2 August 2023 in Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering
The purpose of research is to increase the efficiency of recognition and control of interaction between buyers and sellers of stores by developing a model of automated recognition and control of human interaction by video image. Methods. The research is aimed at solving the fundamental scientific problem of developing models and methods for monitoring and recognizing human interaction by video image. At the moment, the sphere of trade is rapidly developing, there are more and more online resources that take over a significant part of the flow of customers, and therefore, ordinary stores and shopping centers need to introduce new ways and methods of interacting with customers, and therefore provide a better service. Modern companies are trying to solve this problem in different ways: counting visitors, monitoring devices, various neural network solutions, and so on. However, none of the currently available offers on the market is able to automatically classify a person as a buyer or seller by video image, as well as to assess the degree of customer satisfaction with the service provided. To remedy this situation, methods and models have been developed that make it possible to develop software based on them, with the help of which it will be possible to determine the satisfaction of visitors and customers, recognize customers and sellers among people and determine the quality of employees' work. Results. Models and methods for classifying customers and sellers by uniform, methods for determining the level of interaction between sellers and customers based on algorithms for determining the satisfaction of visitors andcustomers by voice and face, and algorithms for determining the quality of employees' work have been developed. Conclusion. As a result, models have been developed that allow improving the quality of interaction between sellers and customers by video image.
31 May 2016 in Gornyi Zhurnal
EUEkaterinburg UralEnergoResurs
Ekaterinburg UralEnergoResurs
One of the modern methods of lining of mine workings is based on the use of friction rock stabilizers (FRS). Their application allows high degree of automation of the entire work process. As an anchor rod, a hollow cylinder with a longitudinal groove along its length is used. Due to the diff erence between its outer diameter and the diameter of the hole created by the frictional force, locking of the anchor from shifting is ensured. Functionality of the bolting is determined by its capacity to bear frictional load and by the type of the rod support assembly interacting with the baseplate. To increase the bearing capacity of the support unit, a new design solution is proposed. It is based on thecreation of a system consisting of the support ring welded to the rod and the support of the lock formed during the installation process. In the conventional design of the supporting units of foreign manufacture, the external load gives rise to shear stresses in the weld. In the new technical solution developed and patented by the Russian company UralEnergoResurs, normal stresses additionally appear in the supporting lock. The experimental study of bearing capacity of the traditional design support unit TFA and new FRS has been carried out. It is found that the magnitude of the bearing axial force increases by 22–27% due to the lock support. The new key sample unit requires changing technology of roof bolting to provide correct sequence of operations performed. The article identifi es options for advanced technological solutions to strengthen mine exposures based on the design of roof bolting with FRS.The authors acknowledge the participation of S. S. Neugomonov, Associate Professor, Candidate of Engineering Sciences, and P. V. Volkov, Senior Lecturer, Candidate of Engineering Sciences (Nosov Magnitogorsk State Technical University).
26 July 2024 in Herald of Dagestan State Technical University. Technical Sciences
Objective. Today, capture is a chain for the implementation of medical rehabilitation systems, systems for measuring human physical activity and other medical applications. Their solutions often use hardware systems - sensors, which have a set of limitations and reduce the efficiency of access systems, increasing their cost. The following goal is required: Increasing the availability of application systems being developed, achieving steps without increasing the number of restrictions.Method. To achieve the goals given in the article, the following approach is used, based on processing a video stream from a camera that records the spectrum of visible radiation. During the research, a set of experimental data was collected.Result. As a result, a method for classifying video images of a visible phenomenon was developed, which differs from the use of existing models to detect key points of an anthropomorphic body in an image.Conclusion. This method avoids the use of special equipment and sensors (for example, the Kinect infrared camera) to implement application systems, increasing the availability of such systems and recording their special limitations.
7 April 2026 in Journal of Volgograd State Medical University
One of the tasks in modern cataract surgery is the precise calculation of the intraocular lens power to achieve target refraction in the postoperative period. The purpose of the study. Conduct a comparative analysis of the clinical and functional outcomes of surgical treatment of uncomplicated cataract in patients from the control and main groups, determining the accuracy of IOL selection to achieve target refraction in the postoperative period with a deviation of no more than ±0.5 Dpt, as well as evaluating the criteria of efficacy, safety, predictability, and stability. Research methodology. A comparative analysis of the clinical and functional results of surgical treatment for uncomplicated cataracts was conducted on 1.038 patients (1.923 eyes) in the control group and 82 patients (146 eyes) in the main group, focusing on the accuracy of selecting intraocular lenses (IOLs) to achieve target refraction in the postoperative period with a possible deviation of no more than ±0.5 diopters. The results of the study. The use of an optimized technology for selecting the formula to calculate IOL power based on machine learning showed a significant advantage in the main group of patients. Six months after surgery, the uncorrected visual acuity in the main group was (0.80 ± 0.19) compared to (0.68 ± 0.23) in the control group (p 0.00001), and the best-corrected visual acuity was (0.83 ± 0.18) versus (0.74 ± 0.21) (p 0.00006). The achievement of target refraction in the postoperative period was significantly higher for patients whose calculations were made using the developed machine learning-based system, as confirmed by statistically significant lower values of subjective refraction and spherical equivalent refraction (p 0.05). The predictability of achieving target refraction within ±0.50 diopters using the machine learning system was 92.5 % compared to 76.1 % with the standard approach (p = 0.001), indicating a significant clinical advantage of the developed technology. Conclusion. The obtained clinical and functional results confirmed the applicability of the intelligent software system LensCalc as a decision-support tool for ophthalmologists. Achieving the target refraction in the postoperative period was significantly higher in patients whose calculations were performed using the developed machine learning-based system, as confirmed by statistically significant lower values of subjective refraction and spherical equivalent refraction (p 0.05).
2 August 2023 in Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering
The purpose of research is to increase the effectiveness of respiratory rehabilitation through the development of automated methods for determining the type of breathing based on machine learning. Methods. After the COVID-19 pandemic, respiratory rehabilitation became particularly important, as well as methods of home (remote) rehabilitation using the means provided by modern technologies, for which new methods and means began to be developed, including using wireless sensors or motion capture systems. Special attention during respiratory rehabilitation is paid to the type of human breathing, as well as automated methods for analyzing breathing. At the moment, the problem arises that most of the developed methods for analyzing breathing do not work with types of breathing: they either determine only one type, for example, diaphragmatic, or simply analyze the condition of the lungs. In this regard, there is a need to develop a method for analyzing and determining directly the types of human respiration. This article discusses three methods for solving the problem of determining the type of human breathing using a motion capture system and machine learning. The first method is based on static characteristics, for which the Random Forest model was used. The second method, which is based on time characteristics, used the Catch22 model. The third method, which determines the type of respiration using the characteristics of the sinusoid, used a composite model based on two models of Hist Gradient Boosting. Results. Three methods have been developed to determine the type of human breathing. Machine learning models were trained for each of the methods to find the best accuracy result. After conducting a comparative analysis of the developed approaches, the approach with the best accuracy is determined. Conclusion. A method for determining the type of human breathing based on machine learning has been developed, the accuracy of which is 0.81.