-
公开(公告)号：US20210042648A1
公开(公告)日：2021-02-11
申请号：US16532543
申请日：2019-08-06
发明人： Lingyun Wang , Junmei Qu , Xi Xia , Xin Xin Bai , Jin Yan Shao
IPC分类号： G06N5/04
摘要： A method, a device and a computer program product for abnormal air pollution emission prediction are proposed. In the method, a first set of features characterizing air condition in a zone is obtained. Whether the zone is subject to abnormal air pollution emission in a future first time period is determined based on the first set of features and using a first prediction classifier. In response to determining that the zone is subject to abnormal air pollution emission in the first time period, a second set of features characterizing air condition in the zone is obtained. A future second time period in which the zone is subject to abnormal air pollution emission is determined based on the second set of features and using a second prediction classifier. The second time period is included in the first time period. In this way, the abnormal air pollution emission in the zone can be accurately and efficiently predicted.
-
公开(公告)号：US11307187B2
公开(公告)日：2022-04-19
申请号：US16589714
申请日：2019-10-01
发明人： Junmei Qu , Lingyun Wang , Xin Xin Bai , Xi Xia , Jin Yan Shao
摘要： An abnormal area is detected using an initial spatial weights matrix between pairs of air quality sensors in a plurality of air quality sensors distributed across a geographical area and air quality data for each air quality sensor. The spatial weights matrix utilizes a distance between pairs of air quality sensors and wind direction through the geographical area. The initial spatial weights matrix and air quality data are used to calculate a plurality of local moran's indexes, one for each air quality sensor. The plurality of local moran's indexes are used to divide the plurality of air quality sensors into four groups. The groups are classified as proper or improper, and the proper groups are identified as abnormal areas.
-
公开(公告)号：US20220198260A1
公开(公告)日：2022-06-23
申请号：US17129998
申请日：2020-12-22
发明人： Chao Xue , Lin Dong , Xi Xia , Zhi Hu Wang
摘要： Multi-level objectives improve efficiency of multi-objective automated machine learning. A hyperband framework is established with a kernel density estimator to shrink the search space based on evaluation of lower-level objectives. A Gaussian prior assumption directly shrinks the search space to find a main objective.
-
公开(公告)号：US20210026038A1
公开(公告)日：2021-01-28
申请号：US16518205
申请日：2019-07-22
发明人： Junmei Qu , Lingyun Wang , Xi Xia , Jin Yan Shao , Xin Xin Bai
IPC分类号： G01W1/02
摘要： Embodiments of the present invention relate to methods, systems, and computer program products for correction management. In a method, a deviation may be detected by one or more processors between a first data obtained from a sensor in a plurality of sensors and a second data obtained from other sensors in the plurality of sensors, the first data and the second data being obtained in an identical or similar ambient situation. The ambient situation where the first data and second data are obtained may be identified by one or more processors. A group of raw data that is monitored under the ambient situation may be selected by one or more processors from historical raw data monitored by the plurality of sensors. The first data may be corrected by one or more processors based on the selected group of raw data. With these embodiments, data obtained from an ambient sensor under a certain ambient situation may be corrected based on historical data associated with time durations under a similar certain ambient situation.
-
公开(公告)号：US20170184561A1
公开(公告)日：2017-06-29
申请号：US14980588
申请日：2015-12-28
发明人： Xin X. Bai , Jin Dong , Hui Du , Xiao G. Rui , Xi Xia , Bao G. Xie , Wen Jun Yin , Wei Zhao
CPC分类号： G01N33/0062 , G01N2033/0068 , G01W1/10
摘要： An embodiment of the invention provides a method where an air quality forecast having an air quality turning point is received. A processor identifies an updated air quality turning point based on weather observation information. An air quality forecast at the updated air quality turning point is generated with the weather observation information and human input, which can include human knowledge from a weather expert or an air quality expert. An air quality forecast for a first time period directly prior to the updated air quality turning point is generated with the air quality forecast at the updated air quality turning point and the human input. An air quality forecast for a second time period directly after the updated air quality turning point is generated with the air quality forecast for the first time period, the air quality forecast at the updated air quality turning point, and the human input.
