DIAGNOSIS OF EARLY STAGES OF ATTENTION DISORDERS BASED ON HYBRID FUZZY DECISION RULES
A.V. Polyakov, S.N. Rodionova, N.L. Korzhuk, L.V. Starodubtseva
The work is devoted to improving the quality of differential diagnosis of early stages of cognitive impairment in terms of fuzzy description of the studied classes of States.To assess the functions of attention, a device developed at the Department of biomedical engineering of SUSU is used to determine such properties of attention as concentration, volume, selectivity, switchability, distributability and stability. As a mathematical apparatus is used, the hybrid methodology for the synthesis of fuzzy decision rules. The basic element of which is the function of belonging to the studied classes of States (norm, mild cognitive impairment, moderate cognitive impairment, initial clinical stage) with a basic variable determined by the scales of the selected properties of attention.The decision on classification is made by the maximum value of the analyzed membership functions.The obtained mathematical models allow to diagnose the early stages of violations of all the studied functions of attention. Expert confidence in the obtained mathematical models exceeds 0.8. If, together with the level of attention, additional indicators characterizing the functional reserve, levels of psycho-emotional stress and fatigue and energy imbalance of the Meridian structures of the body are used, confidence in the correct classification of the early stages of attention disorders reaches a value of 0.9, which allows us to recommend the results in practical psychology and medicine.
Keywords: the early stage of cognitive impairment of attention, and hybrid decision rules, membership functions, confidence in the correct classification.
STUDY ON METHOD FOR MANAGING LOCATION AND PARAMETERS OF FOCAL SPOT FOR NON-INVASIVE SURGERY
E.G. Dombrugova, N.N. Chernov
The paper is dedicated to approbation of method for managing location and parameters of focal spot by changing physical characteristics of matching layer. A method is proposed for determining the speed of sound in matching layer for adjusting focal spot by calculating layer thickness-averaged speed of sound in biological tissues on the path of ultrasonic waves. A description of the experimental setup and research methodology is given. The influence of changes in the physical parameters of the matching layer on the distribution of the pressure amplitude in the frontal section of the acoustic field generated by the ultrasonic emitter when the angle of its inclination to the interface varies is estimated. The experimental data are compared with the results of mathematical modeling performed with the same input parameters. The results of calculations of the acoustic field generated by a focusing antenna array in a layered inhomogeneous medium (simulation layers) are presented and the influence of changes in the physical characteristics of the matching layer on the spatial distribution of the acoustic pressure amplitude in the focal region is estimated. The study results showed the possibility of using a matching layer with calculated parameters to control the location of the focal spot in the direction of ultrasonic waves propagation. The developed method for correcting the location of the focal spot can be used both for antenna arrays and for single emitters having the shape of a spherical segment.
Keywords: layer thickness averaged speed of sound, experimental setup, focused ultrasound, matching layer, refraction of ultrasonic waves.
AUTOMATIC CONTROL OF A CONTINUOUS ROBOT USING THE FABRIK ALGORITHM
V.V. Danilov, D.Y. Kolpashchikov, N.V. Laptev
Nowadays transcatheter minimally invasive surgery has gained popularity due to the shorter rehabilitation period of patients and lower risks during such interventions. However, this type of surgery is manually performed by surgeons and clinicians, which requires a high skill of specialists. Additionally, transcatheter surgery takes a lot of time and thereby increases the risk of medical error. The robotic solutions available today are expensive and inaccessible to most hospitals, clinics and medical centers. A solution of this problem may be the development of a simple automated control system, the usage of which will increase accuracy, repeatability, and reduce the risks related to the human factor. A medical catheter represents a manipulator that can bend in any point of its structure. This structural feature allows these manipulators to work in places with complex geometry, including the anatomical structures of the human body. In this regard, catheters have found their application in many fields, including medicine and industry. However, the control of this type of robots is complicated by the presence of flexible links tending to infinity. For positioning and orientation of continuous robots, forward and inverse kinematics algorithms are used. One of the most promising approaches is the Forward And Backward Reaching Inverse Kinematics algorithm (FABRIK). In this regard, this paper presents a fast and reliable system without feedback and based on the FABRIK algorithm for automatic control of a continuous robot.
Keywords: continuous robot, catheter, automation, positioning, FABRIK.
