Patents by Inventor Yonghua Lin
Yonghua Lin 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: 11568220Abstract: The present disclosure relates to methods, systems, and computer program products for implementing a deep neural network in a field-programmable gate array (FPGA). In response to receiving a network model describing a deep neural network, a plurality of layers associated with the deep neural network may be determined. With respect to a layer in the plurality of layers, a parallelism factor for processing operations associated with the layer simultaneously by processing elements in an FPGA may be determined based on a workload associated with the layer and a configuration of the FPGA.Type: GrantFiled: July 25, 2018Date of Patent: January 31, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Junsong Wang, Chao Zhu, Yonghua Lin, Yan GY Gong
-
Patent number: 11562225Abstract: Methods and systems for training a machine learning model include training a machine learning model using training data. A status of the machine learning model's training is determined based on an accuracy curve of the machine learning model over the course of the training. Parameters of the training are adjusted based on the status. Training of the machine learning model is completed using the adjusted parameters.Type: GrantFiled: November 26, 2018Date of Patent: January 24, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Chao Xue, Rong Yan, Yonghua Lin, Yonggang Hu, Yu Song
-
Patent number: 11386645Abstract: According to one embodiment, a method, computer system, and computer program product for generating anchors and selecting feature maps for a multi-scale object detection program based on analysis of the dataset is provided. The present invention may include generating a scale distribution of one or more scales of ground-truth objects, and, based on the scale distribution, dividing the effective scale range into a number of anchors greater than zero; furthermore, the invention may include generating a ratio distribution of ratios of the ground-truth objects; based on the ratio distribution, generating a ratio for at least one of the number of anchors; determining a template scale of one or more feature maps; and assigning the number of anchors to the feature maps based on the relative size of a scale of an anchor matching the relative size of a template scale of a feature map.Type: GrantFiled: July 1, 2020Date of Patent: July 12, 2022Assignee: International Business Machines CorporationInventors: Junsong Wang, Jie Zhang, Qing Wang, Yonghua Lin
-
Patent number: 11373407Abstract: A computer-implemented method for attention generation is provided. In this method, a plurality of image frames can be obtained from a video stream. An original attention for a first image frame of the plurality of image frames can be generated. Then, at least one interested area can be identified in the first image frame. A local attention for each of the at least one interested area can be generated. Moreover, a total attention for the first image frame can be generated based on the original attention of the first image frame and the local attention of each of the at least one interested area.Type: GrantFiled: October 25, 2019Date of Patent: June 28, 2022Assignee: International Business Machines CorporationInventors: Qing Wang, Shi Lei Zhang, Yonghua Lin
-
Publication number: 20220004759Abstract: According to one embodiment, a method, computer system, and computer program product for generating anchors and selecting feature maps for a multi-scale object detection program based on analysis of the dataset is provided. The present invention may include generating a scale distribution of one or more scales of ground-truth objects, and, based on the scale distribution, dividing the effective scale range into a number of anchors greater than zero; furthermore, the invention may include generating a ratio distribution of ratios of the ground-truth objects; based on the ratio distribution, generating a ratio for at least one of the number of anchors; determining a template scale of one or more feature maps; and assigning the number of anchors to the feature maps based on the relative size of a scale of an anchor matching the relative size of a template scale of a feature map.Type: ApplicationFiled: July 1, 2020Publication date: January 6, 2022Inventors: Junsong Wang, Jie Zhang, Qing Wang, Yonghua Lin
-
Patent number: 11164078Abstract: A method, computer system, and computer program product for model selection for training a new dataset is provided. The present invention may include choosing a model from a set of models to be evaluated for training the new dataset, selecting a sample input from a subset of the new dataset, calculating a model activation score for each of the sample inputs in the chosen model, calculating an accumulated model activation score for the chosen model, depending on the model activation score of each of the sample inputs in the chosen model, calculating an accumulated model activation score for each model from the set of models to be evaluated for training the new dataset, and selecting the model for training the new dataset with the highest accumulated model activation score.Type: GrantFiled: November 8, 2017Date of Patent: November 2, 2021Assignee: International Business Machines CorporationInventors: Ke Jin, Yubo Li, Yonghua Lin, Junsong Wang, Qing Wang
-
