Brain-machine interface based on deep learning to control asynchronously a lower-limb robotic exoskeleton: a case-of-study.

BACKGROUND: This research focused on the development of a motor imagery (MI) based brain-machine interface (BMI) using deep learning algorithms to control a lower-limb robotic exoskeleton. The study aimed to overcome the limitations of traditional BMI approaches by leveraging the advantages of deep learning, such as automated feature extraction and transfer learning. The experimental protocol to evaluate the BMI was designed as asynchronous, allowing subjects to perform mental tasks at their own will. METHODS: A total of five healthy able-bodied subjects were enrolled in this study to participate in a series of experimental sessions. The brain signals from two of these sessions were used to develop a generic deep learning model through transfer learning. Subsequently, this model was fine-tuned during the remaining sessions and subjected to evaluation. Three distinct deep learning approaches were compared: one that did not undergo fine-tuning, another that fine-tuned all layers of the model, and a third one that fine-tuned only the last three layers. The evaluation phase involved the exclusive closed-loop control of the exoskeleton device by the participants' neural activity using the second deep learning approach for the decoding. RESULTS: The three deep learning approaches were assessed in comparison to an approach based on spatial features that was trained for each subject and experimental session, demonstrating their superior performance. Interestingly, the deep learning approach without fine-tuning achieved comparable performance to the features-based approach, indicating that a generic model trained on data from different individuals and previous sessions can yield similar efficacy. Among the three deep learning approaches compared, fine-tuning all layer weights demonstrated the highest performance. CONCLUSION: This research represents an initial stride toward future calibration-free methods. Despite the efforts to diminish calibration time by leveraging data from other subjects, complete elimination proved unattainable. The study's discoveries hold notable significance for advancing calibration-free approaches, offering the promise of minimizing the need for training trials. Furthermore, the experimental evaluation protocol employed in this study aimed to replicate real-life scenarios, granting participants a higher degree of autonomy in decision-making regarding actions such as walking or stopping gait.

The occurrence of squeaking under wear testing standards for ceramic on ceramic total hip replacements.

Ceramic on ceramic total hip replacement clinical reports may on occasion note a noise or squeaking. There is much debate on whether this is an actual concern, but some medical centres want to avoid any possible negative impact on the patients' wellbeing due to the noise generated. The aim of this study was to determine what sound frequencies can be picked up from hip testing standards for ceramic on ceramic under different lubrication conditions. The ISO-14242-1 (35° cup angle) and ISO-14242-4 (55° cup angle with a 4 mm translational mismatch) standards were used for testing with dry, water and serum lubrication conditions up to 10000 cycles. No sound was detected for water and serum conditions under standard walking (ISO-14242-1) testing. An audible noise with a frequency range of 0.4-0.8 kHz was picked up within 600 cycles under water and edge loading (ISO-14242-4) conditions. All dry testing produced a high pitch squeak when the frequency was higher than 2 kHz. One sample under dry edge loading conditions had an audible noise of 0.8 kHz, considered not as squeaking, as it was not high pitch. Dry testing for both, standard walking (ISO-14242-1) and edge loading (ISO-14242-4) conditions, which resulted in a high pitch noise, had a frequency range of 2-8 kHz and 5-9 kHz respectively. One sample tested with edge loading and serum produced a faint squeak noise after 6000 cycles with a frequency of 7 kHz. Edge loading due to ISO-14242-4 conditions had an increased torque which may be playing a role in increased friction leading to noise. Edge loading conditions were more prone to the generation of audible noise and squeaking whilst under lubricated conditions.

Chronic cardiovascular and renal actions of leptin: role of adrenergic activity.

This study was designed to determine the role of changes in adrenergic activity in mediating the chronic cardiovascular, renal, and metabolic actions of leptin. Male Sprague-Dawley rats were implanted with catheters for mean arterial pressure (MAP) and heart rate (HR) measurements and IV infusions of either vehicle (n= 7) or alpha- and beta-adrenergic receptor antagonists, terazosin and propranolol (10 mg/kg/d; n= 8) throughout the study. After control measurements, murine leptin was infused IV (1.0 microg/kg/min) for 7 days along with vehicle or adrenergic antagonists, followed by a 7-day recovery period. Leptin infusion significantly reduced food intake in control rats from 22.6 +/- 0.8 to 10.6 +/- 0.4 g/d and, in adrenergic blockade rats, from 22.6 +/- 0.8 to 13.2 +/- 0.8 g/d. Fasting plasma insulin decreased from 48 +/- 10 to 5 +/- 2 microU/mL in control rats and from 51+/- 9 to 9 +/- 2 microU/mL in adrenergic blockade rats during leptin infusion. Leptin infusion did not significantly alter glomerular filtration rate in either group. MAP and HR increased by 6 +/- 1 mm Hg and 23 +/- 7 bpm after 7 days of leptin infusion in control rats. However, in adrenergic blockade rats, leptin infusion did not significantly alter MAP (-1 +/- 1 mm Hg) and decreased, rather than increased, HR (-23 +/- 8 bpm). These results indicate that leptin-induced increases in blood pressure and tachycardia are mediated by increased adrenergic activity and support the concept that leptin may be an important link between obesity, increased sympathetic activity, and hypertension. However, the chronic effects of leptin on insulin and glucose regulation do not appear to be altered by alpha- and beta-adrenergic receptor blockade.