Fujitsu Corporation

Kazuho Maeda

Akihiro Inomata

Tatsuya Mori

Yoshinori Yaginuma

Daisuke Uchida

Masahiro Hara

Toshiaki Funakubo

Jun Maeda

Yasuyuki Nakata

Masato Sakata

Shinji Hotta

Michihiko Aki

Takuro Oya

Shiho Washizawa

A meal detection method executed by a processor of a computer, the meal detection method includes acquiring first sensing data from a first sensor configured to detect a motion of an arm of a target person; acquiring second sensing data from a second sensor configured to detect a heart rate of the target person; calculating a first evaluation value indicating likelihood that a meal is being performed based on a first feature amount extracted from the first sensing data; calculating a second evaluation value indicating likelihood that the meal is performed based on a second feature amount extracted from the second sensing data; and determining whether the target person has eaten the meal or not, based on the first evaluation value and the second evaluation value.

Meal detection method, meal detection system, and storage medium

A meal detection method executed by a processor of a computer, the meal detection method includes acquiring first sensing data from a first sensor configured to detect a motion of an arm of a target person; acquiring second sensing data from a second sensor configured to detect a heart rate of the target person; setting a motion section in which a specific motion by the arm of the target person is executed at least twice or more based on the first sensing data; and determining whether a meal is performed in a section including at least a portion of the motion section, based on the second sensing data corresponding to the motion section and learning information corresponding to a unit motion of the specific motion at a time of the meal.

A pulse wave analysis apparatus including a memory, and a processor coupled to the memory and the processor configured to execute a process, the process including extracting, from each of a plurality of captured images of a subject, a plurality of image areas corresponding to each of a plurality of parts of the subject respectively, generating pieces of waveform data corresponding to the plurality of parts based on an image analysis for the plurality of image areas, each of the pieces of waveform data indicating a pulse wave of the subject, calculating a first matching degree between the pieces of waveform data, and determining whether a noise is included in the pieces of waveform data based on the first matching degree.

Pulse wave analysis apparatus, pulse wave analysis method, and non-transitory computer-readable storage medium

A meal intake detection device includes: a memory; and a processor coupled to the memory and configured to: detect a rise of heart rate; extract as a meal intake candidate a time range from a detected rise to time when the heart rate decreases to a predetermined value in temporal changes in heart rate, and when a second meal intake candidate is extracted in a time range of an extracted first meal intake candidate, separate the first meal intake candidate and the second meal intake candidate along a predetermined line; and detect whether each of the first meal intake candidate and the second meal intake candidate is a meal intake based on feature quantities relating to the first meal intake candidate and the second meal intake candidate that are separated.

Meal intake detection device, meal intake detection method and computer-readable non-transitory medium

An information processing device including: a processor configured to: obtain external times that are measured at different time points in another device, measure of the information processing device in response to obtaining each of external times, and correct a first external time that is obtained in a first time period of a plurality of sequential time periods based on a rate of a change in the internal times from a second external time to a third external time, the second external time being an external time at which a time difference between a corrected time of an external time and an internal time is minimum in the second time period, the third external time being an external time at which a time difference between a corrected time of an external time and an internal time is minimum in the third time period.

Information processing device, information processing method, and computer readable storage medium

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.

Signal processor, signal processing method, and recording medium

An information processing device configured to communicate with a plurality of mobile terminals, the information processing device includes a memory and a processor coupled to the memory and configured to acquire, from the plurality of mobile terminals, information related to movements of the plurality of mobile terminals, identify, based on the information, movement patterns of the plurality of mobile terminals, identify, based on the movement patterns, a queue including at least two mobile terminals of the plurality of mobile terminals, identify, based on the information of the mobile terminals included in the queue, a waiting time that elapses before a first mobile terminal that is one of the plurality of mobile terminals and that is included in the queue reaches a head of the queue, and output the identified waiting time.

Information processing device, computer-implemented method of estimating a waiting time, and non-transitory computer-readable storage medium

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.

Information processing method, apparatus, and program

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.

Rare pattern extracting device and rare pattern extracting method

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.

Computer-readable recording medium, apparatus and method for calculating scale-parameter

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. An importance degree calculation program comprises: a section generation step that receives, as an input, an instance set and an explanatory variable and uses the instance set to divide the explanatory variable into a plurality of sections to obtain a section set; a neighborhood instance set extraction step that uses the instance set, the section set, and a neighborhood instance number threshold to extract from across all sections a neighborhood instance set of each section in which the number of instances is greater than the neighborhood instance number threshold; an objective variable distribution calculation step that calculates an objective variable distribution from the neighborhood instance set of each section extracted by the neighborhood instance set extraction step; and an importance degree calculation step that calculates importance degree of each section from the objective variable distribution in each section obtained by the objective variable distribution calculation step and instance set.

Importance degree calculation program, importance degree calculation method, and importance degree calculation apparatus

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.

Computer-readable storage medium storing data analysis program

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.

Growing community of inventors

Kawasaki, Japan

Kazuho Maeda