IDENTIFYING ACTIVITY IN AN AREA UTILIZING SOUND DETECTION AND COMPARISON

• US 20110037596A1
• Filed: 09/24/2010
• Published: 02/17/2011
• Est. Priority Date: 07/25/2006
• Status: Abandoned Application

• Current Assignee: Fariborz M. Farhan
• Original Assignee: Fariborz M. Farhan
• Inventors: Farhan, Fariborz M.
• Application Number:
  US12/890,254
• Publication Number:
  US 20110037596A1
• Time in Patent Office: Days
• US Class Current: 340/573.1
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule
• CPC Class Codes: G08B 21/0469 Presence detectors to detect unsafe condition, e.g. infrared sensor, microphone G08B21/0476 takes precedence
• CPC Class Codes: G16H 40/60 for the operation of medical equipment or devices

Abstract

Microprocessor technology is used to detect routine sounds in a substantially enclosed environment to determine normal or abnormal activity or noise within the environment (i.e., habitual behavior of an individual) A device is situated in a substantially enclosed environment with audio input device similar to a microphone and an optional visual display for interaction with the local users. The device has the ability to be controlled locally via key-pad or USB port connected to a local laptop computer, or remotely via a phone line or Ethernet connection to internet. The device further performs audio pattern recognition using waveform matching scheme to detect the occurrence of pre-programmed sounds representing routine activities. The microprocessor counts the number occurrence of each recognizable sound for a particular interval and over a length of a day or other duration and reports to a remote server. The remote server performs tracking and trending analysis to a web-based caregiver client. Significant changes are detected and reported to caregiver or family web-based client.

Claims

1. A device for identifying activity of a subject in an environment, the device comprising the components of:

a memory element that includes a plurality of expected audio signal waveforms;

a detector configured to;

detect the presence of audio energy in the environment;

detect human speech within the environment;

detect silence within the environment; and

provide a record signal output when audio energy is detected in the environment but the audio energy is not human speech;

a recorder configured to receive the record signal and record audio energy within the environment for a period of time controlled by the record signal and store an environment audio signal waveform representing the recorded audio energy into a memory element;

a digital audio waveform analyzer configured compare two or more digital audio waveforms to perform pattern recognition; and

a processing unit configured to;

compare the environment audio signal waveform with the plurality of expected audio signal waveforms to identify a match; and

generate an alarm if the environment audio signal does not match any expected audio signal waveforms.

2. The device of claim 1, wherein said processor is configured to enter a learning mode to store expected audio signal waveforms.

3. The device of claim 2, includes a user interface and the processor is configured such that in the learning mode, to provide an indicator to a user to actuate the user interface prior to conducting an activity that will generate audio energy and then, cause the recorded to record and store the detected audio energy as an expected audio signal waveform.

4. A method for detecting abnormal activity in an environment, the method comprising the steps of:

recording sounds expected to occur in the environment;

storing information representing each unique expected sound into a waveform record;

a recorder recording audio energy that does not include human speech in the environment over a first period of time;

a processor processing each audio energy recording by comparing the audio energy recording to the stored information of unique expected sounds in the waveform record to determine if there is a match;

the processor maintaining a count of the number of matches for each identified audio energy recording over the first period of time;

the processor comparing the counts to expected values for each count within that first period of time; and

the processing sounding an alarm condition based at least in parts on the counts and the expected values.

5. The method of claim 4, wherein the step of sounding an alarm further comprises the step of, if the maintained counts deviate from the expected counts by a threshold amount, reporting such information to a centralized server.

6. The method of claim 4, wherein the step of sounding an alarm further comprises the steps of:

for each count, reporting (a) if the count exceeds the expected count by a first threshold amount, (b) is less than the expected count by a second threshold amount or (c) is within a threshold distance from the expected count.