Apparatus and method for analyzing information relating to physical and mental condition

• US 5,884,626 A
• Filed: 08/31/1995
• Issued: 03/23/1999
• Est. Priority Date: 09/02/1994
• Status: Expired due to Term

• Current Assignee: Director-General of the Agency of Industrial Science and Technology, the Ministry of International Trade and Industry of Japan (Government of Japan), National Institute of Advanced Industrial Science and Technology (Government of Japan), Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Director-General of the Agency of Industrial Science and Technology, the Ministry of International Trade and Industry of Japan (Government of Japan), Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: Yoshida, Tomoyuki, Kuroda, Yukio
• Primary Examiner(s): NASSER, ROBERT L
• Assistant Examiner(s): Huang, Stephen
• Application Number:
  US08/521,810
• Time in Patent Office: 1,300 Days
• Field of Search: 128/731, 128/732, 128/630
• US Class Current: 600/300
• CPC Class Codes: A61B 5/0006 ECG or EEG signals
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/7232 involving compression of the physiological signal, e.g. to extend the signal recording period
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

An apparatus and method are provided for analyzing information relating to the physiological and psychological conditions of a driver. Psychological conditions such as comfortableness or degree of alertness are estimated on the basis of physical data such as fluctuation in brain waves. This apparatus comprises a first neural network having a pre-processed 1/f fluctuation signal for brain waves as an input and for estimating a degree of alertness of the driver, and a second neural network receiving the estimated degree of alertness and the pre-processed 1/f fluctuation signal, for estimating and outputting driving comfortableness. By employing a neural network, which has a mapping ability as well as flexible adaptability even for non-linear data, based on the learning function, more accurate estimation of mental conditions can be achieved in comparison with conventional statistical analysis.

Claims

1. An apparatus for analyzing a physiological fluctuation signal of a subject to determine at least one psychological condition of the subject, the apparatus comprising a neural network receiving the physiological fluctuation signal as an input for estimating physiological conditions using frequency variations, wherein said neural network is an hourglass type neural network, training of the hourglass type neural network carried out by supplying the physiological fluctuation signal to both an input and an output of the hourglass type neural network, output values of an intermediate layer of the hourglass type neural network representing at least one psychological condition.

2. The apparatus according to claim 1, wherein said neural network receives a pre-processed EEG fluctuation signal as a physiological fluctuation signal.

3. The apparatus of claim 2, wherein said hourglass-type neural network outputs a signal indicative of an alertness of the subject as the at least one psychological condition of the subject.

4. The apparatus of claim 2, wherein said hourglass type neural network outputs a signal indicative of a comfortableness of the subject as the at least one psychological condition of the subject.

5. The apparatus of claim 1, further comprising signal sensing means, attachable to the subject, for sensing a fluctuating physiological condition of the subject and outputting the physiological fluctuation signal.

6. The apparatus of claim 1, wherein the physiological fluctuation signal is an EEG fluctuation signal.

9. The apparatus of claim 5, further comprising:

signal sensing means, attachable to the subject for sensing an EEG fluctuation signal; and

processing means for generating the preprocessed EEG fluctuation signal from the EEG fluctuation signal.

14. The method of claim 6, wherein the physiological fluctuation signal is an EEG fluctuation signal.

7. An apparatus for analyzing information relating to physiological and psychological conditions comprising a neural network receiving a preprocessed EEG fluctuation signal of a subject as an input for estimating physiological conditions of the subject, wherein said neural network comprises:

a first neural network receiving the pre-processed EEG fluctuation signal as an input for estimating a degree of alertness; and

a second neural network receiving the degree of alertness estimated by the first neural network and the pre-processed EEG fluctuation signal as inputs for estimating comfortableness, to estimate both alertness and comfortableness as psychological conditions.

8. The apparatus according to claim 7, wherein said first and second neural networks are hourglass type neural networks, the EEG fluctuation signals are supplied to both input and output of each of the neural networks for training the neural networks, and output of an intermediate layers of the neural network represents the psychological conditions.

10. A method for analyzing information relating physiological and psychological conditions, comprising:

applying a physiological fluctuation signal to a neural network; and

estimating psychological conditions using frequency variations;

wherein said neural network is an hourglass type neural network, training of the hourglass type neural network carried out by supplying the physiological fluctuation signal to both an input and an output of the hourglass type neural network, output values of an intermediate layer of the hourglass type neural network representing the psychological conditions.

11. The method according to claim 10 wherein said physiological fluctuation signal includes a pre-processed EEG fluctuation signal.

12. The method according to claim 11, wherein said psychological conditions include alertness.

13. The method according to claim 11, wherein said psychological conditions include comfortableness.

15. A method for analyzing information relating physiological and psychological conditions, comprising:

applying a physiological fluctuation signal of a subject to a neural network, the physiological fluctuation signal including a pre-processed EEG fluctuation signal of the subject;

applying the pre-processed EEG fluctuation signal to an alertness estimation portion of the neural network to estimate alertness; and

applying the estimated alertness and the pre-processed EEG fluctuation signal to a comfortableness estimation portion of the neural network to estimate both alertness and comfortableness as the psychological conditions.

16. The method according to claim 15, wherein the alertness estimation neural network and the comfortableness estimation neural network are hourglass type neural networks, both of which have been trained with the EEG fluctuation signals at both input and output, and the output of an intermediate layer of each neural network represents the psychological conditions.