Invention Grant
- Patent Title: Selection of features predictive of biological conditions using protein mass spectrographic data
- Patent Title (中): 使用蛋白质质谱数据选择预测生物条件的特征
-
Application No.: US11929169Application Date: 2007-10-30
-
Publication No.: US07676442B2Publication Date: 2010-03-09
- Inventor: Asa Ben-Hur , André Elisseeff , Olivier Chapelle , Jason Aaron Edward Weston
- Applicant: Asa Ben-Hur , André Elisseeff , Olivier Chapelle , Jason Aaron Edward Weston
- Applicant Address: US GA Savannah
- Assignee: Health Discovery Corporation
- Current Assignee: Health Discovery Corporation
- Current Assignee Address: US GA Savannah
- Agency: Procopio, Cory, Hargreaves & Savitch LLP.
- Agent Eleanor M. Musick
- Main IPC: G06N5/00
- IPC: G06N5/00

Abstract:
Support vector machines are used to classify data contained within a structured dataset such as a plurality of signals generated by a spectral analyzer. The signals are pre-processed to ensure alignment of peaks across the spectra. Similarity measures are constructed to provide a basis for comparison of pairs of samples of the signal. A support vector machine is trained to discriminate between different classes of the samples. to identify the most predictive features within the spectra. In a preferred embodiment feature selection is performed to reduce the number of features that must be considered.
Public/Granted literature
- US20080097940A1 KERNELS AND KERNEL METHODS FOR SPECTRAL DATA Public/Granted day:2008-04-24
Information query
IPC分类:
G | 物理 |
G06 | 计算;推算或计数 |
G06N | 基于特定计算模型的计算机系统 |
G06N5/00 | 利用基于知识的模式的计算机系统 |