MACHINE-BASED PATIENT-SPECIFIC SEIZURE CLASSIFICATION SYSTEM
First Claim
1. A device, comprising:
- an analog front-end (AFE) to sense electroencephalography (EEG) information;
a digital back end (DBE) including at least a feature extraction (FE) engine and a non-linear support vector machine (NL-SVM) classification engine to determine onset of a seizure based on the EEG information; and
an analog-to-digital converter (A/D) stage to convert analog signals provided by the AFE for use by the DFE.
2 Assignments
0 Petitions
Accused Products
Abstract
This disclosure is directed to a machine-based patient-specific seizure classification system. In general, an example system may comprise a non-linear SVM seizure classification system-on-chip (SoC) with multichannel EEG data acquisition and storage for epileptic patients is presented. The SoC may integrate a hardware-efficient log-linear Gaussian Basis Function engine, floating point piecewise linear natural log, and low-noise, high dynamic range readout circuits. In at least one example implementation, the SoC may consume 1.83W/classification while classifying 8 channel results with an average detection rate, average false alarm rate and latency of 95.1%, 0.94% and <2 s, respectively.
-
Citations
23 Claims
-
1. A device, comprising:
-
an analog front-end (AFE) to sense electroencephalography (EEG) information; a digital back end (DBE) including at least a feature extraction (FE) engine and a non-linear support vector machine (NL-SVM) classification engine to determine onset of a seizure based on the EEG information; and an analog-to-digital converter (A/D) stage to convert analog signals provided by the AFE for use by the DFE. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A method, comprising:
-
receiving analog electroencephalography (EEG) information in a device; converting the analog EEG information into digital EEG information; extracting feature vectors (FVs) from the digital EEG information; and determining onset of a seizure based on the extracted FVs. - View Dependent Claims (11, 12, 13, 14, 15, 16)
-
-
17. At least one machine-readable storage medium having stored thereon, individually or in combination, instructions that when executed by one or more processors result in the following operations comprising:
-
receiving analog electroencephalography (EEG) information; converting the analog EEG information into digital EEG information; extracting feature vectors (FVs) from the digital EEG information; and determining on the onset of a seizure based on the extracted FVs. - View Dependent Claims (18, 19, 20, 21, 22, 23)
-
Specification