Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (6): 1687-1695.DOI: 10.11772/j.issn.1001-9081.2022060926
Special Issue: 综述; CCF第37届中国计算机应用大会 (CCF NCCA 2022)
• The 37 CCF National Conference of Computer Applications (CCF NCCA 2022) • Previous Articles Next Articles
Jing QIN1, Xueqian MA2, Fujie GAO2, Changqing JI2,3, Zumin WANG2()
Received:
2022-06-27
Revised:
2022-07-27
Accepted:
2022-07-29
Online:
2022-09-22
Published:
2023-06-10
Contact:
Zumin WANG
About author:
QIN Jing, born in 1981, Ph. D., associate professor. Her research interests include signal processing, big data analysis.Supported by:
秦静1, 马雪倩2, 高福杰2, 季长清2,3, 汪祖民2()
通讯作者:
汪祖民
作者简介:
秦静(1981—),女,甘肃张掖人,副教授,博士,CCF会员,主要研究方向:信号处理、大数据分析CLC Number:
Jing QIN, Xueqian MA, Fujie GAO, Changqing JI, Zumin WANG. Survey of Parkinson’s disease auxiliary diagnosis methods based on gait analysis[J]. Journal of Computer Applications, 2023, 43(6): 1687-1695.
秦静, 马雪倩, 高福杰, 季长清, 汪祖民. 基于步态分析的帕金森病辅助诊断方法综述[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1687-1695.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2022060926
数据集 | 数据类型 | 受试者数 | 实例数 | 基本活动 |
---|---|---|---|---|
HAR(Human Activity Recognition)[ | 加速度计线速度、 陀螺仪角速度 | 30 | 10 299 | 走路、上楼、下楼、坐、站、躺 |
USC-HAD(University of Southern California Human Activity Dataset)[ | 加速度计线速度、 陀螺仪角速度 | 14 | 2 520 000 | 向前走、向左(右)转、上(下)楼、向前跑、跳跃、 坐下、站立、睡觉等 |
Gait in Parkinson’s Disease[ | 垂直地面反作用力 | 166 | 以通常的、自行选择的速度行走大约2 min | |
Daphnet(Daphnet freezing of gait data set)[ | 加速度计线速度 | 10 | 237 | 直线行走、转弯行走、日常生活活动 |
mHealth(mobile Health)[ | 加速度计线速度、 陀螺仪角速度、 磁强计信号、 二导联心电图信号 | 10 | 16 740 | 站立、坐下和放松、躺下、行走、爬楼梯、骑自行车、慢跑、前后跳跃等 |
Tab. 1 Gait datasets of wearable devices
数据集 | 数据类型 | 受试者数 | 实例数 | 基本活动 |
---|---|---|---|---|
HAR(Human Activity Recognition)[ | 加速度计线速度、 陀螺仪角速度 | 30 | 10 299 | 走路、上楼、下楼、坐、站、躺 |
USC-HAD(University of Southern California Human Activity Dataset)[ | 加速度计线速度、 陀螺仪角速度 | 14 | 2 520 000 | 向前走、向左(右)转、上(下)楼、向前跑、跳跃、 坐下、站立、睡觉等 |
Gait in Parkinson’s Disease[ | 垂直地面反作用力 | 166 | 以通常的、自行选择的速度行走大约2 min | |
Daphnet(Daphnet freezing of gait data set)[ | 加速度计线速度 | 10 | 237 | 直线行走、转弯行走、日常生活活动 |
mHealth(mobile Health)[ | 加速度计线速度、 陀螺仪角速度、 磁强计信号、 二导联心电图信号 | 10 | 16 740 | 站立、坐下和放松、躺下、行走、爬楼梯、骑自行车、慢跑、前后跳跃等 |
方法 | 受试者数 | 受试者情况 | 安放 位置 | 实验方法 | 实验结果/% | ||
---|---|---|---|---|---|---|---|
敏感性 | 特异性 | 准确率 | |||||
文献[ | 15 | 7名男性和8名女性 | 脚踝、口袋、 腰部 | AdaBoost.M1算法分类FoG事件 | 86.00 | 92.50 | |
文献[ | 60 | 25名患者和 35名健康对照组 | 小腿 | 采用9种机器学习分类算法训练二元分类器 | 91.13 | ||
文献[ | 40 | PD患者:35名男性和 5名女性 | 手腕、脚踝 | 使用SVM检测FoG,并使用Lasso回归算法估计PD严重等级 | 89.00 | 82.00 | |
文献[ | 20 | 5名女性和 15名男性患者 | 髋关节 | 使用Moore-Bachlin算法和加入步长信息的 改进算法识别FoG事件 | 87.57 | 94.97 | 84.30 |
文献[ | 20 | H&Y量表中处于 2~4阶段患者 | 腰部 | 利用冻结阈值(FIth)和能量阈值(EIth)确定FoG事件 | 90.60±7.71 | 94.30±8.36 |
Tab. 2 Gait analysis methods based on smartphone devices
方法 | 受试者数 | 受试者情况 | 安放 位置 | 实验方法 | 实验结果/% | ||
---|---|---|---|---|---|---|---|
敏感性 | 特异性 | 准确率 | |||||
文献[ | 15 | 7名男性和8名女性 | 脚踝、口袋、 腰部 | AdaBoost.M1算法分类FoG事件 | 86.00 | 92.50 | |
文献[ | 60 | 25名患者和 35名健康对照组 | 小腿 | 采用9种机器学习分类算法训练二元分类器 | 91.13 | ||
