EMaGer: A Wearable Full-Circumference HD-EMG Sensor and Data Augmentation Method for Robust Hand Gesture Recognition.

This work presents EMaGer, a new 360° 64-channel high-density electromyography (HD-EMG) bracelet combined with an original data augmentation method for improved robustness in gesture recognition. By leveraging homogeneous electrode density and powerful deep learning techniques, the sensor is capable of rotation invariance around the arm axis, thus increasing gesture recognition robustness to electrode movement and inter-session evaluation. The system is made of a 4x16 electrode array covering the full circumference of the limb, and uses a sampling frequency of 1 kHz and a 16-bit resolution. The sensor's uniform and adjustable geometry paired with an array barrel shifting data augmentation (ABSDA) technique allows a convolutional neural network to maintain a 76.98% inter-session classification accuracy for a 6 gestures dataset, from a baseline intra-session accuracy of 93.75%. High inter-session classification accuracy decreases the training burden for users of EMG control systems such as myoelectric prostheses by minimizing calibration requirements. The same methods applied with different state-of-the-art sensors are demonstrated to be less effective. Thus, this work evidences the importance of co-designing the EMG sensor system with the gesture inference algorithms to leverage synergistic properties and solve state-of-the-art challenges.Clinical relevance- This paper establishes a method that alleviates clinical manipulations in setting up and calibrating myoelectric prosthetic devices.

Novel Wearable HD-EMG Sensor With Shift-Robust Gesture Recognition Using Deep Learning.

In this work, we present a hardware-software solution to improve the robustness of hand gesture recognition to confounding factors in myoelectric control. The solution includes a novel, full-circumference, flexible, 64-channel high-density electromyography (HD-EMG) sensor called EMaGer. The stretchable, wearable sensor adapts to different forearm sizes while maintaining uniform electrode density around the limb. Leveraging this uniformity, we propose novel array barrel-shifting data augmentation (ABSDA) approach used with a convolutional neural network (CNN), and an anti-aliased CNN (AA-CNN), that provides shift invariance around the limb for improved classification robustness to electrode movement, forearm orientation, and inter-session variability. Signals are sampled from a 4×16 HD-EMG array of electrodes at a frequency of 1 kHz and 16-bit resolution. Using data from 12 non-amputated participants, the approach is tested in response to sensor rotation, forearm rotation, and inter-session scenarios. The proposed ABSDA-CNN method improves inter-session accuracy by 25.67% on average across users for 6 gesture classes compared to conventional CNN classification. A comparison with other devices shows that this benefit is enabled by the unique design of the EMaGer array. The AA-CNN yields improvements of up to 63.05% accuracy over non-augmented methods when tested with electrode displacements ranging from -45 ° to +45 ° around the limb. Overall, this article demonstrates the benefits of co-designing sensor systems, processing methods, and inference algorithms to leverage synergistic and interdependent properties to solve state-of-the-art problems.

Intuitive real-time control strategy for high-density myoelectric hand prosthesis using deep and transfer learning.

Myoelectric hand prostheses offer a way for upper-limb amputees to recover gesture and prehensile abilities to ease rehabilitation and daily life activities. However, studies with prosthesis users found that a lack of intuitiveness and ease-of-use in the human-machine control interface are among the main driving factors in the low user acceptance of these devices. This paper proposes a highly intuitive, responsive and reliable real-time myoelectric hand prosthesis control strategy with an emphasis on the demonstration and report of real-time evaluation metrics. The presented solution leverages surface high-density electromyography (HD-EMG) and a convolutional neural network (CNN) to adapt itself to each unique user and his/her specific voluntary muscle contraction patterns. Furthermore, a transfer learning approach is presented to drastically reduce the training time and allow for easy installation and calibration processes. The CNN-based gesture recognition system was evaluated in real-time with a group of 12 able-bodied users. A real-time test for 6 classes/grip modes resulted in mean and median positive predictive values (PPV) of 93.43% and 100%, respectively. Each gesture state is instantly accessible from any other state, with no mode switching required for increased responsiveness and natural seamless control. The system is able to output a correct prediction within less than 116 ms latency. 100% PPV has been attained in many trials and is realistically achievable consistently with user practice and/or employing a thresholded majority vote inference. Using transfer learning, these results are achievable after a sensor installation, data recording and network training/fine-tuning routine taking less than 10 min to complete, a reduction of 89.4% in the setup time of the traditional, non-transfer learning approach.

