Now showing 1 - 10 of 11
No Thumbnail Available
Publication

EVOLUTIONARY ALGORITHMS LEARNING METHODS IN STUDENT EDUCATION

2021, Grabusts, Pēteris, Zorins, Aleksejs

Teaching experience shows that during educational process student perceive graphical information better than analytical relationships. As a possible solution, there could be the use of package Matlab in realization of different algorithms for IT studies. Students are very interested in modern data mining methods, such as artificial neural networks, fuzzy logic, clustering and evolution methods. Series of research were carried out in order to demonstrate the suitability of the Matlab for the purpose of visualization of various simulation models of some data mining disciplines – particularly genetic algorithms. Nowadays the possibilities of evolutionary algorithms are widely used in many optimization and classification tasks. There are four paradigms in the world of evolutionary algorithms: evolutionary programming, evolution strategies, genetic algorithms and genetic programming. This paper analyses present-day approaches of genetic algorithms and genetic programming and examines the possibilities of genetic programming that will be used in further research. Genetic algorithm learning methods are often undeservedly forgotten, although the implementation of their algorithms is relatively strong and can be implemented even for students. In the research part of the study the modelling capabilities in data mining studies were demonstrated based on genetic algorithms and real examples. We assume that students already have prior knowledge of genetic algorithms.

No Thumbnail Available
Publication

The Influence of Hidden Neurons Factor on Neural Nework Training Quality Assurance

2015, Grabusts, Pēteris, Zorins, Aleksejs

The work shows the role of hidden neurons in the multilayer feed-forward neural networks. The numeric expression of hidden neurons is usually determined in each case empirically. The methodology for determining the number of hidden neurons are described. The neural network based approach is analyzed using a multilayer feed-forward network with backpropagation learning algorithm. We have presented neural network implementation possibility in bankruptcy prediction (the experiments have been performed in the Matlab environment). On the base of bankruptcy data analysis the effect of hidden neurons to specific neural network training quality is shown. The conformity of theoretical hidden neurons to practical solutions was carried out.

No Thumbnail Available
Publication

Artificial Neural Networks and Human Brain: Survey of Improvement Possibilities of Learning

2015, Zorins, Aleksejs, Grabusts, Pēteris

There are numerous applications of Artificial Neural Networks (ANN) at the present time and there are different learning algorithms, topologies, hybrid methods etc. It is strongly believed that ANN is built using human brain’s functioning principles but still ANN is very primitive and tricky way for real problem solving. In the recent years modern neurophysiology advanced to a big extent in understanding human brain functions and structure, however, there is a lack of this knowledge application to real ANN learning algorithms. Each learning algorithm and each network topology should be carefully developed to solve more or less complex problem in real life. One may say that almost each serious application requires its own network topology, algorithm and data pre-processing. This article presents a survey of several ways to improve ANN learning possibilities according to human brain structure and functioning, especially one example of this concept – neuroplasticity – automatic adaptation of ANN topology to problem domain.

No Thumbnail Available
Publication

Developing Ecological Safety of Artificial Intelligence in Human Society

2020, Zorins, Aleksejs, Grabusts, Pēteris

The paper presents cyber systems especially based on artificial intelligence (AI) from a perspective of ecological safety for humanity. The study provides a definition of ecological safety of AI and discusses its relevance to a modern science and society, as well as reviews risks of smart AI systems.

No Thumbnail Available
Publication

APPROACHES AND SOLUTIONS FOR SIGN LANGUAGE RECOGNITION PROBLEM

2018, Zorins, Aleksejs, Grabusts, Pēteris

The goal of the paper is reviewing several aspects of Sign Language Recognition problems focusing on Artificial Neural Network approach. The lack of automated Latvian Sign Language has identified and proposals of how to develop such a system have made. Tha authors use analytical, statistical methods as well as practical experiments with neural network software. The main results of the paper are description of main Sign Language Recognition problem solving methods with Artificial Neural Networks and directions of future work based on authors’ previous expertise.

No Thumbnail Available
Publication

DATA MINING TEACHING POSSIBILITIES USING MATLAB

2018, Grabusts, Pēteris, Zorins, Aleksejs

The teaching experience in the study process shows that students are better at perceiving graphical information rather than analytical relationships. Many training courses run on models that were previously available only in mathematics or physics. The use of Matlab package for the implementation of various algorithms in the Information Technology fields could be a possible solution. Often, the analytical solution is much simpler than the visual Matlab model, but for the purposes of perspective training it gives understanding of the usefulness of using such models. In the previous articles the authors had given examples of how Matlab's possibilities could be used for economic research purposes (optimal tax rate searching and modelling market equilibrium price). Students are very interested in modern data mining methods, such as artificial neural networks. In the research part of the study, the modelling capabilities in data mining studies are demonstrated by neural network examples.

No Thumbnail Available
Publication

ETHICAL DEVELOPMENT AND IMPLEMENTATION OF ARTIFICIAL INTELLIGENCE

2021, Zorins, Aleksejs, Grabusts, Pēteris

The paper discovers an essence and importance of introduction of ethical dimension in all phases of artificial intelligence (AI): development of concept and source code, implementation in real-life applications and support and improvement of existing solutions. Modern society largely depends on cybertechnologies most of which are using elements of AI and ethical aspects of it is of paramount importance.

No Thumbnail Available
Publication

LATVIAN SIGN LANGUAGE RECOGNITION CLASSIFICATION POSSIBILITIES

2017, Zorins, Aleksejs, Grabusts, Pēteris

There is a lack of automated sign language recognition system in Latvia while many other countries have been already equipped with such a system. Latvian deaf society requires support of such a system which would allow people with special needs to enhance their communication in governmental and public places. The aim of this paper is to recognize Latvian sign language alphabet using classification approach with artificial neural networks, which is a first step in developing integral system of Latvian Sign Language recognition. Communication in our daily life is generally vocal, but body language has its own significance. It has many areas of application like sign languages are used for various purposes and in case of people who are deaf and dumb, sign language plays an important role. Gestures are the very first form of communication. The paper presents Sign Language Recognition possibilities with centre of gravity method. So this area influenced us very much to carry on the further work related to hand gesture classification and sign’s clustering.

No Thumbnail Available
Publication

SAFETY OF ARTIFICIAL SUPERINTELLIGENCE

2019, Zorins, Aleksejs, Grabusts, Pēteris

The paper analyses an important problem of cyber security from human safety perspective which is usually described as data and/or computer safety itself without mentioning the human. There are numerous scientific predictions of creation of artificial superintelligence, which could arise in the near future. That is why the strong necessity for protection of such a system from causing any farm arises. This paper reviews approaches and methods already presented for solving this problem in a single article, analyses its results and provides future research directions.

No Thumbnail Available
Publication

Review of Data Preprocessing Methods for Sign Language Recognition Systems based on Artificial Neural Networks

2016, Zorins, Aleksejs, Grabusts, Pēteris

The article presents an introductory analysis of relevant research topic for Latvian deaf society, which is the development of the Latvian Sign Language Recognition System. More specifically the data preprocessing methods are discussed in the paper and several approaches are shown with a focus on systems based on artificial neural networks, which are one of the most successful solutions for sign language recognition task.