METHOD OF DIFFERENTIAL DIAGNOSTICS OF THE NOSOLOGICAL FORM OF VIRAL HEPATITIS WITH THE APPLICATION OF NEURAL NETWORK OF CASCADE CORRELATION
An important aspect of determining the nosological form of hepatitis is the combination of input data at the beginning of the study. The use of neural networks in medicine, which have the ability to search for hidden dependencies by learning from the experience of doctors, makes it easier to work in the role of advisor. However, the question of selecting the most effective topology for a specific task remains open. This paper substantiates the need to use neural network algorithms to solve the problem of determining the nosological form of hepatitis. The analysis and selection of input factors characterizing the clinical condition of the patient, and output factors characterizing the specific nosological form of hepatitis, neural network. The algorithm, its use is described, and a cascade neural network is compared with others in the context of the problem under consideration. At the end, a description is made of the established system for determining the nosological form of hepatitis using a cascade correlation neural network, and also describes the clinical efficacy.
Keywords: neural network, viral hepatitis, nosological form of hepatitis, neural network of cascade correlation, classification.
INFORMATION-MEASUREMENT SYSTEM FOR RESEARCH OF KINEMATICS OF MOVEMENTS OF THE LOWER LIMBS OF THE PERSON AND WIRELESS DATA TRANSFER
A.V. Tsareva, A.Y. Kurochkin, V.V.Alekseev
Currently, in medical rehabilitation there are no mobile measuring instruments with software and algorithmic software necessary to control the recovery of the patient in the postoperative period. The existing video systems of motion kinematics control have a high cost and dimensions, so that the acquisition of such a system by medical institutions is difficult. The article describes the information-measuring system for assessing the technique of human walking, consisting of sensors attached to the body and a program on a personal computer that processes the values obtained from the sensors. In the course of work on the creation of this system, rules for selecting the transmission frequency for the measuring channels required for the identification of the step phases using micromechanical sensors have been developed. The spectral characteristics of the accelerometer sensor for each axis of orientation, respectively, are given. The variants of the server implementation when exchanging information via TCP IP Protocol are considered. The software of the server of the distributed information-measuring system is developed. Experimental data of information transfer for each variant of information exchange on the TCP IP Protocol are given. The solution for obtaining the required transmission frequency is described. This system provides for the possibility of use at home, which will help the doctor, the methodist and the patient to monitor the rehabilitation process both during hospital stay and after discharge.
Keywords: biomechanics, medical rehabilitation, kinematic portrait of a person, walking technique, transfer of measuring information
MATHEMATICAL MODEL TO ASSESS THE INFLUENCE OF ELECTROMAGNETIC FIELDS ON THE EMERGENCE AND DEVELOPMENT OF OCCUPATIONAL DISEASES IN THE ELECTRICITY SECTOR
M. A. Myasoedova, N. A. Korenevskiy, L. V. Starodubtseva,
M. V. Pisarev
The aim of the study is to develop mathematical models for assessing the impact of electromagnetic fields of different modality and intensity on the human body providing a solution to the problems of assessing the health of people employed in the electric power industry with acceptable accuracy for medical practice.The technology of soft computing and, in particular, is chosen as the basic mathematical apparatus, the methodology of synthesis of hybrid fuzzy decision models developed in the South-West state University has proven itself in the synthesis of mathematical models of forecasting, early and differential diagnosis of diseases with a similar structure of the studied classes of States. As an example, a mathematical model for predicting the appearance and development of immune system diseases in employees of electric power enterprises of the Kursk region is described. Fuzzy mathematical models use membership functions with basic variables that take into account the intensity of the electromagnetic field of industrial frequency, work experience in the power industry and individual risk factors that provoke the appearance and development of diseases of the nervous system. In the course of mathematical modeling and expert evaluation it was shown that the use of the chosen methodology of synthesis of hybrid fuzzy mathematical models allowed to obtain a mathematical model of forecasting and development of diseases of the immune system in employees of the electric power complex with confidence exceeding 0.9.
