Yang Xiaodong, Shah Syed Aziz, Ren Aifeng, Fan Dou, Zhao Nan, Cao Dongjian, Hu Fangming, Ur Rehman Masood, Wang Weigang, Von Deneen Karen M, Tian Jie
School of Electronic EngineeringXidian UniversityXi'an710071China.
School of Life Science and Technology and School of International EducationXidian UniversityXi'an710071China.
IEEE J Transl Eng Health Med. 2018 Jan 24;6:2000107. doi: 10.1109/JTEHM.2017.2789298. eCollection 2018.
Essential tremor (ET) is a neurological disorder characterized by rhythmic, involuntary shaking of a part or parts of the body. The most common tremor is seen in the hands/arms and fingers. This paper presents an evaluation of ETs monitoring based on finger-to-nose test measurement as captured by small wireless devices working in shortwave or [Formula: see text]-band frequency range. The acquired signals in terms of amplitude and phase information are used to detect a tremor in the hands. Linearly transforming raw phase data acquired in the [Formula: see text]-band were carried out for calibrating the phase information and to improve accuracy. The data samples are used for classification using support vector machine algorithm. This model is used to differentiate the tremor and nontremor data efficiently based on secondary features that characterize ET. The accuracy of our measurements maintains linearity, and more than 90% accuracy rate is achieved between the feature set and data samples.
特发性震颤（ET）是一种神经系统疾病，其特征是身体的一个或多个部位出现有节奏的、不由自主的颤抖。最常见的震颤出现在手部/手臂和手指。本文介绍了一种基于手指对鼻子测试测量的特发性震颤监测评估方法，该测量由工作在短波或[公式：见文本]频段频率范围内的小型无线设备捕获。根据幅度和相位信息获取的信号用于检测手部的震颤。对在[公式：见文本]频段获取的原始相位数据进行线性变换，以校准相位信息并提高准确性。数据样本使用支持向量机算法进行分类。该模型用于根据表征特发性震颤的次要特征有效地区分震颤和非震颤数据。我们测量的准确性保持线性，在特征集和数据样本之间实现了超过90%的准确率。
