Machine Learning Approaches for Activity Recognition and/or Activity Prediction in Locomotion Assistive Devices-A Systematic Review.

Locomotion assistive devices equipped with a microprocessor can potentially automatically adapt their behavior when the user is transitioning from one locomotion mode to another. Many developments in the field have come from machine learning driven controllers on locomotion assistive devices that recognize/predict the current locomotion mode or the upcoming one. This review synthesizes the machine learning algorithms designed to recognize or to predict a locomotion mode in order to automatically adapt the behavior of a locomotion assistive device. A systematic review was conducted on the Web of Science and MEDLINE databases (as well as in the retrieved papers) to identify articles published between 1 January 2000 to 31 July 2020. This systematic review is reported in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines and is registered on Prospero (CRD42020149352). Study characteristics, sensors and algorithms used, accuracy and robustness were also summarized. In total, 1343 records were identified and 58 studies were included in this review. The experimental condition which was most often investigated was level ground walking along with stair and ramp ascent/descent activities. The machine learning algorithms implemented in the included studies reached global mean accuracies of around 90%. However, the robustness of those algorithms seems to be more broadly evaluated, notably, in everyday life. We also propose some guidelines for homogenizing future reports.

Submicronic-Scale Mechanochemical Characterization of Oxygen-Enriched Materials.

Conventional techniques that measure the concentration of light elements in metallic materials lack high-resolution performance due to their intrinsic limitation of sensitivity. In that context, scanning microwave microscopy has the potential to significantly enhance the quantification of element distribution due to its ability to perform a tomographic investigation of the sample. Scanning microwave microscopy associates the local electromagnetic measurement and the nanoscale resolution of an atomic force microscope. This technique allows the simultaneous characterization of oxygen concentration as well as local mechanical properties by microwave phase shift and amplitude signal, respectively. The technique was calibrated by comparison with nuclear reaction analysis and nanoindentation measurement. We demonstrated the reliability of the scanning microwave technique by studying thin oxygen-enriched layers on a Ti-6Al-4V alloy. This innovative approach opens novel possibilities for the indirect quantification of light chemical element diffusion in metallic materials. This technique is applicable to the control and optimization of industrial processes.

Study of Structural, Compression, and Soft Magnetic Properties of Fe65Ni28Mn7 Alloy Prepared by Arc Melting, Mechanical Alloying, and Spark Plasma Sintering.

Soft magnetic Fe65Ni28Mn7 (at. %) alloy was successfully synthesized by mechanical alloying and spark plasma sintering (SPS) and, in parallel, the same composition was prepared by arc melting (AM) for comparison. Several SPS conditions were tested. X-ray diffraction and scanning electron microscopy were used to investigate the structure, phase composition, and morphology of the samples. It was found that mechanical alloying produced BCC and FCC supersaturated solid solution after 130 h of milling, with a fine microstructure (i.e., crystallite size of 10 nm). Spark plasma sintering performed at 750 °C and 1000 °C under two pressures of 50 MPa and 75 MPa revealed stable FCC phases. A single FCC phase was observed after the arc melting synthesis. The magnetic properties of milled powders and solids obtained by AM and SPS were investigated. The specimen consolidated by SPS at 1000 °C under the pressure of 50 MPa exhibits soft magnetic behavior (coercivity 0.07 Oe), whereas the mechanically alloyed sample revealed hard magnetic behavior. The specimen consolidated at 750 °C under a pressure of 75 MPa showed a higher compressive strength of 1700 MPa and a Vickers hardness of 425 ± 18 HV. As a result, sintering at 750 °C/75 MPa can be utilized to enhance the mechanical properties, while those sintered at 1000 °C/50 MPa increase magnetic softness.

High-resolution characterization of the diffusion of light chemical elements in metallic components by scanning microwave microscopy.

An original sub-surface, high spatial resolution tomographic technique based on scanning microwave microscopy (SMM) is used to visualize in-depth materials with different chemical compositions. A significant phase difference in SMM between aluminum and chromium buried patterns has been observed. Moreover this technique was used to characterize a solid solution of a light chemical element (oxygen) in a metal lattice (zirconium). The large solubility of the oxygen in zirconium leads to modifications of the properties of the solid solution that can be measured by the phase shift signal in the SMM technique. The signal obtained in cross-section of an oxidized Zr sample shows the excellent agreement between phase shift profiles measured at different depths. Such a profile can reveal the length of diffusion of the oxygen in zirconium under the surface. The comparison with the oxygen concentration measured by nuclear reaction analysis shows excellent agreement in terms of length of diffusion and spatial distribution of the oxygen. A rapid calibration shows a linear dependence between the phase shift and the oxygen concentration. The SMM method opens up new possibilities for indirect measurements of the oxygen concentration dissolved in the metal lattice.