Attentional Knowledge-Based State-Space Model for Electrocardiogram Signal Classification

Electrocardiogram (ECG) signals inherently encode both localized fluctuations and long-range temporal dynamics, serving as essential indicators for accurate cardiovascular diagnosis. With the rapid expansion of wearable and portable ECG acquisition devices—key enablers in instrumentation and measurement (IM)—the need for robust, scalable, and noise-resilient analytical frameworks has intensified. Yet, existing deep learning approaches often struggle to jointly capture fine-grained transient patterns and global temporal structures due to the high dimensionality and complexity of ECG data. To address these challenges, we propose AttMambaECG, an advanced attentional knowledge-based state-space model designed to enhance feature representation across multiple temporal scales. The architecture comprises four hierarchical attentional state space module (SSM) blocks, each integrating an SSM to capture sequential dynamics and a multi-head self-attention mechanism to extract diverse contextual representations. An intra-attention fusion layer further enhances temporal feature coherence, while the Gaussian error linear unit (GeLU) activation improves non-linear expressivity. This design enables AttMambaECG to achieve high-fidelity modeling across varying time scales and perturbation conditions, aligning with the stringent precision demands of IM. Comprehensive evaluations on three benchmark ECG datasets demonstrate that AttMambaECG consistently outperforms 22 representative machine learning and deep learning baselines. It achieves substantial gains in accuracy, recall, precision, and F₁-score—even under severe noise conditions. Moreover, real-world deployment experiments on Raspberry Pi 4 and PYNQ-Z2 confirm its feasibility for efficient and low-latency inference on edge platforms, highlighting its practical value for mobile and wearable ECG monitoring applications.