帕金森病冻结步态的实时监测系统

目的由于帕金森病冻结步态的突发性,临床上对其进行评估存在一定困难,为此本文研究了一种用于实时监测冻结步态的系统。方法该系统由可穿戴设备和配套的APP两部分构成,其中设备通过惯性传感器和超声波传感器采集患者腿部运动的加速度和抬脚高度数据,并传输至APP软件中,通过软件中的冻结步态识别模型进行分析。系统为构建冻结步态识别模型,首先通过实验采集12位患者的运动数据,然后经过信号预处理、特征提取和机器学习算法训练出模型,最后通过对数据集采用十折交叉验证来评估模型的准确度和精确度。结果系统对冻结步态的识别准确率可达98.6%,精确率达97.2%。结论该系统能够实时监测帕金森病患者日常生活中的冻结步态发作情况,为医生的诊疗提供定量、可靠的参考依据。     

基于支持向量机-隐马尔科夫模型的外骨骼穿戴者步速意图识别

为了提高下肢外骨骼机器人及其穿戴者行走的流畅性和人机相互协调性,本文提出了一种基于惯性传感器信号的下肢外骨骼穿戴者行走步速识别方法。首先选取大腿处和小腿处的三轴加速度和三轴角速度信号,随后根据时间窗口提取当前时刻前0.5 s的信号,以频域信号中的傅里叶变换系数为特征值。接着将支持向量机（SVM）与隐马尔科夫模型（HMM）结合作为分类模型,对该模型进行训练和步速识别。最后结合步速变化规律与人-机约束力,预测当前时刻步速大小。试验结果表明,本文提出的方法能够有效识别下肢外骨骼穿戴者的步速意图,七种步速模式识别率可达到92.14%。本文方法为实现外骨骼与穿戴者之间的人机协调控制提供了新思路和新途径。     

基于青年人足底压力测试的步态实验研究

本文基于力敏电阻(FSR)传感器,设计了压力测量鞋垫,研制出一套结构简单、稳定可靠、方便穿戴和室外实验的步态检测系统。硬件部分包括足底压力传感器阵列、信号调理单元、主电路单元三部分。系统的软件具有数据采集、信号处理、特征提取及分类等功能。系统采集了一个健康人体的27组步态数据并进行分析,研究各种步态下的压力分布特征,对平地行走、上坡、下坡、上楼梯及下楼梯5种步态模式进行模式识别与分类,通过K最近邻(KNN)分类算法达到了90%的正确率,初步验证了该系统的实用性。     

一种基于加速度信号的步态稳定性研究

目的通过不同工况下头部和腰部的加速度信号分析人体步态稳定性,与质心(center of mass,COM)-压力中心(center of pressure, COP)法进行对比,探讨应用可穿戴设备进行步态稳定性分析的可靠性。方法应用基于加速度信号的谐波比(harmonic ratio, HR)参数分析18名健康青年人在3种工况下(穿鞋自然行走、裸足自然行走、不同步速裸足行走)的行走稳定性,并与COM-COP法的评估结果比较。结果自然步速下步态最稳定,此时HR最大;裸足比穿鞋行走时HR显著减小(P0.05),步态稳定性降低。该结果与COM-COP法分析结果一致。综合步速和穿鞋影响因素,基于加速度的HR参数与COM-COP法的步态稳定性评估结果呈显著负线性相关(R~20.50),其中腰部HR具有更显著的线性相关性(R~(2 )0.60)。结论应用基于加速度信号的分析算法可以有效且可靠地评估人体步态稳定性,其中腰部加速度对步态稳定性更敏感。     

