International Business Machines Corporation

Chunhua Tian

Chao Zhang

Wei Shan Dong

Yu Wang

Juhnyoung Lee

Jin Huang

Chun Ma

Yu Ying Wang

Junchi Yan

Hao Wang

Ying Li

Jing Jing Xiao

Shun Jiang

Wei Ding

Rong Zeng Cao

Gregory C Morris

Felipe Albertao

Ning Duan

Yue Chen

Li Li

Ju Wei Shi

Heng Cao

Wen Ting Mo

Jun Zhu

Zhong Su

Dong Wang

Jian Ye Chen

Yao Liang Chen

Zhong Xian Li

Qing Bo Wang

Jie Song

Ji Min Zhang

Rui Xiong Tian

Shenghua Bao

Feng Juan Wang

Le He

Wen Peng Xiao

Ji Jiang Song

Yong G Pan

An approach for a computer to evaluate a predictive model includes identifying features of training samples in a set of training samples. The approach selects evaluation metrics from a set of evaluation metrics as available metrics using identified features and includes determining recommended metrics using the predictive model, the available metrics, and a predetermined set of user-preferred metrics. The approach applies the predictive model created using the set of training samples to a set of test samples to calculate values of the available metrics. The approach evaluates the predictive model by using the available metrics and the values of the available metrics to evaluate the predictive model by evaluating the predictive model using the recommended metrics and the values of the recommended metrics.

Method and apparatus for evaluating predictive model

A method and an apparatus for determining a location of a mobile device. The location of a mobile device is determined accurately according to information which includes call data records of the mobile device. By employing a partial ellipse integral model, two physical world factors are taken into consideration in reducing the location uncertainty in call data records. The factors include: spatiotemporal constraints of the device's movement in the physical world and the telecommunication cell area's geometry information, which increase the accuracy of determining the location of a mobile device.

Determining a location of a mobile device

A system and method are provided. The system includes a feature calculator calculates features of a Pressure Volume diagram. The system further includes a pumpjack condition separator separates normal pumpjack conditions from abnormal pumpjack conditions using a hierarchical decision tree, the conditions being determined using the features. The system also includes a compound indicator generator generates a compound indicator when a predetermined number of at least one of features and conditions exceed respective thresholds. The system additionally includes an abnormal PV diagram indicator provides a user-perceptible indication that the PV diagram is abnormal when the compound indicator exceeds a compound indicator threshold.

Identifying abnormal pumpjack conditions

A method and apparatus for estimating a wave velocity of negative pressure wave in a fluid transportation pipeline. The method including: receiving a plurality of pressure signals from a plurality of sensors; determining time differences produced by the negative pressure wave reaching the adjacent sensors based on the received pressure signals; determining a wave source sensor segment where a wave source of the negative pressure wave is located; and estimating the wave velocities of the negative pressure wave in a non-wave source sensor segment and the wave source sensor segment.

Method and apparatus of estimating wave velocity of negative pressure wave in a fluid transportation pipeline

A method of tagging a geographical area includes obtaining, with a processing device, attribute information and mobile tracking data of a plurality of mobile objects, wherein the mobile tracking data comprises sampling time and corresponding sampling point locations of the mobile objects; converting the mobile tracking data of the plurality of mobile objects into new mobile tracking data according to the correspondence relationship between the sampling time and a time slices, wherein the new mobile tracking data include time slices and corresponding sampling point locations; and obtaining a set of attribute information of at least one geographical area with respect to the time slices based on the new mobile tracking data, wherein the at least one geographical area is obtained by clustering the sampling point locations.

Tagging geographical areas

A method and an apparatus for determining leakage volume of fluid in transportation pipelines are provided. The method comprises: obtaining the negative pressure wave signals detected by at least two pressure sensors arranged on the pipeline; determining the pressure signal at the leakage location based on the negative pressure wave signals; determining the leakage rate during a leakage period based on the pressure signal at the leakage location according to a leakage model; and determining the leakage volume of the fluid in the pipeline based on the leakage rate and the leakage period. The apparatus provided corresponds to the method described above. By using the method and apparatus described above, the leakage volume of the transportation pipelines can be obtained to help understand the leakage profile of the pipelines and thus reduce losses (FIG.).

Determining fluid leakage volume in pipelines

Disclosed are a computer-implemented method for generating a data cube from data, a system and a computer program product. The method comprises selecting a candidate granularity from a plurality of candidate granularities determined for a dimension of the data cube, where a data distribution obtained in the selected candidate granularity satisfies a predetermined condition; and generating the data cube based on the selected candidate granularity for the dimension.

Data cube generation

Method and apparatus for determining a coverage hole of a communication network along a road. The method includes: retrieving typical speed information on the basis of connection history that at least one first mobile device moves along the road; in response to detecting a connection drop when at least one second mobile device moves along the road, estimating a drop position of the at least one second mobile device on the basis of attribute information of the at least one second mobile device and the typical speed information; and determining the coverage hole on the basis of the drop position of the at least one second mobile device. In one embodiment of the present invention, there is provided a corresponding apparatus.

Determining coverage hole of communication network along road

A method and an apparatus for determining leakage volume of fluid in transportation pipelines are provided. The method comprises: obtaining the negative pressure wave signals detected by at least two pressure sensors arranged on the pipeline; determining the pressure signal at the leakage location based on the negative pressure wave signals; determining the leakage rate during a leakage period based on the pressure signal at the leakage location according to a leakage model; and determining the leakage volume of the fluid in the pipeline based on the leakage rate and the leakage period. The apparatus provided corresponds to the method described above. By using the method and apparatus described above, the leakage volume of the transportation pipelines can be obtained to help understand the leakage profile of the pipelines and thus reduce losses.

In an approach for evaluating a predictive model, a computer identifies features of training samples in a set of training samples and selects at least one evaluation metric from a set of evaluation metrics as one or more available metrics based on the identified features. The computer applies a predictive model created based on the set of training samples to a set of test samples so as to calculate values of the one or more available metrics and evaluates the predictive model by using the one or more available metrics and the values of the available metrics. With the technical solutions described with respect to the embodiments of the present invention, one or more evaluation metrics that are applicable to specific training sample features may be determined from several evaluation metrics, so that users can precisely evaluate predictive models by using the determined evaluation metrics.

Growing community of inventors

Beijing, China

Chunhua Tian