An anchored dynamic time-warping for alignment and comparison of swallowing acoustic signals
| Autor: | Elmar Allen Fugmann, Marcelo de Oliveira Rosa, Maria Cristina de Alencar Nunes, Gisele Pinto |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Engineering
Dynamic time warping Time Factors Similarity (geometry) Anchor point business.industry Acoustics 0206 medical engineering Process (computing) 02 engineering and technology Accelerometer 020601 biomedical engineering Deglutition Swallowing 0202 electrical engineering electronic engineering information engineering Humans 020201 artificial intelligence & image processing Computer vision Artificial intelligence business |
| Zdroj: | EMBC |
| DOI: | 10.1109/embc.2017.8037426 |
| Popis: | Properties of signals captured by contact accelerometers assist the evaluation of human organs involved in the swallowing process. Here we present a novel method to account the alignment between two different swallowing signals based on two steps: first, a scaled cross-correlation determines an anchor point of maximum similarity between the signals, dividing both signals in two parts; next, dynamic time warping aligns the left and right parts of both signals. Additional filtering procedures are used smooth the swallowing signals due to their low SNR. The results show that this technique can be used to assess similarities between liquid and solid boluses of a subject. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|