PROJECT TITLE :

Recognition of Nutrition Intake Using Time-Frequency Decomposition in a Wearable Necklace Using a Piezoelectric Sensor

ABSTRACT:

Food intake levels, hydration, ingestion rate, and dietary selections are all factors known to impact the risk of obesity. This paper presents a unique wearable system in the form of a necklace, that aggregates knowledge from an embedded piezoelectric sensor capable of detecting skin motion within the lower trachea throughout ingestion. The skin motion produces an output voltage with varying frequencies over time. Thus, we tend to propose an algorithm based on time-frequency decomposition, spectrogram analysis of piezoelectric sensor signals, to accurately distinguish between food types, like liquid and solid, hot and cold drinks, and laborious and soft foods. The necklace transmits information to a smartphone, that performs the processing of the signals, classifies the food kind, and provides visual feedback to the user to assist the user in monitoring their eating habits over time. We have a tendency to compare our spectrogram analysis with other time-frequency options, such as matching pursuit and wavelets. Experimental results demonstrate promise in using time-frequency options, with high accuracy of distinguishing between food categories using spectrogram analysis and extracting key options representative of the unique swallow patterns of varied foods.