Abstract: A method executed by a computer includes applying a correction to an acceleration value of an object at an interval; calculating an initial speed of the object by assigning the corrected acceleration value in a period to a third relational expression that is obtained by transforming a first relational expression and a second relational expression so as to obtain an initial speed from the acceleration in the period and the interval, where the first relational expression is to obtain an object position from acceleration and an initial speed, and the second relational expression represents force applied to the object due to fluctuation of the center of gravity of the object as a motion equation of a spring model; and calculating coordinate values over a horizontal plane that indicates a center of gravity of the object by assigning the corrected acceleration value and the initial speed to the first relational expression.

Abstract: A pulse wave detection apparatus detects a signal, and calculates a correlation coefficient between waveforms of the signal included in a first window and a second window having a predetermined duration, the correlation coefficient being smaller when a difference between dispersion of the amplitude value in the first window and dispersion of the amplitude value in the second window becomes larger.

Abstract: A method executed by a computer includes applying a correction to an acceleration value of an object at an interval; calculating an initial speed of the object by assigning the corrected acceleration value in a period to a third relational expression that is obtained by transforming a first relational expression and a second relational expression so as to obtain an initial speed from the acceleration in the period and the interval, where the first relational expression is to obtain an object position from acceleration and an initial speed, and the second relational expression represents force applied to the object due to fluctuation of the center of gravity of the object as a motion equation of a spring model; and calculating coordinate values over a horizontal plane that indicates a center of gravity of the object by assigning the corrected acceleration value and the initial speed to the first relational expression.

Abstract: A rare pattern that may be difficult to extract is extracted by extracting data where a rare pattern is likely to exist, and then generating the rare pattern using a degree of influence.

Abstract: The scale-parameter calculating program implements a method of calculating scale parameters, each of which is for use in normalization of a distribution of values of each of explanatory variables in calculation of inter-explanatory variable distances, to predict a value of a objective variable of an unknown case by extracting one or more known cases similar to the unknown case from known cases based on inter-case distances. The inter-case distances is obtained based on the inter-explanatory distances, each of the inter-explanatory variable distances is a distance between each of the known cases and the unknown case taken for each of explanatory variables, each of the cases includes the explanatory variables each expressed by a numerical value and the objective variable expressed by a character string. Each of the known cases is a case that has a known objective variable value while the unknown case has an unknown objective variable value.

Abstract: A computer-readable recording medium stores a case generation program that allows a computer to execute a process of generating a case having one or more design variable values and one or more object variable values corresponding to the design variable values, the process including: acquiring, from a storage section, a plurality of past cases which are obtained through a past evaluation process; predicting the object variable value of the past cases from the design variable values of the acquired past cases; calculating a prediction error and confidence as the prediction result of the past cases; selecting a reference case being a past case used as a reference of the generation based on the calculated prediction error and the confidence; determining a new design variable value based on the design variable value of the selected reference case; and determining a new case based on the new design variable value.

Abstract: The present invention has been made to calculate objective variable distribution having high reliability irrespective of the section size in an explanatory variable in which frequency drastically changes to thereby obtain highly reliable importance degree.

Abstract: A rare pattern that may be difficult to extract is extracted by extracting data where a rare pattern is likely to exist, and then generating the rare pattern using a degree of influence.

Abstract: A computer-readable storage medium storing a data analysis program is used to direct a computer to perform the procedure of: receiving one or more time series cases of free correspondence including a plurality of data points each having one piece of time data and a plurality of attribute values, and an operation level indicating how each attribute works on a state of the time series case; and performing a data analysis using a processing system depending on the operation level.

Abstract: A computer-readable recording medium stores therein a scale-parameter calculating program. The scale-parameter calculating program causes a computer to implement a method of calculating scale parameters, each of which is for use in normalization of a distribution of values of each of explanatory variables in calculation of inter-explanatory variable distances, to predict a value of a objective variable of an unknown case by extracting one or more known cases similar to the unknown case from known cases based on inter-case distances. The inter-case distances is obtained based on the inter-explanatory distances, each of the inter-explanatory variable distances is a distance between each of the known cases and the unknown case taken for each of explanatory variables, each of the cases includes the explanatory variables each expressed by a numerical value and the objective variable expressed by a character string.

Abstract: The present invention has been made to calculate objective variable distribution having high reliability irrespective of the section size in an explanatory variable in which frequency drastically changes to thereby obtain highly reliable importance degree.

Abstract: A computer-readable storage medium storing a data analysis program is used to direct a computer to perform the procedure of: receiving one or more time series cases of free correspondence including a plurality of data points each having one piece of time data and a plurality of attribute values, and an operation level indicating how each attribute works on a state of the time series case; and performing a data analysis using a processing system depending on the operation level.

Abstract: An optimum similar case extracting condition is automatically determined using a known case aggregate, and the unknown field of an unknown case aggregate is predicted from the known case aggregate using the condition. At this point, the degree of similarity depending on the distribution of the values of the unknown field in the known case aggregate is calculated and a similar case aggregate is extracted based on the degree of similarity. When it is confirmed that the degree of similarity does not satisfy a predetermined condition, the similarity calculation is stopped.