A detection system for sleep apnea syndrome based on mutual information network
A sleep apnea and detection system technology, applied in the field of medical detection, can solve the problems of inability to monitor and diagnose, and the cost of sleep laboratories is expensive, and achieve the effect of easy access
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0060] Database introduction: We use the MIT-Physionet Apnea database, which is divided into a training set and a test set. There are 35 nocturnal ECG signals with a length of about 8 hours in the training set and test set respectively, and the sampling frequency is 100Hz. Individuals range in age from 27 to 63 years and weigh from 53 kg to 135 kg.
[0061] There are 35 individuals in the training set. According to AHI=5 as the standard to divide healthy individuals and OSA individuals, 35 individuals can be divided into 22 OSA patients (AHI≥5) and 13 healthy individuals (AHI<5). Similarly, the 35 test set samples can be divided into 23 OSA patients and 12 healthy individuals.
[0062] Pass each ECG with a length of 8 hours through the following modules, see the flow chart figure 1 .
[0063] 1. ECG preprocessing module: use bandwidth filter (0.5-40Hz) to filter out power frequency noise and baseline drift in ECG signal. After the ECG signal is processed, it is re-sampled ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