文献[ | 40 | PD患者:35名男性和 5名女性 | 手腕、脚踝 | 使用SVM检测FoG,并使用Lasso回归算法估计PD严重等级 | 89.00 | 82.00 | |
文献[ | 20 | 5名女性和 15名男性患者 | 髋关节 | 使用Moore-Bachlin算法和加入步长信息的 改进算法识别FoG事件 | 87.57 | 94.97 | 84.30 |
文献[ | 20 | H&Y量表中处于 2~4阶段患者 | 腰部 | 利用冻结阈值(FIth)和能量阈值(EIth)确定FoG事件 | 90.60±7.71 | 94.30±8.36 |
方法 | 受试者数 | 受试者情况 | 传感器 | 实验方法 | 实验结果/% | ||
---|---|---|---|---|---|---|---|
敏感性 | 特异性 | 准确率 | |||||
文献[ 方法 | 10 | Daphnet数据集 | 可穿戴加速度计 | 使用CNN作特征提取器,LSTM对时间特征建模,引入注意力机制,使用数据扩充消除不平衡数据集对模型训练的影响 | 95.10 | 98.80 | |
文献[ 方法 | 10 | Daphnet数据集 | 加速度计传感器 | 使用KNN算法将步态分为pre-FoG,non-FoG和FoG | 94.10 | 97.10 | |
文献[ 方法 | 10 | PD患者:5名男性和 5名女性 | 加速度计、微处理器、微型SD卡 | 小批量k-means聚类算法分类为FoG和non-FoG | 92.40 | 94.90 | 93.20 |
文献[ 方法 | 32 | PD患者:22名男性和 10名女性 | 微电子机械传感器(由两个IMU传感器组成) | 计算角速度和低通滤波器(kleft,kright),使用kleft和kright之和给出的指数K最终与特定的阈值进行 比较,检测FoG事件 | 93.41 | 97.57 | 97.56 |
文献[ 方法 | 8 | 7名PD患者和 1名健康对照者 | IMU(分别安置在 左下肢和右下肢) | 通过DWT识别步态异常 | 60.61 | 86.66 | |
文献[ 方法 | 88 | PD患者:25名男性和 23名女性;健康对照组: 22名男性和18名女性 | 三轴加速度计 (左膝和右膝) | 使用4种分类算法进行分类,决策树的分类器的准确率最高 | 92.86 | 90.91 | 88.46 |
Tab. 3 Gait analysis methods based on limb wearable devices
方法 | 受试者数 | 受试者情况 | 传感器 | 实验方法 | 实验结果/% | ||
---|---|---|---|---|---|---|---|
敏感性 | 特异性 | 准确率 | |||||
文献[ 方法 | 10 | Daphnet数据集 | 可穿戴加速度计 | 使用CNN作特征提取器,LSTM对时间特征建模,引入注意力机制,使用数据扩充消除不平衡数据集对模型训练的影响 | 95.10 | 98.80 | |
文献[ 方法 | 10 | Daphnet数据集 | 加速度计传感器 | 使用KNN算法将步态分为pre-FoG,non-FoG和FoG | 94.10 | 97.10 | |
文献[ 方法 | 10 | PD患者:5名男性和 5名女性 | 加速度计、微处理器、微型SD卡 | 小批量k-means聚类算法分类为FoG和non-FoG | 92.40 | 94.90 | 93.20 |
文献[ 方法 | 32 | PD患者:22名男性和 10名女性 | 微电子机械传感器(由两个IMU传感器组成) | 计算角速度和低通滤波器(kleft,kright),使用kleft和kright之和给出的指数K最终与特定的阈值进行 比较,检测FoG事件 | 93.41 | 97.57 | 97.56 |
文献[ 方法 | 8 | 7名PD患者和 1名健康对照者 | IMU(分别安置在 左下肢和右下肢) | 通过DWT识别步态异常 | 60.61 | 86.66 | |
文献[ 方法 | 88 | PD患者:25名男性和 23名女性;健康对照组: 22名男性和18名女性 | 三轴加速度计 (左膝和右膝) | 使用4种分类算法进行分类,决策树的分类器的准确率最高 | 92.86 | 90.91 | 88.46 |
方法 | 受试者数 | 受试者情况 | 传感器 | 实验方法 | 实验结果/% | ||
---|---|---|---|---|---|---|---|
敏感性 | 特异性 | 准确率 | |||||
文献[ 方法 | 20 | PD患者 | 微型印刷电路板(包含三轴加速度计和一个微型处理器,安装在鞋垫底部) | 采用时域检测算法,使用1D垂直加速度信号或所有的3D信号进行FoG检测,与传统的频域算法进行比较 | 85.80 | 85.80 | |
文献[ 方法 | 20 | PD患者:14名男性和6名女性 | 压力传感器、三轴加速度计 | 使用OpenGo内部的算法,分析压力、力和 加速度,自动检测FoG | 96.00 | 94.00 | |
文献[ 方法 | 5 | PD患者: 5名男性 | FScan压力感应鞋垫 | 将左右脚的FScan压力框连接成一个60×42压力阵列,每一帧都被看作是一个二维图像,使用CNN对步态进行分类 | 94.30 | 95.10 | |
文献[ 方法 | 1 | 记录1个人在 6种不同情况下的步态序列 | 基于Velostat的可穿戴足部压力传感器 | 通过测量足部的压力分布,分析主要参数评估步态,其中步态模式可以通过在时域分析传感器信号,并提取主要参数进行监测 | 94.00 |
Tab. 4 Gait analysis methods based on foot wearable devices
方法 | 受试者数 | 受试者情况 | 传感器 | 实验方法 | 实验结果/% | ||
---|---|---|---|---|---|---|---|
敏感性 | 特异性 | 准确率 | |||||
文献[ 方法 | 20 | PD患者 | 微型印刷电路板(包含三轴加速度计和一个微型处理器,安装在鞋垫底部) | 采用时域检测算法,使用1D垂直加速度信号或所有的3D信号进行FoG检测,与传统的频域算法进行比较 | 85.80 | 85.80 | |
文献[ 方法 | 20 | PD患者:14名男性和6名女性 | 压力传感器、三轴加速度计 | 使用OpenGo内部的算法,分析压力、力和 加速度,自动检测FoG | 96.00 | 94.00 | |
文献[ 方法 | 5 | PD患者: 5名男性 | FScan压力感应鞋垫 | 将左右脚的FScan压力框连接成一个60×42压力阵列,每一帧都被看作是一个二维图像,使用CNN对步态进行分类 | 94.30 | 95.10 | |
文献[ 方法 | 1 | 记录1个人在 6种不同情况下的步态序列 | 基于Velostat的可穿戴足部压力传感器 | 通过测量足部的压力分布,分析主要参数评估步态,其中步态模式可以通过在时域分析传感器信号,并提取主要参数进行监测 | 94.00 |
数据集 | 数据类型 | 受试者数 | 实例数 | 基本活动 |
