Hand Force Estimation from Acoustic Myography Using Deep Wavelet Scattering Transform and Long Short-Term Memory.

The ability to estimate user intention from surface electromyogram (sEMG) signals is a crucial aspect in the design of powered prosthetics. Recently, researchers have been using regression techniques to connect the user's intent, as expressed through sEMG signals, to the force applied at the fingertips in order to achieve a natural and accurate form of control. However, there are still challenges associated with processing sEMG signals that need to be overcome to allow for widespread and clinical implementation of upper limb prostheses. As a result, alternative modalities functioning as promising control signals have been proposed as source of control input rather than the sEMG, such as Acoustic Myography (AMG). In this study, six high sensitivity array microphones were used to acquire AMG signals, with custom-built 3D printed microphone housing. To tackle the challenge of extracting the relevant information from AMG signals, the Wavelet Scattering Transform (WST) was utilized. alongside a Long Short-Term Memory (LSTM) neural network model for predicting the force from the AMG. The subjects were asked to use a hand dynamometer to measure the changes in force and correlate that to the force predicted by using the AMG features. Seven subjects were recruited for data collection in this study, using hardware designed by the research team. the performance results showed that the WST-LSTM model can be robustly utilized across varying window sizes and testing schemes, to achieve average NRMSE results of approximately 8%. These pioneering results suggest that AMG signals can be utilized to reliably estimate the force levels that the muscles are applying.Clinical Relevance- This research presents a new method for controlling upper limb prostheses using Acoustic Myography (AMG) signals. A novel method mapping the AMG signals to force applied by the corresponding muscles is developed. The presented findings have the potential to lead to the development of more natural and accurate control of human-machine interfaces.

Empirical Mode Decomposition-Based Feature Extraction for Environmental Sound Classification.

In environment sound classification, log Mel band energies (MBEs) are considered as the most successful and commonly used features for classification. The underlying algorithm, fast Fourier transform (FFT), is valid under certain restrictions. In this study, we address these limitations of Fourier transform and propose a new method to extract log Mel band energies using amplitude modulation and frequency modulation. We present a comparative study between traditionally used log Mel band energy features extracted by Fourier transform and log Mel band energy features extracted by our new approach. This approach is based on extracting log Mel band energies from estimation of instantaneous frequency (IF) and instantaneous amplitude (IA), which are used to construct a spectrogram. The estimation of IA and IF is made by associating empirical mode decomposition (EMD) with the Teager-Kaiser energy operator (TKEO) and the discrete energy separation algorithm. Later, Mel filter bank is applied to the estimated spectrogram to generate EMD-TKEO-based MBEs, or simply, EMD-MBEs. In addition, we employ the EMD method to remove signal trends from the original signal and generate another type of MBE, called S-MBEs, using FFT and a Mel filter bank. Four different datasets were utilised and convolutional neural networks (CNN) were trained using features extracted from Fourier transform-based MBEs (FFT-MBEs), EMD-MBEs, and S-MBEs. In addition, CNNs were trained with an aggregation of all three feature extraction techniques and a combination of FFT-MBEs and EMD-MBEs. Individually, FFT-MBEs achieved higher accuracy compared to EMD-MBEs and S-MBEs. In general, the system trained with the combination of all three features performed slightly better compared to the system trained with the three features separately.

Acoustic Estimation of the Direction of Arrival of an Unmanned Aerial Vehicle Based on Frequency Tracking in the Time-Frequency Plane.

The development of unmanned aerial vehicles (UAVs) opens up a lot of opportunities but also brings some threats. Dealing with these threats is not easy and requires some good techniques. Knowing the location of the threat is essential to deal with an UAV that is displaying disturbing behavior. Many methods exist but can be very limited due to the size of UAVs or due to technological improvements over the years. However, the noise produced by the UAVs is still predominant, so it gives a good opening for the development of acoustic methods. The method presented here takes advantage of a microphone array with a processing based on time domain Delay and Sum Beamforming. In order to obtain a better signal to noise ratio, the UAV's acoustic signature is taken into account in the processing by using a time-frequency representation of the beamformer's output. Then, only the content related to this signature is considered to calculate the energy in one direction. This method enables to have a good robustness to noise and to localize an UAV with a poor spectral content or to separate two UAVs with different spectral contents. Simulation results and those of a real flight experiment are reported.

