-
公开(公告)号：US20180039863A1
公开(公告)日：2018-02-08
申请号：US15548396
申请日：2015-03-26
Applicant: Intel Corporation
CPC classification number: G06K9/6267 , G06K9/6232 , G06N3/0454 , G06N3/063 , G06N3/082
Abstract: A classification system is described which may include neural network decomposition logic (“NND”), which may perform classification using a neural network (“NN”). The NND may decompose a classification decision into multiple sub-decision spaces. The NND may perform classification using an NN that has fewer neurons than the NND utilizes for classification and/or which accepts feature vectors of a smaller size than are input into the NND. The NND may maintain multiple contexts for sub-decision spaces, and may switch between these in order to perform classification using the sub-decision spaces. The NND may combine results from the sub-decision spaces to decide a classification. By diving the decision into sub-decision spaces, the NND may provide for classification decisions using NNs that might otherwise be unsuitable for a particular classification decisions. Other embodiments may be described and/or claimed.
-
公开(公告)号：US09803982B2
公开(公告)日：2017-10-31
申请号：US14426604
申请日：2014-04-28
Applicant: INTEL CORPORATION , Ke Han , Ke Ding , Jingyi Ma , Yuhuan Huang
Inventor： Ke Han , Ke Ding , Jingyi Ma , Yuhuan Huang
IPC: G01C21/16
CPC classification number: G01C21/16
Abstract: Technologies for determining a user's location by a mobile computing device include detecting, based on sensed inertial characteristics of the mobile computing device, that a user of the mobile computing device has taken a physical step in a direction. The mobile computing device determines a directional heading of the mobile computing device in the direction and a variation of an orientation of the mobile computing device relative to a previous orientation of the mobile computing device at a previous physical step of the user based on the sensed inertial characteristics. The mobile computing device further applies a Kalman filter to determine a heading of the user based on the determined directional heading of the mobile computing device and the variation of the orientation and determines an estimated location of the user based on the user's determined heading, an estimated step length of the user, and a previous location of the user at the previous physical step.
-
公开(公告)号：US09568977B2
公开(公告)日：2017-02-14
申请号：US13976821
申请日：2012-12-11
Applicant: INTEL CORPORATION
Inventor： Ke Ding , Rajasekaran Andiappan , Xiaoyong Du , Ke Han
CPC classification number: G06F1/3225 , G06F1/3206 , G06F1/325 , G06F1/3275
Abstract: A method and system for context sensing is described herein. The method includes determining if sensor data obtained via a number of sensors exceed a predetermined threshold. The method also includes increasing a sampling rate of any of the sensors to obtain context data corresponding to a computing device if the sensor data exceed the threshold. The method further includes analyzing the context data to classify a context of the computing device.
Abstract translation: 本文描述了用于上下文感测的方法和系统。 该方法包括确定通过多个传感器获得的传感器数据是否超过预定阈值。 如果传感器数据超过阈值，该方法还包括增加任何传感器的采样率以获得对应于计算设备的上下文数据。 该方法还包括分析上下文数据以对计算设备的上下文进行分类。
-
公开(公告)号：US09247384B2
公开(公告)日：2016-01-26
申请号：US13976237
申请日：2012-12-28
Applicant: Intel Corporation
Inventor： Martin Junkar , Jun Su , Minnie Ho , Ke Ding
CPC classification number: H04W4/021 , G06Q10/0833 , H04L67/18 , H04M1/72572 , H04W4/023 , H04W64/00
Abstract: In one embodiment a controller comprises logic configured to receive, in the controller, a geofencing definition and input from at least one location information device, update a location of the controller using one or more location parameters from one or more location information devices, and generate a notification signal when the location of the controller indicates that the controller has crossed a threshold. Other embodiments may be described.
Abstract translation: 在一个实施例中，控制器包括被配置为在控制器中接收来自至少一个位置信息设备的地理围栏定义和输入的逻辑，其使用来自一个或多个位置信息设备的一个或多个位置参数更新控制器的位置，并且生成 当控制器的位置指示控制器已经越过阈值时的通知信号。 可以描述其他实施例。
-
公开(公告)号：US20150301581A1
公开(公告)日：2015-10-22
申请号：US13976821
申请日：2012-12-11
Applicant: INTEL CORPORATION
Inventor： Ke Ding , Rajasekaran Andiappan , Xiaoyong Du , Ke Han
IPC: G06F1/32
CPC classification number: G06F1/3225 , G06F1/3206 , G06F1/325 , G06F1/3275
Abstract: A method and system for context sensing is described herein. The method includes determining if sensor data obtained via a number of sensors exceed a predetermined threshold. The method also includes increasing a sampling rate of any of the sensors to obtain context data corresponding to a computing device if the sensor data exceed the threshold. The method further includes analyzing the context data to classify a context of the computing device.
