Data processing apparatus and data processing method

1. A data processing apparatus comprising:

a processor programmed to execute

a data acquiring step of acquiring sampling time series data including biometric information of any one of a heat flux, a wrist temperature, an oxygen saturation level in arterial blood, and a pulse rate;

a data aggregation step of aggregating N types (N≥3) of the sampling time series data to acquire M types (M≥2 and N>M) of classification time series data, wherein the data aggregation step includes

aggregating the N types of sampling data into X types (X M) of classification time series data,

executing principal component analysis or factor analysis of the N types of sampling data to execute the aggregation, and

selecting the M types from the X types of classification time series data as the M types having M largest magnitudes of variance of the classification time series data among the X types, wherein the M types of classification time series data include at least a first principle component and a second principle component, the first principle component representing metabolic intensity and the second principle component representing automatic nerve function degree;

a classification step of classifying the M types of classification time series data into a plurality of clusters; and

an appearance data generation step of generating time series appearance data for each cluster.

2. The data processing apparatus according to claim 1 , wherein

the classification step includes plotting the M types of classification time series data in an M-dimensional space, and clustering the plots to classify the plots into the plurality of clusters.

3. The data processing apparatus according to claim 1 , wherein

the appearance data generation step includes calculating an appearance probability at each calculation time of a plurality of calculation times by averaging the classification time series data belonging to the cluster with a predetermined time width while shifting through the calculation times.

4. The data processing apparatus according to claim 1 , wherein

the processor is programmed to execute

a display control step of controlling display of the time series appearance data in a form of a dial with a time axis in a circumferential direction.

5. A data processing method comprising:

acquiring sampling time series data including biometric information of any one of a heat flux, a wrist temperature, an oxygen saturation level in arterial blood, and a pulse rate;

aggregating N types (N≥3) of the sampling time series data to acquire M types (M≥2 and N>M) of classification time series data, wherein the aggregating includes

aggregating the N types of sampling data into X types (X≥M) of classification time series data,

executing principal component analysis or factor analysis of the N types of sampling data to execute the aggregation, and

selecting the M types from the X types of classification time series data as the M types having M largest magnitudes of variance of the classification time series data among the X types, wherein the M types of classification time series data include at least a first principle component and a second principle component, the first principle component representing metabolic intensity and the second principle component representing automatic nerve function degree;

classifying the M types of classification time series data into a plurality of clusters; and

generating time series appearance data for each cluster.