Monitoring wellness using a wireless handheld device

• US 8,527,213 B2
• Filed: 06/30/2010
• Issued: 09/03/2013
• Est. Priority Date: 07/21/2009
• Status: Active Grant

• Current Assignee: NTT Docomo Incorporated (Nippon Telegraph and Telephone Corporation)
• Original Assignee: NTT Docomo Incorporated (Nippon Telegraph and Telephone Corporation)
• Inventors: Kailas, Aravind, Chong, Chia-Chin, Watanabe, Fujio
• Primary Examiner(s): NGHIEM, MICHAEL P
• Application Number:
  US12/827,963
• Publication Number:
  US 20110022332A1
• Time in Patent Office: 1,161 Days
• Field of Search: 702/42, 702/19, 702/32
• US Class Current: 702/32
• CPC Class Codes: A61B 5/01 Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue clinical contact thermometers G01K13/20
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

A method for detecting a subject'"'"'s stress level associated with an activity includes (a) connecting the subject to a sensor that senses a value of a biometric; (b) during the activity, (i) repeatedly sensing the value of the biometric over each of a plurality of time windows; and (ii) computing, for each time window, a deviation in the sensed values of the biometric; and (c) detecting the stress level based on the computed deviations. In one implementation, the value of the biometric is a skin temperature measurement. The method may be implemented as an application in a wireless handheld device, such as a cellular telephone.

Claims

1. A method for detecting a subject'"'"'s stress level associated with an activity, comprising:

connecting the subject to a sensor that senses a value of a biometric;

during the activity,

repeatedly sensing the value of the biometric over each of a plurality of time windows;

computing, for each time window, a difference between each sensed biometric value in the time window and an ambient value to determine a maximum difference for the time window and a minimum difference for the time window;

computing, for each time window, a deviation, for the sensed biometric values in the time window by subtracting the time window'"'"'s minimum difference from the time window'"'"'s maximum difference; and

detecting the stress level based on the computed deviations for the time windows, wherein detecting the stress level further comprises inferring a stress state transition from time window to time window based on a temporal Bayesian Network (TBN) model and corresponding computed deviations.

2. A method as in claim 1, wherein the value of the biometric is a skin temperature measurement.

3. A method as in claim 1, wherein the TBN model is updated at a given time step by

(a) predicting a stress state for the given time step based on a conditional probability of a hidden stress state of an immediate previous time step given observable values of one or more previous time steps, including the immediate previous time step;

and

(b) computing the hidden stress state of the given time step using the predicted stress state of the given time step and the observable values of the given time step.

4. A method as in claim 3, wherein the TBN model includes a state transition model, an inference model and a detection model.

5. A method as in claim 4, wherein the state transition model is based on a conditional probability of the hidden stress state at the given time step, given the hidden stress state of the immediate previous time step.

6. A method as in claim 4, wherein the inference model is based on a conditional probability of the hidden stress state of the immediate previous time step, given the observable values of one or more previous time steps, including the observable values of the immediate previous time step.

7. A method as in claim 1, wherein missing parameters of the TBN model is provided by a procedure based on an expectation maximization algorithm.

8. A method as in claim 1, wherein the method is implemented in a wireless handheld device.