Osaka University

Pamela, Inc.

National Institute of Information and Communications Technology, Incorporated

Aya Nakae

Koutarou Nomura

Takahiro Soshi

Yasushi Naruse

The problem to be solved is to provide a system and the like for augmenting supervisory data while maintaining the relationship among a plurality supervisory data used for machine learning. The present disclosure provides a system for augmenting supervisory data used for machine learning, the system including an obtaining means that obtains a plurality of supervisory data, a first processing means that derives a covariance matrix from the plurality of supervisory data, a second processing means that decomposes the covariance matrix, and a third processing means that applies a random number to the decomposed matrix.

System, method, and program for augmenting training data used for machine learning

A method is described for making determinations on or classifying the pain of an estimation subject on the basis of the brainwaves of the estimation subject. This method includes: (a) stimulating the estimation subject at a plurality of levels of stimulation intensity; (b) acquiring brainwave data for the estimation subject; (c) extracting a brainwave feature quantity from the brainwave data or the analysis data; (d) for plugging the feature quantity into a Sparse model analysis, making the feature quantity approach a quantitative level and/or a qualitative level for pain, and estimating or making a determination on a pain level. Another method is described including comparing of brainwave data or analysis data from the 2,000 msec following the earliest of an induced brainwave component, an initial-event-related voltage component, and 250 msec after a target stimulus has been applied.

Pain classification and momentary-pain determination using sparse modeling

A high accuracy information extracting device construction system includes: a feature quantity extraction expression list generating unit for generating a feature quantity extraction expression list; a feature quantity calculating unit for calculating feature quantities of teacher data by means of respective feature quantity extracting expressions; a teacher data supply unit for supplying teacher data; an evaluation value calculating unit for generating information extracting expressions by means of machine learning on the basis of the calculated feature quantities of teacher data and the teacher data, and calculating evaluation values for the respective feature quantity extracting expressions; and a synthesis unit for constructing a high accuracy information extracting device using T weak information extracting parts F(X)t output from the evaluation value calculating unitand confidence levels Ct corresponding thereto.

Pain determination using trend analysis, medical device incorporating machine learning, economic discriminant model, and IoT, tailormade machine learning, and novel brainwave feature quantity for pain determination

Provided is a pain estimating device with which it is possible to estimate objectively and accurately pain being experienced by a subject. A pain estimating deviceestimates the magnitude of pain being experienced by a subject, on the basis of brainwaves of the subject, and is provided with: a measurement unitwhich acquires a plurality of items of brainwave data or analysis data thereof by measuring brainwaves from the subject a plurality of times; and an estimation unitwhich estimates the relative magnitude of the pain being experienced when the brainwave measurements were conducted a plurality of times, from the plurality of items of brainwave data or the analysis data thereof (for example the amplitude), on the basis of the linearity of a relationship between the brainwave data or the analysis data thereof (for example the amplitude) and the pain. The present invention also provides a pain estimating method and device with which it is possible to estimate objectively and accurately pain being experienced by a subject, and to classify simply the quality and quantity thereof. The present invention also provides a method for generating a pain classification value for classifying pain being experienced by the subject, on the basis of brainwaves of the subject.

Pain estimating device, pain estimating method, and pain classification

The computer implemented method makes it possible to discern, for a variety of sensations, whether a sensation is a pleasant (comfortable) sensation or a sensation of discomfort. A classifier is generated for discerning the stress or comfort/discomfort of a subject. The method comprising: a) imparting, to a subject, different stimuli under the same environment, and obtaining brain wave data or analysis data thereof for the environment; b) correlating a reaction of the subject relating to the stimulation and the difference of the brain wave data or analysis data thereof obtained under the environment; c) generating a classifier for discerning the stress or comfort/discomfort of the subject, on the basis of the correlation; and d) performing comfort/discomfort discernment using a basic step for amplifying a sample from a small stimulation.

Growing community of inventors

Osaka, Japan

Aya Nakae