In recent years, deep learning algorithms have become increasingly more prominent for their unparalleled ability to automatically learn discriminant features from large amounts of data. However, within the field of electromyographybased gesture recognition, deep learning algorithms are seldom employed as they require an unreasonable amount of effort from a single person, to generate tens of thousands of examples.This work's hypothesis is that general, informative features can be learned from the large amounts of data generated by aggregating the signals of multiple users, thus reducing the recording burden while enhancing gesture recognition. Consequently, this paper proposes applying transfer learning on aggregated data from multiple users, while leveraging the capacity of deep learning algorithms to learn discriminant features from large datasets. Two datasets comprised of 19 and 17 able-bodied participants respectively (the first one is employed for pre-training) were recorded for this work, using the Myo Armband. A third Myo Armband dataset was taken from the NinaPro database and is comprised of 10 able-bodied participants. Three different deep learning networks employing three different modalities as input (raw EMG, Spectrograms and Continuous Wavelet Transform (CWT)) are tested on the second and third dataset. The proposed transfer learning scheme is shown to systematically and significantly enhance the performance for all three networks on the two datasets, achieving an offline accuracy of 98.31% for 7 gestures over 17 participants for the CWT-based ConvNet and 68.98% for 18 gestures over 10 participants for the raw EMG-based ConvNet. Finally, a use-case study employing eight able-bodied participants suggests that real-time feedback allows users to adapt their muscle activation strategy which reduces the degradation in accuracy normally experienced over time.

In the realm of surface electromyography (sEMG) gesture recognition, deep learning algorithms are seldom employed. This is due in part to the large quantity of data required for them to train on. Consequently, it would be prohibitively time consuming for a single user to generate a sufficient amount of data for training such algorithms. In this paper, two datasets of 18 and 17 able-bodied participants respectively are recorded using a low-cost, low-sampling rate (200Hz), 8-channel, consumer-grade, dry electrode sEMG device named Myo armband (Thalmic Labs). A convolutional neural network (CNN) is augmented using transfer learning techniques to leverage inter-user data from the first dataset and alleviate the data generation burden imposed on a single individual. The results show that the proposed classifier is robust and precise enough to guide a 6DoF robotic arm (in conjunction with orientation data) with the same speed and precision as with a joystick. Furthermore, the proposed CNN achieves an average accuracy of 97.81% on seven hand/wrist gestures on the 17 participants of the second dataset.

No abstract

No abstract

This paper describes a multimodal body-machine interface (BoMI) to help individuals with upper-limb disabilities using advanced assistive technologies, such as robotic arms. The proposed system uses a wearable and wireless body sensor network (WBSN) supporting up to six sensor nodes to measure the natural upper-body gesture of the users and translate it into control commands. Natural gesture of the head and upper-body parts, as well as muscular activity, are measured using inertial measurement units (IMUs) and surface electromyography (sEMG) using custom-designed multimodal wireless sensor nodes. An IMU sensing node is attached to a headset worn by the user. It has a size of 2.9 cm 2.9 cm, a maximum power consumption of 31 mW, and provides angular precision of 1. Multimodal patch sensor nodes, including both IMU and sEMG sensing modalities are placed over the user able-body parts to measure the motion and muscular activity. These nodes have a size of 2.5 cm 4.0 cm and a maximum power consumption of 11 mW. The proposed BoMI runs on a Raspberry Pi. It can adapt to several types of users through different control scenarios using the head and shoulder motion, as well as muscular activity, and provides a power autonomy of up to 24 h. JACO, a 6-DoF assistive robotic arm, is used as a testbed to evaluate the performance of the proposed BoMI. Ten able-bodied subjects performed ADLs while operating the AT device, using the Test d'Évaluation des Membres Supérieurs de Personnes Âgées to evaluate and compare the proposed BoMI with the conventional joystick controller. It is shown that the users can perform all tasks with the proposed BoMI, almost as fast as with the joystick controller, with only 30% time overhead on average, while being potentially more accessible to the upper-body disabled who cannot use the conventional joystick controller. Tests show that control performance with the proposed BoMI improved by up to 17% on average, after three trials.