International Business Machines Corporation

Beijing Institute of Technology

Siemens Ltd., China

Chang Li

Wei Shan Dong

Peng Gao

Chun Ma

Xin Zhang

Jian Ding

Guo Qiang Hu

Ren Jie Yao

Ting Yuan

Jing Min Xu

Fan Jing Meng

Xu Liang Li

Yu Wang

Ning Duan

Chao Zhang

Jun Chi Yan

Junchi Yan

Renjie Yao

Wei Sun

Edith H Stern

Bo Yang

Zhi Hu Wang

Lin Y Yang

Zhi Jun Wang

Min Li

Dong Sheng Li

Ajay Arvind Apte

Wen Han Luo

Han Wang

Stephen Mingyu Chu

Joseph Paul Wigglesworth

Weipeng Zhang

Xue Jun Zhuo

Xuejun Zhuo

Jian Li

Qi Cheng Li

Xin Zhou

Shao Chun Li

Kai Yang

Soumitra Sarkar

Min Gong

Qiang Huang

Guo Chen

Wen Ji Huang

Shengjie Wang

Philip L Schwartz

Qing Shi

Xu Xian Hua

Xiu Fang Zhu

Peter J Arterburn

Kateryna Svynarenko

Mengchao Ma

Mingjie Zou

Fukuda Toshio

John C Anderson

Provided are an electric motor, a laminated iron core, and a manufacturing method. In. an embodiment, the method includes S1: introducing inert gas into an additive manufacturing printing apparatus, pouring silicon steel metal particles into a fanning cylinder of the apparatus, and performing laser scanning on the silicon steel metal particles to gradually melt the silicon steel metal particles into at least one silicon steel metal layer; and S2: continuing to pour silicon steel metal particles into the forming cylinder, and stopping performing laser scanning on the silicon steel metal particles or reducing the laser power executing the laser scanning, such that the silicon steel metal particles do not entirely melt and form an insulating layer. Execution of steps S1 and S2 is alternated until a laminated iron core having a plurality of alternating silicon steel metal layers and insulating layers is formed.

Electric motor, laminated iron core and manufacturing method therefor

A waist imitating device of robotic rat based on multiple-connecting-rod transmission comprises a pitch parallel connecting rod group () and a yaw parallel connecting rod group (). The pitch parallel connecting rod group () and the yaw parallel connecting rod group () are respectively connected with a front joint and a back joint of a waist of a robotic rat. Under the drive of a first motor (), crank connecting rods drive the yaw parallel connecting rod group () such that left-right yaw motion of the waist of the robotic rat relative to wheels and forelimbs can be achieved. Under the drive of a second motor (), crank connecting rods drive the pitch parallel connecting rod group () such that upper-down pitch motion of the waist of the robotic rat relative to the wheels and the forelimbs can be achieved.

Waist imitating device of robotic rat based on multiple-connecting-rod transmission

Methods and apparatus, including computer program products, implementing and using techniques for identifying a driver of a vehicle. Measurement values representing the movement of a vehicle are received from one or more sensors measuring features relating to the movement of the vehicle. Instantaneous dimensions for measuring driver identification are defined. For each dimension statistical features within a given time frame are calculated and a feature map is built, including the time frame and the statistical features. A set of driving features is extracted from the feature map. The set of extracted driving features is compared with previously extracted sets of driving features to create a set of similarity metrics between two drivers. A classification model is trained based on the similarity metrics and is used with the similarity metrics to determine whether data pertaining to a new trip segment should be associated with a known or unknown driver.

Method and apparatus for driver identification leveraging telematics data

Systems and methods for training a neural network model are disclosed. In the method, training data is obtained by a deep neural network (DNN) first, the deep neural network comprising at least one hidden layer. Then features of the training data are obtained from a specified hidden layer of the at least one hidden layer, the specified hidden layer being connected respectively to a supervised classification network for classification tasks and an autoencoder based reconstruction network for reconstruction tasks. And at last the DNN, the supervised classification network and the reconstruction network are trained as a whole based on the obtained features, the training being guided by the classification tasks and the reconstruction tasks.

