Data processing device, data processing method, and data processing program for evaluation an object based on a persistence diagram from time-series image data
According to one embodiment, a data processing device includes an acquisition part, and a processor. The acquisition part is configured to acquire first data including time-series image data. The processor is configured to derive first feature information based on a multidimensional array of n dimensions based on the first data acquired by the acquisition part. n is an integer not less than 3. A first axis of the multidimensional array is related to time.
1. A data processing device, comprising:
processing circuitry configured to:
acquire first data including time-series image data, wherein the first data corresponds to a temporal change of an arc of a circuit interrupter;
derive first feature information based on a multidimensional array of n dimensions based on the first data; and
control the circuit interrupter by supplying a control signal to the circuit interrupter based on the first feature information, wherein,
n is an integer not less than 3,
a first axis of the multidimensional array is related to time,
a second axis of the multidimensional array is related to a first coordinate value of a first spatial axis in space,
a third axis of the multidimensional array is related to a second coordinate value of a second spatial axis in the space, the second spatial axis crosses the first spatial axis,
a fourth axis of the multidimensional array is related to a chromaticity coordinate value,
the first feature information includes a plurality of persistent feature values in a persistence diagram,
a time of one of the plurality of persistent feature values is different from a time of another one of the plurality of persistent feature values, and
the persistence diagram corresponds to a dispersion state of at least a portion of the first data, and is derived based on values of the multidimensional array.
2. The data processing device according to claim 1 , wherein
the time-series image data includes a value related to a brightness at a position corresponding to the first and second coordinate values.
3. The data processing device according to claim 1 , wherein
the time-series image data includes a value related to a color at the position corresponding to the first and second coordinate values.
4. The data processing device according to claim 1 , wherein
the first data is subdivided into a plurality of periods, and
the persistence diagram corresponds to one of the plurality of periods.
5. The data processing device according to claim 1 , wherein
the persistence diagram includes zero-dimensional persistence.
6. The data processing device according to claim 1 , wherein
the first feature information includes a feature vector obtained by converting the persistent feature value.
7. The data processing device according to claim 1 , wherein
the processing circuitry is further configured to output the first feature information for the first data based on a result of comparing the persistent feature value and a first reference value related to the persistent feature value.
8. The data processing device according to claim 1 , wherein
the processing circuitry is further configured to extract a characteristic portion of the first data based on machine learning, and
the machine learning has the first feature information as an input.
9. The data processing device according to claim 1 , wherein
the data processing device is configured to supply a control signal to an object device based on the first feature information, and
the first data is related to the object device.
10. A data processing method, comprising:
acquiring first data including time-series image data, wherein the first data corresponds to a temporal change of an arc of a circuit interrupter;
deriving first feature information based on a multidimensional array of n dimensions based on the first data; and
controlling the circuit interrupter by supplying a control signal to the circuit interrupter based on the first feature information, wherein
n is an integer not less than 3,
a first axis of the multidimensional array is related to time,
a second axis of the multidimensional array is related to a first coordinate value of a first spatial axis in space,
a third axis of the multidimensional array is related to a second coordinate value of a second spatial axis in the space, the second spatial axis crosses the first spatial axis,
a fourth axis of the multidimensional array is related to a chromaticity coordinate value,
the first feature information includes a plurality of persistent feature values in a persistence diagram,
a time of one of the plurality of persistent feature values is different from a time of another one of the plurality of persistent feature values, and
the persistence diagram corresponds to a dispersion state of at least a portion of the first data, and is derived based on values of the multidimensional array.
11. The data processing method according to claim 10 , wherein
the time-series image data includes a value related to a brightness at a position corresponding to the first and second coordinate values.
12. The data processing method according to claim 10 , wherein
the time-series image data includes a value related to a color at the position corresponding to the first and second coordinate values.
13. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a device, cause the device to:
acquire first data including time-series image data, wherein the first data corresponds to a temporal change of an arc of a circuit interrupter;
derive first feature information based on a multidimensional array of n dimensions based on the first data; and
control the circuit interrupter by supplying a control signal to the circuit interrupter based on the first feature information, wherein
n is an integer not less than 3,
a first axis of the multidimensional array is related to time,
a second axis of the multidimensional array is related to a first coordinate value of a first spatial axis in space,
a third axis of the multidimensional array is related to a second coordinate value of a second spatial axis in the space, the second spatial axis crosses the first spatial axis,
a fourth axis of the multidimensional array is related to a chromaticity coordinate value,
the first feature information includes a plurality of persistent feature values in a persistence diagram,
a time of one of the plurality of persistent feature values is different from a time of another one of the plurality of persistent feature values, and
the persistence diagram corresponds to a dispersion state of at least a portion of the first data, and is derived based on values of the multidimensional array.
14. The non-transitory computer-readable medium according to claim 13 , wherein
the time-series image data includes a value related to a brightness at a position corresponding to the first and second coordinate values.