Key result
Novel Wave-Segment Synthesizing lightweight CNN increases cardiovascular anomaly detection accuracy ~40% vs. existing models.
Why the study?
Existing models for cardiovascular anomaly detection on wearable devices are vulnerable to deterioration from stochastic environmental factors such as pressure, altitude, and temperature.
Does the WSS algorithm improve cardiovascular anomaly detection accuracy on lightweight systems compared to existing models?
Does the WSS algorithm improve cardiovascular anomaly detection accuracy on lightweight systems compared to existing models?
The proposed WSS algorithm significantly improves ECG anomaly detection accuracy for wearable devices, offering robust performance across varying environmental conditions.
AbstractThe proposed study brings a novel classification and detection ability for stochastic environmental conditions by its WSS (Wave-Segment Synthesizing) functionality by tightly adapting a Lightweight CNN with an increase of about 40% accuracy over the literature. This study synthesizes heterogeneously coherent ECG signals and adapts them to the input system of wearable devices. It consists of novel operations which are called Wave Form Geneticization, ECG Segment Shifting, Time Contraction, and Expansion, Magnification, Projection, Permutation, Upscaling, Downscaling, Noising, and Denoising on the signal pattern to ensure a robust anomaly detection mechanism in such a sensor-independent and tempered manner. The proposed WSS Algorithm for heterogeneous harmonization of ECG signals differs from the literature by its robust classification capability of anomalies even in the weakest, loudest, most unstable, and most corrupt data collection environments. It provides a platform-independent mechanism for wearable technologies with low computational capability. Thus, anomaly detection will be more accessible to following the disorders in the circulatory system and making an early diagnosis before death. It mitigates the vulnerabilities of literature models that are affected by the deterioration of environmental factors such as sea level, pressure, optical effects, altitude, and temperature. The applied dynamic algorithm is a candidate to be a pioneer for detecting abnormalities in the heart that closely concerns all body systems in the human body.Keywords: Cardiovascular anomalyconvolutional neural networksECG signalMIT-BIH arrhythmia databasesignal processing Disclosure statementNo potential conflict of interest was reported by the authors.Additional informationFundingThis work was supported by the Roketsan under Grant graduate support programs.
No takes yet. Share an insight, caveat, or question.
Çakal et al. (2023) studied Cardiovascular anomaly. Wave-Segment Synthesizing (WSS) algorithm with Lightweight CNN vs. Literature models was evaluated on Classification and detection accuracy. A novel Wave-Segment Synthesizing algorithm adapted to a lightweight CNN increased cardiovascular anomaly detection accuracy by about 40% compared to existing literature models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: