Browsing by Department "Informācijas un komunikācijas tehnoloģiju laboratorija / Information and Communication Technology Lab"
Now showing 1 - 20 of 102
Results Per Page
Sort Options
- PublicationANALYSIS AND EVALUATION OF FISCAL POLICY IN LATVIA(2019)
;Erika ZubuleThe choice and topicality of the research topic is based on the fact that upon strengthening of the government's regulating role in economy, the notion of public finances positions itself, and state budget has become an important subject of both economic and political discussions as implementation of fiscal policy is takes place through it. In order to evaluate fiscal policy, it is necessary to evaluate the potential influence of different fiscal policy instruments on social and economic situation in the state. Aim of the research – to evaluate activities of fiscal policy implemented in Latvia in context of certain tax, namely, influence of corporate income tax on state's economic and financial indicators, identifying the main risks and imperfections of fiscal policy when ensuring state's budget. Applying simulation methods in the environment of Matlab/Simulink, the authors analyze and evaluate the influence of fiscal decisions and their implementation on the situation in Latvia, analyzing the most important tendencies in the sphere of corporate income tax payments according to the tax reform commenced in 2018. - PublicationANALYSIS OF ARTIFICIAL INTELLIGENCE APPLICATIONS FOR AUTOMATED TESTING OF VIDEO GAMES(2019)Game testing is a software testing process for quality control in video games. Game environments, sometimes called levels or maps, are complex and interactive systems. These environments can include level geometry, interactive entities, player and non-player controllable characters etc. Depending on the number and complexity of levels, testing them by hand may take a considerable effort. This is especially true for video games with procedurally generated levels that are automatically created using a specifically designed algorithm. A single change in a procedural generation algorithm can alter all of the video game levels, and they will have to be retested to ensure they are still completable or meet any other requirements of the game. This task may be suitable for automation, in particular using Artificial Intelligence (AI). The goal of this paper is to explore the most promising and up-to-date research on AI applications for video game testing to serve as a reference for anyone starting in the field.
Scopus© Citations 8 - PublicationANALYSIS OF CONTACTLESS RADIO FREQUENCY IDENTIFICATION TECHNOLOGIES AND ITS USAGE IN REZEKNE CITY INFRASTRUCTURE OBJECTS(2016-04-20)
;Zalužinskis, ArtūrsAuthor made the analysis of usage of contactless radio frequency identification technologies in Rezekne city infrastructure objects. Author provides the main types of radio frequency hardware, working principles and worldwide usage statistics. In the conclusion of the paper, author describes the further development opportunities of the radio frequency identification technologies. - PublicationAnalysis of factors affecting zero-waste food consumption in schools(2022)
;Deksne, Juta ;Litavniece, Lienīte ;Zvaigzne, Anda; Kodors, SergejsThe research aims to identify the factors affecting food waste and waste generation in schools and, consequently, barriers to zero-waste food consumption based on a systematic review of literature for the period 2015-2022. The research employed qualitative methods: systematic literature review, analysis and synthesis, as well as the monographic method. The literature review examined 1702 research papers and the abstracts. Using a PRISMA 2020 flow diagram, 54 papers were selected from the ScienceDirect, Scopus and Google Scholar databases for an in-depth analysis. Based on the literature review, 8 groups of factors that affected the generation of food waste in schools in the consumption process were identified: demographical, political, school food policy, environmental, socio-economic, personal/human, physical/human and geographical. The factors identified and aggregated might provide a basis for further discussions on zero-waste food consumption and food waste reduction in schools, as well as specific actions to optimize school food consumption and promote effective food and food waste management. - PublicationAnalysis of Fuzzy Time Series Forecasting for Migration Flows(2022)
;Oleg Uzhga-RebrovThe goal of this article is to forecast migration flows in Latvia. In comparison with many other countries with sufficiently symmetric emigration and immigration flows, in Latvia, migration flows are very asymmetric: the number of emigrants considerably exceed the number of immigrants. Since statistical data about migration are usually inaccurate, we employ fuzzy time series forecasting methods for prognosticating migration flows in Latvia forecasting. The use of this type of method is often useful not only for forecasting purposes. Three different methods for fuzzy time series forecasting are used. A detailed comparative analysis of the obtained results is given. Generalized forecasts of the expected net migration flow in the future are presented. - PublicationANALYSIS OF THE SIMULATED ANNEALING METHOD IN CLASSIC BOLTZMANN MACHINES(2016-12-10)The paper analyses a model of a neural net proposed by Hinton et al (1985). They have added noise to a Hopfield net and have called it Boltzmann machine (BM) drawing an analogy with the behaviour of physical systems with noises. The concept of simulated annealing is analysed. The experiment aimed at testing the state of thermal equilibrium for a Boltzmann net with three neurons, specified threshold values and weights at two different temperatures, T=1 and T=0,25, is described.
- PublicationApple and Pear Scab Expert System(2023)
;Apeināns, Ilmārs; ;Gunārs LācisLienīte LitavniecePlant disease, such as apple and pear scab, control is a crucial issue of fruit-growing. Apple and pear are among the most widely grown (approximately 43% of all fruit tree area) and economically important fruit crops worldwide and in Latvia. Research projects have produced research data covering various aspects of plant-pathogen interactions, but there is no internal linkage analysis, as well as implementation of other types of data (such as environmental and meteorological data, etc.). Establishing such a data integration system would allow the identification of new regularities in plant-pathogen interactions, and provide mechanisms for disease control decisions. In this study an expert system was developed aimed to help professional fruit-growers evaluate the possible impact of apple and pear scab to the plant health and yield quality. The expert system is based on a previously developed apple and pear scab ontology and consists of a web based front-end and triplestore back-end. - PublicationAPPLE AND PEAR SCAB ONTOLOGY(2021)
; ; ;Toms Bartulsons ;Olga Sokolova ;Lienīte LitavnieceAnna NikolajevaAn important issue in horticulture is ensuring plant disease, such as scab, prevention and treatment. Apple and pear are among the most widely grown (approximately 43% of all fruit tree area [1]) and economically important fruit crops specified worldwide and in Latvia. Scab diseases caused by ascomycetous fungi Venturia inaequalis and V.pyrina are economically the most important diseases worldwide. Research projects have produced research data covering various aspects of plant-pathogen interactions, but there is no internal linkage analysis, as well as implementation of other types of data (such as environmental and meteorological data, etc.). Establishing such a data integration system would allow the identification of new regularities in plant-pathogen interactions, and provide mechanisms for disease control decisions. Semantic analysis is one of information technology approaches to finding relationships in data. The product of analysis is ontology. There are plant disease ontologies which provide classification of diseases and describe their reasons. However, there is no ontology which describes a specific plant and relations among its farming parameters and disease probability. Such an ontology for apple and pear scab is presented in this paper. The constructed ontology can be applied to develop guidelines or digital expert systems.Scopus© Citations 1 - PublicationApple Scab Detection in the Early Stage of Disease Using a Convolutional Neural Network(2022)
;Kodors, Sergejs ;Gunārs Lācis ;Inga Moročko-Bičevska; ;Olga Sokolova ;Toms Bartulsons ;Apeināns, IlmārsVitālijs ŽukovsModern reviews of challenges related to deep learning application in agriculture mention restricted access to open datasets with high-resolution natural images taken in field conditions. Therefore, artificial intelligence solutions trained on these datasets containing low-resolution images and disease symptoms in the advanced stage are not suitable for early detection of plant diseases. The study aims to train a convolutional neural network for apple scab detection in an early stage of disease development. In this study a dataset was collected and used to develop a convolutional neural network based on the sliding-window method. The convolutional neural network was trained using the transfer-learning approach and MobileNetV2 architecture tuned on for embedded devices. The quality analysis in laboratory conditions showed the following accuracy results: F1 score 0.96 and Cohen’s kappa 0.94; and the occlusion maps — correct classification features.Scopus© Citations 1 - PublicationAPPLICATION OF CLUSTERING METHOD IN THE RBF NEURAL NETWORKS(2001)This paper describes one of classification algorithms, cluster analysis, that plays a significant role in the implementation of learning algorithm as applied to RBF-type artificial mural networks. The mathematical description of the K-means clustering algorithm is given and its implementation is demonstrated by experiment.
- PublicationApplication of the Ontology Concept for the Needs of Theoretical Mechanics(2015)
;Aivars VilkasteThe concepts of theoretical mechanics have been sufficiently well studied, they are used both for educational purposes and practical application. Nowadays, the use of ontologies is developing rapidly, thus allowing acquiring knowledge about the specific field of application. The author of this research analyses appropriateness of ontologies for the needs of theoretical mechanics. The study shows the use of graphs in the work with taxonomy concepts and describes the key notions of the ontologies. The author has tried to develop the concept of domain ontology for better understanding of the key notions of theoretical mechanics with a help of Protégé, which would be useful for students in the process of studying theoretical mechanics. - PublicationAPPROACHES AND SOLUTIONS FOR SIGN LANGUAGE RECOGNITION PROBLEM(2018)
; 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. - PublicationArtificial Neural Networks and Human Brain: Survey of Improvement Possibilities of Learning(2015)
; 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.Scopus© Citations 3 - PublicationAssessment of Name Based Algorithms for Land Administration Ontology Matching(2015-03-13)
; ; ;Aldis RausisJazeps BulsAbstract The purpose of this paper is to tackle semantic heterogeneity problem between land administration domain ontologies using name based ontology matching approach. The majority of ontology matching solutions use one or more string similarity measures to determine how similar two concepts are. Due to wide variety of available general purpose techniques it is not always clear which ones to use for a specific domain. The goal of this research is to evaluate several most applicable string similarity measures for use in land administration domain ontology matching. To support the research ontology matching tool prototype is developed, where the proposed algorithms are implemented. The practical results of ontology matching for State Land Service of Latvia are presented and analyzed. Matching of Land Administration Domain Model international standard, present Latvian Land Administration ontology is conducted.Scopus© Citations 5 - PublicationAutomatic Transformation of Relational Database Schema into OWL Ontologies(2015)Ontology alignment, or ontology matching, is a technique to map different concepts between ontologies. For this purpose at least two ontologies are required. In certain scenarios, such as data integration, heterogeneous database integration and data model compatibility evaluation, a need to transform a relational database schema to an ontology can arise. To conduct a successful transformation it is necessary to identify the differences between relational database schema and ontology information representation methods, and then to define transformation rules. The most straight forward but time consuming way to carry out transformation is to do it manually. Often this is not an option due to the size of data to be transformed. For this reason there is a need for an automated solution. The automatic transformation of OWL ontology from relational database schema is presented in this paper; the data representation differences between relational database schema and OWL ontologies are described; the transformation rules are defined and the transformation tool’s prototype is developed to perform the described transformation.
