A comparative analysis of DBSCAN, K-means, and quadratic variation algorithms for automatic identification of swallows from swallowing accelerometry signals

Abstract

Background Cervical auscultation with high resolution sensors is currently under consideration as a method of automatically screening for specific swallowing abnormalities. To be clinically useful without human involvement, any devices based on cervical auscultation should be able to detect specified swallowing events in an automatic manner. Methods In this paper, we comparatively analyze the density-based spatial clustering of applications with noise algorithm (DBSCAN), a k-means based algorithm, and an algorithm based on quadratic variation as methods of differentiating periods of swallowing activity from periods of time without swallows. These algorithms utilized swallowing vibration data exclusively and compared the results to a gold standard measure of swallowing duration. Data was collected from 23 subjects that were actively suffering from swallowing difficulties. Results Comparing the performance of the DBSCAN algorithm with a proven segmentation algorithm that utilizes k-means clustering demonstrated that the DBSCAN algorithm had a higher sensitivity and correctly segmented more swallows. Comparing its performance with a threshold-based algorithm that utilized the quadratic variation of the signal showed that the DBSCAN algorithm offered no direct increase in performance. However, it offered several other benefits including a faster run time and more consistent performance between patients. All algorithms showed noticeable differen-tiation from the endpoints provided by a videofluoroscopy examination as well as reduced sensitivity. Conclusions In summary, we showed that the DBSCAN algorithm is a viable method for detecting the occurrence of a swallowing event using cervical auscultation signals, but significant work must be done to improve its performance before it can be implemented in an unsupervised manner.

A matched dual-tree wavelet denoising for tri-axial swallowing vibrations

“…The beginning and end points of each swallow were based on widely accepted clinical landmarks. However, these points do not necessarily correlate perfectly with the beginning and end of cervical vibrations [34]. While the results presented in this study are valuable when analyzing data from this clinical perspective, it may be beneficial to investigate how these algorithms perform when incorporating data from outside of this accepted range so that information not included in a standard clinical examination may also be studied.…”

Study on frequency optimization and mechanism of ultrasonic waves assisting water flooding in low-permeability reservoirs

“…Agglomerative clustering is a hierarchical-based clustering method that can produce an informative hierarchical structure of clusters [40] . The DBSCAN algorithm (Density-Based Clustering of Application with Noise) is a widely-used density-based clustering algorithm [41] . The sample set will be divided into core points, boundary points and noise points according to the set radius (Eps) and the number of samples (MinPts).…”

Combining Statistical and Machine Learning Techniques in IoT Anomaly Detection for Smart Homes

“…This consideration is based on the basic principles of the Peer Group Analysis [4]. The Density Based Spatial Clustering (DBSCAN) [23] was selected for the clustering procedure, due to its simplicity, which is reflected by the fact that there is no need to predetermine the number of clusters and due to its superiority over other clustering algorithms, regarding the performance [24]. Finally, using the clusters as labels, an ensemble classifier is trained, having as independent variables the previously calculated values of the principal components and as dependent variable the label-cluster.…”