-
公开(公告)号：US20230050708A1
公开(公告)日：2023-02-16
申请号：US17402764
申请日：2021-08-16
Applicant: International Business Machines Corporation
Inventor： Shoichiro Watanabe , Kenichi Takasaki , Mari Abe Fukuda , Sanehiro Furuichi , Yasutaka Nishimura
Abstract: A computer system trains a federated learning model. A federated learning model is distributed to a plurality of computing nodes, each having a set of local training data comprising labeled data samples. Statistical data is received from each computing node that indicates the node's count of data samples for each label, and is analyzed to identify one or more computing nodes having local training data in which a label category is underrepresented beyond a threshold value with respect to data samples. Additional data samples labeled with the underrepresented labels are provided, and the computing nodes perform training. Results of training are received and are processed to generate a trained global model. Embodiments of the present invention further include a method and program product for training a federated learning model in substantially the same manner described above.
-
公开(公告)号：US20220343219A1
公开(公告)日：2022-10-27
申请号：US17302187
申请日：2021-04-27
Applicant: International Business Machines Corporation
Inventor： Kenichi Takasaki , Shoichiro Watanabe , Mari Abe Fukuda , Sanehiro Furuichi , Yasutaka Nishimura
Abstract: A computer-implemented method, a computer program product, and a computer system for parallel cross validation in collaborative machine learning. A server groups local models into groups. In each group, each local device uses its local data to validate accuracies of the local models and sends a validation result to a group leader or the server. The group leader or the server selects groups whose variances of the accuracies are not below a predetermined variance threshold. In each selected group, the group leader or the server compares an accuracy of each local model with an average value of the accuracies and randomly selects one or more local models whose accuracies do not exceed a predetermined accuracy threshold. The server obtains weight parameters of selected local models and updates the global model based on the weight parameters.
-
公开(公告)号：US20220292955A1
公开(公告)日：2022-09-15
申请号：US17198893
申请日：2021-03-11
Applicant: International Business Machines Corporation
Inventor： Kenichi Takasaki , Shoichiro Watanabe , Sanehiro Furuichi , Yasutaka Nishimura
IPC: G08G1/01
Abstract: A method for calculating traffic flow changes includes detecting a traffic event. The method further includes determining an affected area of the traffic event and determining an investigation area based on the affected area. The method further includes selecting at least one vehicle located within the investigation area and calculating a change in traffic flow due to the traffic event based on a comparison of a predicted traffic flow with a current traffic flow, wherein the current traffic flow is based on information received from the at least one vehicle. The method further includes updating the affected area based on the change in traffic flow and calculating an updated change in traffic flow based on the updated affected area when the updated affected area is larger than a predetermined threshold area.
-
公开(公告)号：US11200286B1
公开(公告)日：2021-12-14
申请号：US16878660
申请日：2020-05-20
Applicant: International Business Machines Corporation
Inventor： Sanehiro Furuichi , Shoichiro Watanabe , Kenichi Takasaki , Yasutaka Nishimura
IPC: G06F16/00 , G06F16/909 , G06F9/54 , G06F16/9035
Abstract: Described are techniques for acquiring geospatial data according to an information value. The techniques including determining a context for geospatial data to be used in an application, where the context is based on one or more external factors that influence variation of the geospatial data. The techniques further include calculating an information value of the geospatial data in the context for each of a plurality of information acquisition methods, where the plurality of information acquisition methods include respective data acquisition frequencies and respective spatial resolutions, and where the information value is based on an information loss function, an information amount, and a cost. The techniques further include selecting a first information acquisition method with a highest information value and acquiring the geospatial data using the first information acquisition method.
-
公开(公告)号：US11079238B2
公开(公告)日：2021-08-03
申请号：US16202380
申请日：2018-11-28
Applicant: International Business Machines Corporation
Inventor： Yasutaka Nishimura , Shoichiro Watanabe , Sanehiro Furuichi , Kenichi Takasaki
Abstract: A method of calculating a most probable path (MPP) comprising: with a classification module, classifying each of a plurality of origin and destination (O/D) trajectories into one of a plurality of periods of time, the classification comprising: changing a data sampling time period of any of the plurality of trajectories within the determined classification periods; with the classification module, detecting any O/D data descriptive of an aperiodic O/D trajectory using context data descriptive of the aperiodic O/D trajectory; and with the classification module, calculating a route trajectory serving as a candidate of the MPP to determine a priority O/D trajectory that matches the context data.