A Fully Embedded Adaptive Real-Time Hand Gesture Classifier Leveraging HD-sEMG and Deep Learning.

This paper presents a real-time fine gesture recognition system for multi-articulating hand prosthesis control, using an embedded convolutional neural network (CNN) to classify hand-muscle contractions sensed at the forearm. The sensor consists in a custom non-intrusive, compact, and easy-to-install 32-channel high-density surface electromyography (HDsEMG) electrode array, built on a flexible printed circuit board (PCB) to allow wrapping around the forearm. The sensor provides a low-noise digitization interface with wireless data transmission through an industrial, scientific and medical (ISM) radio link. An original frequency-time-space cross-domain preprocessing method is proposed to enhance gesture-specific data homogeneity and generate reliable muscle activation maps, leading to 98.15% accuracy when using a majority vote over 5 subsequent inferences by the proposed CNN. The obtained real-time gesture recognition, within 100 to 200 ms, and CNN properties show reliable and promising results to improve on the state-of-the-art of commercial hand prostheses. Moreover, edge computing using a specialized embedded artificial intelligence (AI) platform ensures reliable, secure and low latency real-time operation as well as quick and easy access to training, fine-tuning and calibration of the neural network. Co-design of the signal processing, AI algorithms and sensing hardware ensures a reliable and power-efficient embedded gesture recognition system.

Quantum secured gigabit optical access networks.

Optical access networks connect multiple endpoints to a common network node via shared fibre infrastructure. They will play a vital role to scale up the number of users in quantum key distribution (QKD) networks. However, the presence of power splitters in the commonly used passive network architecture makes successful transmission of weak quantum signals challenging. This is especially true if QKD and data signals are multiplexed in the passive network. The splitter introduces an imbalance between quantum signal and Raman noise, which can prevent the recovery of the quantum signal completely. Here we introduce a method to overcome this limitation and demonstrate coexistence of multi-user QKD and full power data traffic from a gigabit passive optical network (GPON) for the first time. The dual feeder implementation is compatible with standard GPON architectures and can support up to 128 users, highlighting that quantum protected GPON networks could be commonplace in the future.

Infrared spectra of aluminum hydrides in solid hydrogen: Al2H4 and Al2H6.

The reaction of laser-ablated Al atoms and normal-H(2) during co-deposition at 3.5 K produces AlH, AlH(2), and AlH(3) based on infrared spectra and the results of isotopic substitution (D(2), H(2) + D(2) mixtures, HD). Four new bands are assigned to Al(2)H(4) from annealing, photochemistry, and agreement with frequencies calculated using density functional theory. Ultraviolet photolysis markedly increases the yield of AlH(3) and seven new absorptions for Al(2)H(6) in the infrared spectrum of the solid hydrogen sample. These frequencies include terminal Al-H(2) and bridge Al-H-Al stretching and AlH(2) bending modes, which are accurately predicted by quantum chemical calculations for dibridged Al(2)H(6), a molecule isostructural with diborane. Annealing these samples to remove the H(2) matrix decreases the sharp AlH(3) and Al(2)H(6) absorptions and forms broad 1720 +/- 20 and 720 +/- 20 cm(-1) bands, which are due to solid (AlH(3))(n). Complementary experiments with thermal Al atoms and para-H(2) at 2.4 K give similar spectra and most product frequencies within 2 cm(-1). Although many volatile binary boron hydride compounds are known, binary aluminum hydride chemistry is limited to the polymeric (AlH(3))( solid. Our experimental characterization of the dibridged Al(2)H(6) molecule provides an important link between the chemistries of boron and aluminum.