穿戴塑料踝足矫形器对下肢肌肉疲劳性的影响

背景：目前尚未见到系统研究踝足矫形器对下肢肌肉影响的文献。 目的：提取正常人穿戴固定踝足矫形器时的下肢肌电信号,分析固定踝足矫形器对下肢肌肉疲劳性的影响。 方法：选择5名健康男性受试者参加试验,每名受试者分别进行3组试验：①第1组,在不穿戴任何矫形器的情况下以自然步态行走。②第2组,受试者穿戴平跟踝足矫形器以自然步态行走(此时矫形器踝部包裹超过踝中心1 cm,记1.0 cm),穿戴同一矫形器但在踝部去掉1.0 cm、踝部塑料边缘刚好通过踝中心时采集(记     0 cm),在踝部再去掉1.0 cm后以自然步态行走(记-1.0 cm)。③第3组,受试者穿戴1.5 cm正常跟高踝足矫形器以自然步态行走,穿戴同一矫形器,但跟高分别改为1.0,2.0 cm后以自然步态行走。行走中采用肌电采集仪检测受试者下肢股二头肌、股直肌、胫骨前肌、腓肠肌的表面肌电信号。 结果与结论：①正常不穿戴任何矫形器时,4块肌肉的肌电信号是最弱的。②对于任何一块肌肉,正常不穿戴矫形器时所对应肌电值比穿戴不同硬度矫形器时所对应的肌电值要小。③对于股二头肌,正常不穿戴矫形器时所对应的积分肌电值与穿戴正常跟高矫形器时所对应的值很接近,同时这两个值要比穿戴不正常跟高矫形器时所对应的积分肌电值小。表明固定塑料踝足矫形器会引起股二头肌、股直肌、胫骨前肌、腓肠肌的疲劳,当固定塑料踝足矫形器的跟高不合适时会进一步增加股二头肌的疲劳程度。中国组织工程研究杂志出版内容重点：生物材料;骨生物材料; 口腔生物材料; 纳米材料; 缓释材料; 材料相容性;组织工程全文链接：     

基于共空间模式算法和支持向量机二重分类的癫痫发病预测

目前癫痫患者的发病预测手段十分耗时且易受主观因素干扰,因此文中提出了一种基于共空间模式算法(CSP)和支持向量机(SVM)二重分类的癫痫发病自动预测方法。此方法将提取空域特征的共空间模式算法应用到癫痫脑电信号检测中,但是该算法未考虑信号的非线性动力学特征且忽略了其时频信息,所以在特征提取阶段选取了标准差、熵和小波包能量这几种互补特征来进行组合。分类过程采取一种基于支持向量机的全新二重分类模式,即将癫痫患者正常期、发作间期和发作期三个阶段分成正常期和准发病期(包括发作间期和发作期)两类进行支持向量机识别,然后对属于准发病期的样本进行发作间期和发作期的分类,最终实现三个时期的分类识别。实验数据来自德国波恩大学的癫痫研究数据库。实验结果显示,第一重分类平均识别率为98.73%,第二重分类平均识别率可达99.90%。结果表明,引入空域特征和二重分类模式能够有效解决众多文献中发作间期和发作期识别率不高的问题,提升各个时期的识别效率,为癫痫患者的发病预测提供有效的检测手段。     

脊髓损伤患者E-MAG和落环锁式膝踝足矫形器的应用对比

背景：落环锁式膝踝足矫形器在较高位脊髓损伤患者中被广泛应用,但该矫形器在行走时有一个主要限制即摆动期膝关节锁定,导致患者在行走时需要通过上肢活动来补偿。目前有关不同矫形器治疗效果的对比鲜有研究。 目的：探究并对比E-MAG活跃型矫形器和落环锁式膝踝足矫形器在脊髓损伤患者步态提升中的临床效果。 方法：采用自身交叉对照研究的实验设计,观察E-MAG活跃型矫形器和落环锁式膝踝足矫形器在1例T10脊髓水平损伤患者中的应用效果。通过测量下肢的三维步态数据,对比摆动期允许膝关节屈曲、支撑期膝关节锁定和整个步态周期中膝关节均锁定两种步态的差异。 结果与结论：定性观察和运动学三维步态数据证明该患者在使用E-MAG活跃型矫形器时行走更快,更有效。尽管患者无法自主控制其膝关节,由于摆动期膝关节屈曲,支撑期膝关节锁定,使用E-MAG活跃型矫形器可以帮助患者在行走时更加安全和顺利,且需要的上肢补偿更加少。与落环锁膝式膝踝足矫形器相比,E-MAG活跃型矫形器包含站立期控制,因此会有更高的接受度和实用性     

基于光电容积脉搏波的精神疲劳评估方法

目的 针对精神疲劳难于定量评估的问题,本文探索一种非侵入式可穿戴检测方法获取人体生理参数,从而实现对人体精神疲劳的定量评估。方法 搭建光电容积脉搏波（photoplethysmography,PPG）采集平台,采集20名健康在校生的PPG信号,对PPG信号进行预处理和特征提取,获取时域、频域共143维特征。使用机器学习算法建立分类模型,对于Pearson相关系数法、F检验和relief-F得到的特征权值,选择最优的特征子集,使用降维后的特征子集训练模型,减少复杂度和过拟合概率。结果 与实际状态对比,基于该方法的单个体疲劳检测平均准确率为92.48%,多个体疲劳检测准确率最大值为92.2%,可以有效地识别精神疲劳。结论 光电容积脉搏波信号经过时域和频域分析构建的特征能够使用机器学习算法进行准确的精神疲劳状态分类评估。     

步态识别研究现状与进展

步态识别是生物特征识别技术中的一个新兴领域，它旨在根据人们的行走方式进行身份识别或生理、病理及心理特征检测，具有广阔的应用前景，因此引起了国内外许多研究者的浓厚兴趣，成为近年来生物医学信息检测领域备受关注的前沿方向。本文主要介绍了利用步态特征进行身份识别的基本原理与方法及其潜在的应用前景，分析了其国内外研究现状与存在的关键技术难点，并展望了其可能的发展趋势。     

可穿戴式多参数监护装置信号处理平台的设计与实现

背景：可穿戴式多参数监护装置具有生理信号检测和处理、信号特征提取和数据传输等基本功能模块,可实现对人体的无创检测、诊断。 目的：将信号处理平台运用到对时效性和精确度要求较高的可穿戴式多参数监护装置中,提高ECG信号QRS波检测的检测速度和检定准确率。 方法：提出了一种新型可穿戴式多参数监护装置信号处理平台的设计思路,应用TMS320VC5509系列DSP系统实现改进后的LADT压缩算法结合小波变换和阈值检测ECG信号中QRS波的方法。 结果与结论：采用硬件DSP的方法显著提高了QRS波检测的速度,其结果可以用于穿戴式多参数监护装置异常心电检测的实际应用。     

Investigating body motion patterns in patients with Parkinson's disease using matching pursuit algorithm

Several recent studies have quantified abnormalities in Parkinsonian gait. However, few studies have attempted to quantify the regularity of body motion during walking in patients with Parkinson's disease. The aim of the paper was to characterise body motion patterns in healthy, elderly subjects and patients with Parkinson's disease during walking. Body motion was recorded during walking for 16 patients with Parkinson's disease and ten healthy, elderly subjects using a tri-axial accelerometer device. To characterise the body motion patterns, time-frequency patterns of the body acceleration signal were estimated using a matching pursuit algorithm. Data from the study showed that the healthy, elderly subjects and patients with Parkinson's disease had different time-frequency patterns. The time-frequency patterns were classified into four distinct patterns based on their time durations: vertical (<0.15 s), circular (0.15–0.5 s), short horizontal (0.5–2.0 s) and long horizontal (>2.0 s). The data showed that the energy of the long horizontal patterns, representing long-term smooth and regular (rhythmic) activities, significantly decreased, but the energy of the circular patterns, representing irregular activities, increased in the patients with mild Parkinson's disease, compared with those of the healthy, elderly subjects (p<0.01). Futhermore, these features were seen more clearly in the body motions of severe case patients than is that of mild case patients. It was concluded that these differences are probably due to a lack of ability to control normal and smooth movement is Parkinson's disease.     

Deep Arm/Ear-ECG Image Learning for Highly Wearable Biometric Human Identification

In this study, to advance smart health applications which have increasing security/privacy requirements, we propose a novel highly wearable ECG-based user identification system, empowered by both non-standard convenient ECG lead configurations and deep learning techniques. Specifically, to achieve a super wearability, we suggest situating all the ECG electrodes on the left upper-arm, or behind the ears, and successfully obtain weak but distinguishable ECG waveforms. Afterwards, to identify individuals from weak ECG, we further present a two-stage framework, including ECG imaging and deep feature learning/identification. In the former stage, the ECG heartbeats are projected to a 2D state space, to reveal heartbeats’ trajectory behaviors and produce 2D images by a split-then-hit method. In the second stage, a convolutional neural network is introduced to automatically learn the intricate patterns directly from the ECG image representations without heavy feature engineering, and then perform user identification. Experimental results on two acquired datasets using our wearable prototype, show a promising identification rate of 98.4% (single-arm-ECG) and 91.1% (ear-ECG), respectively. To the best of our knowledge, it is the first study on the feasibility of using single-arm-ECG/ear-ECG for user identification purpose, which is expected to contribute to pervasive ECG-based user identification in smart health applications.     

Microprocessor-controlled optical stimulating device to improve the gait of patients with Parkinson's disease

Different types of visual cue for subjects with Parkinson's disease (PD) produced an improvement in gait and helped some of them prevent or overcome freezing episodes. The paper describes a portable gait-enabling device (optical stimulating glasses (OSGs) that provides, in the peripheral field of view, different types of continous optic flow (backward or forward) and intermittent stimuli synchronised with external events. The OSGs are a programmable, stand-alone, augmented reality system that can be interfaced with a PC for program set-up. It consists of a pair of non-corrective glasses, equipped with two matrixes of 70 micro light emitting diodes, one on each side, controlled by a microprocessor. Two foot-switches are used to synchronise optical stimulation with specific gait events. A pilot study was carried out on three PD patients and three controls, with different types of optic flow during walking along a fixed path. The continuous optic flow in the forward direction produced an increase in gait velocity in the PD patients (up to+11% in average), whereas the controls had small variations. The stimulation synchronised with the swing phase, associated with an attentional strategy, produced a remarkable increase in stride length for all subjects. After prolonged testing, the device has shown good applicability and technical functionality, it is easily wearable and transportable, and it does not interfere with gait.     

Comparative Motor Pre-clinical Assessment in Parkinson’s Disease Using Supervised Machine Learning Approaches

Millions of people worldwide are affected by Parkinson’s disease (PD), which significantly worsens their quality of life. Currently, the diagnosis is based on assessment of motor symptoms, but interest toward non-motor symptoms is increasing, as well. Among them, idiopathic hyposmia (IH) is associated with an increased risk of developing PD in healthy adults. In this work, a wearable inertial device, named SensFoot V2, was used to acquire motor data from 30 healthy subjects, 30 people with IH, and 30 PD patients while performing tasks from the MDS-UPDRS III for lower limb assessment. The most significant and non-correlated extracted parameters were selected in a feature array that can identify differences between the three groups of people. A comparative classification analysis was performed by applying three supervised machine learning algorithms. The system resulted able to distinguish between healthy and patients (specificity and recall equal to 0.967), and the people with IH can be identified as a separate class within a three-group classification (accuracy equal to 0.78). Thus, the system could support the clinician in objective assessment of PD. Further, identification of IH together with changes in motor parameters could be a non-invasive two-step approach to investigate the early onset of PD.     

蓝牙低功耗可穿戴血氧监测设备的设计

设计一种基于蓝牙低功耗技术的可穿戴血氧饱和度监测设备,用于实时、连续检测人体血氧饱和度和脉率。主要工作包括设计实现耳夹式光电传感器、太阳能电池插接件以及蓝牙模块等核心部件。设备和硬件设计采用低功耗元件及模块,数据通过低功耗蓝牙技术传至手机App,软件设计优化数据发送策略,具有低功耗、可穿戴、稳定可靠等特点,适合户外运动或者缺氧性疾病的血氧监测。测试表明,设备蓝牙通信误码率最终控制为0,脉率精度高达98.0%,当模拟仪输出血氧饱和度大于75%时,设备的检测精度高达97.9%。此外,创新性地使用太阳能电池进行冗余供电,整机待机电流为11 μA,全功率工作时长为18 h以上,续航性能优于市面上主流的指夹式血氧仪。     

Effects of Wearable Powered Exoskeletal Training on Functional Mobility,Physiological Health and Quality of Life in Non-ambulatory Spinal Cord Injury Patients

BackgroundSpinal cord injury (SCI) is a serious clinical condition that impacts a patient''s physical, psychological, and socio-economic status. The aim of this pilot study was to evaluate the effects of training with a newly developed powered wearable exoskeleton (Hyundai Medical Exoskeleton [H-MEX]) on functional mobility, physiological health, and quality of life in non-ambulatory SCI patients.MethodsParticipants received 60 minutes of walking training with a powered exoskeleton 3 times per week for 10 weeks (total 30 sessions). The 6-minute walking test (6MWT) and timed-up-and-go test (TUGT) were performed to assess ambulatory function. The physiological outcomes of interest after exoskeleton-assisted walking training were spasticity, pulmonary function, bone mineral density, colon transit time, and serum inflammatory markers. Effects of walking training on subjective outcomes were estimated by the Korean version of the Falls Efficacy Scale—International and the 36-Item Short-Form Health Survey version 2.ResultsTen participants finished 30 sessions of training and could ambulate independently. No severe adverse events were reported during the study. After training, the mean distance walked in the 6MWT (49.13 m) was significantly enhanced compared with baseline (20.65 m). The results of the TUGT also indicated a statistically significant improvement in the times required to stand up, walk 3 m and sit down. Although not statistically significant, clinically meaningful changes in some secondary physiological outcomes and/or quality of life were reported in some participants.ConclusionIn conclusion, this study demonstrated that the newly developed wearable exoskeleton, H-MEX is safe and feasible for non-ambulatory SCI patients, and may have potential to improve quality of life of patients by assisting bipedal ambulation. These results suggest that the H-MEX can be considered a beneficial device for chronic non-ambulatory SCI patients.Trial RegistrationClinicalTrials.gov Identifier: {"type":"clinical-trial","attrs":{"text":"NCT04055610","term_id":"NCT04055610"}}NCT04055610     