-
Patent Agency Ranking
公开(公告)号：US10969235B2
公开(公告)日：2021-04-06
申请号：US16190286
申请日：2018-11-14
Applicant: International Business Machines Corporation
Inventor： Sanehiro Furuichi , Yasutaka Nishimura , Kenichi Takasaki , Shoichiro Watanabe
Abstract: The method, computer program product and computer system may include computing device which may determine a destination route. The computing device may receive current travel data associated with a primary user on the destination route and determine past travel data associated with a primary user on the destination route. The computing device may calculate, in response to determining that past travel data associated with a primary user on the destination route exists, a reliability degree of the current travel data associated with a primary user on the destination route based on the past travel data associated with a primary user on the destination route. The computing device may transmit a signal to a user device, the signal providing an instruction to display features according to an abstraction level of points of interest on the destination route based on the reliability degree.
-
公开(公告)号：US10915665B2
公开(公告)日：2021-02-09
申请号：US16513076
申请日：2019-07-16
Applicant: International Business Machines Corporation
Inventor： Yasutaka Nishimura , Mari Abe Fukuda , Shoichiro Watanabe
Abstract: Position data may gradually pseudonymized by a method, comprising: generating a sequence of relative positions from a sequence of absolute positions of a moving object; randomizing the sequence of relative positions using at least a sequence of random numbers generated from at least one seed; in response to receiving an analytical job comprising the at least one seed, restoring the sequence of relative positions from the randomized sequence of relative positions; and in response to receiving an analytical job comprising both the at least one seed and at least one absolute position derived from the sequence of absolute positions, restoring the sequence of absolute positions from the randomized sequence of relative positions.
-
公开(公告)号：US10745010B2
公开(公告)日：2020-08-18
申请号：US15850533
申请日：2017-12-21
Applicant: International Business Machines Corporation
Inventor： Mari Abe Fukuda , Satoshi Hosokawa , Yasutaka Nishimura
IPC: B60W40/09 , B60W30/095 , G08G1/01 , G08G1/16 , G08G1/0967
Abstract: Methods and apparatus, including computer program products, implementing and using techniques for detecting anomalous vehicle behavior. It is determined whether a plurality of received car probes include one or more indicators of unusual behavior. An object agent corresponding to a vehicle having a car probe that includes an indicator of unusual behavior is selected. A search is performed to select one or more vehicles surrounding the vehicle having a car probe that includes an indicator of unusual behavior. An information entropy is determined from received car probes, for the vehicle having a car probe that includes an indicator of unusual behavior and for each of the selected surrounding vehicles. An anomalous point value is calculated for each vehicle, based on the determined information entropies. In response to determining that the anomalous point value for a car exceeds a pre-determined threshold, the vehicle is flagged as a vehicle exhibiting anomalous behavior.
-
公开(公告)号：US20200166345A1
公开(公告)日：2020-05-28
申请号：US16202380
申请日：2018-11-28
Applicant: International Business Machines Corporation
Inventor： Yasutaka Nishimura , Shoichiro Watanabe , SANEHIRO FURUICHI , KENICHI TAKASAKI
Abstract: A method of calculating a most probable path (MPP) comprising: with a classification module, classifying each of a plurality of origin and destination (O/D) trajectories into one of a plurality of periods of time, the classification comprising: changing a data sampling time period of any of the plurality of trajectories within the determined classification periods; with the classification module, detecting any O/D data descriptive of an aperiodic O/D trajectory using context data descriptive of the aperiodic O/D trajectory; and with the classification module, calculating a route trajectory serving as a candidate of the MPP to determine a priority O/D trajectory that matches the context data.
-
公开(公告)号：US09939274B2
公开(公告)日：2018-04-10
申请号：US14765028
申请日：2014-02-13
Inventor： Yasutaka Nishimura , Masami Tada , Akihiko Takajo , Takahito Tashiro
CPC classification number: G01C21/206 , G01C21/3484
Abstract: Providing a route guide to a destination using building information modeling (BIM) data. A request from a user for a route guide to a destination in a building is received. BIM data for the building, security information for a route, and a user profile of the user that requested the route guide to the destination is received. A route guide to the destination in the building is created, based at least on the BIM data, security information, and the user profile. Creating the route guide may be further based on use restriction information, including time, weight, operation, impassable information, information related to the method of using the facility equipment, or precaution information when using the facility equipment. The route guide may include a method of using the facility equipment in the building, a method of operating, a direction of operation, a method of unlocking or locking, or precaution information.
-
-
-
-
-
-
-
-
-
Search Results
67
records
(took 0.025 seconds)
