Machine Intelligence on the Edge: Interpretable Cardiac Pattern Localization Using Reinforcement Learning

Abstract Matched filters are widely used to localize signal patterns due to their high efficiency and interpretability. However, their effectiveness deteriorates for low signal-to-noise ratio (SNR) signals, such as those recorded on edge devices, where prominent noise patterns can closely resemble the target within the limited length of the filter. One example is the ear-electrocardiogram (ear-ECG), where the cardiac signal is attenuated and heavily corrupted by artifacts. To address this, we propose the sequential matched filter (SMF), a paradigm that replaces the conventional single matched filter with a sequence of filters designed by a reinforcement learning agent. By formulating filter design as a sequential decision-making process, SMF adaptively designs signal-specific filter sequences that remain fully interpretable by revealing key patterns driving the decision-making process. The proposed SMF framework has strong potential for reliable and interpretable clinical decision support, as demonstrated by its state-of-the-art R-peak detection and physiological state classification performance on three challenging real-world ECG datasets. The proposed formulation can also be extended to a broad range of applications that require accurate pattern localization from noise-corrupted signals.