Sergejs Kodors

• Dr.sc.ing.
• Senior Researcher at Rezekne Academy of Riga Technical University

Flowering intensity is an important parameter to predict and control fruit yield. However, its estimation is often based on subjective evaluations of fruit growers. This study explores the application of the YOLO framework for flowering intensity estimation. YOLO is a popular computer vision solution for object-detecting tasks. It was applied to de...

A fundamental step to foster a sustainable future is enhancing students’ awareness of responsible food consumption. The present research study assessed students’ awareness of food waste (FW) issues, attitudes towards school catering and lunch management, and the reasons for plate waste (PW) in Rezekne city schools, Latvia. A survey was conducted in...

Purpose The present research study aims to conduct a thematic literature review of the negative impacts of artificial intelligence (AI) on the tourism industry. Design/methodology/approach The research study is based on a comprehensive review of prior research by various authors on AI and its negative consequences in the tourism industry. Finding...

Food waste (FW) threatens food security, environmental sustainability, and economic efficiency, with about one-third of global food production lost or wasted. Schools play a crucial role in addressing FW, representing lost resources and missed educational opportunities. The present research assessed three interventions to reduce plate waste (PW) in...

In the context of precision horticulture, decision support tools play a significant role in providing fruit growers with insights into orchard conditions, facilitating informed decisions regarding orchard management practices. This study presents the development of an autonomous yield estimation system designed to provide decision support to small...

Food waste indicates ineffective and irresponsible consumption of resources, particularly during the food consumption stage. The aim of our research study is to optimize the catering management process at Latvian schools by reducing the amount of plate waste. The experts developed a set of recommendations aimed at improving the catering management...

The paper explores Large Language Model (LLM) training on custom datasets for classification microservice development. As training general purpose models for every possible situation is not feasible on smaller scale, because of limitations of computation power, usage of smaller model architectures, such as NanoGPT for training LLM model for specifi...

The monitoring of Colorado potato beetles in large fields is a complex and time-consuming process that requires accurate data collection, analysis, and interpretation. The use of artificial intelligence (AI) can greatly simplify this complex process by automatically monitoring fields and detecting beetles marking locations of their location. We tra...

It is a common task to select optimal technologies for a prototype implementation. If a prototype of a cyber-physical system is developed, it is required to select suitable components, devices and software development tools, which are compatible with each other. Traditionally, the market analysis is conducted reviewing components, searching for a t...

In order to avoid having to fight with aphids and plant virus diseases caused by them in gardens, it is very important to notice ant colonies. As a result we decided to train artificial intelligence to detect ant colonies, then this artificial intelligence can be integrated into an autonomous orchard monitoring system using unmanned aerial vehicles...

Agriculture 5.0 incorporates autonomous decision-making systems in order to make agriculture more productive. Our study is related to the development of the autonomous orchard monitoring system using unmaned aerial vehicles for automatic fruiting assessment and yield forecasting. Respectively, artificial intelligence must be developed to count frui...

The release of ChatGPT technology identified the large language models as a new disruptive technology, which changes the behaviours of society and its attitude towards the presence of artificial intelligence in everyday life. The tourism industry is one of the economic sectors, which will be impacted by the large language models through personalize...

The yield estimation using artificial intelligence is based on object detection algorithms. Firstly, the object detection algorithms identify the number of fruits on images, then tree fruit load is predicted using regression algorithms. YOLO is a popular convolution neural network architecture for object detection tasks. It is sufficiently well stu...

This article provides a systematic review of innovations in smart fruit-growing. The research aims to highlight the technological gap and define the optimal studies in the near future moving toward smart fruit-growing based on a systematic review of literature for the period 2021–2022. The research object is the technological gap until the smart fr...

Semantic ontology languages are a way for experts to write down their knowledge in a commonly accepted way, it allows information to be understood by humans and machines. However, ontology tools do not provide the ability to use this data in a database for geodata-based analysis easily. The project is focused on ontology web language (OWL) usage fo...

The aim of this work is to develop an algorithm to find the shortest path for drone flight planning with a limited time frame. Author used the local search shortest path algorithm to find the most efficient algorithm to use for further modification to apply to a drones flight calculation. The algorithm was modified to use the distance between point...

