-
公开(公告)号：US20230229945A1
公开(公告)日：2023-07-20
申请号：US17648447
申请日：2022-01-20
申请人： Dell Products L.P.
CPC分类号： G06N5/045 , G06K9/6284 , G06N20/20
摘要： An outlier detection mechanism is disclosed that improves transparency and explainability in machine learning models. The outlier detection mechanism can quantify, at prediction time, how a new observation differs from training observations. The outlier detection mechanism can also provide a way to aggregate outputs from decision trees by weighting the outputs of the decision trees based on their explainability.
-
公开(公告)号：US20190234866A1
公开(公告)日：2019-08-01
申请号：US16034901
申请日：2018-07-13
申请人： VIAVI Solutions Inc.
发明人： Changmeng HSIUNG
CPC分类号： G01N21/255 , G01N21/27 , G01N21/359 , G01N2021/1748 , G01N2201/129 , G06K9/00536 , G06K9/6269 , G06K9/6284
摘要： A device may receive information identifying results of a spectroscopic measurement performed on an unknown sample. The device may determine a decision boundary for a quantification model based on a configurable parameter, such that a first plurality of training set samples of the quantification model is within the decision boundary and a second plurality of training set samples of the quantification model is not within the decision boundary. The device may determine a distance metric for the spectroscopic measurement performed on the unknown sample relative to the decision boundary. The device may determine a plurality of distance metrics for the second plurality of training set samples of the quantification model relative to the decision boundary. The device may provide information indicating whether the spectroscopic measurement performed on the unknown sample corresponds to the quantification model.
-
公开(公告)号：US20190220757A1
公开(公告)日：2019-07-18
申请号：US16362866
申请日：2019-03-25
CPC分类号： G06N5/04 , G01C21/20 , G01C21/206 , G06K9/00335 , G06K9/00771 , G06K9/6274 , G06K9/6284 , G06N3/0445 , G06N3/084 , G06N20/00 , G06Q50/00
摘要： A system and method of navigating in areas. A machine learning model is trained in multiple levels with data concerning basic interpretation of sensors and with analysis of the layout of areas. The model is downloaded to a second processor which may further train the model with sensor data gathered after the download. Additional sensor data along with data from a server or other sources may be used as an input to the model and the second or another processor evaluates the model with the inputs to create outputs which determine the state of compliance. Specific applications include movement around in areas of interest. A vehicle which is controlled by a driver or by data from the machine loading model and it's analysis may be included. The model is used to calculate a path which may be displayed in visual, auditory or tactile modes.
-
公开(公告)号：US20190210387A1
公开(公告)日：2019-07-11
申请号：US16243707
申请日：2019-01-09
发明人： Shuji OTSUKA , Kazumi ARUGA
CPC分类号： B41J29/46 , G06K9/6251 , G06K9/6284 , G08B21/182 , G08B21/187
摘要： A method for warning an abnormality of a target object by using a self-organizing map prescribed by a plurality of nodes indicating a normal state of the target object includes acquiring detection data indicating a state of the target object, performing learning of the self-organizing map by using the detection data indicating a distance between a feature value and a node smaller than an abnormality threshold value predefined, storing the detection data indicating the distance larger than the abnormality threshold value in a storage unit as recorded data, and performing notification of the abnormality of the target object when the number of pieces of the recorded data stored in the storage unit reaches a predetermined number.
-
公开(公告)号：US20180268634A1
公开(公告)日：2018-09-20
申请号：US15544379
申请日：2015-07-13
发明人： Guanglu Liu , Jian Chen , Zhuming Xiao , Weirui Zheng
CPC分类号： G07D7/183 , G01N21/3563 , G06K9/4609 , G06K9/6284 , G07D7/00 , G07D7/12 , G07D7/20 , G07D7/2008 , G07D7/2041 , G07D2207/00
摘要： A folded bill recognizing method and a folded bill recognizing device are provided. The folded bill recognizing device includes: a bill input port configured to receive a to-be-recognized bill or a sample bill; a signal collecting module configured to collect a CIS image of the bill, to obtain an infrared transmission image T and an infrared reflection image F; a signal recognizing module configured to recognize whether the to-be-recognized bill has a fold; and a receiving/rejecting module configured to perform a receiving or rejecting operation on the to-be-recognized bill. The device can effectively recognize a folded bill.
-
6.发明申请公开(公告)号：US20180260656A1
公开(公告)日：2018-09-13
申请号：US15903116
申请日：2018-02-23
申请人： HITACHI, LTD.
