公开(公告)号：US6058352A

公开(公告)日：2000-05-02

申请号：US900319

申请日：1997-07-25

Applicant: Taiwei Lu ,  Robert A. Lieberman

Inventor： Taiwei Lu ,  Robert A. Lieberman

IPC: G01J3/28 ,  A61B5/00 ,  A61B5/103 ,  A61B10/00 ,  G01B15/02 ,  G01J3/02 ,  G01N21/27 ,  G01N21/31 ,  G01N21/35 ,  G06F17/00 ,  G06F19/00

CPC classification number: A61B5/0059 ,  A61B5/411 ,  A61B5/445 ,  A61B5/7264 ,  G01J3/02 ,  G01J3/0218 ,  G01J3/0272 ,  G01J3/28 ,  G01N21/31 ,  G06F19/345 ,  A61B5/7232 ,  A61B5/7267 ,  G01N2021/3155 ,  G01N21/359 ,  G01N2201/1296 ,  Y10S706/924

Abstract: Systems and methods using a neural network based portable absorption spectrometer system for real-time automatic evaluation of tissue injury are described. An apparatus includes an electromagnetic signal generator; an optical fiber connected to the electromagnetic signal generator; a fiber optic probe connected to the optical fiber; a broad band spectrometer connected to the fiber optic probe; and a hybrid neural network connected to the broad band spectrometer. The hybrid neural network includes a principle component analyzer of broad band spectral data obtained from said broad band spectrometer.

Abstract translation: 描述了使用基于神经网络的便携式吸收光谱仪系统的实时自动评估组织损伤的系统和方法。 一种装置包括电磁信号发生器; 连接到电磁信号发生器的光纤; 连接到光纤的光纤探针; 连接到光纤探头的宽带光谱仪; 以及连接到宽带光谱仪的混合神经网络。 混合神经网络包括从所述宽带光谱仪获得的宽带光谱数据的主成分分析仪。

公开(公告)号：US5715182A

公开(公告)日：1998-02-03

申请号：US286257

申请日：1994-08-08

Applicant: Hideki Asai ,  Hideyuki Horiuchi ,  Ryohei Yabe ,  Norio Oowada

Inventor： Hideki Asai ,  Hideyuki Horiuchi ,  Ryohei Yabe ,  Norio Oowada

IPC: G01N15/14 ,  G06F19/00

CPC classification number: G01N15/14 ,  G01N2201/1296 ,  Y10S706/924

Abstract: A particle image in a sample is formed at an imaging position by an objective lens of a microscope, projected on the image picking up plane of a TV camera via a projection lens and is subjected to photo-electric conversion. Image signals from the TV camera are supplied to an image memory via an A/D converter as well as to an image processing control unit. Image signals outputted from the image memory are supplied to a characteristic picking out unit and there a plurality of characteristics of the particle concerned are picked out. The picked-out characteristics are supplied to the classification unit and there classification of the sediment components is perfumed via a neural network with a learning capability. Accordingly, the classification unit performs provisionally an automatic classification of the objective sediment components by making use of the inputted characteristic parameters. The device allows accurate and fast automatic component particle analysis even for patient specimens containing a variety of components in high concentration.

Abstract translation: 通过显微镜的物镜在成像位置形成样品中的粒子图像，通过投影透镜投影在电视摄像机的图像拾取面上，并进行光电转换。 来自TV摄像机的图像信号经由A / D转换器以及图像处理控制单元提供给图像存储器。 从图像存储器输出的图像信号被提供给特征选择单元，并且拾取有关粒子的多个特征。 所选择的特征被提供给分类单元，并且通过具有学习能力的神经网络对沉积物成分进行分类。 因此，分类单元通过使用输入的特征参数临时执行目标沉积物成分的自动分类。 该装置允许准确和快速的自动组分颗粒分析，即使对于含有高浓度各种组分的患者标本也是如此。

公开(公告)号：US5267151A

公开(公告)日：1993-11-30

申请号：US578793

申请日：1990-09-07

Applicant: Frederic M. Ham ,  Glenn M. Cohen ,  Samuel P. Kozaitis

Inventor： Frederic M. Ham ,  Glenn M. Cohen ,  Samuel P. Kozaitis

IPC: G01N21/35 ,  G06F17/00 ,  G06N3/04 ,  G06F15/00 ,  G06F15/18

CPC classification number: G06K9/00503 ,  G01N21/3577 ,  G06K9/00536 ,  G06N3/0454 ,  G01N2201/1296 ,  Y10S128/922

Abstract: A method and apparatus for sensing and classifying a condition of interest in a system from background noise in which a parameter representative of the condition of interest is sensed and an electrical signal representative of the sensed parameter is produced. The electrical signal is converted into a digital signal, this digital signal containing a signal of interest representative of the condition of interest and background noise. The digital signal is received by an artificial neural network which filters out the background noise to produce a filtered signal from the digital signal, and classifies the signal of interest from the filtered signal to produce an output representative of the classified signal.