-
公开(公告)号：US11836644B2
公开(公告)日：2023-12-05
申请号：US16532543
申请日：2019-08-06
发明人： Lingyun Wang , Junmei Qu , Xi Xia , Xin Xin Bai , Jin Yan Shao
CPC分类号： G06N5/048 , G01W1/10 , G16Z99/00 , G01N33/0004
摘要： A method, a device and a computer program product for abnormal air pollution emission prediction are proposed. In the method, a first set of features characterizing air condition in a zone is obtained. Whether the zone is subject to abnormal air pollution emission in a future first time period is determined based on the first set of features and using a first prediction classifier. In response to determining that the zone is subject to abnormal air pollution emission in the first time period, a second set of features characterizing air condition in the zone is obtained. A future second time period in which the zone is subject to abnormal air pollution emission is determined based on the second set of features and using a second prediction classifier. The second time period is included in the first time period. In this way, the abnormal air pollution emission in the zone can be accurately and efficiently predicted.
-
公开(公告)号：US20220188620A1
公开(公告)日：2022-06-16
申请号：US17117458
申请日：2020-12-10
发明人： Chao Xue , Lin Dong , Xi Xia , Zhi Hu Wang
IPC分类号： G06N3/08 , G06F16/2458 , G06N5/04
摘要： A method for optimizing a neural network architecture by estimating an inference time for each operator in the neural network architecture is provided. The method may include determining a benchmark time for at least one single-path architecture out of a plurality of single-path architectures associated with the neural network by sampling the at least one single-path architecture from the neural network, wherein the at least one single-path architecture comprises one or more operators. The method may further include, based on the benchmark time for the at least one single-path architecture, determining an estimated inference time for an operator, wherein determining the estimated inference time for the operator comprises, applying an operator function, wherein the operator function comprises a function based on a difference between the benchmark time associated with the at least one single-path architecture and the estimated latency of the neural network.
-
公开(公告)号：US10444211B2
公开(公告)日：2019-10-15
申请号：US14980588
申请日：2015-12-28
发明人： Xin X. Bai , Jin Dong , Hui Du , Xiao G. Rui , Xi Xia , Bao G. Xie , Wen Jun Yin , Wei Zhao
摘要： An embodiment of the invention provides a method where an air quality forecast having an air quality turning point is received. A processor identifies an updated air quality turning point based on weather observation information. An air quality forecast at the updated air quality turning point is generated with the weather observation information and human input, which can include human knowledge from a weather expert or an air quality expert. An air quality forecast for a first time period directly prior to the updated air quality turning point is generated with the air quality forecast at the updated air quality turning point and the human input. An air quality forecast for a second time period directly after the updated air quality turning point is generated with the air quality forecast for the first time period, the air quality forecast at the updated air quality turning point, and the human input.
-
公开(公告)号：US20180313649A1
公开(公告)日：2018-11-01
申请号：US15807332
申请日：2017-11-08
发明人： Xin Xin Bai , Xin Jie Lv , Xiao Guang Rui , Xi Xia , Jian Yao , Wen Jun Yin , Wei Zhao , Yu Xin Zhao
摘要： A method for tracking and identifying a polluted air mass's transmission trajectory in real 3-D space. In one aspect, a polluted air mass's transmission path identification is based on a monitoring of PM2.5 concentration in cubic volumes of an air mass. The method computes a transmission path of polluted air that considers wind-pressure conversion, the displacement estimation with mass concentration, and planetary boundary layer (PBLP height constraint) for 3-D cubic grids. The resultant determination of a polluted air mass's transmission trajectory in real 3-D space generates more practical and reliable results for intensive knowledge of the transport pathways and potential pollution sources in real 3-D space.
-
公开(公告)号：US20180239057A1
公开(公告)日：2018-08-23
申请号：US15439395
申请日：2017-02-22
发明人： Xin X. Bai , Jin Dong , Hui Du , Xiao G. Rui , Lingyun Wang , Xi Xia , Wen Jun Yin , Wei Zhao
CPC分类号： G01W1/10 , G01N33/0062 , G01W1/02
摘要： A computer-implemented method includes comparing, by a computer processor, meteorological conditions of a first duration of time to meteorological conditions of at least one second duration of time. The beginning of the second duration of time is determined based at least in part on a first event relating to air quality conditions. The end of the second duration of time is determined based at least in part on a second event relating to air quality conditions. The method also includes outputting a forecast of air quality conditions for the first duration of time based at least in part on the comparing.
-
-
-
-
-
-
-
-
-
搜索结果
17 条记录 (耗时 0.019 秒)