发明人： Keiko OHKUBO , Toshiaki SUZUKI
CPC分类号： G06K9/6203 , G06F5/01 , G06F17/18 , G06K9/00536 , G06K9/6212 , G06K9/6284
摘要： The present invention includes acquiring an event point which is part of a reference waveform and which satisfies a predetermined condition, and extracting a singular point being part of the reference waveform in a period to which the acquired event point belongs, and has a value that indicates predetermined change, acquiring, when part of a target waveform corresponds to the event point, the part as a correspondence event point, and detecting a correspondence singular point in the period of the target waveform to which the correspondence event point belongs and corresponding to the singular point of the reference waveform, calculating a dissimilarity degree between a correction waveform generated based on the above four points and the reference waveform and the target waveform newly acquired, determining whether the target waveform has abnormality based on the dissimilarity degree, and outputting abnormality information.
-
公开(公告)号：US20180226154A1
公开(公告)日：2018-08-09
申请号：US15949657
申请日：2018-04-10
发明人： Metin N. Gurcan , Chandan K. Sen , Gayle Gordillo
CPC分类号： G16H50/20 , G06F19/321 , G06K9/6284 , G06T7/0016 , G06T7/62 , G06T2207/20076 , G06T2207/30088 , G16H30/20
摘要： Disclosed are systems and methods for automated monitoring of the size, area or boundary of chronic wound images. The disclosure includes use of a probability map that measures the likelihood of wound pixels belonging to granulation, slough or eschar, which can then be segmented using any standard segmentation techniques. Measurement of the wound size, area or boundary occurs automatically and without user input related to outlining, filling in, or making measurement lines over the image on a display.
-
公开(公告)号：US09984283B2
公开(公告)日：2018-05-29
申请号：US15044928
申请日：2016-02-16
发明人： Christos Davatzikos , Ke Zeng , Ali Guray Erus
CPC分类号： G06K9/00288 , G06K9/6247 , G06K9/6284 , G06K2009/4695 , G06T7/0012 , G06T7/0014 , G06T7/0016 , G06T7/337 , G06T2207/10088 , G06T2207/20081 , G06T2207/30016
摘要： Methods, systems, and computer readable media for automated detection of abnormalities in medical images are disclosed. According to a method for automated abnormality detection, the method includes receiving a target image. The method also includes deformably registering to the target image or to a common template a subset of normative images from a plurality of normative images, wherein the subset of normative images is associated with a normal variation of an anatomical feature. The method further includes defining a dictionary using the subset of normative images. The method also includes decomposing, using sparse decomposition and the dictionary, the target image. The method further includes classifying one or more voxels of the target image as normal or abnormal based on results of the sparse decomposition.
-
公开(公告)号：US09946936B2
公开(公告)日：2018-04-17
申请号：US15096483
申请日：2016-04-12
申请人： Xerox Corporation
发明人： Howard A. Mizes , Rakesh S. Kulkarni , Peter Paul
CPC分类号： G06K9/00785 , G06K9/00718 , G06K9/00812 , G06K9/3233 , G06K9/6269 , G06K9/6284 , G06T2207/30264 , H04N7/181
摘要： A method and system for parking occupancy detection comprises collecting video of the parking facility with a video capturing device, counting an occupancy of a parking facility using at least one sensor to establish a sensor occupancy count, classifying each of a plurality of parking spots as occupied or vacant with a classifier according to the classification threshold in order to establish a video occupancy count, determining a difference between the sensor occupancy count and the video occupancy count, and setting the sensor occupancy count to equal the video occupancy count if the difference between the sensor occupancy count and the video occupancy count exceeds a difference threshold.
-
公开(公告)号：US09805002B2
公开(公告)日：2017-10-31
申请号：US15152867
申请日：2016-05-12
发明人： Tsuyoshi Ide , Tetsuro Morimura , Bin Tong
CPC分类号： G06F17/18 , G01B21/30 , G06K9/00536 , G06K9/6267 , G06K9/6284 , G06K9/6298
摘要： A method providing an analytical technique introducing label information into an anomaly detection model. The method includes the steps of: inputting measurement data having an anomalous or normal label and measurement data having no label as samples; determining a similarity matrix indicating the relationship between the samples based on the samples; defining a penalty based on the similarity matrix and calculating parameters in accordance with an updating equation having a term reducing the penalty; and calculating a degree of anomaly based on the calculated parameters. The present invention also provides a program and system for detecting an anomaly based on measurement data.
-
-
-
-
-
-
-
-
-
搜索结果
447 条记录 (耗时 0.034 秒)
