Abstract:
A computer-implemented method for generating a predicting model includes: accumulating a plurality of combinations of a parameter representing a branch condition and a branch probability in relation to one or more condition branch components in a workflow; and generating, using the plurality of combinations accumulated, a model that predicts a branch probability corresponding to a parameter used when a particular condition branch component among the one or more condition branch components is used.
Abstract:
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.
Abstract:
A meal time estimation method includes: acquiring time series data of heart rate, by a processor; calculating a feature amount obtained by indexing a degree of similarity with a feature of heart rate change that appears at end of a meal from the time series data of the heart rate, by the processor; and estimating a meal time from the feature amount, by the processor.
Abstract:
An information processing apparatus includes a memory, and a processor coupled to the memory and configured to obtain time series data indicating a time-dependent change of a biological signal value after a meal, determine, based on the obtained time series data, a first feature amount of the time-dependent change of the biological signal value after the meal, determine, based on the determined first feature amount, an index value related to the meal, and output the determined index value.
Abstract:
A pulse wave detection method includes obtaining an image obtained by photographing a subject with an imaging device, extracting intensities representative of signal components of a specific frequency band for respective wavelength components among signals of a plurality of wavelength components included in the image, calculating, using the intensities extracted for the respective wavelength components, a weight coefficient by which a signal is multiplied when the signals are calculated between the wavelength components to minimize an arithmetic value of the signal components in the specific frequency band after multiplication, multiplying at least one of the signals of the respective wavelength components by the weight coefficient, performing arithmetic operation on the signals between the wavelength components after multiplication by the weight coefficient, and detecting pulse waves of the subject using a signal after the arithmetic operation.
Abstract:
A specifying method includes specifying a first period for which it is determined that a specific movement or a specific posture is being performed by applying a first threshold to time series data obtained from a sensor for detecting a movement of a person, specifying a second period for which it is determined that the specific movement or the specific posture is being performed by applying a second threshold to the time series data, the second threshold being eased compared to the first threshold, specifying a transitional period based on a difference between the second period and the first period, the transitional period corresponding to one of a period of a transition to the specific movement or the specific posture, and another period of another transition from the specific movement or the specific posture to another movement or another posture and outputting a result.
Abstract:
A blood flow index calculating method includes: obtaining, by a camera, an image capturing a first site of a living body and a second site of the living body; extracting an area of the first site of the living body and an area of the second site of the living body, by a processor; detecting a pulse wave pattern of the first site of the living body from the area of the first site of the living body and detecting a pulse wave pattern of the second site of the living body from the area of the second site of the living body, by the processor; first calculating a delay amount from the pulse wave pattern of the first site and the pulse wave pattern of the second site, by the processor; and second calculating an index related to blood flow by using the delay amount, by the processor.