Purpose This study presents the concept of digital twin technology for the digitalization of tourism product competitiveness promotion recommendations. Design/methodology/approach A qualitative research method was applied, conducting pilot interviews with representatives of the tourism industry in order to evaluate the key performance indicators (...

Fruit yield estimation and forecasting are essential processes for data-based decision-making in agribusiness to optimise fruit-growing and marketing operations. The yield forecasting is based on the application of historical data, which was collected in the result of periodic yield estimation. Meanwhile, the object detection methods and regression...

Orchard management can benefit greatly from the use of modern technology to reach higher yields, decrease costs and achieve more sustainable farming. Implementation or such a smart farming approach into orchard management can be realised via application of unmanned aerial vehicles (UAV) for data collection and artificial intelligence (AI) for yield...

Risk analysis is an integral part of modern business management because successful business largely depends on the effective implementation of risk analysis. Agriculture is an important sector in the national economy, therefore Industry 4.0 increasingly provides digital solutions in orchard management, which facilitate and simplify decision-making...

The continuous evolution of technology and industrial revolutions provides new horizons for the application of smart solutions in every aspect of human lives. At the same time, it causes new social and engineering challenges, which require appropriate methodologies and solutions to overcome them. A smart orchard is an example of an eco-cyber-physic...

40% percent of crops are lost every year due to plant diseases. It is physically difficult for people to detect plant diseases in large-scale fields, especially at an early stage. The paper deals with the YoloV5 neural network training using different technologies. The neural network is trained to classify plant species and their diseases using pho...

The 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 met...

Modern 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...

Smart farming leverages modern information and communication technology to advance high yield, cost-effective and sustainable agriculture through collection of data on environmental parameters, smart processing of the data and other activities that support data-driven decision making. Such smart farming services can be achieved via application of u...

This research was conducted within the framework of a research project aimed at detecting patterns of plate waste and developing recommendations for improving catering in seven schools in Rezekne city (Latvia) by a combination of observation, physical weighing, semi-structured interview approaches and statistical analysis of variance (ANOVA). We id...

Food waste is a global problem, which becomes apparent at various stages of the food supply chain. The present research study focuses on the optimization of food consumption in schools and effective food management through data-driven decision making within the trends: zero food waste and digital transformation. The paper presents a plate waste for...

To equip Latvian gardeners with a digital tool for apple scab detection, our project team developed a prototype (TRL4) of a mobile application based on an artificial intelligence solution. The goal of the mobile application is to assist different user groups with appropriate functionality to overcome the apple scab problem. Currently, the mobile a...

A system simulation is a one of the approaches to understand business processes or to explain them to other people. It is an excellent decision making solution to provide data-driven conclusions based on system modelling and experiments. This paper proposes simulation results of a school canteen. The aim of the research was to investigate the relat...

In this work, authors compare training time of standard convolution neuron network model with model trained using transfer learning. Both models are based on Alexnet architecture. CNN model training from scratch included full model, but using transfer learning, some layers of model were frozen for learning acceleration considering transfer learning...

The aim of this work is to develop a neural network, which can recognize apples and pears. To achieve the goal, the authors applied AlexNet architecture and the open dataset “Fruits360”. The trained model showed a good result testing it on validation images - total accuracy 0.97 and latency 35ms/step. In the future research, authors consider traini...

The goal of smart and precise horticulture is to increase yield and product quality by simultaneous reduction of pesticide application, thereby promoting the improvement of food security. The scope of this research is apple scab detection in the early stage of development using mobile phones and artificial intelligence based on convolutional neural...

Clay has a great biomedical application potential, however there are just a few instrumental studies and the impact of lake clay on the skin has not yet been studied. The DermaLab skin analysis system (Cortex Technology) was used for hydration, elasticity, transepidermal water loss (TEWL) and pH measurements after lake clay facial applications. Res...

Apple and pear are among the most widely grown and economically important fruit species worldwide and in Latvia. In turn, scab diseases caused by ascomycetous fungi Venturiainaequalis and V. pyrina, are economically the most important diseases worldwide. Durable plant resistance has been widely regarded as the preferred disease limitation method du...

