Chi Yung Fu

US Patent:

6598459, Jul 29, 2003

Filed:

Jan 2, 1999

Appl. No.:

09/223831

Inventors:

Chi Yung Fu - San Francisco CA 94131

International Classification:

G01N 700

US Classification:

73 2334, 73 2406

Abstract:

The artificial olfactory system is an ultra-sensitive and selective odor sensing system for the detection of odorant molecules down to the part per trillion level. The system includes multiple ultra sensitive frequency sensors, such as sensors based on piezoelectric substrates or micro-machined resonators, capable of detecting frequency changes resulting from the interaction of odorant molecules with the sensor. A coating applied to the sensor greatly increases the surface of interaction between the odorant molecules or biological agents and the sensor. An array of these sensors, each responding to the interaction of an odorant molecule species but in a different manner, results in different frequency shifts. An ultra sensitive frequency measurement device measures as small as part per billion shift in frequency. An intelligent processor based on artificial neural networks and other intelligent signal processing system detects, recognizes, and generalizes the signature resulting from the collective response of all the sensors.

US Patent:

6763339, Jul 13, 2004

Filed:

Jun 25, 2001

Appl. No.:

09/888965

Inventors:

Chi Yung Fu - San Francisco CA
Loren I. Petrich - Livermore CA

Assignee:

The Regents of the University of California - Oakland CA

International Classification:

G06N 302

US Classification:

706 22, 706 15, 706 16, 704205

Abstract:

The method and system described herein use a biologically-based signal processing system for noise removal for signal extraction. A wavelet transform may be used in conjunction with a neural network to imitate a biological system. The neural network may be trained using ideal data derived from physical principles or noiseless signals to determine to remove noise from the signal.

US Patent:

7076371, Jul 11, 2006

Filed:

Mar 2, 2002

Appl. No.:

10/087049

Inventors:

Chi Yung Fu - San Francisco CA, US

International Classification:

G01N 33/48
G06F 19/00
G06G 7/58

US Classification:

702 19, 702 24, 703 11

Abstract:

A set of volatile markers are determined which are characteristic of a particular condition or disease, and which will be found in the exhaled breath of a person or odor from other parts of a body or from an entity. These markers are detected in the breath odor or gaseous emanations from the body or entity noninvasively using a volatile substance detector of sufficient sensitivity, such as an artificial olfactory system. The detected marker data is processed in an artificial neural network/fuzzy filter system with an algorithm that intelligently adapts to the individual body or entity and also optionally (if necessary) with a correction algorithm to eliminate environmental and other erroneous contributions to the markers. Any number of markers may be used, depending on how well they correlate with the condition and how accurate a result is desired, i. e. general screening or accurate diagnosis and monitoring.

US Patent:

7519488, Apr 14, 2009

Filed:

May 31, 2005

Appl. No.:

11/142049

Inventors:

Chi Yung Fu - San Francisco CA, US
Loren Petrich - Lebanon OR, US

Assignee:

Lawrence Livermore National Security, LLC - Livermore CA

International Classification:

G06F 19/00
G01R 13/00
G01R 29/26

US Classification:

702 69, 702179, 702191, 706 14, 706 15, 37524019

Abstract:

A signal processing method and system combining smooth level wavelet pre-processing together with artificial neural networks all in the wavelet domain for signal denoising and extraction. Upon receiving a signal corrupted with noise, an n-level decomposition of the signal is performed using a discrete wavelet transform to produce a smooth component and a rough component for each decomposition level. The nlevel smooth component is then inputted into a corresponding neural network pre-trained to filter out noise in that component by pattern recognition in the wavelet domain. Additional rough components, beginning at the highest level, may also be retained and inputted into corresponding neural networks pre-trained to filter out noise in those components also by pattern recognition in the wavelet domain. In any case, an inverse discrete wavelet transform is performed on the combined output from all the neural networks to recover a clean signal back in the time domain.

US Patent:

7901632, Mar 8, 2011

Filed:

Nov 16, 2005

Appl. No.:

11/281048

Inventors:

Chi Yung Fu - San Francisco CA, US

International Classification:

G01N 7/00

US Classification:

422 83, 422 681, 422 84, 422 90, 422 98, 436151, 436181, 73 233, 73 234

Abstract:

An array of sensor elements is formed by the incorporation of sensing materials into porous structures, creating sensing systems with extremely large surface areas with sensing molecules attached to mimic the large number of cilia of an olfactory system. In each sensor element, the sensing material or molecules are attached to spacer molecules or groups, which are attached to linker molecules or groups, which are attached to the porous substrate material. More specifically, a porphyrin doped aerogel material is used. The porphyrin sensing material is attached to the aerogel throughout its high surface area pore space. The porphyrin is covalently bonded to the silica network of the aerogel with a triethoxysilyl group linker that covalently attaches to the aerogel, and an alkyl group spacer.

US Patent:

20040016287, Jan 29, 2004

Filed:

Jul 28, 2003

Appl. No.:

10/629072

Inventors:

Chi Fu - San Francisco CA, US

International Classification:

G01N033/00

US Classification:

073/023340, 073/031050, 073/024060, 422/088000, 435/287200

Abstract:

The artificial olfactory system is an ultra-sensitive and selective odor sensing system for the detection of odorant molecules down to the part per trillion level. The system includes multiple ultra sensitive frequency sensors, such as sensors based on piezoelectric substrates or micro-machined resonators, capable of detecting frequency changes resulting from the interaction of odorant molecules with the sensor. A coating applied to the sensor greatly increases the surface of interaction between the odorant molecules or biological agents and the sensor. An array of these sensors, each responding to the interaction of an odorant molecule species but in a different manner, results in different frequency shifts. An ultra sensitive frequency measurement device measures as small as part per billion shift in frequency. An intelligent processor based on artificial neural networks and other intelligent signal processing system detects, recognizes, and generalizes the signature resulting from the collective response of all the sensors.

US Patent:

55389155, Jul 23, 1996

Filed:

Jun 5, 1992

Appl. No.:

7/894391

Inventors:

Chi Y. Fu - San Francisco CA

Assignee:

The Regents of the University of California - Oakland CA

International Classification:

H01L 21205

US Classification:

437 60

Abstract:

Customizable neural network in which one or more resistors form each synapse. All the resistors in the synaptic array are identical, thus simplifying the processing issues. Highly doped, amorphous silicon is used as the resistor material, to create extremely high resistances occupying very small spaces. Connected in series with each resistor in the array is at least one severable conductor whose uppermost layer has a lower reflectivity of laser energy than typical metal conductors at a desired laser wavelength.

US Patent:

56029659, Feb 11, 1997

Filed:

Sep 14, 1995

Appl. No.:

8/530393

Inventors:

Chi Y. Fu - San Francisco CA

Assignee:

The Regents of the University of California - Oakland CA

International Classification:

G06F 1546
G06G 702

US Classification:

395 24

Abstract:

Customizable neural network in which one or more resistors form each synapse. All the resistors in the synaptic array are identical, thus simplifying the processing issues. Highly doped, amorphous silicon is used as the resistor material, to create extremely high resistances occupying very small spaces. Connected in series with each resistor in the array is at least one severable conductor whose uppermost layer has a lower reflectivity of laser energy than typical metal conductors at a desired laser wavelength.