Abstract: Indoor positioning on a Wi-Fi network belongs to a class of tasks in which the dependence of output characteristics on input variables is influenced by many parameters and external factors. When solving such problems, it is necessary to take into account that in determining the location, it is of significant interest not only to determine the static coordinates of an object, but also to predict the vector of its movements. In the case where the location of an object is determined only by the level of signal power received from several access points on a Wi-Fi network, the use of signal attenuation models that take into account the conditions of propagation of radio waves indoors is difficult due to the need for reliable information about the material of ceilings, floors and ceilings, the presence of fixed and mobile shading objects, etc. Since the electromagnetic environment inside the room varies depending on many factors, the above-mentioned models have to be adjusted to these changes. Since finding patterns in a large amount of data requires non-standard algorithms, artificial neural networks can be used to solve the positioning problem. It is important to choose a neural network architecture that can take into account changes in the signal strength received by a mobile device from Wi-Fi access points. Before training a neural network, statistical data is preprocessed. For example, abnormal cases are excluded from the machine learning dataset when the device detects a signal from less than three access points at one measuring point. As a result of the analysis of statistical data, it was found that the same distance between the measuring points leads to the fact that the neural network incorrectly determines the location of the object. The paper shows that in order to increase the accuracy of positioning the location in conditions of complex radio placement, when compiling radio maps, it is necessary to determine the optimal varying distances between measuring points. The conducted experimental studies, taking into account the proposed approach to optimizing the distances between measuring points, prove that the accuracy of location determination in the vast majority of measuring points reaches 100%.

Keywords: machine learning, hidden layer, signal strength, neural network, RSSI, measuring point, positioning, Wi-Fi, training sample, training set

Abstract: The subject of the research in this article is the generalization of texts in Russian using artificial intelligence models. In particular, the authors compare the popular models GigaChat, YaGPT2, ChatGPT-3.5, ChatGPT-4, Bard, Bing AI and YouChat and conduct a comparative study of their work on Russian texts. The article uses datasets for the Russian language, such as Gazeta, XL-Sum and WikiLingua, as source materials for subsequent generalization, as well as additional datasets in English, CNN Dailymail and XSum, were taken to compare the effectiveness of generalization. The article uses the following indicators: ROUGE, BLEU score, BERTScore, METEOR and BLEURT to assess the quality of text synthesis. In this article, a comparative analysis of data obtained during automatic generalization using artificial intelligence models is used as a research method. The scientific novelty of the research is to conduct a comparative analysis of the quality of automatic generalization of texts in Russian and English using various neural network models of natural language processing. The authors of the study drew attention to the new models GigaChat, YaGPT2, ChatGPT-3.5, ChatGPT-4, Bard, Bing AI and YouChat, considering and analyzing their effectiveness in the task of text generalization. The results of the generalization in Russian show that YouChat demonstrates the highest results in terms of the set of ratings, emphasizing the effectiveness of the model in processing and generating text with a more accurate reproduction of key elements of content. Unlike YouChat, the Bard model showed the worst results, representing the model with the least ability to generate coherent and relevant text. The data obtained during the comparison will contribute to a deeper understanding of the models under consideration, helping to make a choice when using artificial intelligence for text summarization tasks as a basis for future developments.

Keywords: text compression, YouChat, Bing AI, Bard, ChatGPT-4, ChatGPT-3, YaGPT2, GigaChat, text summarization, natural language processing