Decision support in complex organizational systems using neural network technologies

In complex organizational systems in which there is asymmetry of information, an important element of effective work is equal access to objective statistics. Because of the benefits to one of the parties in such systems, key elements of effective management and making the right decisions, it is necessary to develop independent approaches. The developed approach makes it possible to assess risks in various situations and with various interactions within the system, and also allows you to recreate the missing information for decision-making from open statistical databases. The key element of the developed approach is the use of self-organizing Kohonen neural networks, which make it possible to classify objects based on the reconstructed information. The importance of the correct grouping of system objects makes it possible to recommend a management decision with greater accuracy. The developed approach allows you to reduce uncertainty (risk), and, as a result, reduce losses and maximize profits.

Vegetables, Potatoes and Their Products as Sources of Energy and Nutrients to the Average Diet in Poland

The aim of our study was to analyse vegetables, potatoes and their products as sources of energy and nutrients in the average diet in Poland. Representative data of the 2016 Household Budget Survey from 36,886 households were used. This is the largest study sample in Poland, so we generalized the conclusions to the whole population using the statement ‘average diet’. We analysed three main product groups: vegetables, vegetable products, and potatoes and potatoes products, dividing them into 14 subgroups (e.g., tomatoes, cabbage, carrots, other vegetables, and mushrooms). The percentages of energy, protein, carbohydrates, total fat, nine vitamins (thiamine, riboflavin, niacin, vitamin B6, folate, vitamin C, vitamin A, vitamin D, and vitamin E), seven minerals (calcium, phosphorus, sodium, potassium, iron, magnesium and zinc), and fibre from the analysed food subgroups are presented. Additionally, the influence of household characteristics on the supply of energy and nutrients from each subgroup of vegetables, potatoes, and their products was evaluated using cluster analysis. In the analysis, R programme and Kohonen neural networks were applied. Our study showed that vegetables, potatoes, and their products provide 7.3% of daily dietary energy supply. Vegetables contribute more than 20% of the supply of six nutrients: vitamin C (51.8%), potassium (32.5%), folate (31.0%), vitamin A (30.6%), vitamin B6 (27.8%), and magnesium (20.2%), as well as fibre (31.8%). Cluster analysis distinguished three clusters that differed in nutritional supply from vegetables, potatoes, and their products. Educational level, income measured by quintile groups, village size, socio-economic characteristics, urbanization degree, and land use were the most important factors determining differences between clusters.

A MULTILEVEL RESOURCE-SAVING BLAST FURNACE PROCESS CONTROL

A multilevel resource-saving blast furnace process control is considered. The resource-saving control is provided for operating, adaptation, technical and economic control in the automated systems of blast-furnace processes. It is proposed to form optimal operation modes of blast furnace heating, metal charge structures, natural gas and oxygen consumption. Decisions are made using Kohonen neural networks taking into account current and planned parameters of coke quality, iron ore, raw materials and blast. At the level of operating control, the work suggests a model predictive control to improve the resource conservation indicators. The method is based on decomposition of the general problem of the process dynamics identification on particular problems: dynamic synchronization and identification of process transfer functions. At the level of adaptive control, optimal operating modes of blast furnaces are expedient to be developed with respect to blast furnace heating, structure of metal charge, natural gas and oxygen rate considering the current and planned parameters of coke, blasting. The blast furnace operating modes are suggested to be determined based on Kohonen neural networks. In evaluating the efficiency of introducing the model predictive control, the existing actual statistics of scatter of BF mode parameters should be based upon. The fact is that the introduction of model predictive control assumes no radical change of the BF melt technology. Like in all the control systems, the BF process is considered as the set control object with all its characteristics. Changing process settings, raw material content does not introduce any cardinal variation in the scatter of process characteristics. However, in this case a transient process occurs which is necessary for the control system to identify the changing conditions. The transient process is inherent to all the control systems and the blast furnace process is not an exclusion. As a result of transient process, the control system is set to the optimal mode.

Towards More Sustainable Diets—Attitudes, Opportunities and Barriers to Fostering Pulse Consumption in Polish Cities

Despite the evidence-based health benefits of pulses and their significant role in sustainable diets, consumption remains at a very low level in highly developed countries. In an attempt to fill in the knowledge gaps on factors influencing this phenomenon, a study aimed at identifying attitudes, incentives and barriers to pulse consumption was carried out in a sample of 1027 Polish urban employees aged 25–40 years. The sample (quota type) was representative in terms of age and gender. Exploratory classifications using Kohonen neural networks were performed to define profiles of participants for each analysed issue. Pearson’s chi-square analysis was used to check whether the profiles depended on socio-demographic characteristics of the respondents. The results suggest that very low pulse consumption is a result of lack of habits, discomfort after eating and long preparation time. Pulses were recognized as a good source of protein (72% of the sample), especially among women (81%). Only 43% of the sample saw pulses as a substitute for meat. The majority of consumers pictured pulses as a tasty and healthy food, although they were not sure if this is true for small children. Women recognised pulses as a more environmentally friendly food but this knowledge would not impact their intake. Profiles of respondents with positive attitudes towards increased pulse consumption were identified, constituting 39% of the sample. These consumers could eat more if they were encouraged to do so. This shows that programmes aimed at fostering greater pulse consumption are crucial to activate a change towards more sustainable diets. At the same time, simple and clear guidelines should be developed to overcome the unjustified stereotypes about pulses. These would support consumers to make healthier and more sustainable choices and help professionals carry out effective promotion and education activities.

Small-scale clustering of the Russian part of Arctic by periodicity type of the topographic patterns

<p>Homogeneous topography pattern - can be an indicator of similar Earth's surfaces genesis and age. It is difficult to automatically formally describe these features and map the terrain. To describe the Earth's surface periodicity, we developing spectral terrain characteristics (STC). Their calculation consists of the following: a sliding window of different sizes decomposes the DEM into a Fourier row from which it is extracted:  1) amplitude of the main harmonic wave; 2) its length; 3) dispersion of heights given by 5% of the most important waves in relation to the general dispersion of heights; 4) general direction of oscillations of the height field; 5) unidirectionality / expression of this direction, etc. Areas with similar values of these parameters have visually homogeneous topographic pattern. We have calculated the above mentioned and some more complicated parameters for the whole territory of the Russian Arctic on a shallow scale: according to GMTED 2010 30" (1000 m per cell) on moving windows with sizes from 40 to 100 km and with the step of 10 km. Fifty-six raster models of SRC were obtained - 8 parameters at 7 scales each. Using them, a map of topographic dissection types in the Russian part of the Arctic was created with the help of self-organizing Kohonen neural networks and subsequent hierarchical clustering of individual neurons. 10 clusters have been identified related to geostructural, geological and geomorphological differences. </p><p>This study was funded by the Russian Science Foundation, project no. 19-77-10036.</p>

Applying topic model combined with Kohonen networks to discover and visualize communities on social networks

Users are members of communities on social networks. Users’ interested topics keep changing, resulting in the change of their communities’ interested topics as well. Level, period of time, and interested topics represent features of a community which (i) change upon preferences of each user on social networks for making friends or being interested in topics (based on message content); (ii) are formed or change from online groups of friends or the suggestions to make friends. Hence, the link of users in communities can be viewed as a network of users by their features in social network communities. In this paper, the author studies and proposes a new model for discovering communities using Temporal-Author-Recipient-Topic (TART) model combined with Kohonen neural networks to discover communities of users with the same interested topics over different periods of time. The research goal is achieved through testing models on two Vietnamese datasets (collected from social networks at universities and online newspapers).