Haptic-based artificial neural network training

• US 9,218,565 B2
• Filed: 06/19/2014
• Issued: 12/22/2015
• Est. Priority Date: 12/18/2013
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Chatterjee, Aveek N., Adoni, Siddique M., Shanmugam, Dhandapani
• Primary Examiner(s): Holmes, Michael B
• Application Number:
  US14/309,001
• Publication Number:
  US 20150170024A1
• Time in Patent Office: 551 Days
• Field of Search: 706/16
• US Class Current: 1/1
• CPC Class Codes: G06F 3/016 Input arrangements with force or tactile feedback as computer generated output to the user
• CPC Class Codes: G06N 3/08 Learning methods

Abstract

In a method for training an artificial neural network based algorithm designed to monitor a first device, a processor receives a first data. A processor determines a first service action recommendation for a first device using the received first data and an artificial neural network (ANN) algorithm. A processor causes a second device to provide haptic feedback using the received first data. A processor receives a second service action recommendation for the first device based on the haptic feedback. A processor adjusts at least one parameter of the ANN algorithm such that the ANN algorithm determines a third service action recommendation for the first device using the received first data, wherein the third service action recommendation is equivalent to the second service action recommendation.

Claims

1. A method for training an artificial neural network based algorithm designed to monitor a first device, the method comprising:

receiving a first data;

determining, by one or more processors, a first service action recommendation for a first device using the received first data and an artificial neural network (ANN) algorithm;

causing a second device to provide haptic feedback using the received first data;

receiving a second service action recommendation for the first device based on the haptic feedback;

determining, by the one or more processors, that the second service action recommendation is different than the first service action recommendation; and

adjusting, by the one or more processors, at least one parameter of the ANN algorithm such that the ANN algorithm determines a third service action recommendation for the first device using the received first data, wherein the third service action recommendation is equivalent to the second service action recommendation.

2. The method of claim 1, wherein the step of receiving the first data comprises receiving the first data from one or more sensors operably affixed to the first device.

3. The method of claim 2, wherein the one or more sensors collect amplitude and frequency data of vibrations of the first device.

4. The method of claim 1, further comprising:

receiving a previously stored data and a previously stored service action recommendation for the first device associated with the previously stored data; and

wherein the step of adjusting, by the one or more processors, the at least one parameter of the ANN algorithm such that the ANN algorithm determines the third service action recommendation for the first device using the received first data, wherein the third service action recommendation is equivalent to the second service action recommendation comprises;

adjusting, by the one or more processors, the at least one parameter of the ANN algorithm such that the ANN algorithm determines a fourth service action recommendation for the first device using the previously stored data and the ANN algorithm determines the third service action recommendation for the first device using the received first data, wherein the third service action recommendation is equivalent to the second service action recommendation and wherein the fourth service action recommendation is equivalent to the previously stored service action recommendation.

5. The method of claim 1, further comprising the steps of:

receiving a video feed from one or more video recording devices depicting at least a portion of the first device; and

causing the video feed to be displayed.

6. The method of claim 5, wherein the step of receiving a second service action recommendation for the first device based on the haptic feedback comprises:

receiving a second service action recommendation for the first device based on the haptic feedback and the video feed.

7. The method of claim 1, wherein the haptic feedback includes generated physical properties to simulate how a surface of a component of the first device feels.

8. The method of claim 1, wherein the at least one parameter includes a function and a weight.