Revolutionizing attack detection in healthcare WSNs with stereoscopic scalable quantum convolutional neural networks

Attack Detection (AD) in healthcare-based wireless sensor networks (H-WSNs) presents major challenges due to low processing speeds, limited storage, poor detection rates, long deployment times, restricted communication ranges, and reduced energy efficiency. These limitations hinder effective implementation and expose networks to security threats. The complexity of existing methods, especially the curse of dimensionality, further reduces detection efficiency and accuracy. This research addresses these challenges by optimizing storage, computational time, and detection accuracy through a three-phase approach: pre-processing, dimensionality reduction, and classification. First, raw patient health data is enhanced using the Guided Box Filtering (GBF) method. Next, dimensionality reduction is performed using Principal Component Analysis (PCA) with Lotus Effect Optimization (LEO), termed QLPAFMT-LEO. This hybrid method improves parameter interpretation, reduces computational time, and minimizes space complexity. Finally, the Stereoscopic Scalable Quantum Convolutional Neural Networks (SSQCNN) model is applied to classify normal, black hole, and grayhole attacks. To enhance accuracy, the Gooseneck Barnacle Optimization Algorithm (GBOA) optimizes SSQCNN parameters. The proposed SSQCNN-GBOA model is validated using the NS2.34 network simulator, demonstrating superior AD, optimized computational efficiency, and reduced energy consumption. This approach significantly enhances H-WSN security and operational performance, making it a robust solution for real-world deployment.