STRIDE: Systematic Radar Intelligence Analysis for ADRD Risk Evaluation With Gait Signature Simulation and Deep Learning
STRIDE: Systematic Radar Intelligence Analysis for ADRD Risk Evaluation With Gait Signature Simulation and Deep Learning
复制标题
DOI：
10.1109/jsen.2023.3263071
复制
发表时间：
2023-05
影响因子：
4.3
通讯作者：
Fulin Cai;Abhidnya Patharkar;Teresa Wu;F. Lure;Harry Chen;V. C. Chen
中科院分区：
文献类型：
--
作者：
Fulin Cai;Abhidnya Patharkar;Teresa Wu;F. Lure;Harry Chen;V. C. Chen
步态异常是阿尔茨海默病(AD)和AD相关痴呆(ADRD)的一个重要的非认知生物标志物。微多普勒雷达(MDR)是一项不可穿戴的技术，可以捕捉人体步态运动，用于潜在的早期ADRD风险评估。在本文中，我们建议设计一种系统的雷达情报分析，用于ARDR风险评估(STRDE)，将MDR传感器与先进的人工智能(AI)技术相结合。STRIDE嵌入了一个新的深度学习(DL)分类框架。作为概念验证，我们开发了一个由人类行走模拟模型和MDR模拟模型组成的STRIDE数字孪生模型，以生成步态特征数据集。该步行模型采用已建立的人体行走参数，模拟了不同条件下患有ADRD的个体。基于电磁散射的雷达模型和多普勒频移模型被用来生成不同运动身体部位(如脚、肢体、关节、躯干和肩部)的微多普勒特征。开发了一个依赖于频带的DL框架来预测ADRD风险。实验结果验证了STRIDE用于评估ADRD风险的有效性和可行性。
Abnormal gait is a significant noncognitive biomarker for Alzheimer’s disease (AD) and AD-related dementia (ADRD). Micro-Doppler radar (MDR), a nonwearable technology, can capture human gait movements for potential early ADRD risk assessment. In this article, we propose to design a systematic radar intelligence analysis for ARDR risk evaluation (STRIDE) integrating MDR sensors with advanced artificial intelligence (AI) technologies. STRIDE embeds a new deep learning (DL) classification framework. As a proof of concept, we develop a “digital twin” of STRIDE, consisting of a human walking simulation model and an MDR simulation model, to generate a gait signature dataset. Taking established human walking parameters, the walking model simulates individuals with ADRD under various conditions. The radar model based on electromagnetic scattering and the Doppler frequency shift model is employed to generate micro-Doppler signatures from different moving body parts (e.g., foot, limb, joint, torso, and shoulder). A band-dependent DL framework is developed to predict ADRD risks. The experimental results demonstrate the effectiveness and feasibility of STRIDE for evaluating ADRD risk.