Abstract translation: 一种用于从背景噪声中感测和分类系统中的感兴趣条件的方法和装置，其中产生表示感兴趣条件的参数并且产生表示感测参数的电信号。 电信号被转换为数字信号，该数字信号包含表示感兴趣条件和背景噪声的感兴趣信号。 数字信号由人造神经网络接收，该人工神经网络滤除背景噪声，以从数字信号产生滤波信号，并将来自滤波信号的感兴趣信号进行分类，以产生表示分类信号的输出。

公开(公告)号：TW200815749A

公开(公告)日：2008-04-01

申请号：TW096127431

申请日：2007-07-27

Applicant: 財團法人工業技術研究院 INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： 柯俊宏 KO, CHUN HUNG ,  顧逸霞 KU, YI SHA ,  張中柱 CHANG, CHUNG CHU

IPC: G01N ,  G01J ,  G06F

CPC classification number: G01N21/47 ,  G01B21/08 ,  G01B21/20 ,  G01N21/211 ,  G01N2201/1296

Abstract: 一種多參數檢測系統之量測效能提昇方法,包含進行一量測程序以擷取一待測樣品之量測圖譜,再利用一權重演算法計算該待測參數間相關性的權重値。其次,利用一取樣轉換規則將該權重値轉換為一取樣函數,並根據該取樣函數更新該量測圖譜及複數條標稱圖譜。之後,比對該量測圖譜及該複數條標稱圖譜,並根據比對結果決定該待測樣品之結構參數値。

Abstract in simplified Chinese: 一种多参数检测系统之量测性能提升方法,包含进行一量测进程以截取一待测样品之量测图谱,再利用一权重算法计算该待测参数间相关性的权重値。其次,利用一采样转换守则将该权重値转换为一采样函数,并根据该采样函数更新该量测图谱及复数条标称图谱。之后,比对该量测图谱及该复数条标称图谱,并根据比对结果决定该待测样品之结构参数値。

公开(公告)号：US20240288375A1

公开(公告)日：2024-08-29

申请号：US18572215

申请日：2021-06-21

Applicant: Nissan Motor Co., Ltd.

Inventor： Takahiro KAITO ,  Shota YAMAZAKI ,  Yoshitaka UEHARA ,  Kentarou YUGE ,  Mori NAGAYAMA

IPC: G01N21/84 ,  G01N21/47 ,  G01N21/57

CPC classification number: G01N21/8422 ,  G01N21/4738 ,  G01N21/57 ,  G01N2021/8427 ,  G01N2201/1296

Abstract: In a coating evaluation device and a coating evaluation method, a coating surface is irradiated with incident light having a first intensity distribution, and a second intensity distribution of light reflected from the coating surface is acquired. Additionally, a third intensity distribution associated with the second intensity distribution is calculated based on shape information representing a curved shape of the coating surface, and an evaluation value that corresponds to the third intensity distribution is estimated by using an evaluation model that outputs a brilliance evaluation value pertaining to the coating surface in response to an input including the third intensity distribution. The curved shape of the coating surface is acquired based on measuring a coating surface or based on design data pertaining to the coating surface.

公开(公告)号：US20240210324A1

公开(公告)日：2024-06-27

申请号：US18596665

申请日：2024-03-06

Applicant: WUHAN UNIVERSITY

Inventor： Xiangheng XIAO ,  Shilian DONG ,  Fubing WANG ,  Changzhong JIANG

IPC: G01N21/65 ,  G01N1/28 ,  G01N33/543

CPC classification number: G01N21/658 ,  G01N1/2813 ,  G01N33/54346 ,  G01N2001/2846 ,  G01N2201/1296 ,  G01N2800/7028

Abstract: A spectroscopy and artificial intelligence-interaction serum analysis method includes: collecting bulk SERS spectral data of clinical serum samples, performing dimension reduction on the spectral data by using a covariance matrix to obtain spectral different peak positions of cancer patients and normal individuals, and performing spectral data processing and algorithm identification by using an svm model of an artificial intelligence algorithm to obtain a cancer identification rate. Compared with the conventional serum analysis method, the spectroscopy and artificial intelligence-interaction serum analysis method requires no antibody-antigen or other biological specificity modification processes, and the serum of cancer patients and normal individuals can be identified more cheaply, rapidly and accurately. Also the different peak positions in SERS spectra of a large amount of serum samples can be located, which provides an entirely novel detection and analysis method at a molecular bond energy level for the field of liquid biopsy of clinical cancers.

