Estimation device, estimation method, and estimation program
An estimation device includes processing circuitry configured to acquire time-series data of a pupil diameter during work of a subject of work performance estimation, smooth the time-series data of the pupil diameter of the subject by a first time window, smooth the time-series data of the pupil diameter by a second time window that is a time window larger than the first time window, calculate a difference between time-series data of the pupil diameter smoothed by the first time window and time-series data of the pupil diameter smoothed by the second time window, and estimate a level of work performance of the subject based on a magnitude of the difference between the time-series data of the pupil diameter smoothed by the first time window and the time-series data of the pupil diameter smoothed by the second time window, and output a result of the estimation.
1. An estimation device comprising:
processing circuitry configured to:
acquire time-series data of a pupil diameter during work of a subject of work performance estimation;
smooth the time-series data of the pupil diameter of the subject by a first time window;
smooth the time-series data of the pupil diameter by a second time window that is a time window larger than the first time window;
calculate a difference between time-series data of the pupil diameter smoothed by the first time window and time-series data of the pupil diameter smoothed by the second time window; and
estimate a level of work performance of the subject based on a magnitude of the difference between the time-series data of the pupil diameter smoothed by the first time window and the time-series data of the pupil diameter smoothed by the second time window, and output a result of the estimation.
2. The estimation device according to claim 1 ,
wherein the processing circuitry is further configured to
estimate that the larger the difference between the time-series data of the pupil diameter smoothed by the first time window and the time-series data of the pupil diameter smoothed by the second time window, the lower the work performance of the subject.
3. The estimation device according to claim 1 ,
wherein the processing circuitry is further configured to estimate that the smaller the difference between the time-series data of the pupil diameter smoothed by the first time window and the time-series data of the pupil diameter smoothed by the second time window, the higher the work performance of the subject.
4. The estimation device according to claim 1 ,
wherein the pupil diameter during work of the subject is a pupil diameter measured by an infrared camera or a visible light camera.
5. The estimation device according to claim 1 , wherein the processing circuitry is further configured to calculates a first value that is an average value of absolute values of values obtained by first differentiating the time-series data of the pupil diameter smoothed by the first time window, calculate a second value that is an average value of absolute values of values obtained by first differentiating the time-series data of the pupil diameter smoothed by the second time window, and set an absolute value of a difference between the first value and the second value as the difference.
6. The estimation device according to claim 1 ,
wherein the processing circuitry is further configured to
set an average value of absolute values of differences between the time-series data of the pupil diameter smoothed by the first time window and the time-series data of the pupil diameter smoothed by the second time window at each time as the difference.
7. The estimation device according to claim 1 , wherein the processing circuitry is further configured to exclude, from the time-series data of the pupil diameter, time-series data of the pupil diameter in a period in which a value of the pupil diameter is equal to or less than a predetermined threshold.
8. An estimation method performed by an estimation device, the estimation method comprising:
acquiring time-series data of a pupil diameter during work of a subject of work performance estimation;
smoothing the time-series data of the pupil diameter of the subject by a first time window;
smoothing the time-series data of the pupil diameter by a second time window that is a time window larger than the first time window;
calculating a difference between time-series data of the pupil diameter smoothed by the first time window and time-series data of the pupil diameter smoothed by the second time window; and
estimating a level of work performance of the subject based on a magnitude of the difference between the time-series data of the pupil diameter smoothed by the first time window and the time-series data of the pupil diameter smoothed by the second time window, and outputs a result of the estimation.
9. A non-transitory computer-readable recording medium storing therein an estimation program that causes a computer to execute a process comprising:
acquiring time-series data of a pupil diameter during work of a subject of work performance estimation;
smoothing the time-series data of the pupil diameter of the subject by a first time window;
smoothing the time-series data of the pupil diameter by a second time window that is a time window larger than the first time window;
calculating a difference between time-series data of the pupil diameter smoothed by the first time window and time-series data of the pupil diameter smoothed by the second time window; and
estimating a level of work performance of the subject based on a magnitude of the difference between the time-series data of the pupil diameter smoothed by the first time window and the time-series data of the pupil diameter smoothed by the second time window, and outputs a result of the estimation.