Patents by Inventor Shang Wen Chen

Shang Wen Chen has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11263485
    Abstract: A system for training transfer models that includes a memory and a processor coupling to each other. The memory stores instructions. The processor accesses the instructions to retrieve raw datasets from a first-type device and train a feature extraction model, a transfer feature and a preliminary classify model based on the raw datasets. The processor further transfers the feature extraction model, the transfer feature and the preliminary classify model to a host of a manufacturer so that the host directly applies the feature extraction model and the transfer feature, and retrains the preliminary classify model as an adapted classify model based on practical datasets.
    Type: Grant
    Filed: December 2, 2019
    Date of Patent: March 1, 2022
    Assignee: INSTITUTE FOR INFORMATION INDUSTRY
    Inventors: Tse-Yung Huang, Chin-Wei Tien, Shang-Wen Chen
  • Patent number: 11164676
    Abstract: A computer-aided recognition system for treatment response of rectal cancer is provided to predict the probability of a pathological complete response (pCR) of a rectal cancer patient after preoperative neoadjuvant chemoradiotherapy. The system includes a random forest model having several decision trees. Each decision tree has at least a feature node. Each feature node generates two branches according to a feature threshold, wherein each branch connects to another feature node or corresponds to an elementary pCR predicting probability. The random forest model integrates the elementary pCR probability of each decision tree, so as to generate a final pCR probability.
    Type: Grant
    Filed: July 12, 2019
    Date of Patent: November 2, 2021
    Assignee: CHINA MEDICAL UNIVERSITY HOSPITAL
    Inventors: Chia-Hung Kao, Shang-Wen Chen, Wei-Chih Shen, Kuo-Chen Wu
  • Publication number: 20210150271
    Abstract: A system for training transfer models that includes a memory and a processor coupling to each other. The memory stores instructions. The processor accesses the instructions to retrieve raw datasets from a first-type device and train a feature extraction model, a transfer feature and a preliminary classify model based on the raw datasets. The processor further transfers the feature extraction model, the transfer feature and the preliminary classify model to a host of a manufacturer so that the host directly applies the feature extraction model and the transfer feature, and retrains the preliminary classify model as an adapted classify model based on practical datasets.
    Type: Application
    Filed: December 2, 2019
    Publication date: May 20, 2021
    Inventors: Tse-Yung HUANG, Chin-Wei TIEN, Shang-Wen CHEN
  • Patent number: 10896502
    Abstract: A prediction system of tumor image-aided prediction of prognosis for patients with uterine cervical cancer is provided. The prediction system includes a data augmentation module and a deep convolution neural network model. The data augmentation module is used to apply a data expansion process of the image data, so as to generate a plurality of slice sets of the uterine cervical cancer tumor. The deep convolution neural network model is used to apply a feature analysis to the slices, so as to predict the prognosis of a patient after chemoradiotherapy.
    Type: Grant
    Filed: April 29, 2019
    Date of Patent: January 19, 2021
    Assignee: CHINA MEDICAL UNIVERSITY HOSPITAL
    Inventors: Chia-Hung Kao, Shang-Wen Chen, Wei-Chih Shen, Kuo-Chen Wu
  • Publication number: 20200211712
    Abstract: A computer-aided recognition system for treatment response of rectal cancer is provided to predict the probability of a pathological complete response (pCR) of a rectal cancer patient after preoperative neoadjuvant chemoradiotherapy. The system includes a random forest model having several decision trees. Each decision tree has at least a feature node. Each feature node generates two branches according to a feature threshold, wherein each branch connects to another feature node or corresponds to an elementary pCR predicting probability. The random forest model integrates the elementary pCR probability of each decision tree, so as to generate a final pCR probability.
    Type: Application
    Filed: July 12, 2019
    Publication date: July 2, 2020
    Inventors: Chia-Hung KAO, Shang-Wen CHEN, Wei-Chih SHEN, Kuo-Chen WU
  • Publication number: 20200202516
    Abstract: A prediction system of tumor image-aided prediction of prognosis for patients with uterine cervical cancer is provided. The prediction system includes a data augmentation module and a deep convolution neural network model. The data augmentation module is used to apply a data expansion process of the image data , so as to generate a plurality of slice sets of the uterine cervical cancer tumor. The deep convolution neural network model is used to apply a feature analysis to the slices, so as to predict the prognosis of a patient after chemoradiotherapy.
    Type: Application
    Filed: April 29, 2019
    Publication date: June 25, 2020
    Inventors: Chia-Hung KAO, Shang-Wen CHEN, Wei-Chih SHEN, Kuo-Chen WU
  • Patent number: 6034185
    Abstract: This invention relates to an epoxy resin composition which comprises polyalkyl phenol resins or polyalkyl phenol epoxy resins or both, wherein the polyalkyl phenol resins are represented by formula (I): ##STR1## wherein Ra, Rb and Rc may be the same or different from each other and stand for C.sub.1-5 alkyl styryl or halogen respectively;n is an integer of 0 to 4;k is an integer of 0 to 3;l is an integer of 0 to 4; andm is an integer of 1 to 10;and the polyalkyl phenol epoxy resins, which are obtained by reacting polyalkyl phenol resins of formula (I) with epihalohydrins, are represented by formula (II): ##STR2## wherein G stands for ##STR3## while the other symbols are the same as those defined above. The epoxy resin composition of this invention is able to provide a reactivity at lower temperatures and provide lower viscosity when used as hardener resins, as compared with traditional phenolic novolacs.
    Type: Grant
    Filed: October 6, 1997
    Date of Patent: March 7, 2000
    Assignee: Chang Chun Plastics Co., Ltd.
    Inventors: Kuen-Yuan Hwang, Hong-Hsing Chen, Biing Lu Perng, Shang Wen Chen