FPGA Medical Big Data System and Ischemic Stroke Rehabilitation Nursing

Abstract Ischemic stroke is one of the most deadly illnesses in the world, leading to high mortality. Due to lung disease, stroke is the abnormal growth of cells characterized by a single irregular cell and spreads throughout the body. Therefore, to detect and heal the affected area at an early stage, it is necessary to detect the affected area after application. Ischemic stroke is generally regarded as an essential indicator of stroke rehabilitation care. The previous method uses SVM (Support Vector Machine) and STFT (Short Time Fourier Transform Algorithm) to process an image processing system based on stroke detection. This is more accurate and efficient for CT (Computed Tomography) images. The conversion method is significantly slower, and the advanced risk architecture cannot verify the image. The proposed FPGA (Field Programmable Gate Array) and CNN (Convolutional Neural Network) are used to develop image processing and easily interact with the database without introducing complexity. FPGA (Field Programmable Gate Array) is mainly realized by ASIC (Application Specific Integrated Circuit). The system speeds up detecting strokes and lung diseases and can be used as a single process system or another biomedical imaging system component. According to the medical big data system, the image processing system relies on bilateral filtering, edge detection, multiple thresholds, image segmentation, morphological image processing, and image labeling to collect stroke symptoms.