Abstract
This paper focuses on the design and comparison of different deep neural networks for the real-time prediction of locomotor and transition intentions of one osseointegrated transfemoral amputee using only data from inertial measurement units. The deep neural networks are based on convolutional neural networks, recurrent neural networks, and convolutional recurrent neural networks. The architectures' input are features in both the time domain and the time-frequency domain, which are derived from either one inertial measurement unit (placed above the prosthetic knee) or two inertial measurement units (placed above and below the prosthetic knee). The prediction of eight different locomotion modes (i.e., sitting, standing, level ground walking, stair ascent and descent, ramp ascent and descent, walking on uneven terrain) and the twenty-four transitions among them is investigated. The study shows that a recurrent neural network, realized with four layers of gated recurrent unit networks, achieves (with a 5-fold cross-validation) a mean F1 score of 84.78% and 86.50% using one inertial measurement unit, and 93.06% and 89.99% using two inertial measurement units, with or without sitting, respectively.
Highlights
For individuals with lower-limb amputation, the need to conveniently perform activities of daily living is critical [1]
This study shows that a Recurrent neural networks (RNNs), realized with four layers of gated recurrent unit networks, achieves a mean F1 score of 84.78% and 86.50% using one inertial measurement units (IMUs), and 93.06% and 89.99% using two IMUs, with or without the sitting mode, respectively
The features are (i) the means of the angular accelerations and angular velocities computed within the time window W ; (ii) the quaternions calculated on the mean IMU data in the same time window W, by using the filter proposed in [28], with the implementation in [29]; (iii) the time-localized frequency information of each IMU, calculated using the short-time Fourier transform (STFT) within the same time window W
Summary
For individuals with lower-limb amputation, the need to conveniently perform activities of daily living is critical [1]. A variety of data analysis and machine learning techniques has been proposed to translate data from inertial measurement units (IMUs) into locomotion information in real-time These pattern recognition techniques can be broadly divided into two categories, namely, methods based on feature engineering [3] and methods based on feature learning [4], either with handcrafted or raw input IMU data. To recognize hand motions in healthy subjects, a RNN is used with time domain features from one in-hand IMU in [23], while a neural network (NN) is used with raw data from one in-hand IMU in [24]. [13] 2016 [13] 2016 [13] 2016 [14] 2018 [15] 2020 [16] 2020 [17] 2019 [17] 2019 [18] 2019 [19] 2017 [20] 2016 [21] 2016 [21] 2016 [21] 2016 [21] 2016 [22] 2018 [23] 2017 [24] 2019 [25] 2018 [25] 2018 [26] 2019
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