Scopus© Citations 2 - PublicationBuilding Recognition Using LiDAR and Energy Minimization Approach(2015)
;Kodors, Sergejs ;Aivars Ratkevics ;Aldis RausisJazeps BulsThe most important component of the economics of any country is the segment of a real estate. Light Detection and Ranging (LiDAR) is the modern remote sensing method how to scan the geospatial surface, it is a good platform for the monitoring of the real estate; but LiDAR data are 3D point cloud, which must be classified and transformed into vector data like shape files before using them in the geographical information systems (GIS) to solve urban planning and monitoring problems. The document describes the energy minimization approach how to detect and recognize buildings in LiDAR point cloud.Scopus© Citations 10 - Publication
- PublicationClustering Methodology for Time Series Mining(2009)
; Arkady BorisovA time series is a sequence of real data, representing the measurements of a real variable at time intervals. Time series analysis is a sufficiently well-known task; however, in recent years research has been carried out with the purpose to try to use clustering for the intentions of time series analysis. The main motivation for representing a time series in the form of clusters is to better represent the main characteristics of the data. The central goal of the present research paper was to investigate clustering methodology for time series data mining, to explore the facilities of time series similarity measures and to use them in the analysis of time series clustering results. More complicated similarity measures include Longest Common Subsequence method (LCSS). In this paper, two tasks have been completed. The first task was to define time series similarity measures. It has been established that LCSS method gives better results in the detection of time series similarity than the Euclidean distance. The second task was to explore the facilities of the classical k-means clustering algorithm in time series clustering. As a result of the experiment a conclusion has been drawn that the results of time series clustering with the help of k-means algorithm correspond to the results obtained with LCSS method, thus the clustering results of the specific time series are adequate.< - PublicationCOMPARISON OF ALGORITHMS FOR CONSTRUCTION DETECTION USING AIRBORNE LASER SCANNING AND NDSM CLASSIFICATION(2019)Kodors, SergejsTraditional approach to classify the point cloud of airborne laser scanning is based on the processing of a normalized digital surface model (nDSM), when ground facilities are detected and classified. The main feature to detect a ground facility is height difference between adjacent points. The simplest method to extract a ground facility is region-growing algorithm, which applies threshold to identify the connection between two points. Region growing algorithm is working with the constant value of height difference. Therefore, it is not applicable due to diverse conditions of earth surface, when height difference must be defined for each region separately. As result, researchers propose hierarchical, statistical and cluster methods to solve this problem. The study goal is to compare four algorithms to generate nDSM: region growing, progressive morphological filter, adaptive TIN surfaces and graph-cut. The experiment is divided into two stages: 1) to calculate the number of detected and lost buildings in nDSM; 2) to measure the classification accuracy of extracted shapes. The experiment results have showed that progressive morphological filter and graph-cut provides the minimal loss of buildings (only 1%). The most effective algorithm for ground facility detection is the graph-cut (total accuracy 0.95, Cohen’s Kappa 0.89, F1 score 0.93).
Scopus© Citations 2 - PublicationConstruction Methods of the Decision Trees for Genetic Programming(2008)Mūsdienās ģenētiskās programmēšanas iespējas tiek plaši izmantotas daudzos optimizācijas un klasifikācijas uzdevumos. Lai ģenētiskās programmēšanas metodes varētu tikt veiksmīgi pielietotas, ir nepieciešams konstruēt attiecīgus lēmumu kokus. Lēmumu koki un likumi uz to pamata ir intelektuālās datu analīzes sastāvdaļa un veiksmīgi tiek pielietoti klasifikācijas problēmu risināšanā. Pastāv vesela virkne dažādu paņēmienu, kas dod iespēju konstruēt lēmumu kokus ģenētiskās programmēšanas iespēju izmantošanai. Literatūras analīze liecina, ka optimālākā metode lēmumu koku konstruēšanā sastāv no diviem etapiem. Sākotnēji tiek veidots lēmumu koks, izmantojot C4.5 algoritmu, kas turpmāk tiek izvērsts ar ģenētiskās programmēšanas operatoru palīdzību. Šajā gadījumā ģenētiskā programmēšana tiek lietota kā globāla meklēšanas stratēģija precīza lēmumu koka atrašanā. Rakstā analizētas mūsdienu pieejas lēmumu koku konstruēšanā un izskatītas ģenētiskās programmēšanas iespējas, kas tiks izmantotas turpmākajā pētnieciskajā darbībā.