A New Approach to Constructing a Decentralized Hierarchical Modular Network for Solving Complex Problems in the Paradigm of Training Artificial Neural Networks with a Teacher

Mirkin, E. L.; Savchenko, Elena

doi:10.3103/s1060992x21020107

Cited by 2 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To create a neural network medical classifier, we will use a system architecture that implements the approach of training an artificial neural network with an “interval teacher” [ 26 ]. Prediction of the patient’s condition will be implemented using a trained intelligent neural network module [ 27 ] based on the data collected during the examination of the patient.…”

Section: Discussionmentioning

confidence: 99%

Joint Methodology Based on Optical Densitometry and Dynamic Light Scattering for Liver Function Assessment

et al. 2023

View full text Add to dashboard Cite

A pressing health problem, both in clinical and socio-economic terms, is the increase in the number of patients with liver damage caused by viral diseases (hepatitis), cancer, toxicological damage, or metabolic disorders. Liver function assessment is a complex task, for which various existing diagnostic methods are used. Unfortunately, they all have several limitations which frequently make prompt and accurate diagnosis impossible. The high level of disability and mortality caused by liver diseases makes the development of new liver diagnostic methods very urgent. In this paper, we describe a new joint methodology for studying liver function based on optical densitometry and dynamic light scattering. This will help to diagnose and predict the dynamics of liver function during treatment with greater efficiency, due to including in consideration the individual characteristics of the cardiovascular system and tissue metabolism. In this paper, we present a laboratory model of a combined sensor for optical densitometry and dynamic light scattering. We also developed special software for controlling the sensor and processing the recorded data. Modeling experiments and physical medical studies were carried out to adjust and calibrate the sensor and software. We also assessed the sensor resolution when registering the concentration of dye in the human body and the minimum measured flow rate.

show abstract

Section: Discussionmentioning

confidence: 99%