Low-power-consumption epilepsy detection circuit based on master and slave support vector machines

Abstract

The invention discloses a low-power-consumption epilepsy detection circuit based on master and slave support vector machines, and belongs to the field of intelligent medical application. The circuit comprises a clock module, a feature extraction module, a master-slave support vector machine module and a judgment module. The master-slave support vector machine module comprises a master support vector machine and a slave support vector machine, wherein the master support vector machine is a linear support vector machine, and the slave support vector machine is a nonlinear support vector machine;the master support vector machine controls starting and stopping of the slave support vector machine; in the detection process, the master support vector machine detects the start of epileptic seizure, and makes the slave support vector machine started, and the slave support vector machine corrects the end of epileptic seizure; and the detection result of the master-slave support vector machine module is the logic AND of the detection result of the master and slave support vector machines. Master-slave support vector machines and continuous sequence detection are utilized, so that on the premise of ensuring the detection performance, the operation complexity is greatly reduced, the power consumption is reduced, and the requirements of intelligent medical application are better met.

Description

technical field [0001] The invention relates to a low-power epilepsy detection circuit based on a master-slave support vector machine, and belongs to the field of intelligent medical applications. Background technique [0002] As of 2019, World Health Organization data shows that there are 60 million epilepsy patients worldwide. Epilepsy is known to be a chronic and recurring neurological disorder caused by sudden overdischarge of neuronal cells, ranging from brief distractions or muscle twitches to severe and persistent twitches. Due to the specificity of epileptic seizures, patients are brought to great difficulties in social life, such as discrimination, isolation, fear, inability to drive and work. Brain diseases are numerous, so correct detection and diagnosis is important. [0003] For seizure detection, early long-range EEG (Electroencephalogram, EEG) monitoring is the most effective method for epilepsy diagnosis and detection. This method relies on expert physician...

AI Technical Summary

Problems solved by technology

[0005] Among the above methods, some of them use complex classification algorithms and feature extraction methods in order to pursue higher detection performance such as sensitivity, resulting in a large power consumption, and the other part uses a single linear SVM detection, although the power consumption is reduced , but also reduces the sensitivity of the detection circuit

Images