Keywords: :mathematical model, fuzzy logic, occupational diseases, immune system, power engineering, forecasting
INFORMATION TRAINING SYSTEM FOR DISTANCE LEARNING THE METHODOLOGY FOR CARRYING OUT A MICRONUCLEAR TEST IN A HUMAN BUCKLE EPITELIUM
V.N. Kalaev, M.S. Nechaeva, A.Y. Vasilyeva, I.Y. Vasilyev,
A.P. Preobrazhenskiy, I.Y. Lvovich
Informational training system contains visual, generalized, structured material on micronuclear analysis of human buccal epithelium cells: the history of the development of method, methodology, description of objects of analysis, photos of nuclear anomalies, list of factors affecting the genetic apparatus, materials for interactive assessment of learning outcomes. The informational training system allows to the researcher to quickly and visually get acquainted with the methodology of the micronucleus test, learn how to analyze microscopic preparations, find and correctly determine the anomalies of the nucleus of epithelial cells, carry out statistical processing of the results obtained and at the end of mastering the technique to evaluate the skills obtained through interactive testing. This information system summarizes the results of Russian and international studies on the assessment of the genetic homeostasis of the human organism using micronucleus test in the buccal epithelium, thereby contributing to the development of a standardized methodology and unifying approaches to describing the results of experiments to avoid incorrect interpretation of the data. The information system presents training video demonstrating the collection of material, preparation of micropreparations, basic equipment and reagents used in the performance of micronuclear analysis. The information system promotes the introduction of the micronucleus test in the human buccal epithelium as a routine procedure in clinical practice, monitoring of the environment, assessment of occupational risks, and allows for the development of measures to assess human genetic safety.
Keywords: :database, micronucleus test, human buccal epithelium, anomalies of the nucleus, epithelial cells of the oral cavity
EXPERT EVALUATION AND OPTIMIZATION MODELING OF CONTROL AND OVERSIGHT ACTIVITY ON ENSURING THE QUALITY OF DRUGS
I.V. Safonov, Y.E. Lvovich
Ensuring the quality of medicines is currently one of the most important provisions of the state health policy. To reduce the risk of receipt of substandard and counterfeit medicines to the population, it is necessary to optimize the functioning of the current system of control and supervision activities aimed at the optimal use of available resources under specified conditions and restrictions. The main form of control and supervisory activities are inspections of objects of circulation of medicines or objects of control. To ensure an optimal plan for the audit, an optimization model is proposed that minimizes the number of objects included in the inspection plan, taking into account the limitation on planned costs and the necessary frequency of inspection of producers at risk. At the same time, the maximum number of tested drugs should be provided during the inspection of each object. A model refers to the problems of the multialternative optimization. A two-step procedure is proposed to solve this problem. A typical problem of discrete programming is solved – the problem of minimal coverage. When searching for the number of dominant solutions to the problem, basic variational procedures are used to obtain several solutions. To select the best option, it is proposed to use expert evaluation procedures. The developed optimization model is aimed at wide application in the work of the regional Department of Roszdravnadzor of the Voronezh region.
Keywords: expert evaluation,optimization modeling, the problem of minimum coverage, control and supervisory activities, drugs.
FORECESSION ELECTROMYOGRAPHY RECOGNITION AND GESTURES SELECTION FOR PROTESIS CONTROL
UDC 612.743, 612.817.2
R.Y. Budko, N.N. Chernov, N.A. Budko, A.Y. Budko
The relevance of this study is due to one of the main problems existing today in the field of building man-machine interfaces – is the creation of an effective management system that interacts directly with the user and external devices replacing functions (prostheses, wheelchairs, etc.). In this regard, this work is devoted to the study of the possibility of using physiological gestures from the daily life of a person to control the prosthesis with the safety of the forearm for at least one third. The leading approach to the study of this problem is the use of methods of statistical processing of experimental data, digital signal processing, machine learning algorithms and pattern recognition. This approach allows a comprehensive study of the electromyogram (EMG) of the forearm when making voluntary movements at different levels of the implementation of the myo-control system. The article presents the results of the EMG study recorded for 11 arbitrary movements from a group of subjects, describes the procedure for pre-processing the EMG and identifying characteristic features for signal recognition, discloses a method for classifying movements using an artificial neural network based on radial basic functions (RBF). Eight of the most suitable for classification movements were identified and ranked according to the classification accuracy: relaxation (like zero movement), hand opening, fist, hand flexion, hand supination, hand extension, hand pronation, pinch. The materials of the article are of practical value for building systems based on the human-machine interface, as well as for classification tasks in electrophysiology applications.
Keywords: :electromyogram, prosthesis, biocontrol, human-machine interface, machine learning, artificial neural networks.