Information processing apparatus, program, and information processing method

1. An information processing apparatus for training a prediction model for predicting a label to be allocated to a prediction target explanatory variable set, the information processing apparatus comprising program instructions executable by a processor to cause the processor to perform a method comprising:

acquiring one or more sets of training data, each of the one or more sets of training data comprising at least one set of explanatory variables and a label allocated to the at least one explanatory variable set, wherein respective labels comprise respective maintenance index control (MCI) labels for road conditions of respective portions of road, wherein respective MCI labels are associated with a crack ratio, a rutting amount, and an unevenness amount of a road surface;

extracting a plurality of explanatory variable subsets from the at least one set of explanatory variables by:

extracting at least luminance information and gradient information for at least a portion of the plurality of explanatory variable subsets from the at least one set of explanatory variables; and

extracting, as the plurality of explanatory variable subsets, a plurality of data sequences continuous in time series, wherein the plurality of data sequences partially overlap one another in a time series;

generating a feature vector, concerning each of the plurality of explanatory variable subsets, comprising a plurality of feature values;

training a prediction model, where the prediction model is trained utilizing the training data where the plurality of explanatory variable subsets is reflected on a label predicted by the prediction model to be allocated to a prediction target explanatory variable set with each of the plurality of explanatory variable subsets weighted respectively, wherein training the prediction model further comprises:

allocating a different weight coefficient to each of the plurality of explanatory variable subsets;

utilizing a regression vector comprising a plurality of regression coefficients respectively corresponding to the plurality of feature values of the feature vector and the weight coefficient of each of the plurality of explanatory variable subsets;

executing Bayesian inference using prior distributions of the regression vector, the weight coefficients, and the training data;

utilizing an objective function to be minimized for training the prediction model, the objective function comprising a weighted sum of terms indicating errors between labels predicted for the plurality of explanatory variable subsets based on the feature vector and the regression vector, and the label allocated to the at least one explanatory variable set; and

outputting a posterior probability distribution of the regression vector and the weight coefficients as a training result;

acquiring a prediction target data set comprising a prediction target explanatory variable set, wherein the prediction target data set comprises image data photographed by a drive recorder mounted on a passenger vehicle, acceleration data measured by an acceleration sensor mounted on the passenger vehicle, and position data measured by a global positioning system (GPS) unit attached to the passenger vehicle; and

predicting a MCI label corresponding to the prediction target explanatory variable set based on the prediction model, wherein the MCI label is displayed to a display screen.