The main problem of higher education modernization is the balance between inputs and relevant outputs, specifically, the right balance of enrolled and graduated students. The strategic policy of higher education institutions may cause the number growth but not necessarily the education quality increase of the graduated students. Therefore, the purpose of this paper is, to analyse the causes of the first year students’ dropout rates in higher education institutions using the real data of engineering study program in Latvia University of Agriculture. The following factors were evaluated using the Proportional hazard model of Survival analysis, i.e., students’ gender; secondary school grades the priority of the program to study (first, second, or third) and the finance source (government-financed or self-finance). The results of this study show that the main reasons for dropping out are students’ low secondary school knowledge and low motivation to study engineering

Mobile devices are becoming increasingly popular; basically mobile devices are reaching all levels of society. Thanks to the popularity of mobile devices, mobile learning has become great tool for delivering educational resources. The continuously increasing demand for mobile technology based learning materials, renders adoption of educational resources for these requirements. Technology by itself does not contribute much to education that is why the aim of this research is to present and evaluate methodology for visualisation and production of electronic materials in mobile environments. Methodology focuses on instructional design and mobile content design and the navigation control. Findings showed that given methodology and recommendations is effective for improving m-learning design across mobile devices

Soil tillage and crop rotation are considered important tools in wheat leaf disease control; however, the results of investigations are inconsistent. The aim of the present study was to determine the effect of the soil tillage system and cropping sequence on the development of winter wheat leaf diseases in 2012–2017. The disease development was assessed in a two-factor experiment: (a) soil tillage system; and (b) crop rotation. Foliar fungicides were used uniformly in all variants. The results showed that tan spot (caused by Pyrenophora tritici-repentis) dominated in 2012, 2013, and 2016, but the level of Septoria tritici blotch (Zymoseptoria tritici) was essentially lower and exceeded the severity of tan spot only in 2015. The agronomic practice used significantly influenced only the development of tan spot. Reduced soil tillage and continuous wheat sowing substantially increased tan spot severity, especially when both practices were used simultaneously. Short crop rotation (only wheat and oilseed rape) provided sufficient control of tan spot in ploughed fields, whereas in non-ploughed fields, the level of this disease did not decrease. The results could be explained by differences in the pathogens’ life cycle: P. tritici-repentis ascospores in wheat debris is the main source of infection; in contrast, Z. tritici spreads by conidia from living plants.

To achieve a sophisticated and self-sufficient production environment that aims to optimize a particular production sequence or direction, a combination of multiple interconnected IoT devices, software, and decision-making expertise is required. This is nowadays referred to as “smart” systems and can be related to almost any field. In the case of the poultry industry, “smart” stands for automatic data gathering, in-depth processing, and decision-making support. The implementation of a smart poultry concept introduces several challenges that are production related (e.g., productivity forecasting); therefore, this study focuses on hen egg production forecasting with limited data sets. Different methods and approaches used in the poultry sector for egg production forecasting were investigated. A cross-comparison was made between different models in order to determine their applicability. The models considered include a non-linear Modified Compartmental and several machine learning (ML) models, such as, Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), XGBoost, and Random Forest (RF). Selected models used only two data sets—one for training and one for testing. Furthermore, the testing data set was significantly different than the training data, therefore setting the forecasting task to be even more challenging. The ML models had significantly more inputs that allowed them to adapt more flexibly to a changing environment in comparison with the nonlinear model that expected only one input, e.g., the week of egg production. The tests showed that the machine learning models proved to be overall more accurate than the selected nonlinear model.

Winter wheat (Triticum aestivum) is a crop of which production is associated with rather large investments for nitrogen fertilization and disease control. The aim of this study was to estimate the effect of five variants of fungicide application and four levels of N (nitrogen) top-dressing rate on the yield and grain quality of winter wheat. Field trials were carried out in Latvia (56° 31′ N; 23° 42′ E) for four seasons. Grain yield and quality depended significantly on the conditions of the trial year, as three of them were characterized by drought in varying degrees. Although the average four-year grain yield increased significantly in all fungicide application variants, the effect of this factor was different in individual years. The application of fungicides increased the yield significantly in one year, decreased significantly in another year, while it had no significant effect on the yield in remaining two seasons. The enhancement of N top-dressing rate increased the grain yield significantly every year. The interaction between both examined factors was significant; however, the use of higher N rates not always means that also spraying with fungicides has to be more intensive. A clear effect of fungicide application was observed on 1000 grain weight and volume weight, while the effect of N top-dressing rate was observed on the crude protein, wet gluten and starch content, and Zeleny index.