Automatic Detection of Swallowing Events by Acoustical Means for Applications of Monitoring of Ingestive Behavior

Abstract

Our understanding of etiology of obesity and overweight is incomplete due to lack of objective and accurate methods for Monitoring of Ingestive Behavior (MIB) in the free living population. Our research has shown that frequency of swallowing may serve as a predictor for detecting food intake, differentiating liquids and solids, and estimating ingested mass. This paper proposes and compares two methods of acoustical swallowing detection from sounds contaminated by motion artifacts, speech and external noise. Methods based on mel-scale Fourier spectrum, wavelet packets, and support vector machines are studied considering the effects of epoch size, level of decomposition and lagging on classification accuracy. The methodology was tested on a large dataset (64.5 hours with a total of 9,966 swallows) collected from 20 human subjects with various degrees of adiposity. Average weighted epoch recognition accuracy for intra-visit individual models was 96.8% which resulted in 84.7% average weighted accuracy in detection of swallowing events. These results suggest high efficiency of the proposed methodology in separation of swallowing sounds from artifacts that originate from respiration, intrinsic speech, head movements, food ingestion, and ambient noise. The recognition accuracy was not related to body mass index, suggesting that the methodology is suitable for obese individuals. Index Terms NIH-PA Author ManuscriptNIH-PA Author Manuscript NIH-PA Author Manuscript I IntroductionThe world is still losing in the battle with the obesity epidemic. According to WHO, in 2005 there were approximately 1.6 billion overweight and at least 400 million obese adults worldwide [1]. Current trends are unsettling: 2015 projections predict 2.3 billion overweight and 700 million obese adults worldwide. Obesity is one of the risk factors for development of chronic diseases and presents a serious health problem. A recent study [2] suggested that effects of obesity on global health may be comparable to those of cancer. Though the etiology of obesity is a topic of ongoing scientific debate, regulation of food intake may be an important factor for maintaining a healthy weight [3] in the environment that provides abundance of inexpensive, highly palatable and energy dense foods, while requiring only minimal levels of physical activity [4].While various methods have been developed for accurate and objective characterization of physical activity [5], at the present time, there is no accurate, inexpensive, non-intrusive way for objective Monitoring of Ingestive Behavior (MIB) in free living conditions. The most precise method of measuring energy intake is the Doubly-Labeled Water (DLW) technique which provides accurate estimates of caloric energy intake over long periods of time (10-14 days), if subjects remain weight stable. However, the DLW technique cannot identify daily intake patterns. Dietary self-report methods like food frequency questionnaires [6], selfreported diet diaries [7], and multimedia diaries [8] have been shown to be ...

Wearable Food Intake Monitoring Technologies: A Comprehensive Review

“…Sazanov et al [64] proposed an ingestive behavior monitoring device that employed methods based on mel-scale Fourier spectrum, wavelet packets and support vector machines to differentiate swallowing events from respiration, intrinsic speech, head movements, food ingestion and ambient noise. Even though these devices still cannot either classify food or quantify energy consumption, they can characterize food intake behaviors such as number and frequency of chews and swallows.…”

“…Moreover, the system includes the hardware/software parts for capturing and scoring sounds' data. Sazonov et al [64] analyzed in greater detail the methodologies for the acoustic detection of swallowing events. The proposed methods for detection are based on the following time-frequency decompositions: msFS (mel-scale Fourier spectrum) and WPD (wavelet packet decomposition) with classification performed by support vector machine (SVM).…”

Mobile Ecological Momentary Diet Assessment Methods for Behavioral Research: Systematic Review (Preprint)

“…Because of the known limitation of existing dietary assessment methods, the research community is motivated to develop new solutions aimed at (semi-)automating the assessment of dietary intake. While the automated methods of real-time image-based detection [14][15][16][17][18][19][20][21][22][23][24] and real-time detection of food intake by biomechanical sensors or hand-held devices [25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42] have seen significant progress [15,24] in terms of identifying foods and estimating portion sizes [14][15][16][17][18][19][20][21][22][23][24] detecting wrist or hand motion [25][26][27][28]…”

“…image-assisted and image-based assessment [14][15][16][17][18][19][20][21][22][23][24] and the detection of food intake by biomechanical sensors or hand-held devices [25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42]. Significant progress has been made in image-assisted and image-based food recording that has resulted in the improved accuracy of dietary self-report [15,24].…”

“…Significant progress has been made in image-assisted and image-based food recording that has resulted in the improved accuracy of dietary self-report [15,24]. Similarly, wearable technology including gyroscopes, microphones, and mechanical or electrical impedance sensors have been adapted to detect wrist or hand motion [25][26][27][28][29][30][31] or patterns of chewing or swallowing indicative of food intake (eg, number of bites) [32][33][34][35][36][37][38][39][40][41]. However, design and proof-of-concept data suggest the automation of dietary assessment remains out of reach for the time being.…”