Kiranyaz S.İnce, TürkerHamila R.Gabbouj, Moncef2023-06-162023-06-1620159.78E+121557-170Xhttps://doi.org/10.1109/EMBC.2015.7318926https://hdl.handle.net/20.500.14365/352437th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 -- 25 August 2015 through 29 August 2015 -- 116805We propose a fast and accurate patient-specific electrocardiogram (ECG) classification and monitoring system using an adaptive implementation of 1D Convolutional Neural Networks (CNNs) that can fuse feature extraction and classification into a unified learner. In this way, a dedicated CNN will be trained for each patient by using relatively small common and patient-specific training data and thus it can also be used to classify long ECG records such as Holter registers in a fast and accurate manner. Alternatively, such a solution can conveniently be used for real-time ECG monitoring and early alert system on a light-weight wearable device. The experimental results demonstrate that the proposed system achieves a superior classification performance for the detection of ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB). © 2015 IEEE.eninfo:eu-repo/semantics/closedAccessalgorithmartificial neural networkelectrocardiographyheart ventricle extrasystolehumanpathophysiologyphysiologic monitoringsupraventricular premature beatAlgorithmsAtrial Premature ComplexesElectrocardiographyHumansMonitoring, PhysiologicNeural Networks (Computer)Ventricular Premature ComplexesConference Object10.1109/EMBC.2015.73189262-s2.0-84953295695