Detection of human respiration patterns using deep convolution neural networks

Abstract

Automatic detection and recognition of human respiratory patterns for health monitoring without any uncomfortable sensors that make continuous measurements impossible was a key problem for technologies that use analysis of respiration and behavior of a human. As a result, there appeared a decision to detect respiration rate, based on signals, received from a variety of body sensors in real time. At continuous measurement of respiration rate, signals received from the sensors, wearable on the body, is much more preferable than signals received from external sensors (for example, a thermal sensor, a pressure sensor, etc.), even if the latter are more accurately. The main reasons are listed below.-Cameras, spirometers or other sensors, not subject to wearing out, suffer from environmental influence and are complicated to use. At the same time, sensors worn on the body do not, so they can carry out measurements much more frequently and even continuously, which provides more accurate results.

Generalized information with examples on the possibility of using a service-oriented approach and artificial intelligence technologies in the industry of e-Health

“…Deep learning, as an improved version of machine learning, together with large repositories of medical data and advanced learning algorithms, supported by doctors, has now reached a higher level than before, including image analysis, language processing, information retrieval and prediction. With the help of deep learning algorithms with models that are constantly trained and updated on real clinical data, future doctors are able to make accurate diagnoses and individually optimized treatment decisions [23,24].…”

Machine learning for diagnosis and monitoring of sleep apnea

“…Основним сенсором у цьому випадку є акселерометр, що зазвичай вимірює прискорення вздовж трьох осей. Пристрій з акселерометром може розміщуватись на грудній клітці [13] або на трахеї. Здебільшого застосовують окремі малогабаритні пристрої з акселерометром, але можна скористатись і звичайними смартфонами, прикріпивши їх до спеціального респіраторного пояса.…”

Graph-Based Fog Computing Network Model

“…Gope & Hwang (2016) suggests Body Sensor Networks (BSN) architecture for distributed edge-level computations with regard to user's privacy. Data acquired from these wearable networks can be processed by deep convolutional neural networks on fog nodes for immediate anomaly detection (Petrenko, Kyslyi, & Pysmennyi, 2018b).…”

“…Each of the device zone, field gateway zone, cloud gateway zone, cloud services zone and remote users' zone operates on constrained scope of user's data and has security requirements most suitable to given context, sensitivity of data being processed and persistence requirements. (Petrenko et al, 2018b) takes the idea further to cloud level allowing secure multi-party computations between akin organizations with help of hyperledger.…”