---|---|---|---|---|
CMU MoBo(Carnegie Mellon University Motion of Body)[ | 人体轮廓 | 25 | 600 | 慢步行、快步行、斜步行、带球步行 |
CASIA-A(CASIA dataset(A))[ | RGB | 20 | 240 | 正常行走 |
CASIA-B(CASIA dataset(B))[ | RGB、人体轮廓 | 124 | 13 680 | 正常行走、背包、穿外套 |
USF HumanID(University of South Florida Human IDentification)[ | RGB | 122 | 1 870 | 户外行走、携带公文包、不同时间间隔 |
OU-MVLP(Osaka University Multi-View Large Population) Pose[ | 骨骼序列 | 10 307 | 259 013 | 正常行走 |
Tab. 5 Gait datasets based on non-wearable devices
数据集 | 数据类型 | 受试者数 | 实例数 | 基本活动 |
---|---|---|---|---|
CMU MoBo(Carnegie Mellon University Motion of Body)[ | 人体轮廓 | 25 | 600 | 慢步行、快步行、斜步行、带球步行 |
CASIA-A(CASIA dataset(A))[ | RGB | 20 | 240 | 正常行走 |
CASIA-B(CASIA dataset(B))[ | RGB、人体轮廓 | 124 | 13 680 | 正常行走、背包、穿外套 |
USF HumanID(University of South Florida Human IDentification)[ | RGB | 122 | 1 870 | 户外行走、携带公文包、不同时间间隔 |
OU-MVLP(Osaka University Multi-View Large Population) Pose[ | 骨骼序列 | 10 307 | 259 013 | 正常行走 |
方法 | 受试 者数 | 受试者情况 | 数据类型 | 实验方法 | 实验结果/% | |
---|---|---|---|---|---|---|
精确率 | 准确率 | |||||
文献[ 方法 | 124 | CASIA-B数据集 | 连续的人体轮廓 生成CSD-maps | 利用CNN从CSD-maps中学习步态事件,对步态进行分类,实验结果显示,在90°视角下,使用6张连续的CSD-maps准确率最高 | 96.78 | |
文献[ 方法 | 60 | 其中18名为PD患者 | RGB图像(只包含 腿和脚) | 利用3D-CNN提取帧序列的多层次特征,使用特征 融合对多层次特征在时间和空间维度上进行聚合 | 92.10 | 90.80 |
文献[ 方法 | 124 | CASIA-B数据集 | 步态能量图像 (Gait Energy Image, GEI) | 应用PixelDTGAN模型,提出了GaitGAN方法, GAN模型作为回归器,生成不变步态图像 | 62.80 | |
文献[ 方法 | 约4 124 | OULP数据集约有4 000名; CASIA-B数据集有124名 | 步态轮廓图像 | 提出DeepGait方法,将原始轮廓图像进行归一化,检测步态周期,将步态周期送入VGG-D进行步态识别 | 94.30 | |
文献[ 方法 | 124 | CASIA-B数据集 | 人体轮廓 | 使用一个具有两级结构的3D-CNN识别多视角下的 步态 | 96.10 |
Tab. 6 Gait analysis methods based on human silhouette
方法 | 受试 者数 | 受试者情况 | 数据类型 | 实验方法 | 实验结果/% | |
---|---|---|---|---|---|---|
精确率 | 准确率 | |||||
文献[ 方法 | 124 | CASIA-B数据集 | 连续的人体轮廓 生成CSD-maps | 利用CNN从CSD-maps中学习步态事件,对步态进行分类,实验结果显示,在90°视角下,使用6张连续的CSD-maps准确率最高 | 96.78 | |
文献[ 方法 | 60 | 其中18名为PD患者 | RGB图像(只包含 腿和脚) | 利用3D-CNN提取帧序列的多层次特征,使用特征 融合对多层次特征在时间和空间维度上进行聚合 | 92.10 | 90.80 |
文献[ 方法 | 124 | CASIA-B数据集 | 步态能量图像 (Gait Energy Image, GEI) | 应用PixelDTGAN模型,提出了GaitGAN方法, GAN模型作为回归器,生成不变步态图像 | 62.80 | |
文献[ 方法 | 约4 124 | OULP数据集约有4 000名; CASIA-B数据集有124名 | 步态轮廓图像 | 提出DeepGait方法,将原始轮廓图像进行归一化,检测步态周期,将步态周期送入VGG-D进行步态识别 | 94.30 | |
文献[ 方法 | 124 | CASIA-B数据集 | 人体轮廓 | 使用一个具有两级结构的3D-CNN识别多视角下的 步态 | 96.10 |
方法 | 受试者数 | 受试者情况 | 数据 类型 | 实验方法 | 实验结果/% | ||
---|---|---|---|---|---|---|---|
敏感性 | 特异性 | 准确率 | |||||
文献[ 方法 | 199 | 其中157名是基于MDS-UPDRS; 42名用于测试 | 骨骼 序列 | 将骨骼序列输入2s-ST-AGCN模型,将它分为关节流和 骨流,分别送入独立的ST-GCN结构中对PD步态进行分类 | 98.90 | ||
文献[ 方法 | Kinect数据集;NTU RGB+D 数据集含有40名受试者 | 骨骼 序列 | 提出ST-GCN,在骨骼序列上构建时空图,应用ST-GCN,在图上生成高级特征,最后由标准的Softmax分类器分类相应动作类别 | 88.30 | |||
文献[ 方法 | 45 | 全部为PD患者 | 视频 帧 | 使用GCN,并使用解剖关节图描述FoG的步态模式 | 81.90 | 82.10 | 82.10 |
文献[ 方法 | 124 | CASIA-B数据集 | RGB 图片 | 提出GaitGraph方法,通过HRNet提取骨骼序列,将该序列输入ResGCN嵌入步态特征 | 87.70 | ||
文献[ 方法 | SBU Kinect数据集;NTU RGB+D 数据集含有40个对象 | 骨骼 序列 | 使用STA-LSTM网络,使用时空注意力模块关注人体骨骼关键特征,并引入正则化的交叉熵损失驱动模型学习 | 91.51 |
Tab. 7 Gait analysis methods based on human joints
方法 | 受试者数 | 受试者情况 | 数据 类型 | 实验方法 | 实验结果/% | ||
---|---|---|---|---|---|---|---|
