Non-myopic multipoint multifidelity Bayesian framework for multidisciplinary design.

The adoption of high-fidelity models in multidisciplinary design optimization (MDO) permits to enhance the identification of superior design configurations, but would prohibitively rise the demand for computational resources and time. Multifidelity Bayesian Optimization (MFBO) efficiently combines information from multiple models at different levels of fidelity to accelerate the MDO procedure. State-of-the-art MFBO methods currently meet two major limitations: (i) the sequential adaptive sampling precludes parallel computations of high-fidelity models, and (ii) the search scheme measures the utility of new design evaluations only at the immediate next iteration. This paper proposes a Non-Myopic Multipoint Multifidelity Bayesian Optimization (NM3-BO) algorithm to sensitively accelerate MDO overcoming the limitations of standard methods. NM3-BO selects a batch of promising design configurations to be evaluated in parallel, and quantifies the expected long-term improvement of these designs at future steps of the optimization. Our learning scheme leverages an original acquisition function based on the combination of a two-step lookahead policy and a local penalization strategy to measure the future utility achieved evaluating multiple design configurations simultaneously. We observe that the proposed framework permits to sensitively accelerate the MDO of a space vehicle and outperforms popular algorithms.

A 6-Month Home-Based Functional Electrical Stimulation Program for Foot Drop in a Post-Stroke Patient: Considerations on a Time Course Analysis of Walking Performance.

Foot drop is a common disability in post-stroke patients and represents a challenge for the clinician. To date, ankle foot orthosis (AFO) combined with conventional rehabilitation is the gold standard of rehabilitation management. AFO has a palliative mechanical action without actively restoring the associated neural function. Functional electrical stimulation (FES), consisting of stimulation of the peroneal nerve pathway, represents an alternative approach. By providing an FES device (Bioness L-300, BIONESS, Valencia, CA, USA) for 6 months to a post-stroke 22-year-old woman with a foot drop, our goal was to quantify its potential benefit on walking capacity. The gait parameters and the temporal evolution of the speed were collected with a specific connected sole device (Feet Me®) during the 10-m walking, the time up and go, and the 6-minute walking tests with AFO, FES, or without any device (NO). As a result, the walking speed changes on 10-m were clinically significant with an increase from the baseline to 6 months in AFO (+0.14 m.s-1), FES (+0.36 m.s-1) and NO (+0.32 m.s-1) conditions. In addition, the speed decreased at about 4-min in the 6-minute walking test in NO and AFO conditions, while the speed increased in the FES conditions at baseline and after 1, 3, and 6 months. In addition to the walking performance improvement, monitoring the gait speed in an endurance test after an ecological rehabilitation training program helps to examine the walking performance in post-stroke patients and to propose a specific rehabilitation program.