Bottom sediment determination device, ultrasonic finder, and method and program for setting parameters

• US 8,990,131 B2
• Filed: 12/05/2011
• Issued: 03/24/2015
• Est. Priority Date: 12/06/2010
• Status: Active Grant

• Current Assignee: Furuno Electric Co, Ltd
• Original Assignee: Furuno Electric Co, Ltd
• Inventors: Wada, Tomoo, Onishi, Yuji
• Primary Examiner(s): Wong, Lut
• Assistant Examiner(s): BUSS, BENJAMIN J
• Application Number:
  US13/311,206
• Publication Number:
  US 20120143803A1
• Time in Patent Office: 1,205 Days
• Field of Search: 706/15, 706/18, 706/20, 706/928, 706/929
• US Class Current: 706/20
• CPC Class Codes: G01S 15/88 Sonar systems specially adapted for specific applications seismic or acoustic prospecting or detecting G01V1/00
• CPC Class Codes: G01S 7/539 using analysis of echo signal for target characterisation; Target signature; Target cross-section
• CPC Class Codes: G01V 2210/62 Physical property of subsurface
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: Y10S 706/929 Geological, e.g. seismology

Abstract

This disclosure provide a bottom sediment determining device, which is inputted with an echo signal corresponding to an ultrasonic wave outputted underwater, and determines water bottom sediment using a neural network. The device includes a memory for storing two or more parameters to be used in the neural network so as to be associated with positional information, a receiver for receiving the positional information, an acquisition module for acquiring the parameters corresponding to the positional information, and a setting module for setting the parameters to the neural network.

Claims

1. A bottom sediment determining device for being inputted with an echo signal corresponding to an ultrasonic wave outputted underwater, and determining water bottom sediment using a neural network, the device comprising:

a memory for storing a set of two or more synaptic connection coefficients to be used in the neural network so as to be associated with positional information;

a receiver for receiving the positional information, the positional information representing a location where the water bottom sediment is determined;

an acquisition module for acquiring the set of synaptic connection coefficients corresponding to the positional information, said acquiring being accomplished by selecting the set of synaptic connection coefficients from among a plurality of sets of synaptic connection coefficients based on the received positional information, the selected set of synaptic connection coefficients being different from a previously-selected set of synaptic connection coefficients even if a water depth and bottom sediment determination are the same as those associated with the previously-selected set of synaptic connection coefficients; and

a setting module for setting the acquired set of synaptic connection coefficients to the neural network.

2. The bottom sediment determining device of claim 1, wherein the sets of synaptic connection coefficients are obtained by learning through the neural network in advance for a plurality of ocean spaces.

3. The bottom sediment determining device of claim 1 or 2 wherein the memory stores general-purpose synaptic connection coefficients, and the acquisition module acquires the general-purpose synaptic connection coefficients when there is no set of synaptic connection coefficients corresponding to the positional information in the memory.

4. The bottom sediment determining device of claim 1, wherein the acquisition module acquires the set of synaptic connection coefficients corresponding to the positional information closest to the received positional information when there is no set of synaptic connection coefficients corresponding to the received positional information.

5. The bottom sediment determining device of claim 1, wherein the sets of synaptic connection coefficients are obtained by learning through the neural network in advance according to an ocean space.

6. The bottom sediment determining device of claim 1, wherein the receiver receives GPS signals as the received positional information.

7. The bottom sediment determining device of claim 1, wherein the receiver receives the positional information inputted by a user.

8. An ultrasonic finder, comprising:

a bottom sediment determining device of claim 1; and

a display unit for displaying the result of the bottom sediment determination by the bottom sediment determining device.

9. The device of claim 1, where the selected set of synaptic connection coefficients correspond to the received positional information and the previously-selected set of synaptic connection coefficients correspond to previously-received positional information different from the received positional information.

10. A method of setting parameters of a neural network that is inputted with an echo signal corresponding to an ultrasonic wave outputted underwater and determines water bottom sediment, the method comprising:

storing a set of two or more synaptic connection coefficients to be used in the neural network so as to be associated with positional information;

receiving the positional information, the positional information representing a location where the water bottom sediment is determined;

acquiring the set of synaptic connection coefficients corresponding to the positional information, said acquiring being accomplished by selecting the set of synaptic connection coefficients from among a plurality of sets of synaptic connection coefficients based on the received positional information, the selected set of synaptic connection coefficients being different from a previously-selected set of synaptic connection coefficients even if a water depth and bottom sediment determination are the same as those associated with the previously-selected set of synaptic connection coefficients; and

setting the acquired set of synaptic connection coefficients to the neural network.

11. The method of claim 10, where the selected set of synaptic connection coefficients correspond to the received positional information and the previously-selected set of synaptic connection coefficients correspond to previously-received positional information different from the received positional information.

12. A non-transitory computer-readable medium having embodied thereon a computer-executable program for causing a computer to perform a method of setting synaptic connection coefficients of a neural network that is inputted with an echo signal corresponding to an ultrasonic wave outputted underwater and determine water bottom sediment, the method comprising:

storing a set of two or more synaptic connection coefficients to be used in the neural network so as to be associated with positional information;

receiving the positional information, the positional information representing a location where the water bottom sediment is determined;

acquiring the set of synaptic connection coefficients corresponding to the positional information, said acquiring being accomplished by selecting the set of synaptic connection coefficients from among a plurality of sets of synaptic connection coefficients based on the received positional information, the selected set of synaptic connection coefficients being different from a previously-selected set of synaptic connection coefficients even if a water depth and bottom sediment determination are the same as those associated with the previously-selected set of synaptic connection coefficients; and

setting the acquired set of synaptic connection coefficients to the neural network.

13. The medium of claim 12, where the selected set of synaptic connection coefficients correspond to the received positional information and the previously-selected set of synaptic connection coefficients correspond to previously-received positional information different from the received positional information.