敏感性 | 特异性 | 准确率 | |||||
文献[ 方法 | 199 | 其中157名是基于MDS-UPDRS; 42名用于测试 | 骨骼 序列 | 将骨骼序列输入2s-ST-AGCN模型,将它分为关节流和 骨流,分别送入独立的ST-GCN结构中对PD步态进行分类 | 98.90 | ||
文献[ 方法 | Kinect数据集;NTU RGB+D 数据集含有40名受试者 | 骨骼 序列 | 提出ST-GCN,在骨骼序列上构建时空图,应用ST-GCN,在图上生成高级特征,最后由标准的Softmax分类器分类相应动作类别 | 88.30 | |||
文献[ 方法 | 45 | 全部为PD患者 | 视频 帧 | 使用GCN,并使用解剖关节图描述FoG的步态模式 | 81.90 | 82.10 | 82.10 |
文献[ 方法 | 124 | CASIA-B数据集 | RGB 图片 | 提出GaitGraph方法,通过HRNet提取骨骼序列,将该序列输入ResGCN嵌入步态特征 | 87.70 | ||
文献[ 方法 | SBU Kinect数据集;NTU RGB+D 数据集含有40个对象 | 骨骼 序列 | 使用STA-LSTM网络,使用时空注意力模块关注人体骨骼关键特征,并引入正则化的交叉熵损失驱动模型学习 | 91.51 |
1 | 崔亚欢,陈乃耀. 帕金森病的发病机制研究[J]. 中华老年心脑血管病杂志, 2019, 21(1):106-110. 10.3969/j.issn.1009-0126.2019.01.028 |
CUI Y H, CHEN N Y. Study on the pathogenesis of Parkinson’s disease[J]. Chinese Journal of Geriatric Heart Brain and Vessel Diseases, 2019, 21(1):106-110. 10.3969/j.issn.1009-0126.2019.01.028 | |
2 | DAUER W, PRZEDBORSKI S. Parkinson’s disease: mechanisms and models [J]. Neuron, 2003, 39(6): 889-909. 10.1016/s0896-6273(03)00568-3 |
3 | KONDRAGUNTA J, WIEDE C, HIRTZ G. Gait analysis for early Parkinson’s disease detection based on deep learning[J]. Current Directions in Biomedical Engineering, 2019, 5(1):9-12. 10.1515/cdbme-2019-0003 |
4 | GODOI B B, AMORIM G D, QUIROGA D G, et al. Parkinson’s disease and wearable devices, new perspectives for a public health issue: an integrative literature review[J]. Revista da Associação Médica Brasileira, 2019, 65(11):1413-1420. 10.1590/1806-9282.65.11.1413 |
5 | NIYOGI S A, ADELSON E H. Analyzing gait with spatiotemporal surfaces [C]// Proceedings of the 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects. Piscataway: IEEE, 1994: 64-69. 10.1109/mnrao.1994.346262 |
6 | 王科俊,丁欣楠,邢向磊,等. 多视角步态识别综述[J]. 自动化学报, 2019, 45(5):841-852. 10.16383/j.aas.2018.c170559 |
WANG K J, DING X N, XING X L, et al. A survey of multi-view gait recognition[J]. Acta Automatica Sinica, 2019, 45(5): 841-852. 10.16383/j.aas.2018.c170559 | |
7 | SILVA DE LIMA A L, EVERS L J W, HAHN T, et al. Freezing of gait and fall detection in Parkinson’s disease using wearable sensors: a systematic review[J]. Journal of Neurology, 2017, 264(8): 1642-1654. 10.1007/s00415-017-8424-0 |
8 | BROGNARA L, PALUMBO P, GRIMM B, et al. Assessing gait in Parkinson’s disease using wearable motion sensors: a systematic review [J]. Diseases, 2019, 7(1): 18. 10.3390/diseases7010018 |
9 | 田皓宇,马昕,李贻斌. 基于骨架信息的异常步态识别方法[J]. 吉林大学学报(工学版), 2022, 52(4):725-737. |
TIAN H Y, MA X, LI Y B. Skeleton-based abnormal gait recognition: a survey[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(4): 725-737. | |
10 | SON H, PARK W S, KIM H. Mobility monitoring using smart technologies for Parkinson’s disease in free-living environment[J]. Collegian, 2018, 25(5): 549-560. 10.1016/j.colegn.2017.11.005 |
11 | 陈龙. 基于移动终端的帕金森疾病筛查系统的研究与实现[D]. 成都:电子科技大学, 2021: 13. |
CHEN L. Research and implementation of Parkinson’s disease screening system based on mobile terminals[D]. Chengdu: University of Electronic Science and Technology of China, 2021: 13. | |
12 | Movement Disorder Society Task Force on Rating Scales for Parkinson’s Disease. The Unified Parkinson’s Disease Rating Scale (UPDRS): status and recommendations[J]. Movement Disorders, 2003, 18(7): 738-750. 10.1002/mds.10473 |
13 | GILADI N, SHABTAI H, SIMON E S, et al. Construction of freezing of gait questionnaire for patients with Parkinsonism[J]. Parkinsonism and Related Disorders, 2000, 6(3):165-170. 10.1016/s1353-8020(99)00062-0 |
14 | NIEUWBOER A, ROCHESTER L, HERMAN T, et al. Reliability of the new freezing of gait questionnaire: agreement between patients with Parkinson’s disease and their carers[J]. Gait and Posture, 2009, 30(4):459-463. 10.1016/j.gaitpost.2009.07.108 |
15 | WRISLEY D M, MARCHETTI G F, KUHARSKY D K, et al. Reliability, internal consistency, and validity of data obtained with the functional gait assessment [J]. Physical Therapy, 2004, 84(10):906-918. 10.1093/ptj/84.10.906 |
16 | PODSIADLO D, RICHARDSON S. The Timed “Up & Go”: a test of basic functional mobility for frail elderly persons [J]. Journal of the American Geriatrics Society, 1991, 39(2):142-148. 10.1111/j.1532-5415.1991.tb01616.x |
17 | RAMAKER C, MARINUS J, STIGGELBOUT A M, et al. Systematic evaluation of rating scales for impairment and disability in Parkinson’s disease [J]. Movement Disorders, 2002, 17(5): 867-876. 10.1002/mds.10248 |
18 | PRASANTH H, CABAN M, KELLER U, et al. Wearable sensor-based real-time gait detection: a systematic review[J]. Sensors, 2021, 21(8): No.2727. 10.3390/s21082727 |
19 | BENSON L C, CLERMONT C A, BOŠNJAK E, et al. The use of wearable devices for walking and running gait analysis outside of the lab: a systematic review[J]. Gait and Posture, 2018, 63: 124-138. 10.1016/j.gaitpost.2018.04.047 |
20 | SEPAS-MOGHADDAM A, ETEMAD A. Deep gait recognition: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 264-284. 10.1109/tpami.2022.3151865 |
21 | ANGUITA D, GHIO A, ONETO L, et al. A public domain dataset for human activity recognition using smartphones [EB/OL].[2022-05-06].. 10.1007/978-3-642-40728-4_54 |
22 | ZHANG M, SAWCHUK A A. USC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors[C]// Proceedings of the 2012 ACM Conference on Ubiquitous Computing. New York: ACM, 2012: 1036-1043. 10.1145/2370216.2370438 |
23 | HAUSDORFF J. Gait in Parkinson’s disease[DB/OL]. (2008-02-25) [2022-05-06].. 10.1201/9780203508596.ch17 |
24 | UCI. Daphnet freezing of gait data set[DB/OL]. [2022-05-06]. . |
25 | BANOS O, GARCIA R, HOLGADO-TERRIZA J A, et al. mHealthDroid: a novel framework for agile development of mobile health applications [C]// Proceedings of the 6th International Work-Conference on Ambient Assisted Living and Daily Activities. Cham: Springer, 2014: 91-98. 10.1007/978-3-319-13105-4_14 |
26 | KIM H, LEE H J, LEE W, et al. Unconstrained detection of freezing of gait in Parkinson’s disease patients using smartphone[C]// Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway: IEEE, 2015: 3751-3754. 10.1109/EMBC.2015.7319209 |
27 | ALTILIO R, ROSSETTI A, FANG Q, et al. A comparison of machine learning classifiers for smartphone-based gait analysis[J]. Medical and Biological Engineering and Computing, 2021, 59(3): 535-546. 10.1007/s11517-020-02295-6 |
28 | PAN D, DHALL R, LIEBERMAN A, et al. A mobile cloud-based Parkinson’s disease assessment system for home-based monitoring[J]. JMIR mHealth and uHealth, 2015, 3(1): No.e29. 10.2196/mhealth.3956 |
29 | CAPECCI M, PEPA L, VERDINI F, et al. A smartphone-based architecture to detect and quantify freezing of gait in Parkinson’s disease [J]. Gait and Posture, 2016, 50:28-33. 10.1016/j.gaitpost.2016.08.018 |
30 | TANG S T, TAI C H, YANG C Y, et al. Feasibility of smartphone-based gait assessment for Parkinson’s disease[J]. Journal of Medical and Biological Engineering, 2020, 40(4): 582-591. 10.1007/s40846-020-00551-6 |
31 | LI B C, YAO Z M, WANG J G, et al. Improved deep learning technique to detect freezing of gait in Parkinson’s disease based on wearable sensors [J]. Electronics, 2020, 9(11): No.1919. 10.3390/electronics9111919 |
32 | DEMROZI F, BACCHIN R, TAMBURIN S, et al. Toward a wearable system for predicting freezing of gait in people affected by Parkinson’s disease[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 24(9): 2444-2451. 10.1109/jbhi.2019.2952618 |
33 | LI B, ZHANG Y Q, TANG L, et al. Automatic detection system for freezing of gait in Parkinson’s disease based on the clustering algorithm [C]// Proceedings of the 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference. Piscataway: IEEE, 2018:1640-1644. 10.1109/imcec.2018.8469471 |
34 | KITA A, LORENZI P, RAO R, et al. Reliable and robust detection of freezing of gait episodes with wearable electronic devices [J]. IEEE Sensors Journal, 2017, 17(6): 1899-1908. 10.1109/jsen.2017.2659780 |
35 | PUNIN C, BARZALLO B, HUERTA M, et al. Wireless devices to restart walking during an episode of FOG on patients with Parkinson’s disease[C]// Proceedings of the IEEE 2nd Ecuador Technical Chapters Meeting. Piscataway: IEEE, 2017: 1-6. 10.1109/etcm.2017.8247520 |
36 | AICH S, PRADHAN P M, CHAKRABORTY S, et al. Design of a machine learning-assisted wearable accelerometer-based automated system for studying the effect of dopaminergic medicine on gait characteristics of Parkinson’s patients[J]. Journal of Healthcare Engineering, 2020, 2020: No.1823268. 10.1155/2020/1823268 |
37 | KWON Y, PARK S H, KIM J W, et al. A practical method for the detection of freezing of gait in patients with Parkinson’s disease[J]. Clinical Interventions in Aging, 2014, 9: 1709-1719. 10.2147/cia.s69773 |
38 | MARCANTE A, DI MARCO R, GENTILE G, et al. Foot pressure wearable sensors for freezing of gait detection in Parkinson’s disease [J]. Sensors, 2021, 21(1): No.128. 10.3390/s21010128 |
39 | BÄCHLIN M, PLOTNIK M, ROGGEN D, et al. Wearable assistant for Parkinson’s disease patients with the freezing of gait symptom[J]. IEEE Transactions on Information Technology in Biomedicine, 2010, 14(2): 436-446. 10.1109/titb.2009.2036165 |
40 | SHALIN G, PARDOEL S, NANTEL J, et al. Prediction of freezing of gait in Parkinson’s disease from foot plantar-pressure arrays using a convolutional neural network[C]// Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway: IEEE, 2020: 244-247. 10.1109/embc44109.2020.9176382 |
