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.

Two-Dimensional Permutation Vectors' (PV) Code for Optical Code Division Multiple Access Systems.

In this paper, we present a new algorithm to generate two-dimensional (2D) permutation vectors' (PV) code for incoherent optical code division multiple access (OCDMA) system to suppress multiple access interference (MAI) and system complexity. The proposed code design approach is based on wavelength-hopping time-spreading (WHTS) technique for code generation. All possible combinations of PV code sets were attained by employing all permutations of the vectors with repetition of each vector weight (W) times. Further, 2D-PV code set was constructed by combining two code sequences of the 1D-PV code. The transmitter-receiver architecture of 2D-PV code-based WHTS OCDMA system is presented. Results indicated that the 2D-PV code provides increased cardinality by eliminating phase-induced intensity noise (PIIN) effects and multiple user data can be transmitted with minimum likelihood of interference. Simulation results validated the proposed system for an agreeable bit error rate (BER) of 10-9.

DNA Assembly with De Bruijn Graphs Using an FPGA Platform.

This paper presents an FPGA implementation of a DNA assembly algorithm, called Ray, initially developed to run on parallel CPUs. The OpenCL language is used and the focus is placed on modifying and optimizing the original algorithm to better suit the new parallelization tool and the radically different hardware architecture. The results show that the execution time is roughly one fourth that of the CPU and factoring energy consumption yields a tenfold savings.

A Wireless Optogenetic Headstage with Multichannel Electrophysiological Recording Capability.

We present a small and lightweight fully wireless optogenetic headstage capable of optical neural stimulation and electrophysiological recording. The headstage is suitable for conducting experiments with small transgenic rodents, and features two implantable fiber-coupled light-emitting diode (LED) and two electrophysiological recording channels. This system is powered by a small lithium-ion battery and is entirely built using low-cost commercial off-the-shelf components for better flexibility, reduced development time and lower cost. Light stimulation uses customizable stimulation patterns of varying frequency and duty cycle. The optical power that is sourced from the LED is delivered to target light-sensitive neurons using implantable optical fibers, which provide a measured optical power density of 70 mW/mm² at the tip. The headstage is using a novel foldable rigid-flex printed circuit board design, which results into a lightweight and compact device. Recording experiments performed in the cerebral cortex of transgenic ChR2 mice under anesthetized conditions show that the proposed headstage can trigger neuronal activity using optical stimulation, while recording microvolt amplitude electrophysiological signals.

DNA assembly with de bruijn graphs on FPGA.

This project aims to see if accelerators based on FPGAs are worthwhile for DNA assembly. It involves reprogramming an already existing algorithm - called Ray - to be run either on such an accelerator or on a CPU to be able to compare both. It has been achieved using the OpenCL language. The focus is put on modifying and optimizing the original algorithm to better suit the new parallelization tool. Upon running the new program on some datasets, it becomes clear that FPGAs are a very capable platform that can fare better than the traditional approach, both on raw performance and energy consumption.

Capacity of UWB wireless channel for neural recording systems.

Ultra wide-band (UWB) short-range communication systems are valuable in medical technology, particularly for implanted devices, due to their low-power consumption, low cost, small size and high data rates. Monitoring of neural responses in the brain requires high data rate if we target a system supporting a large number of sensors. In this work, we are interested in the evaluation of the capacity of the ultra wide-band (UWB) channel that we could exploit using a realistic model of the biological channel. The channel characteristics are examined under two scenarios that are related to TX antenna placements. Using optimal power spectrum allocation (OPSA) at the transmitter side, we have computed this capacity by taking into account the fading characteristics of the channel. The results show the pertinence of the optimal power spectrum allocation for this type of channel. An improvement by a factor of 2 to 3 over a uniform power spectrum allocation (UPSA) when the SNR <; 0 dB was obtained. When the SNR is > 40 dB, both approaches give similar results. Antennas placement is examined under two scenarios having contrasting power constraints.

The N-CODES project: the first year.

Clinical decision making is a complex task, and particularly challenging for the novice nurse. Little assistance is available, and decision supports such as standardized guidelines are difficult to access in the hectic flow of practice. The Nursing Computer Decision Support (N-CODES) project, directed by investigators for nursing and computer engineering, addresses this problem by developing a prototype of a point-of-care system to deliver clinical knowledge via a handheld computer. This article reports on the progress made during the first year of the project. The nursing investigators have developed a novice-nurse decision-making model, a comprehensive knowledge development process, and a series of computerized practice maps. The focus of engineering has been on designing the database architecture and the knowledge representation, extraction, and discovery algorithms used to mimic nursing knowledge and clinical decision processes in software. But the success of an interdisciplinary collaborative project depends on establishing tasks and boundaries, clarifying perspectives and language, and developing a productive process. Therefore, along with the progress of each discipline, strategies used to promote collaboration are discussed.

Knowledge acquisition, synthesis, and validation: a model for decision support systems.

BACKGROUND: Decision tools such as clinical decision support systems must be built on a solid foundation of nursing knowledge. However, current methods to determine the best evidence do not include a broad range of knowledge sources. As clinical decision support systems will be designed to assist nurses when making critical decisions, methods need to be devised to glean the best possible knowledge. AIMS: This paper presents a comprehensive knowledge development process to develop a nursing clinical decision support system. DISCUSSION: The Nurse Computer Decision Support Project (N-CODES) is developing a prototype for a prospective decision support system. The prototype is being constructed on rules and cases generated by the best available evidence. To accommodate the range of decisions made in practice, different types of evidence are necessary. The process incorporates procedures to uncover, evaluate, and assimilate information to develop the knowledge domain for a clinical decision support systems. Both formal and practice-based knowledge are included. The model contains several innovative approaches including the use of clinical experts and a network of practicing clinicians. CONCLUSION: These strategies will assist scientists and practitioners interested in determining the best evidence to support clinical decision support systems.