Simulation/Experiment Confrontation, an Efficient Approach for Sensitive SAW Sensors Design.

Sensitivity is one of the most important parameters to put in the foreground in all sensing applications. Its increase is therefore an ongoing challenge, particularly for surface acoustic wave (SAW) sensors. Herein, finite element method (FEM) simulation using COMSOL Multiphysics software is first used to simulate the physical and electrical properties of SAW delay line. Results indicate that 2D configuration permits to accurately obtain all pertinent parameters, as in 3D simulation, with very substantial time saving. A good agreement between calculation and experiment, in terms of transfer functions (S21 spectra), was also shown to evaluate the dependence of the SAW sensors sensitivity on the operating frequency; 2D simulations have been conducted on 104 MHz and 208 MHz delay lines, coated with a polyisobutylene (PIB) as sensitive layer to dichloromethane (DCM). A fourfold increase in sensitivity was obtained by doubling frequency. Both sensors were then realized and tested as chem-sensors to detect zinc ions in liquid media. 9-{[4-({[4-(9anthrylmethoxy)phenyl]sulfanyl} methyl)]methyl] anthracene (TDP-AN) was selected as the sensing layer. Results show a comparable response curves for both designed sensors, in terms of limit of detection and dissociation constants Kd values. On the other hand, experimental sensitivity values were of the order of [7.0 ± 2.8] × 108 [°/M] and [16.0 ± 7.6] × 108 [°/M] for 104 MHz and 208 MHz sensors, respectively, confirming that the sensitivity increases with frequency.

Software Defined Radio (SDR) and Direct Digital Synthesizer (DDS) for NMR/MRI instruments at low-field.

A proof-of-concept of the use of a fully digital radiofrequency (RF) electronics for the design of dedicated Nuclear Magnetic Resonance (NMR) systems at low-field (0.1 T) is presented. This digital electronics is based on the use of three key elements: a Direct Digital Synthesizer (DDS) for pulse generation, a Software Defined Radio (SDR) for a digital receiving of NMR signals and a Digital Signal Processor (DSP) for system control and for the generation of the gradient signals (pulse programmer). The SDR includes a direct analog-to-digital conversion and a Digital Down Conversion (digital quadrature demodulation, decimation filtering, processing gain…). The various aspects of the concept and of the realization are addressed with some details. These include both hardware design and software considerations. One of the underlying ideas is to enable such NMR systems to "enjoy" from existing advanced technology that have been realized in other research areas, especially in telecommunication domain. Another goal is to make these systems easy to build and replicate so as to help research groups in realizing dedicated NMR desktops for a large palette of new applications. We also would like to give readers an idea of the current trends in this field. The performances of the developed electronics are discussed throughout the paper. First FID (Free Induction Decay) signals are also presented. Some development perspectives of our work in the area of low-field NMR/MRI will be finally addressed.

Inside-out NMR probe for portable spectrometry.

Nuclear magnetic resonance (NMR) measurements in grossly inhomogeneous static magnetic fields are possible if the inhomogeneity is inferior to a theoretical limit. A design is proposed for a single-sided inside-out NMR probe with static and radiofrequency (RF) magnetic fields perpendicular and correlated on a large volume. This probe was constructed with ferrite material. It can found application as a portable scanner for local NMR spectrometry.

ICASENSE: Sensitivity mapping using Independent Component Analysis for parallel Magnetic Resonance Imaging.

Parallel Magnetic Resonance Imaging (MRI) methods employ receiver coils sensitivities to reduce imaging time: reconstruction algorithms need RF field maps which must be measured or estimated. Assuming statistical independence of different regions in a MR image, we consider the sensitivity estimation as a Blind Source Separation (BSS) problem that can be solved with Independent Component Analysis (ICA). This new formulation permits sensitivity maps extraction from only one MR acquisition, without calibration step or acquisition of additional k-space lines. Simulation results are presented for sensitivity encoded (SENSE) MR images, proving that sensitivity data can be extracted from statistical properties of the image, using the method ICASENSE.