Abstract translation: 本文描述了用于上下文感测的方法和系统。 该方法包括确定通过多个传感器获得的传感器数据是否超过预定阈值。 如果传感器数据超过阈值，该方法还包括增加任何传感器的采样率以获得对应于计算设备的上下文数据。 该方法还包括分析上下文数据以对计算设备的上下文进行分类。
-
Patent Agency Ranking
公开(公告)号：US12045986B2
公开(公告)日：2024-07-23
申请号：US17131525
申请日：2020-12-22
Applicant: Intel Corporation
Inventor： Anthony Rhodes , Manan Goel , Ke Ding
CPC classification number: G06T7/11 , G06F18/285 , G06N3/045 , G06T7/10 , G06V10/454 , G06V10/764 , G06V10/82
Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed for interactive image segmentation. An example apparatus includes an inception controller to execute an inception sublayer of a convolutional neural network (CNN) including two or more inception-atrous-collation (IAC) layers, the inception sublayer including two or more convolutions including respective kernels of varying sizes to generate multi-scale inception features, the inception sublayer to receive one or more context features indicative of user input; an atrous controller to execute an atrous sublayer of the CNN, the atrous sublayer including two or more atrous convolutions including respective kernels of varying sizes to generate multi-scale atrous features; and a collation controller to execute a collation sublayer of the CNN to collate the multi-scale inception features, the multi-scale atrous features, and eidetic memory features.
-
公开(公告)号：US20240119287A1
公开(公告)日：2024-04-11
申请号：US18545762
申请日：2023-12-19
Applicant: Intel Corporation
Inventor： Ravi H. Motwani , Ke Ding , Jian Zhang , Chendi Xue , Poovaiah Manavattira Palangappa , Rita Brugarolas Brufau , Xinyao Wang , Yu Zhou , Aasavari Dhananjay Kakne
IPC: G06N3/08
CPC classification number: G06N3/08
Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed that include interface circuitry, machine readable instructions, and programmable circuitry to at least one of instantiate or execute the machine readable instructions to associate first datapoints of a first feature with a first node, associate second datapoints of a second feature with a second node, construct a graph from the first datapoints and the second datapoints, and perform a comparison of a graph accuracy with a baseline accuracy.
-
公开(公告)号：US20210118146A1
公开(公告)日：2021-04-22
申请号：US17132810
申请日：2020-12-23
Applicant: Intel Corporation
Inventor： Anthony Rhodes , Ke Ding , Manan Goel
Abstract: Methods, systems, and apparatus for high-fidelity vision tasks using deep neural networks are disclosed. An example apparatus includes a feature extractor to extract low-level features and edge-enhanced features of an input image processed using a convolutional neural network, an eidetic memory block generator to generate an eidetic memory block using the extracted low-level features or the extracted edge-enhanced features, and an interactive segmentation network to perform image segmentation using the eidetic memory block, the eidetic memory block used to propagate domain-persistent features through the segmentation network.
-
公开(公告)号：US20210110198A1
公开(公告)日：2021-04-15
申请号：US17131525
申请日：2020-12-22
Applicant: Intel Corporation
Inventor： Anthony Rhodes , Manan Goel , Ke Ding
Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed for interactive image segmentation. An example apparatus includes an inception controller to execute an inception sublayer of a convolutional neural network (CNN) including two or more inception-atrous-collation (IAC) layers, the inception sublayer including two or more convolutions including respective kernels of varying sizes to generate multi-scale inception features, the inception sublayer to receive one or more context features indicative of user input; an atrous controller to execute an atrous sublayer of the CNN, the atrous sublayer including two or more atrous convolutions including respective kernels of varying sizes to generate multi-scale atrous features; and a collation controller to execute a collation sublayer of the CNN to collate the multi-scale inception features, the multi-scale atrous features, and eidetic memory features.
-
公开(公告)号：US10918920B2
公开(公告)日：2021-02-16
申请号：US15704838
申请日：2017-09-14
Applicant: Intel Corporation
Inventor： Ke Ding , Lakshman Krishnamurthy , Narayan Sundararajan , Xue Yang
IPC: A63B60/46 , A63B24/00 , A63B71/06 , A63B69/00 , A63B1/00 , A63B102/20 , A63B102/18 , A63B102/32 , A63B102/22 , A63B102/24
Abstract: Methods, apparatus, systems, and articles of manufacture to track movement of sports implements are disclosed herein. An example sensing unit disclosed herein is to be coupled to a sports implement. The sensing unit includes an inertial measurement unit to obtain movement data of said sports implement during a swing of said sports implement and a swing analyzer to determine a follow-through pattern of the swing of said sports implement based on the movement data.
-
-
-
-
-
-
-
-
-
Search Results
35
records
(took 0.021 seconds)
