METHODS FOR BEHAVIOR PATTERN ANALYSIS

• US 20120029865A1
• Filed: 10/15/2010
• Published: 02/02/2012
• Est. Priority Date: 07/27/2010
• Status: Active Grant

• Current Assignee: National Yang-Ming University
• Original Assignee: National Yang-Ming University
• Inventors: KUO, Bo-Jau, YANG, Ching-Hsiu
• Granted Patent: US 8,583,399 B2
• Time in Patent Office: Days
• US Class Current: 702/141
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/6804 Garments; Clothes
• CPC Class Codes: A61B 5/6813 Specially adapted to be attached to a specific body part A61B5/6802 takes precedence
• CPC Class Codes: A63B 2220/40 Acceleration

Abstract

Disclosed is a method for behavior pattern analysis, in which the behavior signals of a subject are continuously detected using tri-axis accelerator, and the behavior signals are divided as a plurality of time windows based on a predetermined time length. The plurality of time windows are configured as an X-Y matrix, and cross analysis is performed on the time windows as X-axis and Y-axis to obtain a plurality of correlation coefficients as being the preferred correlation values. A pattern with bright spots and dark spots is plotted according to the preferred correlation values, and behavior pattern is evaluated from the number and distribution of bright spots and the pattern. The behavior consistency of a subject can be efficiently evaluated, and his/her behavior abnormality, disease development or other situations can be determined accordingly.

Claims

1. An analytic method for a behavior pattern, the method comprising:

(a) continuously detecting behavior signals of a subject by using a tri-axis accelerator;

(b) dividing the behavior signals as n time windows based on a predetermined time length, n being a plural number;

(c) configuring the n time windows as a matrix of an X-axis and a Y-axis;

(d) performing a cross analysis on the n time windows at the X-axis and the n time windows at the Y-axis to obtain a plurality of preferred correlation values; and

(e) estimating a pattern according to the plurality of preferred correlation values to evaluate the behavior pattern.

2. The method according to claim 1, wherein the step (a) further comprises a step (a1) of amplifying or filtering the behavior signals.

3. The method according to claim 1, wherein the n time windows are distinguished as a zeroth time window, a first time window, . . . and an (n−

1)th time window, the zeroth time window at the X-axis is neighbored to the zeroth time window at the Y-axis.

4. The method according to claim 1, wherein the step (d) further is processed by a cross-correlation analysis or a cross-spectral analysis.

5. The method according to claim 1, wherein the step (d) further comprises:

(d1) converting the plurality of preferred correlation values as bright spots or dark spots, the bright spots representing a first consistency of the behavior pattern, the dark spots representing a second consistency of the behavior pattern, and the first consistency is higher than the second consistency.

6. An estimation method of behavior signals, comprising:

(a) continuously detecting the behavior signals of a subject, the behavior signals representing acceleration component values at a three dimensional space;

(b) estimating a total amount of acceleration values at each time point; and

(c) estimating acceleration variance amplitudes at each time interval.