Detection of human respiration patterns using deep convolution neural networks
Journal Title: Восточно-Европейский журнал передовых технологий - Year 2018, Vol 4, Issue 9
Abstract
<p class="a"><span lang="EN-US">The method for realtime recognition of respiration types (patterns) of a patient to monitor his conditions and threats to his health, which is a special case of the problem of human activities recognition (HAR), was proposed. The method is based on application of deep machine learning using the convolution neural network (CNN) to classify the chest motion speed. It was shown that the decisions, taken in this case, are coordinated with mobile medicine technology (mHealth) of the use of body sensors and smartphones for signals processing, but CNN offer important additional opportunities at improving the quality of processing the accelerometersensor signals in the presence of interfering signals (noise) from other sources and instrumental errors of devices. We proposed the method of transformation of onedimensional (1D) accelerometer signals into twodimensional (2D) graphic images, processed using CNN with multiple processing layers, due to which the accuracy of determining the respiration pattern in various situations for different physical states of patients increases compared with the case when twodimensional accelerometer signal conversion is not used. In this case, an increase in accuracy (or quality) of determining different types of respiration occurs while maintaining a sufficient speed of performing procedures of the planned method, which allows classification of respiration types in real time. This technique was tested as a component of the Body Sensor Network (BSN) and high accuracy (88 %) of determining the patient’s respiration state was established, which in combination with contextual data, obtained from other BSN nodes, makes it possible to determine the patient’s state and a signal of the aggravation of their respiratory diseases.</span></p>
Authors and Affiliations
Anatoly Petrenko, Roman Kyslyi, Ihor Pysmennyi
Keywords
Related Articles
- EP ID EP528106
- DOI 10.15587/1729-4061.2018.139997
- Views 76
- Downloads 0
Flow visualization of water jet passing through the empty space of crossflow turbine runner
<p class="TTPAbstract">Hydropower plants are a form of renewable energy resources, which comes from flowing water. The turbine is used to drive the generator then convert mechanical energy into electrical energy. The tur...
Analysis of quality of grain shortbreads for biological activity and medicalbiological assessment
<p class="a">Quality control of new speltbased grain crispbreads with the addition of plant additives by the biological activity and medicobiological assessment was examined and analyzed. It was found that plant additi...
Development of a model for the estimation of financial processes in logistic systems at industrial enterprises
<p>The model and the method for assessment of the effectiveness of management of financial processes in logistic systems of industrial enterprises were substantiated. The model takes into consideration the parameters of...
Development of information technology of term extraction from documents in natural language
<p class="KeywordsCxSpFirst">It is shown that domain dictionaries are widely used at various stages of design and operation of software products. The process of dictionary development, especially term extraction, is very...
Identification of heat exchange process in the evaporators of absorption refrigerating units under conditions of uncertainty
<p>Analysis of the evaporator of the absorption refrigerating secondary condensation unit of ammonia production was performed. The need to minimize the temperature mode of operation of the evaporator, which provides for...