Method and system of segmentation and time duration analysis of dual-axis swallowing accelerometry signals
OwnerTom Chau, Ervin Sejdicinventors
Life of this patent
Estimating the term…
Abstract
The proposed invention is a method and system for the segmentation of dual-axis accelerometry signals for the purposed of identifying problematic swallowing events. The method and system employ a sensor, a data collection means including an algorithm for the analysis of the data. The proposed invention considers the stochastic properties of swallowing signals in both directions, A-P and S-I to extract events associated with swallowing. A segmentation algorithm may be applied to the signals to establish the time duration of swallows and swallows may be classified with respect to gender, body mass index, age or types of swallow.
Claims20
A method for segmentation and analysis of dual-axis accelerometry signals for the indication of problematic swallowing events comprising the following steps:
- a. Providing and accelerometer proximate to a swallowing location for detecting dual-axis movements and their respective time duration and for generating dual-axis accelerometry signals having onset s and offsets;
- b. Transmitting the signals to a data storage device for storage as accelerometry data;
- c. Analyzing said data to determine swallowing segments and non-swallowing segments;
- d. Identifying a set of swallowing signals from the data;
- e. Comparing said set with known attributes of healthy swallowing;
- and,
- f. Identifying a subset of problematic swallows.
The method of claim steps c to f inclusive are computer based.
A computer software program executable by a computer for segmentation and analysis of dual-axis accelerometry signals for the indication of problematic swallowing events comprising the following steps:
- a. Receiving accelerometry data from an accelerometry sensor, said data comprising a series of vibration events having dual-axis acceleration in an A-P direction and a S-I direction and representing swallowing and non-swallowing segments;
- b. Executing a sequential segmentation algorithm;
- c. Forming a first indicator function for a non-swallowing segment in said A-P direction;
- d. Forming a second indicator function for a swallowing segment in the A-P direction;
- e. Forming a first indicator function for a non-swallowing segment in the S-I direction;
- f. Forming a second indicator function for a swallowing segment in the S-I direction;
- g. Applying fuzzy c-means optimization for determining the time boundaries for each of said swallowing and non-swallowing segments;
- h. Multiplying said first function in the A-P direction by said first indicator function in the S-I direction for noise reduction;
- and,
- i. Multiply said second indicator function in the A-P direction by said second indicator function in the S-I direction for noise reduction;
- j. Wherein steps h and I form a binary dual-axis indicator function for swallowing and non-swallowing segments.
The software program of claim 12 further comprising the step of comparing the swallowing events.
A system for segmentation and analysis of dual-axis accelerometry signals for the indication of problematic swallowing events, said system comprising:
- a. A sensor placed proximate to a known swallowing location for detecting dual-axis vibrations and generating dual-axis accelerometry signals;
- b. Data storage means for receiving a storing said signals as accelerometry data;
- c. Data processing means for identifying a set of swallowing and non-swallowing events from said data and determining the duration of individual swallowing events;
- and,
- d. Means for identifying a subset of problematic swallowing events from the set.
Dependencies are inferred from the claim text.