41 | BUCINSKAS V, DZEDZICKIS A, ROZENE J, et al. Wearable feet pressure sensor for human gait and falling diagnosis[J]. Sensors, 2021, 21(15): No.5240. 10.3390/s21155240 |
42 | GUO R, SHAO X X, ZHANG C C, et al. Multi-scale sparse graph convolutional network for the assessment of Parkinsonian gait[J]. IEEE Transactions on Multimedia, 2022, 24:1583-1594. 10.1109/tmm.2021.3068609 |
43 | GROSS R, SHI J B. The CMU Motion of Body (MOBO) database: CMU-RI-TR-01-18 [R/OL]. (2001-06) [2022-07-06].. |
44 | WANG L, TAN T N, NING H Z, et al. Silhouette analysis-based gait recognition for human identification [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(12): 1505-1518. 10.1109/tpami.2003.1251144 |
45 | YU S Q, TAN D L, TAN T N. A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition [C]// Proceedings of the 18th International Conference on Pattern Recognition. Piscataway: IEEE, 2006,4: 441-444. 10.1109/icpr.2006.67 |
46 | SARKAR S, PHILLIPS P J, LIU Z Y, et al. The HumanID gait challenge problem: data sets, performance, and analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(2): 162-177. 10.1109/tpami.2005.39 |
47 | AN W Z, YU S Q, MAKIHARA Y, et al. Performance evaluation of model-based gait on multi-view very large population database with pose sequences[J]. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2020, 2(4): 421-430. 10.1109/tbiom.2020.3008862 |
48 | 赵子建. 基于步态分析的运动障碍疾病诊断恢复辅助系统研究[D].杭州:浙江大学, 2020: 14. |
ZHAO Z J. Research on dyskinesia assisted diagnosis and recovery system based on gait analysis [D]. Hangzhou: Zhejiang University, 2020: 14. | |
49 | TANG Y Q, LI Z R, TIAN H W, et al. Detecting toe-off events utilizing a vision-based method[J]. Entropy, 2019, 21(4): No.329. 10.3390/e21040329 |
50 | CAO X G, XUE Y Z, CHEN J S, et al. Video based shuffling step detection for Parkinsonian patients using 3D convolution [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 641-649. 10.1109/tnsre.2021.3062416 |
51 | YU S Q, CHEN H F, GARCÍA REYES E B, et al. GaitGAN: invariant gait feature extraction using generative adversarial networks[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2017: 532-539. 10.1109/cvprw.2017.80 |
52 | ZHANG X F, SUN S Q, LI C, et al. DeepGait: a learning deep convolutional representation for gait recognition [C]// Proceedings of the 2017 Chinese Conference on Biometric Recognition, LNCS 10568. Cham: Springer, 2017: 447-456. |
53 | THAPAR D, NIGAM A, AGGARWAL D, et al. VGR-net: a view invariant gait recognition network[C]// Proceedings of the IEEE 4th International Conference on Identity, Security, and Behavior Analysis. Piscataway: IEEE, 2018: 1-8. 10.1109/isba.2018.8311475 |
54 | YOO D, KIM N, PARK S, et al. Pixel-level domain transfer [C]// Proceedings of the 2016 European Conference on Computer Vision, LNCS 9912. Cham: Springer, 2016: 517-532. |
55 | YAN S J, XIONG Y J, LIN D H. Spatial temporal graph convolutional networks for skeleton-based action recognition [C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2018: 7444-7452. 10.1609/aaai.v32i1.12328 |
