درخت حوزه‌های تخصصی

The paper considers the possibilities of optimizing the search for agricultural information based on Shannon information entropy criterion. A comparison of the degree of uncertainty of information search through the Internet – search systems with similar indicators of Ukrainian agricultural websites. According to the number of hit count in Ukraine in July 2020 to the search engine, which consists of 10 sources, and to agricultural websites (43 sources) by estimating entropy, a conclusion was made about the significant degree of dispersion of agricultural information sources. It should be emphasized that the artificial division into 4 categories (AgroMedia, Agrotrade web resources, Information and advisory resources, Specialized web resources) did not improve the situation according to the degree of uncertainty compared to the search engine system. As for the entropy index, for almost all 4 categories of entropy indices (heterogeneity or diversity) is close to the case of uniform distribution, i.e., the same hit count of all possible resources (their number for all categories is approximately the same 10-11). As a result of the analysis of the potential client base of electronic consulting, it can be quantified as 4,700,000 of agricultural households and about 50,000 small and medium-sized farms. The transition to the land market is likely to lead to a substantial increase in the number of the latter. It was demonstrated that the current educational level of household owners indicates both the need to increase this indicator and the presence of a close relationship with the existing system of professional advisory in Ukraine, which operates in recent years through self-sufficiency and uncertain financial support from central and regional authorities. The existing official database of advisors should be restructured in line with the call of the times to reduce the degree of uncertainty in finding a specialist of the desired profile.

The article proposes a methodical approach to assessing the competitiveness of enterprises in the logistics infrastructure of the Black Sea region in the context of the strategy of the development of the Black Sea. The article is presented is the author's interpretation of the steel development of the territory and injected into the logistic infrastructure. It was proposed of the methodical approach to assessing the competitiveness of enterprises-moving enterprises in the development of the territory, as one of the stages of the methodology for assessing the development of the territory in the region. It have been identified Indicators for assessing sustainable development in assessing the competitiveness of key enterprises in the region and in terms of using the TOPSIS model. The application of the TOPSIS model allows to assess the value of the aggregate indicator of sustainable development of a region or territory, taking into account the impact of the level of competitiveness of its key enterprises. In the context of this approach, it is studied and evaluated the level of competitiveness of powerful enterprises of the Black Sea region, which form the logistics infrastructure of the region. It was  determined their influence on the strategy of sustainable development of the territory. This approach allowed to expand the methodology for assessing the assessment of sustainable development of the territory through the methodology of assessing the competitiveness of enterprises-engines of development of the territory, as one of the stages of the overall methodology.

Falls are a serious concern among the elderly due to being a major cause of harm to their physical and mental health. Despite their potential for harm, they can be prevented with proper care and monitoring. As such, the motivation for this research is to implement an algorithmic solution to the problem of falls that leverages the benefits of Machine Learning to detect falls in the elderly. There are various studies on fall detection that works on one dataset: wearable, environmental, or vision. Such an approach is biased against low fall detection and has a high false alarm rate. According to the literature, using two datasets can result in high accuracy and lower false alarms. The purpose of this study is to contribute to the field of Machine Learning and Fall Detection by investigating the optimal ways to apply common machine and deep learning algorithms trained on multimodal fall data. In addition, it has proposed a multimodal approach by training two separate classifiers using both Machine and Deep Learning and combining them into an overall system using sensor fusion in the form of a majority voting approach. Each trained model outputs an array comprising three percentage numbers, the average of the numbers in the same class from both arrays is then computed, and the highest percentage is the classification result. The working system achieved results were 97% accurate, with the highest being achieved by the Convolutional Neural Network algorithm. These results were higher than other state-of-the-art research conducted in the field.