Andriy Yerokhin

Kharkiv National University of Radio Electronics · Faculty of Computer Sciences (CS)

Specific features of application of hybrid simulation and control models in information systems and system support for decision-making in solving practical problems under conditions of uncertainty, vagueness, inaccuracy, stochasticity of processes of subject areas are considered. To obtain reliable data, it is necessary to use poorly formalized ope...

One of the crucial problems of natural language processing for languages such as Ukrainian is lack of datasets both unlabeled (for pretraining of word embeddings or large deep learning models) and labeled (for benchmarking existing approaches).In this paper we describe a framework for simple classification dataset creation with minimal labeling eff...

Methods of data mining and intelligent analysis of processes are investigated for the develop¬ment of a mobile intelligent application “Emergency Medical Aid”, which effectively solves the problems of information support for medical purposes in a particular emergency situation for the user. With the help of Data Mining methods, a knowledge base for...

The article is devoted to gesture recognition methods analysis based on the readings of three-axis accelerometers of mobile devices. The basic methods of machine learning applied to the problem of classification of gestures. Conducted initial data processing, feature selection and comparison of algorithms providing recognition quality results.

This paper describes the intelligent information system of heterogeneous medical data analysis for Ear Nose Throat (ENT) domain. Machine learning (ML) methods for medical data processing are analyzed. The scenario of machine learning algorithms for data processing in intelligent information system was developed. Supervised learning algorithms for c...

Active anterior rhinomanometry is important method for diagnosis of rhinological disorders. This paper presents the new approach for feature extraction based on chaos theory for tasks of rhinology. It has been demonstrated that rhinomanometric signals have a fractal properties. The usage of phase space diagram for feature extraction for rhinomanome...

The paper presents a new approach for processing of rhinomanometric signals based on F-transform approximation of phase diagrams. Methods of nonlinear dynamics for processing of time series allow us to obtain a significant features of rhinomanometric signals. Research indicated that the results of classification with F-transform approximation is mo...

A LARS-based method is proposed for constructing a fuzzy regression model. Peculiarities of the use of fuzzy regression analysis for medical diagnosis are considered. The method allows one to reduce the number of parameters of the model that exert influence on the predictable degree of nasal obstruction and to avoid the risk of “overtraining” of th...

Aerodynamic characteristics of nasal airflow are important for obstruction problems detection. In clinical practice, we analyze behavior of hydrodynamic resistance coefficient. This paper proposes a component of real-time automated system for rhinomanometric measurements. The component is a real-time alert to help users define a correct measurement...

Numerous studies are devoted to the behavior of pressure in the maxillary sinus, although most of the researchers focus on the patency of the maxillary junction in identifying the indications for surgery or in measuring the dynamics of treatment. In all cases, characteristics of the pressure in the maxillary sinus were recorded with standard rhinom...

The Active Anterior Rhinomanometry method for an objective assessment of nasal breath is carried out. The preprocessing's methods for rhinomanometric data were analyzed. It was proposed to use the method of fuzzy approximation based on F-transform for preprocessing of rhinomanometric signals.

Currently, there are many objective diagnostic methods for nasal breathing difficulties. The main conventional method in otolaryngological practice is active rhinomanometry. The value of nasal resistance is considered as a diagnostic parameter of active anterior rhinomanometry. However, the results of the rhinomanometric measurements depend on race...