QSRN: QUANTUM SPIKING RESIDUAL NETWORK FOR DISEASE DETECTION-BASED MULTIMODAL SIGNAL USING WEARABLE SENSORS

The recent development establishes an advance in medical care methodology by introducing a Smart Healthcare Wearable Device for earlier disease detection utilizing Deep Learning (DL). This wearable sensor operates with different arrangements of sensors, gathering more important measures like heart rate and Blood Pressure (BP). Wearable sensors for earlier disease detection appeal as a significant requirement for defensive medical care solutions in this period, wherein earlier involvement is critical. Nevertheless, the incorporation and design of Internet of Things (IoT)-based wearable sensors provide more complexities, particularly in the region of data exchange, monitoring, and examination of patients. To overcome this consequence, Disease Detection (DD) from multimodal signals is designed employing a Quantum Spiking Residual Network (QSRN). The wearable sensors are simulated, and then multimodal signals of Electrocardiogram (ECG) and BP signals are preprocessed using Savitzky–Golay (SG) filtering. Furthermore, the DD is implemented utilizing QSRN. Here, the Spiking Residual Network (S-ResNet) and Quantum Neural Network (QNN) are combined for the QSRN network. The assessment metrics taken for QSRN, namely, Accuracy, True Positive Rate (TPR), and False Positive Rate (FPR), acquired 91.640%, 90.721%, and 8.728%.