
these black boxes by reducing the complexity of the network. The factor makes
this possible is the pruning algorithm.

Neural networks (NNs) have been successfully applied to solve a variety of
application problems involving classification and function approximation.
Although backpropagation NNs generally predict better than decision trees do
for pattern classification problems, they are often regarded as black boxes,
i.e., their predictions cannot be explained as those of decision trees. In many
applications, it is desirable to extract knowledge from trained NNs for the
users to gain a better understanding of how the networks solve the problems.

Text classification is the process of classifying documents into predefined
categories based on their content. Existing supervised learning algorithms to
automatically classify text need sufficient documents to learn accurately. This
paper presents a new algorithm for text classification that requires fewer
documents for training. Instead of using words, word relation i.e association
rules from these words is used to derive feature set from preclassified text
documents.

Although backpropagation ANNs generally predict better than decision trees do
for pattern classification problems, they are often regarded as black boxes,
i.e., their predictions cannot be explained as those of decision trees. In many
applications, it is desirable to extract knowledge from trained ANNs for the
users to gain a better understanding of how the networks solve the problems. A
new rule extraction algorithm, called rule extraction from artificial neural
networks (REANN) is proposed and implemented to extract symbolic rules from
ANNs.

This research is to search for alternatives to the resolution of complex
medical diagnosis where human knowledge should be apprehended in a general
fashion. Successful application examples show that human diagnostic
capabilities are significantly worse than the neural diagnostic system. Our
research describes a constructive neural network algorithm with
backpropagation; offer an approach for the incremental construction of
nearminimal neural network architectures for pattern classification.

In this paper, Estimation of Distribution Algorithm (EDA) is used for Zone
Routing Protocol (ZRP) in Mobile Ad-hoc Network (MANET) instead of Genetic
Algorithm (GA). It is an evolutionary approach, and used when the network size
grows and the search space increases. When the destination is outside the zone,
EDA is applied to find the route with minimum cost and time. The implementation
of proposed method is compared with Genetic ZRP, i.e., GZRP and the result
demonstrates better performance for the proposed method.

In this paper I present a novel type of Topology and Weight Evolving
Artificial Neural Network (TWEANN) system called Discover & eXplore Neural
Network (DXNN) Platform.

This paper presents an analysis of building blocks propagation in
Quantum-Inspired Genetic Algorithm, which belongs to a new class of
metaheuristics drawing their inspiration from both biological evolution and
unitary evolution of quantum systems. The expected number of quantum
chromosomes matching a schema has been analyzed and a random variable
corresponding to this issue has been introduced. The results have been compared
with Simple Genetic Algorithm. Also, it has been presented how selected binary
quantum chromosomes cover a domain of one-dimensional fitness function.

The sequential parameter optimization (SPOT) package for R is a toolbox for
tuning and understanding simulation and optimization algorithms. Model-based
investigations are common approaches in simulation and optimization. Sequential
parameter optimization has been developed, because there is a strong need for
sound statistical analysis of simulation and optimization algorithms.

We introduce a new neural architecture and an unsupervised algorithm for
learning invariant representations from temporal sequence of images. The system
uses two groups of complex cells whose outputs are combined multiplicatively:
one that represents the content of the image, constrained to be constant over
several consecutive frames, and one that represents the precise location of
features, which is allowed to vary over time but constrained to be sparse. The
architecture uses an encoder to extract features, and a decoder to reconstruct
the input from the features.

In this paper we present a novel genetic algorithm (GA) solution to a simple
yet challenging commercial puzzle game known as the Zen Puzzle Garden (ZPG). We
describe the game in detail, before presenting a suitable encoding scheme and
fitness function for candidate solutions. We then compare the performance of
the genetic algorithm with that of the A* algorithm.

ECG Feature Extraction plays a significant role in diagnosing most of the
cardiac diseases. One cardiac cycle in an ECG signal consists of the P-QRS-T
waves. This feature extraction scheme determines the amplitudes and intervals
in the ECG signal for subsequent analysis. The amplitudes and intervals value
of P-QRS-T segment determines the functioning of heart of every human.
Recently, numerous research and techniques have been developed for analyzing
the ECG signal.

Mobility prediction allows estimating the stability of paths in a mobile
wireless Ad Hoc networks. Identifying stable paths helps to improve routing by
reducing the overhead and the number of connection interruptions. In this
paper, we introduce a neural network based method for mobility prediction in Ad
Hoc networks. This method consists of a multi-layer and recurrent neural
network using back propagation through time algorithm for training.

Swarm cognition aims at bringing together the studies of the
self-organization of swarms and the cognitive processes of the brain. In this
paper, the Computing Networks (CNs) framework is presented. CNs are used to
generalize neural and swarm architectures. Artificial neural networks, ant
colony optimization, particle swarm optimization, and realistic biological
models are used as examples of instantiations of CNs. The description of these
architectures as CNs allows their comparison.

Complexity of global optimization algorithms makes implementation of the
algorithms difficult and leads the algorithms to require more computer
resources for the optimization process. The ability to explore the whole
solution space without increasing the complexity of algorithms has a great
importance to not only get reliable results but so also make the implementation
of these algorithms more convenient for higher dimensional and complex-real
world problems in science and engineering.

This paper extends the analogies employed in the development of
quantum-inspired evolutionary algorithms by proposing quantum-inspired Hadamard
walks, called QHW. A novel quantum-inspired evolutionary algorithm, called
HQEA, for solving combinatorial optimization problems, is also proposed. The
novelty of HQEA lies in it's incorporation of QHW Remote Search and QHW Local
Search - the quantum equivalents of classical mutation and local search, that
this paper defines. The intuitive reasoning behind this approach, and the
exploration-exploitation balance thus occurring is explained.

As an immune inspired algorithm, the Dendritic Cell Algorithm (DCA) has been
applied to a range of problems, particularly in the area of intrusion
detection. Ideally, the intrusion detection should be performed in real-time,
to continuously detect misuses as soon as they occur. Consequently, the
analysis process performed by an intrusion detection system must operate in
real-time or near-to real-time. The analysis process of the DCA is currently
performed offline, therefore to improve the algorithm's performance we suggest
the development of a real-time analysis component.

The paper introduces particle swarm optimization as a viable strategy to find
numerical solution of Diophantine equation, for which there exists no general
method of finding solutions. The proposed methodology uses a population of
integer particles. The candidate solutions in the feasible space are optimized
to have better positions through particle best and global best positions. The
methodology, which follows fully connected neighborhood topology, can offer
many solutions of such equations.

This piece of research belongs to the field of educational assessment issue
based upon the cognitive multimedia theory. Considering that theory; visual and
auditory material should be presented simultaneously to reinforce the retention
of a mathematical learned topic, a carefully computer-assisted learning (CAL)
module is designed for development of a multimedia tutorial for our suggested
mathematical topic. The designed CAL module is a multimedia tutorial computer
package with visual and/or auditory material.

Because of the stochastic nature of traffic requirement matrix, it is very
difficult to get the optimal traffic distribution to minimize the delay even
with adaptive routing protocol in a fixed connection network where capacity
already defined for each link. Hence there is a requirement to define such a
method, which could generate the optimal solution very quickly and efficiently.
This paper presenting a new concept to provide the adaptive optimal traffic
distribution for dynamic condition of traffic matrix using nature based
intelligence methods.

Inventory management is considered to be an important field in Supply Chain
Management because the cost of inventories in a supply chain accounts for about
30 percent of the value of the product. The service provided to the customer
eventually gets enhanced once the efficient and effective management of
inventory is carried out all through the supply chain. The precise estimation
of optimal inventory is essential since shortage of inventory yields to lost
sales, while excess of inventory may result in pointless storage costs.

This work is an attempt for a state-of-the-art survey of natural and life
sciences with the goal to define the scope and address the central questions of
an original research program. It is focused on the phenomena of emergence,
adaptive dynamics and evolution of self-assembling, self-organizing,
self-maintaining and self-replicating biosynthetic systems viewed from a
newly-arranged perspective and understanding of computation and communication
in the living nature.

This paper describes a new method for the synthesis of planar antenna arrays
using fuzzy genetic algorithms (FGAs) by optimizing phase excitation
coefficients to best meet a desired radiation pattern. We present the
application of a rigorous optimization technique based on fuzzy genetic
algorithms (FGAs), the optimizing algorithm is obtained by adjusting control
parameters of a standard version of genetic algorithm (SGAs) using a fuzzy
controller (FLC) depending on the best individual fitness and the population
diversity measurements (PDM).

CODEQ is a new, population-based meta-heuristic algorithm that is a hybrid of
concepts from chaotic search, opposition-based learning, differential evolution
and quantum mechanics. CODEQ has successfully been used to solve different
types of problems (e.g. constrained, integer-programming, engineering) with
excellent results. In this paper, CODEQ is used to train feed-forward neural
networks. The proposed method is compared with particle swarm optimization and
differential evolution algorithms on three data sets with encouraging results.

In this paper we have investigated the performance of PSO Particle Swarm
Optimization based clustering on few real world data sets and one artificial
data set. The performances are measured by two metric namely quantization error
and inter-cluster distance. The K means clustering algorithm is first
implemented for all data sets, the results of which form the basis of
comparison of PSO based approaches. We have explored different variants of PSO
such as gbest, lbest ring, lbest vonneumann and Hybrid PSO for comparison
purposes.

