Pages: 1 - 12
In this study we investigate information processing in deep neural network models. We demonstrate that
unsupervised training of autoencoder models of certain class can result in emergence of compact and structured
internal representation of the input data space that can be correlated with higher...
Pages: 13 - 27
Artificial immune systems are metaheuristic algorithms that mimic the adaptive capabilities of the immune
system of vertebrates. Since the 1990s, they have become one of the main branches of computer
intelligence. However, there are still many competitive processes in the biological phenomena that...
Pages: 28 - 38
Breast cancer is identified as the most common type of cancer in women worldwide with 1.6 million women around
the world diagnosed every year. This prompts many active areas of research in identifying better ways to prevent,
detect, and treat breast cancer. DESIREE is a European Union funded project,...
Pages: 39 - 58
Pages: 59 - 78
In the association rule mining field many different quality measures have been proposed over time with
the aim of quantifying the interestingness of each discovered rule. In evolutionary computation, many of
these metrics have been used as functions to be optimized, but the selection of a set of...
Pages: 79 - 89
In order to define management and marketing strategies, farmers need adequate knowledge about future
yield with the greatest possible accuracy and anticipation. In citrus orchards, greater variability and
non-normality of yield distributions complicate the early estimation of fruit production. This...
Pages: 90 - 107
Fuzzy rough set theory is a hybrid method that deals with vagueness and uncertainty emphasized in
decision-making. In this research study, we apply the concept of fuzzy rough sets to graphs. We introduce
the notion of fuzzy rough digraphs and describe some of their methods of construction. In particular,...
Pages: 108 - 122
A multi-scale feature selection method based on the Choquet Integral is presented in this paper. Usually, aggregation
decision-making problems are well solved, relying on few decision rules associated to a small number of input
parameters. However, many industrial applications require the use of...
Pages: 123 - 130
This paper shows the implementation of a prototype of street theft detector using the deep learning technique R-
CNN (Region-Based Convolutional Network), applied in the Command and Control Information System (C2IS) of
National Police of Colombia, the prototype is implemented using three models of...
Pages: 131 - 148
Firefly algorithm (FA) is a prominent metaheuristc technique. It has been widely studied and hence
there are a lot of modified FA variants proposed to solve hard optimization problems from various areas.
In this paper an improved chaotic firefly algorithm (ICFA) is proposed for solving global optimization...
Pages: 149 - 163
Global optimization for nonlinear function is a challenging issue. In this paper, an improved monarch
butterfly algorithm based on local search and differential evolution is proposed. Local search strategy is
first embedded into original monarch butterfly optimization to enhance the searching capability....
Pages: 164 - 171
Reinforcement learning (RL) aims to resolve the sequential decision-making under uncertainty problem
where an agent needs to interact with an unknown environment with the expectation of optimising the
cumulative long-term reward. Many real-world problems could benefit from RL, e.g., industrial robotics,...
Pages: 172 - 182
The construction of belief intervals is crucial for decision-making in multi-attribute group information
integration. Based on multi-adjoint and evidence theory, an approach to multi-criteria group decisionmaking(MCGDM) in intuitionistic fuzzy information system is proposed. First, the upper and lower...