Deep Convolutional Neural Network-Based Hemiplegic Gait Detection Using an Inertial Sensor Located Freely in a Pocket

In most previous studies, the acceleration sensor is attached to a fixed position for gait analysis. However, if it is aimed at daily use, wearing it in a fixed position may cause discomfort. In addition, since an acceleration sensor can be built into the smartphones that people always carry, it is more efficient to use such a sensor rather than wear a separate acceleration sensor. We aimed to distinguish between hemiplegic and normal walking by using the inertial signal measured by means of an acceleration sensor and a gyroscope. We used a machine learning model based on a convolutional neural network to classify hemiplegic gaits and used the acceleration and angular velocity signals obtained from a system freely located in the pocket as inputs without any pre-processing. The classification model structure and hyperparameters were optimized using Bayesian optimization method. We evaluated the performance of the developed model through a clinical trial, which included a walking test of 42 subjects (57.8 +/- 13.8 years old, 165.1 +/- 9.3 cm tall, weighing 66.3 +/- 12.3 kg) including 21 hemiplegic patients. The optimized convolutional neural network model has a convolutional layer, with number of fully connected nodes of 1033, batch size of 77, learning rate of 0.001, and dropout rate of 0.48. The developed model showed an accuracy of 0.78, a precision of 0.80, a recall of 0.80, an area under the receiver operating characteristic curve of 0.80, and an area under the precision-recall curve of 0.84. We confirmed the possibility of distinguishing a hemiplegic gait by applying the convolutional neural network to the signal measured by a six-axis inertial sensor freely located in the pocket without additional pre-processing or feature extraction.