In this paper, we introduce elements of probabilistic model that is suitable
for modeling of learning algorithms in biologically plausible artificial neural
networks framework. Model is based on two of the main concepts in quantum
physics - a density matrix and the Born rule. As an example, we will show that
proposed probabilistic interpretation is suitable for modeling of on-line
learning algorithms for PSA, which are preferably realized by a parallel
hardware based on very simple computational units.

This paper reviews application of Artificial Neural Networks in Aircraft
Maintenance, Repair and Overhaul (MRO). MRO solutions are designed to
facilitate the authoring and delivery of maintenance and repair information to
the line maintenance technicians who need to improve aircraft repair turn
around time, optimize the efficiency and consistency of fleet maintenance and
ensure regulatory compliance. The technical complexity of aircraft systems,
especially in avionics, has increased to the point at which it poses a
significant troubleshotting and repair challenge for MRO personnel.

We present a simple neural network model which combines a locally-connected
feedforward structure, as is traditionally used to model inter-neuron
connectivity, with a layer of undifferentiated connections which model the
diffuse projections from the human limbic system to the cortex. This new layer
makes it possible to model global effects such as salience, at the same time as
the local network processes task-specific or local information.

We present several applications of non-linear data modeling, using principal
manifolds and principal graphs constructed using the metaphor of elasticity
(elastic principal graph approach). These approaches are generalizations of the
Kohonen's self-organizing maps, a class of artificial neural networks. On
several examples we show advantages of using non-linear objects for data
approximation in comparison to the linear ones. We propose four numerical
criteria for comparing linear and non-linear mappings of datasets into the
spaces of lower dimension.

In the interconnected power system network, instability problems are caused
mainly by the low frequency oscillations of 0.2 to 2.5 Hz .The supplementary
control signal in addition with AVR and high gain excitation systems are
provided by means of Power System Stabilizer (PSS). Conventional power system
stabilizers provide effective damping only on a particular operating point. But
fuzzy based PSS provides good damping for a wide range of operating points.

Although researchers often discuss the rising popularity of nature-inspired
meta-heuristics (NIM), there has been a paucity of data to directly support the
notion that NIM are growing in prominence compared to other optimization
techniques.

This paper proposes a novel neural-network-based adaptive hybrid-reflectance
three-dimensional (3-D) surface reconstruction model. The neural network
combines the diffuse and specular components into a hybrid model. The proposed
model considers the characteristics of each point and the variant albedo to
prevent the reconstructed surface from being distorted.

Short Term Load forecasting in this paper uses input data dependent on
parameters such as load for current hour and previous two hours, temperature
for current hour and previous two hours, wind for current hour and previous two
hours, cloud for current hour and previous two hours. Forecasting will be of
load demand for coming hour based on input parameters at that hour. In this
paper we are using multiparameter regression method for forecasting which has
error within tolerable range.

There exists a range of different models for estimating and simulating credit
risk transitions to optimally manage credit risk portfolios and products. In
this chapter we present a Coupled Markov Chain approach to model rating
transitions and thereby default probabilities of companies. As the likelihood
of the model turns out to be a non-convex function of the parameters to be
estimated, we apply heuristics to find the ML estimators.

Recursive Neural Networks are non-linear adaptive models that are able to
learn deep structured information. However, these models have not yet been
broadly accepted. This fact is mainly due to its inherent complexity. In
particular, not only for being extremely complex information processing models,
but also because of a computational expensive learning phase.

This paper studies two issues related to the paper on Computing by
Self-reproduction: Autopoietic Automata by Jiri Wiedermann. It is shown that
all results presented there extend to deterministic computations. In
particular, nondeterminism is not needed for a lineage to generate all
autopoietic automata.

Modern evolutionary computation utilizes heuristic optimizations based upon
concepts borrowed from the Darwinian theory of natural selection. We believe
that a vital direction in this field must be algorithms that model the activity
of genomic parasites, such as transposons, in biological evolution. This
publication is our first step in the direction of developing a minimal
assortment of algorithms that simulate the role of genomic parasites.
Specifically, we started in the domain of genetic algorithms (GA) and selected
the Artificial Ant Problem as a test case.

A primary motivation for research in Digital Ecosystems is the desire to
exploit the self-organising properties of natural ecosystems. Ecosystems arc
thought to be robust, scalable architectures that can automatically solve
complex, dynamic problems. However, the biological processes that contribute to
these properties have not been made explicit in Digital Ecosystem research.
Here, we introduce how biological properties contribute to the self-organising
features of natural ecosystems.