چکیده مقاله
Parkinson's disease PD is a progressive neurodegenerative disorder affecting the motor system, caused by the degeneration of nerve cells in the brain's basal ganglia, leading to reduced dopamine levels This reduction impairs motor control, resulting in symptoms like tremors, muscle rigidity, bradykinesia slowness of movement , and balance issues Early diagnosis can significantly improve treatment outcomes and patient quality of life Despite advances in diagnosis and treatment of PD, early and accurate detection remains challenging Modern techniques like artificial intelligence AI and machine learning are being used to enhance diagnostic precision and enable personalized treatments This study introduces a novel approach combining Convolutional Neural Networks CNNs and fuzzy membership functions for detecting PD from medical images Various fuzzy membership functions were integrated into the CNN structure, leading to perfect accuracy of 1 00 for the proposed model These functions effectively modeled complex, nonlinear relationships in the data and extracted diverse features Additionally, the deployment of Takagi Sugeno TSK and the pre trained EfficientNetB0 models maintained similar accuracy The EfficientNetB0 model leveraged broader data features, contributing to precise disease detection The results demonstrate that combining fuzzy membership functions with CNNs and pre trained models is a highly efficient method for analyzing complex medical data, paving the way for improved disease diagnosis
کلیدواژهها
نویسندگان
Elham Bagheri
University of Zanjan, Zanjan, Iran
Leila Safari
University of Zanjan, Zanjan, Iran
شیوه ارجاع
Bagheri, Elham and Safari, Leila,1404,Intelligent Detection of Parkinson Disease based on Deep Learning and Fuzzy Logic,19th International Conference on Health, Treatment and Health Promotion
ارائهشده در
مجموعه مقالات نوزدهمین کنفرانس بین المللی بهداشت، درمان و ارتقای سلامت20 فروردین 1404