Hitachi, Ltd.

Mika Takata

Norifumi Nishikawa

Hideo Aoki

Jun Yamazaki

The data management device includes a determination unit that determines whether the secondary data generated from the source data to be processed complies with the data handling rules that use statistical information and a data processing unit that performs the processing a determination result by the determination unit. The determination unit estimates the statistical information from the source data to be processed, and determines whether the data handling rule is complied with, prior to the generation of the secondary data, based on whether the secondary data generated based on the estimated statistical information satisfies the statistical values of the statistical information. The data processing unit executes processing when it is determined that the data handling rules are complied with to generate secondary data and does not perform the processing process when it is determined that the data handling rules are not complied with.

Data management device, data management system, and data management method

Example implementations described herein are directed to systems and methods for feature preparation that receives patient feature data and determines similarity of pre-stored models with the patient feature data. In an example implementation, a database of the pre-stored models is analyzed to assess similarity indicating that feature preparation of the pre-stored models is compatible with the patient feature data. For similarity indicative of feature preparation to be utilized, the feature preparation is conducted for the patient feature data based on the pre-stored model determined to be similar. The feature preparation retrieves reusable features associate with the similar pre-stored model, where the reusable features comprise pre-calculated features of the model. A machine learning model is generated using results of the feature preparation and patient feature data; and a prediction is provided using the machine learning model.

Feature engineering method, apparatus, and system

Example implementations described herein are directed to systems and methods for selecting appropriate data samples and features in an access and privacy restricted system. Example implementations involve selection of appropriate samples (e.g. patients) which have enough data sources bringing highly important factors based on the experienced risk factors at other facilities, which is stored as metadata. The risk factor management puts more prioritization on some patients which have more data in the required data source than the other patients among all data sample candidates. The similarity of the training data sample can be a criteria to select new sample sets. Further, the risk factor management selects valuable features effectively based on metadata derived from other facilities. Example implementations help improve machine learning accuracy as part of daily system management in a facility, and can be deployed across facilities without compromising access or privacy restrictions of the data.

Data management method, apparatus and system for machine learning system

A monitoring apparatus is coupled to a sensor configured to observe a behavior of a monitoring target, and is accessible a storage device being configured to store: a database stored a phenomenon data group; stability information; and operation history information. The monitoring apparatus is configured to: calculate a stability of input phenomenon data; determine whether the stability of the input phenomenon data is a stability indicating a specific behavior; retrieve from the database, when the stability of the input phenomenon data is a stability, similar phenomenon data that is similar to the input phenomenon data; generate, by acquiring from the stability information a stability of subsequent phenomenon data continuous with the similar phenomenon data, similar case data combining the similar phenomenon data and the subsequent phenomenon data; identify, from the operation history information, operation content; and output the similar case data and the operation content.

Monitoring apparatus, monitoring method, and non-transitory recording medium

Example implementations described herein are directed to detection of historical anomalous events that are similar to currently occurring events in a transmission power system based on phasor management unit (PMU) data to provide information to grid operators with online decision support. From the high-resolution time synchronized PMU data, the historical events can be quickly retrieved and compared to the currently occurring event so that operators can be provided with remedy actions that were attempted in response to the historical events. Utilization of PMU information for such decision support may compliment operation practices relying on supervisory control and data acquisition (SCADA) measurements by allowing a much fast response to the currently occurring event. Accurate identification of similar, historical events can advise grid operators of the cause of disturbances and provide ideas for response. Implementations of the proposed technology may improve the resilience and reliability of the transmission power systems.

Growing community of inventors

San Jose, CA, United States of America

Mika Takata