Patent number: 11164047Abstract: The present disclosure provides a computer-implemented method, computer system and computer program product for object detection. According to the computer-implemented method, a first object can be classified to be a first category based on detection data acquired in a detection area. Then, a confidence score for the first category can be calculated based on historical detection data of the detection area, wherein the confidence score presents possibility degree of at least one object of the first category existing in the detection area. Whether classification of the first object is abnormal can be determined based on the confidence score.Type: GrantFiled: July 22, 2019Date of Patent: November 2, 2021Assignee: International Business Machines CorporationInventors: Ke Wei Sun, Junsong Wang, Yan GY Gong, Rong Yan, Yonghua Lin, Jie Zhang
-
Patent number: 11022669Abstract: A method comprises receiving a first received signal strength indicator (RSSI) of a first beacon in an array of beacons and receiving a second RSSI of a second beacon in an array of beacons, calculating a RSSI of the array (r) as a function of the first RSSI and the second RSSI, retrieving a calibrated RSSI value of the array (r?) from a memory, determining whether r>r?, and outputting a signal to a user device responsive to determining that r>r?.Type: GrantFiled: July 8, 2019Date of Patent: June 1, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: YuBo Li, Yonghua Lin, Qing Wang, Wei Dong Wang, Chao Xue
-
Publication number: 20210124931Abstract: A computer-implemented method for attention generation is provided. In this method, a plurality of image frames can be obtained from a video stream. An original attention for a first image frame of the plurality of image frames can be generated. Then, at least one interested area can be identified in the first image frame. A local attention for each of the at least one interested area can be generated. Moreover, a total attention for the first image frame can be generated based on the original attention of the first image frame and the local attention of each of the at least one interested area.Type: ApplicationFiled: October 25, 2019Publication date: April 29, 2021Inventors: QING WANG, Shi Lei Zhang, Yonghua Lin
-
Patent number: 10943204Abstract: A computer implemented method of detecting excessive customer wait times is provided. The method includes taking a headcount in a digital image obtained by a digital video camera of a monitored area, counting the number of bodies in the digital image, and rectifying the number of heads with the number of bodies to obtain a total count of persons. The method further includes determining which persons are moving and subtracting the moving persons from the total count of persons to obtain a still count, and determining which persons are workers and subtracting the workers from the still count to identify customers in the monitored area and obtain a customer count. The method further includes identifying the number of queues present in the monitored area, assigning each customer to a queue, and determining the wait time for each of the identified customers in each of the identified queues.Type: GrantFiled: January 16, 2019Date of Patent: March 9, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Chang Xu, Ke Wei Sun, Junsong Wang, Yonghua Lin, Yan Gy Gong
-
Publication number: 20210064639Abstract: A computer-implemented method for data augmentation is provided according an embodiment of the present disclosure. In the method, a first feature vector for input data may be obtained based on a first model. The input data may be clustered to a plurality of clusters. For each of the clusters, a second feature vector may be obtained based on the first model. Then, a similarity between the first feature vector and the second feature vector may be estimated for each of the clusters. At least one cluster of the plurality of clusters for which the similarity is lower than a threshold may be determined. Moreover, data augmentation may be performed to the at least one cluster.Type: ApplicationFiled: September 3, 2019Publication date: March 4, 2021Inventors: Qing Wang, Shi Lei Zhang, Yonghua Lin
-
Publication number: 20210027106Abstract: The present disclosure provides a computer-implemented method, computer system and computer program product for object detection. According to the computer-implemented method, a first object can be classified to be a first category based on detection data acquired in a detection area. Then, a confidence score for the first category can be calculated based on historical detection data of the detection area, wherein the confidence score presents possibility degree of at least one object of the first category existing in the detection area. Whether classification of the first object is abnormal can be determined based on the confidence score.Type: ApplicationFiled: July 22, 2019Publication date: January 28, 2021Inventors: Ke Wei Sun, Junsong Wang, Yan GY Gong, Rong Yan, Yonghua Lin, Jie Zhang
-
Publication number: 20200226523Abstract: A computer implemented method of detecting excessive customer wait times is provided. The method includes taking a headcount in a digital image obtained by a digital video camera of a monitored area, counting the number of bodies in the digital image, and rectifying the number of heads with the number of bodies to obtain a total count of persons. The method further includes determining which persons are moving and subtracting the moving persons from the total count of persons to obtain a still count, and determining which persons are workers and subtracting the workers from the still count to identify customers in the monitored area and obtain a customer count. The method further includes identifying the number of queues present in the monitored area, assigning each customer to a queue, and determining the wait time for each of the identified customers in each of the identified queues.Type: ApplicationFiled: January 16, 2019Publication date: July 16, 2020Inventors: Chang Xu, Ke Wei Sun, Junsong Wang, Yonghua Lin, Yan GY Gong
