Biswas Dwaipayan, Cranny Andy, Gupta Nayaab, Maharatna Koushik, Achner Josy, Klemke Jasmin, Jöbges Michael, Ortmann Steffen
Faculty of Physical Sciences and Engineering, University of Southampton, Hampshire, UK.
Brandenburg Klinik, Bernau, Berlin, Germany.
Hum Mov Sci. 2015 Apr;40:59-76. doi: 10.1016/j.humov.2014.11.013. Epub 2014 Dec 19.
In this paper we present a methodology for recognizing three fundamental movements of the human forearm (extension, flexion and rotation) using pattern recognition applied to the data from a single wrist-worn, inertial sensor. We propose that this technique could be used as a clinical tool to assess rehabilitation progress in neurodegenerative pathologies such as stroke or cerebral palsy by tracking the number of times a patient performs specific arm movements (e.g. prescribed exercises) with their paretic arm throughout the day. We demonstrate this with healthy subjects and stroke patients in a simple proof of concept study in which these arm movements are detected during an archetypal activity of daily-living (ADL) - 'making-a-cup-of-tea'. Data is collected from a tri-axial accelerometer and a tri-axial gyroscope located proximal to the wrist. In a training phase, movements are initially performed in a controlled environment which are represented by a ranked set of 30 time-domain features. Using a sequential forward selection technique, for each set of feature combinations three clusters are formed using k-means clustering followed by 10 runs of 10-fold cross validation on the training data to determine the best feature combinations. For the testing phase, movements performed during the ADL are associated with each cluster label using a minimum distance classifier in a multi-dimensional feature space, comprised of the best ranked features, using Euclidean or Mahalanobis distance as the metric. Experiments were performed with four healthy subjects and four stroke survivors and our results show that the proposed methodology can detect the three movements performed during the ADL with an overall average accuracy of 88% using the accelerometer data and 83% using the gyroscope data across all healthy subjects and arm movement types. The average accuracy across all stroke survivors was 70% using accelerometer data and 66% using gyroscope data. We also use a Linear Discriminant Analysis (LDA) classifier and a Support Vector Machine (SVM) classifier in association with the same set of features to detect the three arm movements and compare the results to demonstrate the effectiveness of our proposed methodology.
在本文中，我们提出了一种方法，通过将模式识别应用于来自单个腕戴式惯性传感器的数据，来识别人类前臂的三种基本运动（伸展、弯曲和旋转）。我们认为，该技术可作为一种临床工具，通过跟踪患者在一天中使用患侧手臂执行特定手臂运动（如规定的锻炼）的次数，来评估中风或脑瘫等神经退行性疾病的康复进展。我们在一项简单的概念验证研究中，对健康受试者和中风患者进行了验证，在这项研究中，这些手臂运动是在一项典型的日常生活活动（ADL）——“泡茶”过程中被检测到的。数据是从位于手腕近端的三轴加速度计和三轴陀螺仪收集的。在训练阶段，运动最初在受控环境中进行，由一组排序的30个时域特征表示。使用顺序前向选择技术，对于每组特征组合，使用k均值聚类形成三个簇，然后在训练数据上进行10次10折交叉验证，以确定最佳特征组合。在测试阶段，在ADL期间执行的运动使用多维特征空间中的最小距离分类器与每个簇标签相关联，该多维特征空间由排名最佳的特征组成，使用欧几里得距离或马氏距离作为度量。对四名健康受试者和四名中风幸存者进行了实验，我们的结果表明，所提出的方法能够检测出在ADL期间执行的三种运动，在所有健康受试者和手臂运动类型中，使用加速度计数据的总体平均准确率为88%，使用陀螺仪数据的总体平均准确率为83%。在所有中风幸存者中，使用加速度计数据的平均准确率为70%，使用陀螺仪数据的平均准确率为66%。我们还使用线性判别分析（LDA）分类器和支持向量机（SVM）分类器与同一组特征相结合来检测三种手臂运动，并比较结果以证明我们所提出方法的有效性。
