AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS最新文献

The paper is devoted to the development of an expert system for the diagnosis of pneumonia based on fuzzy logic implemented using the Mamdani algorithm. It discusses the main stages of system development, including the fuzzification of input data, definition of fuzzy rules based on medical expert knowledge, the aggregation of fuzzy inferences, and their defuzzification to obtain the final diagnostic result. The system’s web interface is implemented using the Django framework, which ensures the ease of interaction for users. The use of a medical expert system for diagnosing pneumonia can reduce the time required to establish a diagnosis and improve its quality of integrating the experience of medical experts and modern information technologies.

A tool is developed that recognizes strings, words, and Arabic characters from scanned images. The possibilities and prospects for using this tool in research activities are considered. The results of experiments on the operational performance of the instrument are presented with the example of digitized images of Old Tatar writing.

With educational systems shifting to distance learning and the trend towards remote work growing, an urgent need has arisen to develop reliable biometric identification and authentication technologies to verify employees working remotely. Such technologies can provide a high degree of protection and usability, making their development and optimization extremely important. The issue is that accuracy and efficiency of mouse gesture recognition systems need to be improved without any specialized devices used and in the shortest possible time. This requires efficient preprocessing of such gestures to simplify their trajectories while preserving their key features. The Douglas–Peucker algorithm is proposed to be used for preliminary processing of mouse gesture trajectory data. This algorithm allows significantly reducing the number of points in the trajectories, simplifying them while preserving the principal shape of the gestures. The data with simplified trajectories are then used to train neural networks. The experimental part of the work showed that, when applied, the Douglas–Peucker algorithm allows for a 60% reduction in the number of points on the trajectories, increasing the gesture recognition accuracy from 70 to 82%. Such data simplification contributes to speeding up the neural networks' training process and improving their operational efficiency. The study confirmed the efficiency of using the Douglas–Peucker algorithm for preliminary data processing in mouse gesture recognition problems. The results can be applied to develop more intuitive and adaptive user interfaces. In addition, directions for further research, including optimization of the algorithm’s parameters for different types of gestures and exploring the possibility of combining it with other machine learning methods, are proposed.

In recent years, advances in artificial intelligence and machine learning have been driven by advances in the development of large language models (LLMs) that are based on deep neural networks. At the same time, in spite of their substantial capabilities, LLMs have fundamental limitations, such as their spontaneous unreliability in facts and judgments; commission of simple errors that are dissonant with high competence in general; credulity, manifested by a willingness to accept a user’s false claims as true; and lack of knowledge concerning events occurring after training has been completed. Probably the key reason for these limitations is that bioinspired intelligence learning takes place through an assimilation of implicit knowledge in terms of an embodied form of intelligence to solve interactive real-world physical problems. Bioinspired studies of the nervous systems of organisms suggest that the cerebellum, which coordinates movement and maintains balance in human beings, is a prime candidate for uncovering methods of realizing embodied physical intelligence. Its simple, repetitive structure and ability to control complex movements offer hope for the possibility of creating an analog to adaptive neural networks. This paper explores the bioinspired architecture of the cerebellum as a form of analog computational networks that are capable of modeling complex, real-world physical systems. For a simple example, a realization of embodied AI in the form of a multicomponent model of an octopus tentacle is presented that demonstrates the potential for creating adaptive physical systems that learn from and interact with the environment.

Methods of assessing student answers using language models are currently being studied by various specialists. The results of automated assessment depend on the subject area and characteristics of the academic discipline. This paper analyzes students’ answers received during a Computer Graphics and Design course. It is proposed to determine the cosine similarity of document vectors obtained using language models and refine the estimates by checking keywords. The results obtained can be used for preliminary assessment of students’ answers and form the basis for further research.

The paper is devoted to the study of the cognitive function associated with the generation of elliptical sentences in the Russian language. The study is conducted by testing this cognitive ability using a computer system specially developed by the authors for this purpose. Testing of this cognitive ability is proposed and implemented for the first time. The system is an extension of Moodle and is openly hosted in the github repository. Elliptical constructions are limited to verbal and nominal ellipses, which are theoretically possible to be completely reconstructed based on the context of the sentence. The study is conducted with the participation of SPbPU students as respondents. The texts of planimetric tasks are chosen as the subject area. As a result of the analysis of testing data, the following results are obtained: the influence of the respondent’s knowledge of the subject area (planimetry) on the test results is established; a tendency towards self-study of respondents was discovered, which is manifested in a reduction in time and an increase in scores as they pass tests; it is shown that respondents are poorly motivated if they do not see feedback on the answer to the completed task. The paper discusses the problems of further development of the testing system and its use in adapting questionnaires (tasks) to assess the knowledge of SPbPU students in the field of automation of bug detection in programs, as well as for diagnosing the functional state of operator specialists and express diagnosis of dementia. It also seems promising to use the system to improve the processes of syntactic parsing of elliptic sentences and automate the restoration of ellipses in the subject area of planimetry.

This work commemorates the 25th anniversary of the establishment of the main search engines for our country, Yandex and Google, which happened one after another. This article attempts to describe some events from the history of the development of internet navigation tools from the point of view of a witness (and partly a participant).

The problem of predicting early dropout of students of Russian universities is urgent and requires the development of new innovative approaches to address it. To do so, it is possible to develop predictive systems based on the use of student data that are available in the information systems of universities. This paper investigates machine learning models for the prediction of early student dropout, trained on the basis of student characteristics and performance data. The main scientific novelty of this work lies in the use of explainable artificial intelligence (AI) methods to interpret and explain the performance of the trained machine learning models. Explainable AI methods allow us to understand which of the input features (student characteristics) have the greatest influence on the results of the machine learning models and can also help understand why models make certain decisions. The findings expand the understanding of the influence of various factors on early dropout of students.

This article presents an educational blockchain simulator that is intended to train students and beginning blockchain developers. This simulator was created to provide users with an intuitive and accessible tool for learning the basic concepts and mechanisms of blockchain functioning. The article discusses the main aspects of the design and architecture of the simulator and provides a demonstration of the application. In addition, the possibilities for further development of the simulator and its potential as a teaching tool for research in the field of blockchain technologies are discussed. The resulting simulator contributes to the field of education and science, helping increase the level of competence of specialists and the development of innovative solutions in blockchain.