Support vector machine for classification of walking conditions using miniature kinematic sensors

A portable gait analysis and activity-monitoring system for the evaluation of activities of daily life could facilitate clinical and research studies. This current study developed a small sensor unit comprising an accelerometer and a gyroscope in order to detect shank and foot segment motion and orientation during different walking conditions. The kinematic data obtained in the pre-swing phase were used to classify five walking conditions: stair ascent, stair descent, level ground, upslope and downslope. The kinematic data consisted of anterior-posterior acceleration and angular velocity measured from the shank and foot segments. A machine learning technique known as support vector machine (SVM) was applied to classify the walking conditions. SVM was also compared with other machine learning methods such as artificial neural network (ANN), radial basis function network (RBF) and Bayesian belief network (BBN). The SVM technique was shown to have a higher performance in classification than the other three methods. The results using SVM showed that stair ascent and stair descent could be distinguished from each other and from the other walking conditions with 100% accuracy by using a single sensor unit attached to the shank segment. For classification results in the five walking conditions, performance improved from 78% using the kinematic signals from the shank sensor unit to 84% by adding signals from the foot sensor unit. The SVM technique with the portable kinematic sensor unit could automatically recognize the walking condition for quantitative analysis of the activity pattern.     

Detection of exercise periodic breathing using thermal flowmeter in patients with heart failure

Exercise periodic breathing (EPB) is associated with exercise intolerance and poor prognosis in patients with heart failure (HF). However, EPB detection during cardiopulmonary exercise test (CPET) is difficult. The present study investigated the use of a wireless monitoring device to record the EPB during CPET and proposed quantization parameter estimates for the EPB. A total of 445 patients with HF were enrolled and underwent exercise tests. The ventilation data from the wearable device were compared with the data obtained during the CPET and were analyzed based on professional opinion and on 2 automated programs (decision tree [DT] and oscillatory pattern methods). The measurement accuracy was greater with the DT method (89 %) than with the oscillatory pattern method (75 %). The cutoffs for EPB recognition using the DT method were (1) an intercept of the regression line passing through the minute ventilation rate vs. the time curve during the recovery phase ≥64.63, and (2) an oscillatory phase duration to total exercise time ratio ≥0.5828. The wearable device was suitable for the assessment of EPB in patients with HF, and our new automated analysis system using the DT method effectively identified the EPB pattern.     

The influences of psychosocial aspects and anxiety symptoms on quality of life of patients with arrhythmia: Investigation in paroxysmal atrial fibrillation

The purpose of this study was to investigate the feature of the psychosocial aspects of patients with atrial fibrillation and to explore the influences of the subjective symptoms of attack, perceived psychosocial inducers of attack, and anxiety on the quality of life (QOL). The participants were 240 patients with paroxysmal atrial fibrillation (57.89 ± 13.78 years old), who were requested to complete questionnaires on the subjective symptoms of attack, perceived psychosocial inducers of attack, anxiety symptoms, and QOL. The results of this study showed that 29.5% patients met the criteria of agoraphobia of Diagnostic and Statistical Manual of Mental Disorders (4th ed. [DSM-IV]; American Psychiatric Association, 1994). This percentage of prevalence was higher than the general prevalence of DSM-IV data. The subjective symptoms of attack (frequency, duration, and distress of attack) intensify their fear of attack and agoraphobic symptoms, which worsen their QOL. Psychological stress is the main perceived in-ducer in daily life, and a attack induced by psychological stress affects their anxiety symptoms and QOL.     

Artifacts in wearable photoplethysmographs during daily life motions and their reduction with least mean square based active noise cancellation method

Signal distortion of photoplethysmographs (PPGs) due to motion artifacts has been a limitation for developing real-time, wearable health monitoring devices. The artifacts in PPG signals are analyzed by comparing the frequency of the PPG with a reference pulse and daily life motions, including typing, writing, tapping, gesturing, walking, and running. Periodical motions in the range of pulse frequency, such as walking and running, cause motion artifacts. To reduce these artifacts in real-time devices, a least mean square based active noise cancellation method is applied to the accelerometer data. Experiments show that the proposed method recovers pulse from PPGs efficiently.