56 | HU K, WANG Z Y, MEI S H, et al. Vision-based freezing of gait detection with anatomic directed graph representation[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 24(4):1215-1225. 10.1109/jbhi.2019.2923209 |
57 | TEEPE T, KHAN A, GILG J, et al. GaitGraph: graph convolutional network for skeleton-based gait recognition[C]// Proceedings of the 2021 IEEE International Conference on Image Processing. Piscataway: IEEE, 2021: 2314-2318. 10.1109/icip42928.2021.9506717 |
58 | SUN K, XIAO B, LIU D, et al. Deep high-resolution representation learning for human pose estimation[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 5686-5696. 10.1109/cvpr.2019.00584 |
59 | SONG Y F, ZHANG Z, SHAN C F, et al. Stronger, faster and more explainable: a graph convolutional baseline for skeleton-based action recognition[C]// Proceedings of the 28th ACM International Conference on Multimedia. New York: ACM, 2020: 1625-1633. 10.1145/3394171.3413802 |
60 | SONG S J, LAN C L, XING J L, et al. An end-to-end spatio-temporal attention model for human action recognition from skeleton data [C]// Proceedings of the 31st AAAI Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2017: 4263-4270. 10.1609/aaai.v31i1.11212 |
[1] | Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974. |
[2] | Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918. |
[3] | Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877. |
[4] | Yunchuan HUANG, Yongquan JIANG, Juntao HUANG, Yan YANG. Molecular toxicity prediction based on meta graph isomorphism network [J]. Journal of Computer Applications, 2024, 44(9): 2964-2969. |
[5] | Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703. |
[6] | Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557. |
[7] | Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion [J]. Journal of Computer Applications, 2024, 44(8): 2618-2625. |
[8] | Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650. |
[9] | Zheng WU, Zhiyou CHENG, Zhentian WANG, Chuanjian WANG, Sheng WANG, Hui XU. Deep learning-based classification of head movement amplitude during patient anaesthesia resuscitation [J]. Journal of Computer Applications, 2024, 44(7): 2258-2263. |
[10] | Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072. |
[11] | Zhi ZHANG, Xin LI, Naifu YE, Kaixi HU. DKP: defending against model stealing attacks based on dark knowledge protection [J]. Journal of Computer Applications, 2024, 44(7): 2080-2086. |
[12] | Yiqun ZHAO, Zhiyu ZHANG, Xue DONG. Anisotropic travel time computation method based on dense residual connection physical information neural networks [J]. Journal of Computer Applications, 2024, 44(7): 2310-2318. |
[13] | Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199. |
[14] | Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215. |
[15] | Yajuan ZHAO, Fanjun MENG, Xingjian XU. Review of online education learner knowledge tracing [J]. Journal of Computer Applications, 2024, 44(6): 1683-1698. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||