Abstract:
Provided is an information processing device which is capable of suppressing a deterioration in accuracy of detecting an anomaly and accuracy of analyzing the anomaly, while suppressing an increase in an amount of data to be stored. The information processing system includes anomaly detection unit that collects event data indicating a predetermined event detected in a process of a device to be monitored, determines whether a predetermined index value related to the event exceeds a preset first threshold, and instructs enhanced monitoring of the device to be monitored and the process related to the event when the index value exceeds the first threshold, and collection instruction unit that determines an additional event being an event to be additionally monitored when the enhanced monitoring is instructed, and instructs the device to be monitored, which is subjected to the enhanced monitoring, to monitor the determined additional event.
Abstract:
In an information processing device, a provision means provides multiple terminals with a common search model. A filter acquisition means acquires, from each terminal, a filter configured by a feature value obtained using the search model. A data acquisition means acquires, from each terminal, a target time series data subjected to state estimation. A estimation means estimates a state of the terminal which outputted the target time series data, based on the target time series data and the filter.
Abstract:
A structure deterioration detection system according to the present disclosure includes: a sensing optical fiber (10) laid on a structure; a reception unit (201) that receives vibration information detected by the sensing optical fiber (10); an identification unit (202) that identifies a change pattern of a vibration characteristic of each of a plurality of points on the structure, based on the vibration information; and an analysis unit (203) that analyzes a deterioration state of at least one point among the plurality of points, based on a change pattern of a vibration characteristic of each of the plurality of points.
Abstract:
The diagnosis device specifies a progression degree relating to a first information processing device for output information output by a first detection device at a first timing with respect to the first information processing device, based on device information indicates a progression degree that represents a degree to which the information processing device is abnormal with respect to the information processing device, determines whether or not information in which a first detection device identifier of the first detection device and the specified progression degree are associated with each other is included in progression-degree information in which a detection device identifier capable of identifying a detection device and the progression degree are associated with each other; and calculates the progression degree relating to the first information processing device according to the specified progression degree when the information is determined to be included in the progression-degree information.
Abstract:
Provided is an information processing device which is capable of suppressing a deterioration in accuracy of detecting an anomaly and accuracy of analyzing the anomaly, while suppressing an increase in an amount of data to be stored. The information processing system includes anomaly detection unit that collects event data indicating a predetermined event detected in a process of a device to be monitored, determines whether a predetermined index value related to the event exceeds a preset first threshold, and instructs enhanced monitoring of the device to be monitored and the process related to the event when the index value exceeds the first threshold, and collection instruction unit that determines an additional event being an event to be additionally monitored when the enhanced monitoring is instructed, and instructs the device to be monitored, which is subjected to the enhanced monitoring, to monitor the determined additional event.
Abstract:
The purpose of the present invention is to provide a technology which assists a verifying party in ascertaining an anomaly in an event of which notification has been made. Provided is an assistance device, comprising: an acquisition unit which acquires as an associated event, from among events which take place among a plurality of elements, and with respect to elements which have been associated with an event which has been detected as an anomalous event, an event other than the anomalous event which has been associated with the elements; and a generating unit which, on the basis of the anomalous event and the associated event, generates a relational graph in which the elements are vertices, the relations among the elements are edges, the anomalous event and the associated event are respectively represented, and the associated event is displayed in a display screen in a different manner from the manner in which the anomalous event is displayed.
Abstract:
There is provided a moving-body-abnormal-nearing detection system capable of determining whether abnormal nearing between moving bodies will occur in a short processing time. A projection matrix calculation means 71 calculates a first projection matrix indicating mapping from a 3D space onto a 2D plane based on period information of a first moving body and period information of a second moving body. An abnormal nearing determination means 72 maps the period information of the first moving body to a line segment in the 2D plane by use of the first projection matrix. It then determines whether abnormal nearing between the first moving body and the second moving body will occur by determining how a circle whose center is a passage position of the second moving body and whose radius takes a threshold as a determination standard as to whether abnormal nearing will occur crosses with the line segment.
Abstract:
A learning model is trained so that a signal state can be estimated with high accuracy even in a case where a constellation on a complex plane is rotated. A learning apparatus (1) includes: an acquisition section (11) that acquires a constellation of a known state optical signal transmitted through optical fiber; a generation section (12) that generates a corrected constellation obtained by rotating the constellation on a complex plane; and a learning section (13) that uses the constellation and the corrected constellation to train a learning model.
Abstract:
A utility pole degradation detection system according to the present disclosure includes: a sensing optical fiber (10) laid on a plurality of utility poles (30); a receiving unit (201) that receives vibration information detected by the sensing optical fiber (10); an identifying unit (202) that identifies a natural frequency of each of the plurality of utility poles (30) on the basis of the vibration information; and an analyzing unit (203) that analyzes a degradation state of at least one utility pole (30) among the plurality of utility poles (30) on the basis of a natural frequency of each of the plurality of utility poles (30).
Abstract:
A peripheral aircraft selection means maps a region in a 3D space defined by a start point of period information of the aircraft of interest, a point having the coordinate values of passage position coordinates at an end point of the period information and a lower limit arrival time, and a point having the coordinate values of passage position coordinates at the end point of the period information and an upper limit arrival time onto a 2D plane by use of a first projection matrix. The peripheral aircraft selection means then selects a peripheral aircraft which can abnormally near to the aircraft of interest by determining how the resultant region crosses with a circle whose center is a passage position of the peripheral aircraft and whose radius is a determination standard threshold as to whether abnormal nearing will occur.