Feature extraction using multi-task learning

Determining a characteristic of a configuration file that is used to discover configuration files in a target machine, a computer identifies, using information associated with a configuration item of a machine, a candidate configuration file related to the configuration item of the machine, from among a plurality of files from the machine. The computer extracts a value of a feature of the candidate configuration file and aggregates the candidate configuration file with a second candidate configuration file related to the same configuration item identified from among a plurality of files from a second machine, based on the extracted value. The computer then determines a configuration file related to the configuration item from among the aggregated candidate configuration files based on a result of the aggregation, and determines a characteristic of the configuration file related to the configuration item.

Determining characteristics of configuration files

Techniques for neural network training are provided. One computer-implemented method comprises: obtaining, by an electronic device operatively coupled to a processing unit, based on a similarity between two images, a first image and a second image. The computer-implemented method also comprises training, by the electronic device, a neural network based on the first image and the second image such that a distance between a first vector and a second vector generated respectively from the first image and the second image in the trained neural network is associated with the similarity.

Neural network training

Embodiments are described for minimizing a wait time for a rider after sending a ride request for a vehicle. An example computer-implemented method includes receiving a ride request, the request being for travel from a starting location to a zone in a geographic region during a specified timeslot. The method further includes predicting travel demand based on a number of ride requests in the zone during the specified timeslot. The method further includes requesting transport of one or more vehicles to the zone in response to the predicted number of ride requests when the travel demand is predicted to exceed a number of vehicles in the zone during the specified timeslot.

Neural network computing systems for predicting vehicle requests

A method, system, and computer program product, include receiving a plurality of requests for dynamic context information from a plurality of road segments, determining whether the plurality of road segments are included in a same cluster of road segments in a road network generated by clustering road segments in the road network based on connectivity of the road network; and consolidating the plurality of requests to generate a consolidated request in response to determining that the plurality of road segments are included in the same cluster.

System, method and computer program product for consolidation of requests for access to dynamic map

A method of generating a predictor to classify data includes: training each of a plurality of first classifiers arranged in a first level on current training data; operating each classifier of the first level on the training data to generate a plurality of predictions; combining the current training data with the predictions to generated new training data; and training each of a plurality of second classifiers arranged in a second level on the new training data. The first classifiers are classifiers of different classifier types, respectively and the second classifiers are classifiers of the different classifier types, respectively.

Multi-layer information fusing for prediction

In one embodiment, a computer-implemented method includes receiving training data including a plurality of records, each record having a plurality of attributes. The training data is horizontally parallelized across two or more processing elements. This horizontal parallelizing includes dividing the training data into two or more subsets of records; assigning each subset of records to a corresponding processing element of the two or more processing elements; transmitting each subset of records to its assigned processing element; and sorting, at the two or more processing elements, the two or more subsets of records to two or more candidate leaves of a decision tree. The output from horizontally parallelizing is converted into input for vertically parallelizing the training data. The training data is vertically parallelized across the two or more processing elements. The decision tree is grown based at least in part on the horizontally parallelizing, the converting, and the vertically parallelizing.

Scalable streaming decision tree learning

A system, a computer readable storage medium, and a method for detecting insurance fraud or for comparing references use visual analytics-based techniques. The method can include identifying a scratch and a scratch location on a vehicle in a 3-dimensional rendering in comparison to a base image or in comparison to a stored image in a database, comparing one or more features of the scratch such as color features of the scratch in the scratch location in comparison to the scratch location or comparing one or more texture features of the scratch in the scratch location in comparison to the scratch location in the base image or the stored image. The method can further generate a similarity calculation based on the one or more comparisons for the scratch, the scratch location, the one or more scratch features of the scratch and presents a result in response to the similarity calculation.

Visual analytics based vehicle insurance anti-fraud detection

A mechanism is provided in a data processing system for distributed tree learning. A source processing instance distributes data record instances to a plurality of model update processing items. The plurality of model update processing items determine candidate leaf splitting actions in a decision tree in parallel based on the data record instances. The plurality of model update processing items send the candidate leaf splitting actions to a plurality of conflict resolve processing items. The plurality of conflict resolve processing items identifies conflict leaf splitting actions. The plurality of conflict resolve processing items applies tree structure changes to the decision tree in the plurality of model update processing items.

Horizontal decision tree learning from very high rate data streams with horizontal parallel conflict resolution

Growing community of inventors

Beijing, China

Chang Li