Register | Login
Intellectual Property Today
RFC Express - Document Management System
2013 Top Patent Firms
2013 Top Trademark Firms
Current Issue
_blank

Advertising Opportunities

Click Here

Email A Friend Back to Archived News


Health Discovery Corporation Announces Allowance of New U.S. Patent Covering SVM Pre-Processing Methods


Tuesday, July 31, 2007

Savannah, GA -- Health Discovery Corporation (("HDC") (OTCBB: HDVY) announced that last week the U.S. Patent and Trademark Office issued a notice of allowance on its patent application entitled "Method of Using Kernel Alignment to Extract Significant Features from a Large Dataset." The new patent covers a novel pre-processing technique for use with SVMs, which was developed by Nello Cristianini, a recognized authority in the field of support vector machines and co-author of the widely-referenced books, An Introduction to Support Vector Machines and Kernel Methods for Pattern Analysis.

The application, which is a continuation of Patent No. 6,944,602, entitled "Spectral Kernels for Learning Machines," claims a method of pre-processing data referred to as "kernel alignment." The kernel alignment technique has been adopted by a number of researchers in the field for use in feature selection as well as kernel optimization. Kernel optimization is important for ensuring accuracy of classifications performed by SVMs and other learning machine. Feature selection methods are critical in reducing processor run time when analyzing the high volumes of data, such as that encountered with gene expression data and related information for discovery of biomarkers. Examples of uses of kernel alignment include gene expression analysis for biomarker identification and medical diagnostics, protein homology detection, identification of quantitative structure activity relationships (QSARs) for potential drug leads, and image reconstruction, to provide just a few examples.

Once the USPTO issues the patent described above, Health Discovery Corporation will hold the exclusive rights to 23 issued U.S. and foreign patents covering uses of SVMs for discovery of knowledge from large data sets. The issued patents cover methods and systems for pre-processing of data to enhance knowledge discovery using SVMs, analysis of data using multiple support vector machines and for multiple data sets, and providing SVM analysis services over the Internet. HDVY’s pending U.S. and foreign patent applications cover numerous improvements to and applications of SVMs including computer-aided image analysis using SVMs, with particular application to diagnosis using medical images, methods of feature selection for enhanced SVM efficiency and biomarkers for colon cancer, prostate cancer, BPH and renal cancer discovered with these methods, and use of SVMs for analysis of spectral data, such as mass spectrometry data used for protein analysis.

"This recent Notice of Allowance issued by the USPTO is great news for our company and shareholders as it represents an increase in both size and scope of our valuable patent portfolio," said Stephen D. Barnhill, M.D., HDC's Chairman and CEO. "The continued strengthening of our IP estate is a critical part of our business strategy that gives momentum to our ongoing licensing initiatives and our concurrent patent protection efforts as evidenced by the favorable outcome of our most recent infringement case with Ciphergen. We remain committed to monetizing our technology through expansion of our patent portfolio, collaboration with our licensing partners, and protection of our intellectual property rights when necessary."

Savannah-based Health Discovery Corporation (OTCBB: HDVY) is uniquely positioned in the field of pattern recognition technology. Through the application of its patent protected technology, HDC is a biology-oriented biomarker discovery company providing all aspects of First-Phase Biomarker Discoverysm. The Company's SVM and RFE-SVM pattern recognition tools have significant application potential in other sizable commercial markets such as radiology, financial markets, Internet search and spam, homeland security, and other areas where analysis of large volumes of complex data is required.

This news release contains "forward-looking statements" within the meaning of Section 27a of the Securities Acts of 1933 and Section 21E of the Securities Exchange Act of 1934. Although the management team of HDC believes that the expectations reflected in such forward-looking statements are reasonable, it can give no assurance that such expectations will prove correct.



Back to Archived News
Looking for...

  © Copyright 2013 Intellectual Property Today
Download Adobe Reader for free