Soft Computing

, Volume 20, Issue 11, pp 4203–4204 | Cite as

Special issue SOCO 2015

  • Emilio Corchado
  • Álvaro Herrero

The eleven papers included in this special issue represent a selection of extended contributions presented at the 10th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2015) held in Burgos, Spain, in June 2015, and organized by the BISITE (University of Salamanca) and the GICAP (University of Burgos) research groups, together with the Technological Institute of Castilla y León.

This special issue is aimed at practitioners, researchers and postgraduate students who are engaged in developing and applying soft computing to solve real-world problems. The papers are organized as follows.

The first contribution, by Asencio-Cortés et al., proposes a set of seven algorithms of machine learning that has been selected and applied to prove their effectiveness in the prediction of urban traffic congestion. Collected data from sensors located at the Spanish city of Seville are analysed from a binary classification perspective.

Rincón et al. present an application where humans are immersed into a system that extracts and analyses the emotional states of a human group trying to maximize its welfare. To do so, several artificial intelligence tools are combined in a hybrid application, namely multi-agent system, machine learning and statistical classification.

In the third contribution, a novel framework for improved error detection and correction in spoken conversational interfaces is described and validated by Griol et al. It combines user behaviour and error modelling to estimate the probability of the presence of errors in the user utterance. To calculate the probability of selecting the different user responses given the current state of the dialog, multi-layer perceptrons are applied.

The following paper, by de Moura et al., proposes a nature and biologically inspired meta-heuristic to design proportional, integrative and derivative controllers. More precisely, the swarm intelligence algorithm named grey wolf optimization is applied to PID control. Several case studies are considered to validate authors proposal and compared it with a particle swarm optimization algorithm.

The research by Matei et al. addresses the problem of automated product design by two evolutionary approaches: genetic algorithms and evolutionary ontologies. Both approaches are described, applied and compared in the case of power train design. The paper demonstrates that automated product design is more efficient by applying evolutionary principles on ontologies.

In the following paper, by Herrero et al., a hybrid artificial intelligence system is proposed, aimed at gaining deeper knowledge about knowledge management practices in companies from four different economic sectors. By means of neural networks and classification trees, companies are diagnosed and explanations about crucial KM practices and perspectives are generated.

Salcedo-Sanz et al. propose a coral reefs optimization algorithm with Substrate Layers to tackle the optimization problem of battery scheduling in microgrids. The proposed algorithm is a recently conceived meta-heuristic which promotes co-evolution of different exploration models within a unique population. In the paper, experiments in a real microgrids scenario are described.

The most important genes and clusters related to production outputs of real-world time series microarray data in the industrial microbiology area are studied in the paper by Chira et al. Shape-based clustering models are developed using the pattern of gene expression values over time and further incorporating knowledge about the correlation between the change in the gene expression level and the output value.

In the paper by Carmona et al., it is presented an analysis of the impact of class noise on the most relevant evolutionary fuzzy systems for subgroup discovery. Additionally, it is studied how filtering techniques, devised for predictive tasks, may alleviate the impact of noise on descriptive fields such as subgroup discovery.

Del Val et al. present a multi-agent system that automates the process of gathering data from users’ activity in social networks and performs an in-depth analysis of the evolution of social behaviour at different levels of granularity in online events based on network theory metrics. The proposed system is evaluated for the analysis of users’ activity in events on Twitter.

Finally, the application of multi-agent system to support decision-making process in design for recycling is presented in the paper by Diakun et al. The proposed system suggests design modifications to improve the recycling-oriented assessment of the designed product by taking into account the cost of disassembly and the cost of disposal and recycling of materials. Results of analysis based on real household appliance model are presented.

The guest editors wish to thank Prof Antonio Di Nola and Prof Vincenzo Loia, (Editor-in-Chief and Co-Editor-in-Chief of the Soft Computing Journal) for providing the opportunity to edit this special issue. We would also like to thank the referees who have critically evaluated the papers within the short time and the editorial staff for their support. Finally, we hope the reader will share our joy and find this special issue very useful.


Compliance with ethical standards

Conflict of interest

All authors declare that they have no conflicts of interest.

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Universidad de SalamancaSalamancaSpain
  2. 2.University of BurgosBurgosSpain

Personalised recommendations