Václav Snášel

Proceedings of the Fifth International Conference on Innovations in Bio-Inspired Computing and Applications IBICA 2014

This volume of Advances in Intelligent Systems and Computing contains accepted papers presented at IBICA2014, the 5th International Conference on Innovations in Bio-inspired Computing and Applications. The aim of IBICA 2014 was to provide a platform for world research leaders and practitioners, to discuss the full spectrum of current theoretical developments, emerging technologies, and innovative applications of Bio-inspired Computing. Bio-inspired Computing remains to be one of the most exciting research areas, and it is continuously demonstrating exceptional strength in solving complex real life problems. The main driving force of the conference was to further explore the intriguing potential of Bio-inspired Computing. IBICA 2014 was held in Ostrava, Czech Republic and hosted by the VSB - Technical University of Ostrava.

Proceedings of the Second International Scientific Conference "Intelligent Information Technologies for Industry" (IITI'17)

This volume of Advances in Intelligent Systems and Computing contains papers presented in the main track of IITI 2016, the First International Conference on Intelligent Information Technologies for Industry held in May 16-21 in Sochi, Russia. The conference was jointly co-organized by Rostov State Transport University (Russia) and VSB Technical University of Ostrava (Czech Republic) with the participation of Russian Association for Artificial Intelligence (RAAI) and Russian Association for Fuzzy Systems and Soft Computing (RAFSSC). The volume is devoted to practical models and industrial applications related to intelligent information systems. The conference has been a meeting point for researchers and practitioners to enable the implementation of advanced information technologies into various industries. Nevertheless, some theoretical talks concerning the-state-of-the-art in intelligent systems and soft computing are included in the proceedings as well

Afro-European Conference for Industrial Advancement

This volume contains accepted papers presented at AECIA2014, the First International Afro-European Conference for Industrial Advancement. The aim of AECIA was to bring together the foremost experts as well as excellent young researchers from Africa, Europe, and the rest of the world to disseminate latest results from various fields of engineering, information, and communication technologies. The first edition of AECIA was organized jointly by Addis Ababa Institute of Technology, Addis Ababa University, and VSB - Technical University of Ostrava, Czech Republic and took place in Ethiopias capital, Addis Ababa.

Моделирование распространения излучения в тканях головы с учетом анизотропии рассеяния для оптимизации расположения приемников и источников излучения в интерфейсе мозг-компьютер, основанном на ближней инфракрасной спектроскопии

The application of the Monte Carlo simulation method was described to specify the parameters of the near infrared light propagation through the head tissues necessary to optimize the operation of the brain-computer interfaces. Four-layered spherical head model, consisting of layers of skin, bone, gray and white matter, was used. The dependences of the parameters of the detected light on the distance between the source and the detector are obtained.

Advances in Nature and Biologically Inspired Computing

One of the challenging issues in bioinformatics field is that, microarray datasets are imbalance in nature i.e., the majority class dominates the minority class making it difficult for the conventional classifiers to achieve accurate and useful predictions. However, some studies have addressed this issue merely by focusing on binary–class problems. In this article, an ensemble framework is proposed for multiclass imbalance classification problem that combines a meta learning algorithm ‘decorate’ with a sampling technique to deal with the problem in microarray datasets. The meta-learning algorithm builds diverse ensembles of classifiers constructing artificial samples and the sampling technique introduces bias to achieve uniform class distribution to reduce misclassification error. Experimental results on the two highly imbalanced multiclass microarray cancer datasets indicate that the technique applied provides significant improvement in comparison to other conventional ensembles.

Document Compression Improvements Based on Data Clustering

The modern information society produces immense quantities of textual information. Storing text effectively and searching necessary information in stored texts are the tasks for Information Retrieval Systems (IRS). The size of an IRS increases with the increasing size of available external memories of computers. Therefore, it is now possible to have a several gigabyte IRS on one DVD. Similarly, with the growth of Internet it is possible to have an easy remote access to an extensive IRS, which is stored in an even bigger disk array that operates on an Web server. We can only expect even faster growth of memory capacity requirements in future. The information explosion can be avoided basically in two ways: