Patents by Inventor Lun Liao

Lun Liao 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).

  • Publication number: 20250208205
    Abstract: A testing system and a testing method are provided. The testing system includes a movable mechanism, a testing device, a signal source, a nearfield scanner, a CR reflector, and a processor. The testing device is mounted on the movable mechanism and used for emitting or reflecting an electromagnetic wave. The signal source is configured to emit the electromagnetic wave. The nearfield scanner is used for measuring the incoming electromagnetic wave. The CR reflector has a parabolic surface used for reflecting the electromagnetic wave. The processor is coupled to the movable mechanism, the signal source, and the nearfield scanner. The processor is configured to adjust the orientation of the testing device through the movable mechanism, emit the electromagnetic wave through the signal source, and determine the electromagnetic field information of the electromagnetic wave through the nearfield scanner.
    Type: Application
    Filed: October 8, 2024
    Publication date: June 26, 2025
    Applicant: WaveFidelity Inc.
    Inventors: Ike Lin, You-Hua Lin, Chang-Fa Yang, Chang-Lun Liao
  • Patent number: 12270846
    Abstract: A measuring system and a measuring method of an antenna pattern based on near field to far field transformation (NFTF) are provided. The measuring system includes a probe antenna, a reference antenna, and a control system. The probe antenna measures an electric field radiated by an antenna under test to obtain electric field information. The reference antenna measures the electric field to obtain a reference phase. The control system is coupled to the antenna under test, the probe antenna, and the reference antenna, wherein the control system applies near field focusing to the reference antenna to configure a focus point of the reference antenna on the antenna under test, and the control system performs the NFTF according to the electric field information and the reference phase to output far field patterns.
    Type: Grant
    Filed: May 23, 2023
    Date of Patent: April 8, 2025
    Assignee: Chunghwa Telecom Co., Ltd.
    Inventors: Chang-Lun Liao, You-Hua Lin, Jiahn-Wei Lin, Bo-Cheng You, Chang-Fa Yang, De-Xian Song, Wen-Jiao Liao, Yuan-Chang Hou, Tswen-Jiann Huang
  • Publication number: 20240394605
    Abstract: The invention provides a system and a method thereof for establishing an extubation prediction using a machine learning model capable of obtaining an extubation prediction model and key features used by the extubation prediction model through training and/or verification of a machine learning model, and analyzing key feature data of a patient in real time through the extubation prediction model in order to obtain a possibility of extubation of the patient and its related explanation. Accordingly, the system and the method thereof for establishing the extubation prediction using the machine learning model disclosed in the invention are used as a tool for clinical caregivers to evaluate extubation in order to reduce a possibility of reintubation due to inability to breathe spontaneously after extubation.
    Type: Application
    Filed: June 21, 2023
    Publication date: November 28, 2024
    Inventors: WEN-CHENG CHAO, KAI-CHIH PAI, MING-CHENG CHAN, CHIEH-LIANG WU, MIN-SHIAN WANG, CHIEN-LUN LIAO, TA-CHUN HUNG, YAN-NAN LIN, HUI-CHIAO YANG, RUEY-KAI SHEU, LUN-CHI CHEN
  • Publication number: 20240329108
    Abstract: A measuring system and a measuring method of an antenna pattern based on near field to far field transformation (NFTF) are provided. The measuring system includes a probe antenna, a reference antenna, and a control system. The probe antenna measures an electric field radiated by an antenna under test to obtain electric field information. The reference antenna measures the electric field to obtain a reference phase. The control system is coupled to the antenna under test, the probe antenna, and the reference antenna, wherein the control system applies near field focusing to the reference antenna to configure a focus point of the reference antenna on the antenna under test, and the control system performs the NFTF according to the electric field information and the reference phase to output far field patterns.
    Type: Application
    Filed: May 23, 2023
    Publication date: October 3, 2024
    Applicant: Chunghwa Telecom Co., Ltd.
    Inventors: Chang-Lun Liao, You-Hua Lin, Jiahn-Wei Lin, Bo-Cheng You, Chang-Fa Yang, De-Xian Song, Wen-Jiao Liao, Yuan-Chang Hou, Tswen-Jiann Huang
  • Patent number: 11937932
    Abstract: An acute kidney injury predicting system and a method thereof are proposed. A processor reads the data to be tested, the detection data, the machine learning algorithm and the risk probability comparison table from a main memory. The processor trains the detection data according to the machine learning algorithm to generate an acute kidney injury prediction model, and inputs the data to be tested into the acute kidney injury prediction model to generate an acute kidney injury characteristic risk probability and a data sequence table. The data sequence table lists the data to be tested in sequence according to a proportion of each of the data to be tested in the acute kidney injury characteristics. The processor selects one of the medical treatment data from the risk probability comparison table according to the acute kidney injury characteristic risk probability.
    Type: Grant
    Filed: July 8, 2022
    Date of Patent: March 26, 2024
    Assignees: TAICHUNG VETERANS GENERAL HOSPITAL, TUNGHAI UNIVERSITY
    Inventors: Chieh-Liang Wu, Chun-Te Huang, Cheng-Hsu Chen, Tsai-Jung Wang, Kai-Chih Pai, Chun-Ming Lai, Min-Shian Wang, Ruey-Kai Sheu, Lun-Chi Chen, Yan-Nan Lin, Chien-Lun Liao, Ta-Chun Hung, Chien-Chung Huang, Chia-Tien Hsu, Shang-Feng Tsai
  • Patent number: 11908136
    Abstract: A respiratory status classifying method is for classifying as one of at least two respiratory statuses and includes an original physiological parameter inputting step, an original chest image inputting step, a characteristic physiological parameter generating step, a characteristic chest image generating step, a training step and a classifier generating step. The characteristic chest image generating step includes processing at least a part of the original chest images, segmenting images of a left lung, a right lung and a heart from each of the original chest images that are processed, and enhancing image data of the images being segmented, so as to generate a plurality of characteristic chest images. The training step includes training two respiratory status classifiers using a plurality of characteristic physiological parameters and the characteristic chest images by at least one machine learning algorithm.
    Type: Grant
    Filed: September 27, 2022
    Date of Patent: February 20, 2024
    Assignees: TAICHUNG VETERANS GENERAL HOSPITAL, TUNGHAI UNIVERSITY
    Inventors: Ming-Cheng Chan, Kai-Chih Pai, Wen-Cheng Chao, Yu-Jen Huang, Chieh-Liang Wu, Min-Shian Wang, Chien-Lun Liao, Ta-Chun Hung, Yan-Nan Lin, Hui-Chiao Yang, Ruey-Kai Sheu, Lun-Chi Chen
  • Patent number: 11848318
    Abstract: A package structure and a manufacturing thereof are provided. The package structure includes a base, a chip, a control element and an underfill. The chip is disposed on the base and includes a recess, and the recess has a bottom surface and a sidewall. The control element is disposed between the base and the chip and disposed on the bottom surface of the recess, and a gap exists between the control element and the sidewall of the recess. The underfill is disposed in the recess. The chip and the control element are electrically connected to the base respectively.
    Type: Grant
    Filed: August 19, 2021
    Date of Patent: December 19, 2023
    Assignee: POWERTECH TECHNOLOGY INC.
    Inventors: Pei-Hsun Chou, Ko-Lun Liao
  • Publication number: 20230380742
    Abstract: An acute kidney injury predicting system and a method thereof are proposed. A processor reads the data to be tested, the detection data, the machine learning algorithm and the risk probability comparison table from a main memory. The processor trains the detection data according to the machine learning algorithm to generate an acute kidney injury prediction model, and inputs the data to be tested into the acute kidney injury prediction model to generate an acute kidney injury characteristic risk probability and a data sequence table. The data sequence table lists the data to be tested in sequence according to a proportion of each of the data to be tested in the acute kidney injury characteristics. The processor selects one of the medical treatment data from the risk probability comparison table according to the acute kidney injury characteristic risk probability.
    Type: Application
    Filed: July 8, 2022
    Publication date: November 30, 2023
    Inventors: Chun-Te HUANG, Kai-Chih PAI, Tsai-Jung WANG, Min-Shian WANG, Yan-Nan LIN, Cheng-Hsu CHEN, Chun-Ming LAI, Ruey-Kai SHEU, Lun-Chi CHEN, Chieh-Liang WU, Chien-Lun LIAO, Ta-Chun HUNG, Chien-Chung HUANG, Chia-Tien HSU, Shang-Feng TSAI
  • Publication number: 20230368375
    Abstract: A respiratory status classifying method is for classifying as one of at least two respiratory statuses and includes a training's physiological parameter inputting step, a training's chest image inputting step, a characteristic physiological parameter generating step, a characteristic chest image generating step, a training step and a classifier generating step. The characteristic chest image generating step includes processing at least a part of the training's chest images, segmenting images of a left lung, a right lung and a heart from each of the training's chest images that are processed, and enhancing image data of the images being segmented, so as to generate a plurality of characteristic chest images. The training step includes training a plurality of characteristic physiological parameters and the characteristic chest images by at least one machine learning algorithm.
    Type: Application
    Filed: September 27, 2022
    Publication date: November 16, 2023
    Inventors: Ming-Cheng CHAN, Kai-Chih PAI, Wen-Cheng CHAO, Yu-Jen HUANG, Chieh-Liang WU, Min-Shian WANG, Chien-Lun LIAO, Ta-Chun HUNG, Yan-Nan LIN, Hui-Chiao YANG, Ruey-Kai SHEU, Lun-Chi CHEN
  • Patent number: 11644047
    Abstract: A wall fan suspension structure comprises a wall-side coupling element with a first bottom plate part and a first side plate part connected to each other, the first bottom plate part extends from the first side plate part, and the first bottom plate part is provided for locking on a wall surface; and a fan-side coupling element with a second bottom plate part and a second side plate part connected to each other, the second bottom plate part extends from the second side plate part, the second bottom plate part is provided for coupling with a wall fan, and the second side plate part and the first side plate part are connected by sleeving with each other.
    Type: Grant
    Filed: June 30, 2021
    Date of Patent: May 9, 2023
    Inventor: Chi-Lun Liao
  • Publication number: 20230003234
    Abstract: A wall fan suspension structure comprises a wall-side coupling element with a first bottom plate part and a first side plate part connected to each other, the first bottom plate part extends from the first side plate part, and the first bottom plate part is provided for locking on a wall surface; and a fan-side coupling element with a second bottom plate part and a second side plate part connected to each other, the second bottom plate part extends from the second side plate part, the second bottom plate part is provided for coupling with a wall fan, and the second side plate part and the first side plate part are connected by sleeving with each other.
    Type: Application
    Filed: June 30, 2021
    Publication date: January 5, 2023
    Inventor: Chi-Lun LIAO
  • Patent number: 11488069
    Abstract: A method for predicting air quality with the aid of machine learning models includes: (A) providing air pollution data to perform an eXtreme Gradient Boosting (XGBoost) regression algorithm for obtaining a XGBoost prediction value; (B) providing the air pollution data to perform a Long Short-Term Memory (LSTM) algorithm for obtaining an LSTM prediction value; (C) combining the air pollution data, the XGBoost prediction value and the LSTM prediction value to generate air pollution combination data; (D) performing an XGBoost classification algorithm to obtain a suggestion for whether to issue an air pollution alert; and (E) performing the XGBoost regression algorithm on the air pollution combination data to obtain an air pollution prediction value. Two layers of machine learning models are built, and a situation where prediction results are too conservative when a single model does not have enough data can be improved.
    Type: Grant
    Filed: November 4, 2018
    Date of Patent: November 1, 2022
    Assignee: National Chung-Shan Institute of Science and Technology
    Inventors: Li-Yen Kuo, Chih-Lun Liao, Chun-Han Tai, Hao-Yu Kao
  • Publication number: 20220320063
    Abstract: A package structure and a manufacturing thereof are provided. The package structure includes a base, a chip, a control element and an underfill. The chip is disposed on the base and includes a recess, and the recess has a bottom surface and a sidewall. The control element is disposed between the base and the chip and disposed on the bottom surface of the recess, and a gap exists between the control element and the sidewall of the recess. The underfill is disposed in the recess. The chip and the control element are electrically connected to the base respectively.
    Type: Application
    Filed: August 19, 2021
    Publication date: October 6, 2022
    Applicant: POWERTECH TECHNOLOGY INC.
    Inventors: Pei-Hsun Chou, Ko-Lun Liao
  • Patent number: 11204973
    Abstract: In an example embodiment, position bias and other types of bias may be compensated for by using two-phase training of a machine-learned model. In a first phase, the machine-learned model is trained using non-randomized training data. Since certain types of machine-learned models, such as those involving deep learning (e.g., neural networks) require a lot of training data, this allows the bulk of the training to be devoted to training using non-randomized training data. However, since this non-randomized training data may be biased, a second training phase is then used to revise the machine-learned model based on randomized training data to remove the bias from the machine-learned model. Since this randomized training data may be less plentiful, this allows the deep learning machine-learned model to be trained to operate in an unbiased manner without the need to generate additional randomized training data.
    Type: Grant
    Filed: June 21, 2019
    Date of Patent: December 21, 2021
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Daniel Sairom Krishnan Hewlett, Dan Liu, Qi Guo, Wenxiang Chen, Xiaoyi Zhang, Lester Gilbert Cottle, III, Xuebin Yan, Yu Gong, Haitong Tian, Siyao Sun, Pei-Lun Liao
  • Publication number: 20200401644
    Abstract: In an example embodiment, position bias and other types of bias may be compensated for by using two-phase training of a machine-learned model. In a first phase, the machine-learned model is trained using non-randomized training data. Since certain types of machine-learned models, such as those involving deep learning (e.g., neural networks) require a lot of training data, this allows the bulk of the training to be devoted to training using non-randomized training data. However, since this non-randomized training data may be biased, a second training phase is then used to revise the machine-learned model based on randomized training data to remove the bias from the machine-learned model. Since this randomized training data may be less plentiful, this allows the deep learning machine-learned model to be trained to operate in an unbiased manner without the need to generate additional randomized training data.
    Type: Application
    Filed: June 21, 2019
    Publication date: December 24, 2020
    Inventors: Daniel Sairom Krishnan Hewlett, Dan Liu, Qi Guo, Wenxiang Chen, Xiaoyi Zhang, Lester Gilbert Cottle, Xuebin Yan, Yu Gong, Haitong Tian, Siyao Sun, Pei-Lun Liao
  • Patent number: 10777076
    Abstract: A license plate recognition system and a license plate recognition method are provided. The license plate recognition system includes an image capturing module, a determination module and an output module. The image capturing module is utilized for capturing an image of a target object. The determination module is utilized for dividing the image of the target object into a plurality of image blocks. The determination module utilizes the plurality of image blocks to generate feature data and perform a data sorting process on the feature data to generate a first sorting result. The output module outputs the sorting result.
    Type: Grant
    Filed: December 13, 2018
    Date of Patent: September 15, 2020
    Assignee: National Chung-Shan Institute of Science and Technology
    Inventors: Shu-Heng Chen, Chih-Lun Liao, Cheng-Feng Shen, Li-Yen Kuo, Yu-Shuo Liu, Shyh-Jian Tang, Chia-Lung Yeh
  • Publication number: 20200090506
    Abstract: A license plate recognition system and a license plate recognition method are provided. The license plate recognition system includes an image capturing module, a determination module and an output module. The image capturing module is utilized for capturing an image of a target object. The determination module is utilized for dividing the image of the target object into a plurality of image blocks. The determination module utilizes the plurality of image blocks to generate feature data and perform a data sorting process on the feature data to generate a first sorting result. The output module outputs the sorting result.
    Type: Application
    Filed: December 13, 2018
    Publication date: March 19, 2020
    Inventors: Shu-Heng Chen, Chih-Lun Liao, Cheng-Feng Shen, Li-Yen Kuo, Yu-Shuo Liu, Shyh-Jiang Tang, Chia-Lung Yeh
  • Publication number: 20190325334
    Abstract: A method for predicting air quality with the aid of machine learning models includes: (A) providing air pollution data to perform an eXtreme Gradient Boosting (XGBoost) regression algorithm for obtaining a XGBoost prediction value; (B) providing the air pollution data to perform a Long Short-Term Memory (LSTM) algorithm for obtaining an LSTM prediction value; (C) combining the air pollution data, the XGBoost prediction value and the LSTM prediction value to generate air pollution combination data; (D) performing an XGBoost classification algorithm to obtain a suggestion for whether to issue an air pollution alert; and (E) performing the XGBoost regression algorithm on the air pollution combination data to obtain an air pollution prediction value. Two layers of machine learning models are built, and a situation where prediction results are too conservative when a single model does not have enough data can be improved.
    Type: Application
    Filed: November 4, 2018
    Publication date: October 24, 2019
    Inventors: Li-Yen Kuo, Chih-Lun Liao, Chun-Han Tai, Hao-Yu Kao
  • Patent number: 10418714
    Abstract: In an electronic switching beamforming antenna array, a coplanar feeding line of the antenna array is configured on a metal plane of a substrate, and a plurality of slot antennas of aforementioned antenna array are inclinedly configured on the metal plane and configured on at least one side of the coplanar feeding line. A slot coupling segment of slot antenna is configured at one end of the slot antenna and neighbored with the coplanar feeding line so as to make the slot antenna couple with the coplanar feeding line, and a switch device of the slot antenna is configured at one portion which between one part of the slot antenna and a grounding plane formed by the metal plane. When the switch device is triggered to configure a radiating feature of the slot antenna, the antenna array is able to achieve the purpose of setting beamforming direction.
    Type: Grant
    Filed: February 22, 2017
    Date of Patent: September 17, 2019
    Assignee: Chunghwa Telecom Co., Ltd.
    Inventors: Wen-Jiao Liao, Yan-Yun Lin, Chang-Fa Yang, Chang-Lun Liao
  • Publication number: 20180024284
    Abstract: A method for manufacturing a retardation film by using a dual-axial stretching process uses a PMMA to produce a cast film. The cast film is stretched in both a proceeding direction and a width direction simultaneously by 1.0˜5.0 times in both the length and the width. By using a predetermined annealing temperature to co-coordinate shrinking of the film in both directions simultaneously, decrease of the refraction ability caused by the stretching can be controlled. To attain high uniformity of the optical characteristics of the film, the surface temperature of the film during the stretching process is controlled within a predetermined range, then the optical variation thereof is improved, and thus the following optical characteristics are achieved: R0: 0˜3 nm and Rth: ?40˜0 nm; wherein R0=?*?Te+?*?Xe+?*?Ts+?*?Xs+C1 and Rth=a*?Te+b*?Xe+c*?Ts+d*?Xs+C2.
    Type: Application
    Filed: July 19, 2016
    Publication date: January 25, 2018
    Applicant: Entire Technology Co., Ltd.
    Inventors: Peng-Yi Huang, Shi-Liang Chen, Cheng Lun Liao