In this work, authors experimentally compare latencies of convolution neuron network architectures. Authors measured only recognition time. Four architectures were applied in the experiment: AlexNet, AlexNet Separated, MobileNetV1 and MobileNetV2. Models were trained using Fruits360 dataset. The Android mobile application was developed to measure l...

The aim of this work is to obtain information about impact of the depth of U-Net architecture model into segmentation accuracy. Experiment was completed using dataset of DSM images. Neural networks were trained to recognize building locations. Experiment considered to decrease the number of U-Net filter blokes to measure impact on result accuracy.

The aim of this work is to develop a neural network, which is able to recognize apples and pears. To achieve the goal, the authors of this work used the architecture of the neural network AlexNet and the open dataset “Fruits360”. A trained model showed a good result testing it on validation images: total accuracy 0.97 and latency 35ms/step. In the...

Apples and pears are one of the most widely grown and economically important fruits in the world and in Latvia. Mobile expert system is software running on smartphones that use artificial intelligence to solve problems in a specialized field that usually requires human competence. This article analyses the necessity of mobile expert system that wil...

Authors completed literature analysis to actualize information about secure password in 2020 year. The paper provides description of password cracking methods to identify secure password features

Real estate monitoring is very important aspect of country economics, but old manual methods of land survey are time and resources consuming processes as geodata actualization tasks. Actual, precise, multidimensional and detailed information is the main instrument of geospatial intelligence to understand current economic situation and to make effec...

The most common method to determine the presence of clay in lakebed is coring method. This method requires survey of the whole lake area using stratified sampling method which is time and physical labour consuming process. To lessen the amount of coring samples and narrow the area of clay survey thus making the whole process faster and more effecti...

Traditional 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...

The survey of lake sediments is complex, time consuming and costly process with risks to human health. Additionally, manually obtained sediment samples provide incomplete data about a survey region. In turn, remote sensing methods are cost-effective and can provide continuous data about a survey region. Therefore, authors decided to perform a pilot...

The paper provides PostgreSQL configuration checklist to make databases safer. The main part describes with examples about vulnerabilities and how to solve them.

The inheritance seems to be the natural and the default solution of structuring the logic of software nowadays. But is it always the best option? Considering the increasing need for programming and the speed at which the projects are made, it’s inevitable that the requirements of a project will be changing many times and a lot of fundamental buildi...

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.

A parameter “point density” is often used to evaluate the quality of aerial laser scanning data. It is a parameter simple for understanding and human imagination. However, the true quality of LiDAR point cloud is based on point distribution. There are researches, which mention importance of point distribution and users’ false perception, that highe...

The proposed research is related with building detection in airborne laser scanning data. The result of geospatial surface segmentation provides a vector layer of unclassified shapes. Geometric features of shapes can be applied to classify urban objects and to detect buildings among them. The goal of this research is to select the appropriate geome...

Aerial laser scanning is a modern and accurate remote sensing technology how to scan the earth's surface and to get its digital surface model. The digital surface model is applied for different economical tasks. The result of aerial laser scanning is 3D point cloud, which must be preprocessed before usage. There are three groups of preprocessing ta...

The 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...

The main goal of this paper is to collect information about pathfinding algorithms A*, BFS, Dijkstra's algorithm, HPA* and LPA*, and compare them on different criteria, including execution time and memory requirements. Work has two parts, the first being theoretical and the second practical. The theoretical part details the comparison of pathfindin...

The geospatial information is significant for many socio-technical activities like urban planning, the prediction of natural hazards, the monitoring of land use, weather forecasting, cadastral surveys etc. It is possible to acquire geospatial information from a distance using remote sensing technologies, but remotely sensed images don’t have semant...

This manuscript describes urban objects segmentation using edge detection methods. The goal of this research was to compare an efficiency of edge detection methods for orthophoto and LiDAR data segmentation. The following edge detection methods were used: Sobel, Prewitt and Laplacian, with and without Gaussian kernel. The results have shown, that L...

The article discusses how to generate RGB images with noise using Kohonen’s self-organizing map (SOM). The article also describes the adaptation process and structure of SOM, which can be used to generate RGB images with noise. The authors of the article evaluate the influence of SOM parameters (a learning coefficient, adaptation time, effective wi...