-
公开(公告)号：US20190196170A1
公开(公告)日：2019-06-27
申请号：US16292613
申请日：2019-03-05
Applicant: SHIMADZU CORPORATION
Inventor： Akira NODA , Hiroshi MAEKAWA
IPC: G02B21/36 , G01J3/453 , G01N21/3563 , G01J3/02
CPC classification number: G02B21/36 , G01J3/0248 , G01J3/453 , G01N21/3563 , G01N2021/3595 , G02B21/365
Abstract: A method for setting, within an observed image of a sample, an analysis target region that is a region on which an analysis is to be performed by an analyzer, the method including displaying the observed image of the sample on the display, dividing the observed image into a plurality of divisional areas, calculating a predetermined image characteristic quantity in each of the plurality of divisional areas, designating at least two of the divisional areas of the observed image displayed on the display, calculating a distribution of the values of the image characteristic quantity of the designated divisional areas, determining a value range of the image characteristic quantity for the divisional areas to be extracted as the analysis target region, based on the calculated distribution, and extracting from the observed image each of the plurality of divisional areas having a value of the image characteristic quantity within the value range.
-
公开(公告)号：US20170336370A1
公开(公告)日：2017-11-23
申请号：US15508285
申请日：2014-09-03
Applicant: SHIMADZU CORPORATION
Inventor： Akira NODA
IPC: G01N30/86
Abstract: The EM algorithm for a Gaussian mixture model is applied to the separation of peaks that overlap one another on a chromatogram. However, the number of overlapping components is unknown. Thus, a suitable number of models is set, and the fitting of model parameters is performed while an actually measured signal is appropriately divided for each model by the EM algorithm. Then, when a solution converges, a determination is made as to whether a peak-like waveform is present in a residue signal that is not divided. When the peak-like waveform is present, a peak model is added. The EM algorithm is executed again. In the M step, optimization is performed using, not only a simple Gaussian function, but also a modified Gaussian function assuming a tailing. In the M step, the estimation of a spectrum assuming a chromatogram and the estimation of a chromatogram assuming a spectrum are repeatedly performed.
-
13.发明公开公开(公告)号：US20230160862A1
公开(公告)日：2023-05-25
申请号：US17918259
申请日：2021-01-13
Applicant: Shimadzu Corporation
Inventor： Akira NODA
IPC: G01N30/86
CPC classification number: G01N30/8631 , G01N30/8693
Abstract: A waveform information inference device according to one mode of the present invention includes: a waveform extraction unit (31) configured to extract a partial waveform to be modeled from a signal waveform acquired based on actual measurement using a predetermined analysis device; and an adversarial learning unit (32) configured to acquire a model function corresponding to the partial waveform, or the model function and shape distribution information in the function by performing adversarial learning using two mutually adversarial models which are a generation model and a discriminative model using the partial waveform obtained by the waveform extraction unit as an input. The present invention can acquire a precision peak model function and its shape parameter distribution information.
-
公开(公告)号：US20230126478A1
公开(公告)日：2023-04-27
申请号：US17966557
申请日：2022-10-14
Applicant: Shimadzu Corporation
Inventor： Akira NODA
Abstract: A peak area display device includes an acquirer, a peak area calculator and a display device. The acquirer acquires measurement data measured by a chromatograph. A peak area calculator fits a model function to a chromatogram by performing optimization calculation to maximize or minimize a peak area while keeping a value to be taken by a loss function representing a residual between the chromatogram obtained from the measurement data MD and the model function in a predetermined range. The peak area calculator obtains a maximum value or a minimum value of the peak area. A display device (display) displays the maximum value or the minimum value of the peak area obtained by the peak area calculator, or information obtained by a process of the maximum value or the minimum value of the peak area.
-
公开(公告)号：US20210405002A1
公开(公告)日：2021-12-30
申请号：US17297320
申请日：2018-11-29
Applicant: Shimadzu Corporation
Inventor： Akira NODA
Abstract: A sample measurement device includes a measurement unit (1) configured to measure a sample, and a controller (2) configured to analyze a measurement result of the measurement unit. The controller (2) is configured to estimate and acquire a measurement result under another measurement condition using a model formula based on measurement results under a plurality of measurement conditions with different measurement parameter conditions, and estimate a distribution of a measurement quality indicator with respect to a measurement parameter based on the estimated measurement result.
-
Patent Agency Ranking
公开(公告)号：US20210350283A1
公开(公告)日：2021-11-11
申请号：US17273762
申请日：2018-09-13
Applicant: SHIMADZU CORPORATION
Inventor： Yuichiro FUJITA , Akira NODA
Abstract: A series of processes of dividing given labeled teacher data into model construction data and model verification data, constructing a machine learning model using the model construction data, and applying the model to the model verification data to identify (label) a sample is repeated multiple times (S2 to S5). Although the machine learning model to be constructed changes when the model construction data changes, an accurate identification can be made with a high probability. Thus, there is a high possibility that an original label and an identification result do not coincide in a mislabeled sample, resulting in misidentification. If the number of misidentifications is counted for each sample to obtain a misidentification rate, the mislabeled sample is identified based on the misidentification rate since the misidentification rate is relatively high in the mislabeled sample (S6 to S7). In this manner, the identification performance of the machine learning model can be improved by detecting the sample included in the teacher data that is highly likely to be in a mislabeled state with high accuracy.
-
公开(公告)号：US20180087961A1
公开(公告)日：2018-03-29
申请号：US15714159
申请日：2017-09-25
Applicant: Shimadzu Corporation
Inventor： Akira NODA
CPC classification number: G01J3/0262 , G01J3/027 , G01J3/10 , G01J3/18 , G01J3/28 , G01J3/42 , G01N21/25 , G01N21/274 , G01N30/74
Abstract: In a spectrum analysis apparatus, a controller controls selection of an adequate the correction device based on a plurality of corrected absorption spectra corrected by a plurality of correction devices acquired in advance for eliminating an effect of stray light.
-
公开(公告)号：US20150301323A1
公开(公告)日：2015-10-22
申请号：US14442812
申请日：2012-11-15
Applicant: SHIMADZU CORPORATION
Inventor： Akira NODA , Hiroshi MAEKAWA
IPC: G02B21/36
CPC classification number: G02B21/36 , G01J3/0248 , G01J3/453 , G01N21/3563 , G01N2021/3595 , G02B21/365
Abstract: A system for setting, within an observed image of a sample, an analysis target region that is a region on which an analysis is to be performed by an analyzer, the system including: a characteristic quantity calculator for dividing the observed image into a plurality of areas and for calculating a predetermined image characteristic quantity in each of the divisional areas; a divisional area selector for allowing a user to select a plurality of the divisional areas; a characteristic quantity range calculator for determining a value range of the image characteristic quantity for the divisional areas to be extracted as the analysis target region, based on the values of the image characteristic quantity of the divisional areas selected through the divisional area selector; and an area extractor for extracting, from the observed image, each divisional area having a value of the image characteristic quantity included in the aforementioned value range.
Abstract translation: 一种系统，用于在样本的观察图像内设置分析对象区域，所述分析对象区域是由分析仪进行分析的区域，所述系统包括：特征量计算器，用于将所述观察图像分割成多个 并且用于计算每个分区中的预定图像特征量; 分区区域选择器，用于允许用户选择多个分区; 特征量范围计算器，用于基于通过分割区域选择器选择的分割区域的图像特征量的值，确定要提取的分割区域的图像特征量的值范围作为分析对象区域; 以及区域提取器，用于从观察到的图像中提取包括在上述值范围内的图像特征量的值的每个分割区域。
-
公开(公告)号：US20240393302A1
公开(公告)日：2024-11-28
申请号：US18570400
申请日：2022-06-17
Applicant: Shimadzu Corporation
Inventor： Akira NODA
Abstract: A model function fitting device includes an acquirer that acquires a chromatogram, and a fitter that fits a model function to the chromatogram, while applying, to the model function, a constraint that the model function described by a logarithmic scale has a first portion being approximatable to a quadratic function and second portions being located at both sides of the first portion and being approximatable to a linear function.
-
公开(公告)号：US20240264132A1
公开(公告)日：2024-08-08
申请号：US18434524
申请日：2024-02-06
Applicant: SHIMADZU CORPORATION
Inventor： Akira NODA
IPC: G01N30/86
CPC classification number: G01N30/8693 , G01N30/8637 , G01N30/8651
Abstract: A waveform shape learning device learns a waveform of a sample using measurement data of the sample, the measurement data being obtained in an analysis device, and includes an extractor that retrieves the measurement data stored in a storage device and extracts input data from the measurement data, a latent variable generator that outputs, based on the input data, a latent variable by which the input data is characterized, a waveform data generator that outputs waveform data based on the latent variable and stores the waveform data in the storage device, a comparer that compares, using a loss function, the input data and the waveform data that are stored in the storage device, and a trainer that optimizes the latent variable generator and the waveform data generator so that output of the loss function is minimized.
-
-
-
-
-
-
-
-
-
Search Results
25
records
(took 0.018 seconds)
