Machine learning approach to wave height prediction

• US 8,423,487 B1
• Filed: 08/11/2010
• Issued: 04/16/2013
• Est. Priority Date: 08/11/2010
• Status: Expired due to Fees

• Current Assignee: the united states of america as represented by the secretary of the navy
• Original Assignee: the united states of america as represented by the secretary of the navy
• Inventors: Rubin, Stuart H.
• Primary Examiner(s): Gaffin, Jeffrey A.
• Assistant Examiner(s): Sugent, James F
• Application Number:
  US12/854,602
• Time in Patent Office: 979 Days
• Field of Search: 706/12, 706/48, 114/312, 116/107, 441 1- 34
• US Class Current: 706/12
• CPC Class Codes: G01W 1/00 Meteorology
• CPC Class Codes: G01W 1/10 Devices for predicting weather conditions computers per se G06; display devices G09
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

Sea characteristics are determined by using a buoy with multiple tilt switches configured to sense at plural tilt angles of the buoy. The tilt switches provide binary outputs of tilt data corresponding to the tilt angles. The binary outputs are received by a processor and are compared with sample patterns of tilt data. The comparison is used to provide an output corresponding to sea conditions.

Claims

1. A system comprising:

a buoy having more than two tiers each having plurality of tilt switches, the tiers located at different vertical positions of the buoy; and

a processor, operatively connected to the tilt switches, configured to match binary outputs of observed tilt switch data from each tier of tilt switches to stored tilt switch data contained in a database operatively connected to the processor, each string of stored tilt switch data associated with a particular sea state condition level, the processor further configured to use majority voting to determine a selected sea state condition level based upon the particular sea state condition levels associated with the matched stored tilt switch data for each of the tiers of tilt switches and return the selected sea state condition level from the database.

2. The system of claim 1 further comprising:

a transceiver operatively connected to the processor; and

an antenna connected to the transceiver.

3. A method comprising the steps of:

providing a buoy having more than two tiers each having plurality of tilt switches, the tiers located at different vertical positions of the buoy;

matching, using a processor operatively connected to the tilt switches, binary outputs of observed tilt switch data from each tier of tilt switches to stored tilt switch data contained in a database, each string of stored tilt switch data associated with a particular sea state condition level;

using majority voting to determine a selected sea state condition level based upon the particular sea state condition levels associated with the matched stored tilt switch data for each of the tiers of tilt switches; and

returning the selected sea state condition level from the database.

4. The method of claim 3 further comprising the step of, prior to the step of matching binary outputs of observed tilt switch data from each tier of tilt switches to stored tilt switch data contained in a database, filtering the observed tilt switch data to remove noise.

5. The method of claim 4 further comprising the steps of:

receiving user feedback regarding the selected sea state condition level; and

if the user feedback indicates a correct selection, then associating in the database, the observed tilt switch data from each tier with the selected sea state condition level.

6. The method of claim 3, wherein if any of the binary outputs of observed tilt switch data from the tiers of tilt switches matches to more than one string of the stored tilt switch data contained in the database, the associated particular sea state condition level used in the majority voting is the particular sea state condition level most-recently acquired in the database.