An event-driven spiking neutral network system for detection of physiological conditions

Abstract

The invention relates to an event-driven spiking neural network system (100) and a method for detecting a physiological condition of a person based on a detected physiological signal of the person, the system comprising at least the following components: - At least one sensor (111-1) configured and arranged to detect a physiological signal and to convert the physiological signal in a sensor signal (112) indicative of the physiological signal, - A signal conversion module (120) configured and arranged to receive the sensor signal (112) from the at least one sensor (111-1) and to convert the sensor signal (112) in at least one time series of discrete events, - An artificial neuron population (140) comprising a plurality of artificial event-driven spiking neurons (131-1, 131-N) arranged in an event-driven spiking neural network, wherein the neuron population (140) is configured and arranged to receive events, wherein the neuron population (140) is arranged to recognize the physiological condition of the person based on the received events, wherein the neuron population (140) is configured to provide one or more processed time series of events to, - A condition detection module (150) arranged and configured to receive the events from the neuron population (140) and to output a trigger signal (180), when the events received from the artificial neuron population (140) indicate that the physiological signal comprises a feature indicative of the physiological condition.

Description

technical field [0001] The present invention relates to an event-driven spiking neural network system for identifying human physiological conditions based on detected physiological signals, and a method for detecting physiological conditions. Background technique [0002] Many pathological conditions can be detected by examining measured physiological signals from a subject. For example, pathological cardiac conditions may be detected by examining signals caused by the electrical activity of the subject's heart. Sometimes one or more simultaneous electrical recordings are used, which can detect the electrical signals used to cause the heart muscle to contract. Alternatively, optical or other sensors may measure pressure waves in the blood flow through the body, which reflect the contraction of the heart. These sensor signals are collectively referred to as a biogram, regardless of the sensor used. Thus, a biometric bundle includes a sensor signal or a plurality of sensor ...

AI Technical Summary

Problems solved by technology

However, the technique employed in that paper does not allow for a more detailed analysis of physiological signals, such as the shape of the heartbeat signal or the determination of other characteristics of the signal indicative of physiological conditions, because pulse encoding is based on a synchronous, clock-based system

However, this in turn does not allow reconstruction of the original signal from the sensor, which means that a more detailed analysis of the sensor signal cannot be performed due to the loss of information associated with clock-based methods

Images