3-D motion system ("data-gloves"): application for Parkinson's disease

Abstract

In this application, three-dimensional electromagnetic sensors have been integrated into a data-glove to accurately model and capture the motion of the human hand. By modeling the movement of the human hand, this system has been shown to accurately measure the tremor evident in subjects with Parkinson's disease (PD). It was found that 11 sensors were sufficient to model the human hand including all the phalanges. A capture rate of 10 measurements/s was achieved. A discrete Fourier analysis has been applied to extract the tremor frequency from the sensor data time series. Further, an analysis of the instantaneous speed of hand motion has been used to extract clinically significant diagnosis. The technique described is seen to provide an objective and quantitative method for the analysis of clinic conditions, such as PD and essential tremor, as a way to assess the effect of therapeutic interventions

Upper limb intention tremor assessment: opportunities and challenges in wearable technology

“…Analogous to accelerometers, gyroscopes have also been used individually [ 174 – 178 ], in smartphones [ 179 ] and smartwatches [ 180 – 182 ] to decompose tremorous and voluntary movement using different signal processing techniques such as EMD, HHT [ 183 , 184 ], WFLC, and EKF [ 185 ]. Other types of motion detection sensors, such as force transducers [ 186 – 188 ] or electromagnetic sensors [ 189 – 194 ], have been proposed to track tremors in ET, PD, and MS.…”

Classification of Hand-Movement Disabilities in Parkinson’s Disease Using a Motion-Capture Device and Machine Learning

“…Sensor-based devices designed for quantitative kinematic measurements of limb movements have recently become readily available. These devices include wearable sensors [7]- [9], accelerometers [10], gyroscopes [11] and camera-based sensors [12]- [14], but they might not be suitable for practical application in clinical settings due to their size, cost, and time requirements. In addition, although video recording devices are inexpensive, they mostly are not able to capture small finger movements [14].…”

MagIK: A Hand-Tracking Magnetic Positioning System Based on a Kinematic Model of the Hand

“…Hand tracking data and machine learning can be used to recognize characteristic motor symptoms associated with a particular disease (e.g. Parkinson's disease) [18]- [20], or to compare performed gestures with standard references extracted from control sets in targeted rehabilitation exercises [21], [22]. Hand tracking and machine learning are also being studied for automatic sign language recognition [3], [23], [24].…”

“…Another technique that does not require line-of-sight, is based on magnetic field sources and sensors [5], [17], [18]. Magnetic sources can be mounted on the hand, while sensors are external [34], or, conversely, the magnetic field source is external, while magnetic sensors are mounted on the hand, as, for example, using the commercial magnetic positioning system Polhemus [35], [36].…”