-
公开(公告)号：US20210103857A1
公开(公告)日：2021-04-08
申请号：US17064560
申请日：2020-10-06
Applicant: Coretronic Corporation
Inventor： Feng Wang , Yen-Chun Huang
Abstract: The invention provides an automated model training method for training a pipeline for different spectrometers. The automated model training method includes: obtaining first spectral data corresponding to a first spectrometer, and second spectral data corresponding to a second spectrometer; and training the pipeline for the first spectrometer and the second spectrometer according to the first spectral data and the second spectral data, wherein the pipeline corresponds to at least one candidate recognition model. The invention also provides an automated model training device.
-
公开(公告)号：US11852532B2
公开(公告)日：2023-12-26
申请号：US17535691
申请日：2021-11-26
Applicant: Coretronic Corporation
Inventor： Feng Wang , Yen-Chun Huang , Kui-Ting Chen
CPC classification number: G01J3/0275 , G01J2003/2836
Abstract: An electronic device and a method for spectral model explanation are provided. The method includes: obtaining first labeled spectral data; storing a plurality of pipelines, selecting a selected pipeline from the pipelines, and generating a first measurement result corresponding to the first labeled spectral data according to the selected pipeline; and determining an important wavelength range corresponding to the selected pipeline according to the first measurement result.
-
公开(公告)号：US20220171994A1
公开(公告)日：2022-06-02
申请号：US17513896
申请日：2021-10-29
Applicant: Coretronic Corporation
Inventor： Ching-Wen Cheng , Yen-Chun Huang , Yi-Fan Liou , Kui-Ting Chen
Abstract: The invention provides a method of generating an image recognition model and an electronic device using the method. The method includes the following. A source image is obtained; a first image is cut out of a first region of the source image to generate a cut source image; a preliminary image recognition model is pre-trained according to feature data and label data, in which the feature data is associated with the cut source image, and the label data is associated with the first image; and the pre-trained preliminary image recognition model is fine-tuned to generate the image recognition model. The method of generating the image recognition model and the electronic device provided by the invention may correctly restore an input image.
-
Patent Agency Ranking
公开(公告)号：US20210103855A1
公开(公告)日：2021-04-08
申请号：US17037557
申请日：2020-09-29
Applicant: Coretronic Corporation
Inventor： Feng Wang , Yen-Chun Huang
Abstract: The disclosure provides an automated model training method for a spectrometer, wherein the model training method is executed by a processor, and the model training method includes: obtaining spectral data; selecting at least one preprocessing model from one or a plurality of preprocessing models; selecting a first machine learning model from one or a plurality of machine learning models; establishing a pipeline corresponding to the at least one preprocessing model and the first machine learning model; and training an identification model corresponding to the pipeline according to the spectral data and the pipeline. The disclosure further provides a model training device and a spectrometer.
-
公开(公告)号：US20220092350A1
公开(公告)日：2022-03-24
申请号：US17467453
申请日：2021-09-07
Applicant: Coretronic Corporation
Inventor： Yi-Fan Liou , Yen-Chun Huang
Abstract: An electronic device and a method for training or applying a neural network model are provided. The method includes the following steps. An input data is received. Convolution is performed on the input data to generate a high-frequency feature map and a low-frequency feature map. One of upsampling and downsampling is performed to match a first size of the high-frequency feature map and a second size of the low-frequency feature map. The high-frequency feature map and the low-frequency feature map are concatenated to generate a concatenated data. The concatenated data is inputted to an output layer of the neural network model.
-
公开(公告)号：US20220170790A1
公开(公告)日：2022-06-02
申请号：US17535691
申请日：2021-11-26
Applicant: Coretronic Corporation
Inventor： Feng Wang , Yen-Chun Huang , Kui-Ting Chen
IPC: G01J3/02
Abstract: An electronic device and a method for spectral model explanation are provided. The method includes: obtaining first labeled spectral data; storing a plurality of pipelines, selecting a selected pipeline from the pipelines, and generating a first measurement result corresponding to the first labeled spectral data according to the selected pipeline; and determining an important wavelength range corresponding to the selected pipeline according to the first measurement result.
-
公开(公告)号：US20220163387A1
公开(公告)日：2022-05-26
申请号：US17533116
申请日：2021-11-23
Applicant: Coretronic Corporation
Inventor： Feng Wang , Yen-Chun Huang , Kui-Ting Chen
Abstract: A method for optimizing an output result of a spectrometer and an electronic device using the method are provided. The method includes the following. First spectral data and second spectral data are obtained. A plurality of pipelines including a first pipeline and a second pipeline are obtained. The first pipeline is selected from the plurality of pipelines as a selected pipeline. The output result corresponding to the second spectral data is generated according to the selected pipeline. A performance of the first pipeline is calculated according to the first spectral data, and a first instruction is generated according to the performance. The selected pipeline is changed into the second pipeline according to the first instruction to update the output result.
-
公开(公告)号：US11893083B2
公开(公告)日：2024-02-06
申请号：US17467453
申请日：2021-09-07
Applicant: Coretronic Corporation
Inventor： Yi-Fan Liou , Yen-Chun Huang
IPC: G06F18/214 , G06N3/04
CPC classification number: G06F18/214 , G06N3/04
Abstract: An electronic device and a method for training or applying a neural network model are provided. The method includes the following steps. An input data is received. Convolution is performed on the input data to generate a high-frequency feature map and a low-frequency feature map. One of upsampling and downsampling is performed to match a first size of the high-frequency feature map and a second size of the low-frequency feature map. The high-frequency feature map and the low-frequency feature map are concatenated to generate a concatenated data. The concatenated data is inputted to an output layer of the neural network model.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.103 seconds)