-
Publication number: 20200193231Abstract: Embodiments of embodiments of the present invention relate to generation of a training model using virtual dataset and probe training models. A computer-implemented method comprises: receiving, by a device operatively coupled to one or more processors, a user dataset for training; testing, by the device, the user dataset with one or more probe training models; and in response to a result of the testing being similar to an existing result of running the one or more probe training models on an existing virtual dataset, grouping, by the device, the user dataset with the existing virtual dataset.Type: ApplicationFiled: December 17, 2018Publication date: June 18, 2020Inventors: Chao Xue, Rong Yan, Yonghua Lin, Yonggang Hu
-
Publication number: 20200167639Abstract: Methods and systems for training a machine learning model include training a machine learning model using training data. A status of the machine learning model's training is determined based on an accuracy curve of the machine learning model over the course of the training. Parameters of the training are adjusted based on the status. Training of the machine learning model is completed using the adjusted parameters.Type: ApplicationFiled: November 26, 2018Publication date: May 28, 2020Inventors: Chao Xue, Rong Yan, Yonghua Lin, Yonggang Hu, Yu Song
-
Patent number: 10656962Abstract: A method, system and computer program product for accelerating a deep neural network (DNN) in a field-programmable gate array (FPGA) are disclosed. The method includes receiving a DNN net file and weights, converting the received DNN net file to one or more source files, generating an executable FPGA bit file using the one or more source files, and downloading the executable FPGA bit file from the DNN conversion platform to the FPGA. Converting of the received DNN net file and the weights to the one or more source files can further include analyzing the DNN net file to identify a plurality of neural layers, decomposing one or more neural layers of the plurality of neural layers to one or more operation blocks, instantiating the one or more source files, based on the one or more operation blocks.Type: GrantFiled: October 21, 2016Date of Patent: May 19, 2020Assignee: International Business Machines CorporationInventors: Yonghua Lin, Jianbin Tang, Junsong Wang
-
Publication number: 20200034696Abstract: The present disclosure relates to methods, systems, and computer program products for implementing a deep neural network in a field-programmable gate array (FPGA). In response to receiving a network model describing a deep neural network, a plurality of layers associated with the deep neural network may be determined. With respect to a layer in the plurality of layers, a parallelism factor for processing operations associated with the layer simultaneously by processing elements in an FPGA may be determined based on a workload associated with the layer and a configuration of the FPGA.Type: ApplicationFiled: July 25, 2018Publication date: January 30, 2020Inventors: Junsong Wang, Chao Zhu, Yonghua Lin, Yan GY Gong
-
Publication number: 20190331753Abstract: A method comprises receiving a first received signal strength indicator (RSSI) of a first beacon in an array of beacons and receiving a second RSSI of a second beacon in an array of beacons, calculating a RSSI of the array (r) as a function of the first RSSI and the second RSSI, retrieving a calibrated RSSI value of the array (r?) from a memory, determining whether r>r?, and outputting a signal to a user device responsive to determining that r>r?.Type: ApplicationFiled: July 8, 2019Publication date: October 31, 2019Inventors: YuBo Li, Yonghua Lin, Qing Wang, Wei Dong Wang, Chao Xue
-
Patent number: 10386446Abstract: A method comprises receiving a first received signal strength indicator (RSSI) of a first beacon in an array of beacons and receiving a second RSSI of a second beacon in an array of beacons, calculating a RSSI of the array (r) as a function of the first RSSI and the second RSSI, retrieving a calibrated RSSI value of the array (r?) from a memory, determining whether r>r?, and outputting a signal to a user device responsive to determining that r>r?.Type: GrantFiled: July 27, 2017Date of Patent: August 20, 2019Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: YuBo Li, Yonghua Lin, Qing Wang, Wei Dong Wang, Chao Xue
-
Patent number: 10386445Abstract: A method comprises receiving a first received signal strength indicator (RSSI) of a first beacon in an array of beacons and receiving a second RSSI of a second beacon in an array of beacons, calculating a RSSI of the array (r) as a function of the first RSSI and the second RSSI, retrieving a calibrated RSSI value of the array (r?) from a memory, determining whether r>r?, and outputting a signal to a user device responsive to determining that r>r?.Type: GrantFiled: July 27, 2017Date of Patent: August 20, 2019Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: YuBo Li, Yonghua Lin, Qing Wang, Wei Dong Wang, Chao Xue