基于自适应层次分析法的脑卒中康复仪研究  

Research on Stroke Rehabilitation Device Based on Adaptive Analytic Hierarchy Process

作　　者：李春莉 胡宏美 LI Chunli;HU Hongmei(Xi’an Siyuan University,Xi’an 710038,China)

机构地区：[1]西安思源学院,西安710038

出　　处：《自动化与仪器仪表》2025年第2期275-278,283,共5页Automation & Instrumentation

基　　金：陕西省教育厅2022年度一般专项科研计划项目《医养康养结合下老年脑卒中患者养老意向及康复护理需求研究》(2022JK0152);陕西省哲学科学重大理论与现实问题研究项目《医养康养结合下老年脑卒中患者养老意向及康复护理需求研究》(2022HZ1236)。

摘　　要：针对脑卒康复中传统康复效果评估方法不能准确反映患者的真实康复状况的问题,研究将深度置信网络与层次分析法进行融合,建立一种全新的脑电信号研究方法。研究首先利用深度置信网络对脑电信号的特征进行提取,然后在特征提取的基础上将深度置信网络与层次分析法进行融合,对脑卒中患者康复效果进行有效研究。结果表明,研究构建的评估方法在脑电信号数据处理过程中的正确率和准确率分别为94.28%和96.35%。同时在脑电信号数据处理过程中的数据召回率和F1值分别为95.21%和0.93。这说明研究构建的评估研究方法能够在脑电信号处理的基础上对脑卒康复仪的效果进行有效性评估,为脑卒康复仪的发展以及脑卒患者的恢复提供重要的数据支撑。In response to the problem that traditional rehabilitation evaluation methods in stroke rehabilitation cannot accurately reflect the true rehabilitation status of patients,this study integrates deep confidence networks with analytic hierarchy process to estab-lish a new method for studying EEG signals.The study first utilizes deep confidence networks to extract features from EEG signals,and then integrates deep confidence networks with Analytic Hierarchy Process(AHP)on the basis of feature extraction to effectively study the rehabilitation effect of stroke patients.The results showed that the accuracy and precision of the evaluation method construc-ted in the study were 94.28%and 96.35%,respectively,in the process of EEG signal data processing.At the same time,the data recall rate and F1 value during EEG signal data processing are 95.21%and 0.93,respectively.This indicates that the evaluation re-search method constructed in the study can provide informative evaluation of the effectiveness of stroke rehabilitation devices based on EEG signal processing,providing important data support for the development of stroke rehabilitation devices and the recovery of stroke patients.

关 键 词：深度置信网络 层次分析法 脑卒 脑电信号 康复仪 

分 类 号：TS02[轻工技术与工程] TP29[自动化与计算机技术—检测技术与自动化装置]