In response to the demand of memory efficient algorithms for electrocardiogram (ECG) signal processing and anomaly detection on wearable and mobile devices, an implementation of the antidictionary coding algorithm for memory constrained devices is presented. Pre-trained finite-state probabilistic models built from quantized ECG sequences were constructed in an offline fashion and their performance was evaluated on a set of test signals. The low complexity requirements of the models is confirmed with a port of a pre-trained model of the algorithm into a mobile device without incurring on excessive use of computational resources.
CITATION STYLE
Frias, G., Morita, H., & Ota, T. (2019). Arrhythmia Detection with Antidictionary Coding and Its Application on Mobile Platforms. In Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST (Vol. 297 LNICST, pp. 50–67). Springer. https://doi.org/10.1007/978-3-030-34833-5_5
Mendeley helps you to discover research relevant for your work.