公开(公告)号：US11988602B2

公开(公告)日：2024-05-21

申请号：US17054300

申请日：2019-05-10

Applicant: Carrier Corporation

Inventor： David L. Lincoln ,  Michael J. Birnkrant ,  Jose-Rodrigo Castillo-Garza ,  Marcin Piech ,  Catherine Thibaud ,  Michael J. Giering ,  Kishore K. Reddy ,  Vivek Venugopalan

IPC: G01N21/552 ,  G01N27/12 ,  G01N29/036 ,  G01N33/00

CPC classification number: G01N21/553 ,  G01N27/125 ,  G01N29/036 ,  G01N33/0034 ,  G01N2201/1296 ,  G01N2291/0256

Abstract: An example SPR detection system includes a first prism having a first surface adjacent to a first metal layer exposed to a sample gas, and a second prism having a second surface adjacent to a second metal layer exposed to a reference gas. At least one light source is configured to provide respective beams to the first and second surfaces, where each of the beams causes SPR of a respective one of the metal layers. At least one photodetector is configured to measure a reflection property of reflections of the respective beams from the metal layers during the SPR. A controller is configured to determine whether a target gas is present in the sample gas based on a known composition of the reference gas and at least one of an electrical property of the first and second metal layers during the SPR and the reflection property of the metal layers.

公开(公告)号：US20240048848A1

公开(公告)日：2024-02-08

申请号：US17816778

申请日：2022-08-02

Applicant: Hong Kong Applied Science and Technology Resrearch Institute Company Limited

Inventor： Tai Wai David CHIK ,  Chi Shing WONG

IPC: H04N5/232 ,  G01N21/95 ,  G01N21/88 ,  G06T7/73

CPC classification number: H04N5/23299 ,  G01N21/9515 ,  G01N21/8851 ,  G06T7/75 ,  G01N2021/8887 ,  G01N2201/1296

Abstract: A movable camera travels along an inspection path for optically inspecting an inspection surface of an object for defect detection. In planning the inspection path, a set of viewpoints on the inspection surface is generated. Each viewpoint is associated with a patch, which is a largest area of the inspection surface within a field of view (FOV) of the camera when the camera is located over the viewpoint for capturing an image of FOV. An effective region of the patch is advantageously predicted by a neural network according to a three-dimensional geometric characterization of the patch such that the predicted effective region is valid for defect detection based on the captured image. A valid area is one whose corresponding area on the captured image is not blurred and is neither underexposed nor overexposed. The inspection path is determined according to respective effective regions associated with the set of viewpoints.

公开(公告)号：US11834696B2

公开(公告)日：2023-12-05

申请号：US16500370

申请日：2018-04-05

Applicant: Arizona Board of Regents on behalf of Arizona State University

Inventor： Nongjian Tao ,  Shaopeng Wang ,  Hui Yu

IPC: C12Q1/18 ,  G16H10/40 ,  G16H50/20 ,  G16H30/40 ,  G01N21/51 ,  G06T7/00

CPC classification number: C12Q1/18 ,  G01N21/51 ,  G06T7/0012 ,  G16H10/40 ,  G16H30/40 ,  G16H50/20 ,  G01N2201/1296 ,  G06T2207/10016 ,  G06T2207/10056 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30024

Abstract: A method for deep learning video microscopy-based antimicrobial susceptibility testing of a bacterial strain in a sample by acquiring image sequences of individual bacterial cells of the bacterial strain in a subject sample before, during, and after exposure to each antibiotic at different concentrations. The image sequences are compressed into static images while preserving essential phenotypic features. Data representing the static images is input into a pre-trained deep learning (DL) model which generates output data; and antimicrobial susceptibility for the bacterial strain is determined from the output data.

公开(公告)号：US20230341329A1

公开(公告)日：2023-10-26

申请号：US18005077

申请日：2021-07-28

Applicant: ALLEN INSTITUTE

Inventor： Gregory JOHNSON ,  Chawin OUNKOMOL ,  Forrest COLLMAN ,  Sharmishtaa SESHAMANI ,  Nathalie GAUDREAULT ,  Calysta YAN ,  Jianxu CHEN ,  Susanne RAFELSKI

IPC: G01N21/64

CPC classification number: G01N21/6458 ,  G01N2201/1296 ,  G01N2500/10

Abstract: The present invention provides various methods for screening one or more compounds, suitably using non-invasive visual methods and neural networks for generating predicted fluorescence images of cells, to assess an effect of the compound on the cell, as well as to classify a compound or to determine an activity of a compound. Also provided are systems and methods for carrying out such assessments.