Now showing 1 - 10 of 25
  • Publication
    Real Estate Monitoring System Based on Remote Sensing and Image Recognition Technologies
    (2017)
    Kodors, Sergejs
    ;
    Aldis Rausis
    ;
    Aivars Ratkevics
    ;
    Janis Zvirgzds
    ;
    ;
    Ivonna Ansone
    Geoinformation are changing fast, therefore a change detection of real estate must be processed in short time. The increasing resolution of sensed geospatial data creates critically important to develop high performance computing solutions to process geospatial information. The topic of scientific work is the real estate monitoring system based on image recognition and remote sensing technologies. System's practical application is automatic building recognition from LiDAR data using saliency based method, vector map generation and change detection in actual cadastral maps. The scientific work describes high performance computing solution and gives its performance comparison with traditional method.
    Scopus© Citations 11
  • Publication
    INFORMATIONAL WARFARE – INFLUENCE ON INFORMATIONAL STRUCTURES
    The concept of information warfare encompasses the use of information and communication technologies to gain an advantage over a potential opponent. The information warfare is the manipulation with the information that trusts the goal, so that the goal should make decisions about its interests in the interests of opponents. Information structures are treated as systems that process different types of information, provide storage and access to users. Such structures may enclose neural networks, self-learning systems etc. They need to be ready to learn, respond to threats and ensure their safety, which is topical in today's information warfare. This paper will address aspects related to the security of information systems from a system theory point of view. The knowledge base of information structures can be elements of artificial intelligence, which security must be protected against various threats. The authors considers artificial neural networks to be one of the potential threats in the context of information warfare.
    Scopus© Citations 1
  • Publication
    E-LEARNING: DEVELOPING TOMORROW'S EDUCATION
    E-learning refers to the term to deliver education or training using digital resources. Computer-based learning, which is considered the keystone of today's E-learning concept, was born in the 80s. Earlier E-learning provides education using only text as with the development in technology it allows adding various forms, i.e., Graphical Text, Images, Video Conferencing etc. In today's time, the concept of is E-learning growing at a rapid pace. Improved bandwidth and growing technology helped in pushing the expansion of E-learning. Along with the university, large corporate companies are also resorting to E-learning. E-learning provides many advantages as compare to Instructor-led training (ILT). E-learning saves the times of travel as physical presence is not required. Education can be provided from anywhere at any time. E-learning is cost-effective also as the course, once developed, can be modified easily. There can some concern which can be faced by the trainer and leaners in future. Adopting E-learning will be a step towards saving the environment. It will be environmentally friendly as tablets will replace books; paper notes will be replaced with digital messages. Digital tools will help to reduce the burden of a student. Artificial Intelligence is a prevalent concept in computer science. A branch of AI, known as a Neural Network, is based on the human brain. The research's main aim is to review existing methods and analyse further possibilities of E-learning systems with neural networks.
  • Publication
    AUTOMATION OF FEEDBACK ANALYSIS IN ASYNCHRONOUS E-LEARNING
    (2023)
    Rohit
    ;
    ; ;
    Atis Kapenieks
    With the recent hit of the Pandemic study process is shifted to E-learning. Measuring the actual progress of a student in Asynchronous e-learning because of machine-human interaction and feedback is also considered a primary issue in this area. With the rapid development of artificial intelligence, computers can capture surroundings. Image processing is a rising technique in Artificial Intelligence (AI).  Recognition of an individual's emotion helps identify the person's inner state. It is easy to measure a student's feedback about the session by doing it. The main functionality of this project is to capture the student's enough frames during the study session and provide the analysis of the average emotions to the administration panel. This prototype was used on 10 minutes of lecture to capture the emotion. The primary goal of this proposed system is to capture the learner's emotion at a specific interval during the e-learning session and provide the feedback of it to the instructor.
  • Publication
    METHOD FOR COLOR LASER MARKING PROCESS OPTIMIZATION WITH THE USE OF GENETIC ALGORITHMS
    Optimization of color laser marking process mostly depends on effective identification of optimal values of laser marking parameters. This is a difficult combinatorial optimization problem, which is still essential for companies that use laser marking systems. The study proposes a new approach to the process optimization through the use of genetic algorithms, carrying out preliminary experimental investigation, analyzing the laser marking results, and presenting possible improvements to the current implementation of genetic algorithms.
    Scopus© Citations 9
  • Publication
    Machine Learning Technology Overview In Terms Of Digital Marketing And Personalization
    (2021) ;
    Nikolajeva, Anna
    The research is dedicated to artificial intelligence technology usage in digital marketing personalization. The doctoral theses will aim to create a machine learning algorithm that will increase sales by personalized marketing in electronic commerce website. Machine learning algorithms can be used to find the unobservable probability density function in density estimation problems. Learning algorithms learn on their own based on previous experience and generate their sequences of learning experiences, to acquire new skills through self-guided exploration and social interaction with humans. An entirely personalized advertising experience can be a reality in the nearby future using learning algorithms with training data and new behaviour patterns appearance using unsupervised learning algorithms. Artificial intelligence technology will create website specific adverts in all sales funnels individually.
  • Publication
    IPTV Statistic Data Collection, Processing and Preparation for use in a Modeling System
    (2015)
    Vjaceslavs Dubovskis
    ;
    ;
    Nikolajs Visockis
    Abstract Today most people get information from a TV. Trust level for television is very high and this kind of media can strongly influence public opinion. To research content watched on TV or public opinion, questioning and other methods are used today and respondents know about the research process. This knowledge forces people to give untruthful answers, because sometimes they don’t want to share their thoughts. This kind of research result is not satisfactory and conclusions can create misconceptions. Fast development of IPTV gives new opportunities for research using collected statistics. To make research legal, all statistical data must be anonymous. If a TV watcher doesn’t think that he has to make a choice, he will watch TV content he is interested in. At the moment there is no one united standard for collecting and processing IPTV statistical data. Each vendor handles data differently. Some solutions do not allow collecting data about watched TV channels and programs. In this paper the author will present a possible, universal method for data collection in a variety of IPTV networks, and different types of streaming and Middleware.
    Scopus© Citations 1
  • Publication
    Object-Oriented Modelling and Simulation of Large-Scale Systems
    (2017) ;
    Merkuryev, Yuri
    Abstract The paper discusses a methodology of object-oriented modelling and simulation. This methodology was developed for large-scale systems modelling and simulation. From modelling point of view, presented methodology can be classified as Object-Oriented methodology, and from simulation point of view as discrete event system (DEYS) methodology.
  • Publication
    Mathematical Model of the Distribution of Laser Pulse Energy
    (2016)
    Pavels Narica
    ;
    ; ;
    Pavels Cacivkins
    ;
    Method allows for modelling of the complex process of laser pulse energy distribution over flat work surface. The process of calculating the correct result does not use common lasing formulas but instead employs the mathematical model of matrix multiplication of three input matrices representing a pulse model, a line model, and a plane model. The pulse model represents the distribution of planar energy densities within the laser pulse. The line model represents the distribution of pulses within the line. The plane model represents the distribution of lines within the plane. Because mathematical model is implemented within a spreadsheet processor, its size can be adjusted as needed and it can be instantiated multiple times for simultaneous modelling of different input parameters.
  • Publication
    Assessment of Name Based Algorithms for Land Administration Ontology Matching
    (2015) ; ;
    Aldis Rausis
    ;
    Jazeps Buls
    Abstract 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