This paper aimed to develop and evaluate an environment-aware locomotion mode recognition system for volitional control of powered artificial legs. A portable terrain (TR) module, consisting inertia measurement unit a laser distance meter, was built identify the type in front wearer while walking. decision tree used classify types provide either coarse or refined information about walking environment. Then, obtained environmental modeled as priori probability integrated with...

Algorithms for locomotion mode recognition (LMR) based on surface electromyography and mechanical sensors have recently been developed could be used the neural control of powered prosthetic legs. However, variations in input signals, caused by physical changes at sensor interface human physiological changes, may threaten reliability these algorithms. This study aimed to investigate effectiveness applying adaptive pattern classifiers LMR. Three classifiers, i.e., entropy-based adaptation...

Recent studies have reported various methods that recognize amputees' intent regarding locomotion modes, which is potentially useful for volitional control of powered artificial legs. However, occasional errors in mode recognition are inevitable. When these decisions used prosthesis control, the effects decision on operation and user's task performance unknown. Hence, goals this study were to 1) systematically investigate prosthetic legs gait stability, 2) identify critical impact safe...

In this study, we aimed to improve the performance of a locomotion-mode-recognition system based on neuromuscular-mechanical fusion by introducing additional information about walking environment. Linear-discriminant-analysis-based classifiers were first designed identify lower limb prosthesis user's locomotion mode electromyographic signals recorded from residual leg muscles and ground reaction forces measured prosthetic pylon. Nine transfemoral amputees who wore passive hydraulic knee or...

Novel techniques in deep learning networks are proposed for the staked sparse autoencoder (SAE) and bagged decision tree (TreeBagger), achieving significant improvement detection localization of myocardial infarction (MI) from single-lead electrocardiograph (ECG) signals. With our layer-wise training strategies, SAE-based diagnostic feature extraction network can automatically steadily extract distinguishing features ECG signals avoid vanishing gradient problem. This is formed by stacking...

Amputees are prone to experiencing discomfort when wearing their prosthetic devices. As the amputee population grows this becomes a more prevalent and pressing concern. There is need for new technologies construct comfortable well-fitted liners sockets. One of well-recognized impediments development technology lack practical inner socket sensors monitor environment (ISE), or region between residual limb socket. Here we present capacitive pressure sensor fabricated through simple, scalable...

The tuning of robotic prosthesis control is essential to provide personalized assistance individual users. Emerging automatic algorithms have shown promise ease the device personalization procedure. However, very few consider user preference as goal, which may limit adoptability prosthesis. In this study, we propose and evaluate a novel framework for knee prosthesis, could enable preferred robot behavior in process. consists 1) User-Controlled Interface that allows select their kinematics...

Using wearable robotics to modulate step width in normal walking for enhanced mediolateral balance has not been demonstrated the field. We designed a bilateral hip exoskeleton with admittance control power abduction and adduction width.

With the rise of global temperatures, climate change has become one major challenges facing humanity. Carbon dioxide is main gases causing greenhouse effect, and an increase in its emissions directly leads to warming. Therefore, development efficient CO2 storage technology important strategies mitigate change. By prediction amount buried, potential under different geological conditions can be assessed optimize schemes select suitable sites. In this study, 184 real data points were collected....

This paper aims to design a wearable terrain recognition system, which might assist the control of powered artificial prosthetic legs. A laser distance sensor and inertial measurement unit (TMU) sensors were mounted on human body. These used identify movement state user, reconstruct geometry in front user while walking, recognize type before stepped it. Different configurations investigated compared. The designed system was evaluated one healthy subject when walking an obstacle course...

Diurnal PM2.5 samples were collected during summer and winter at an industrial complex site (site A) electronic waste (e–waste) recycling B) in Qingyuan, South China. The concentration of organic carbon (OC), elemental (EC), water soluble ions (WSI) elements investigated for their seasonal diurnal variations. Organic matter (OM) was the most abundant specie winter, accounting 40.2% 48.8% sites A B, respectively; while summer, excluding portion, WSI biggest part, which accounted 37% 49.4%...

Robotic exoskeletons are exciting technologies for augmenting human mobility. However, designing such a device seamless integration with the user and to assist movement still is major challenge. This paper aims at developing novel data-driven solution framework based on reinforcement learning (RL), without first modeling human-robot dynamics, provide optimal adaptive personalized torque assistance reducing efforts during walking. Our automatic personalization includes assistive profile two...

Current powered prosthetic legs require switching control modes according to the task user is performing (e.g. level-ground walking, stair climbing, walking on slopes, etc.). To allow prosthesis users safely and seamlessly transition between tasks, it critical determine when switch mode during transitions. Our previous study defined timings for different types of transitions in ambulation; however, unknown whether unique timing that allows safe seamless The goals this were (1) systematically...

The application effect of computer ultrasound images in the diagnosis tendon diseases caused by athletic injuries and efficacy optimized treatment plans were explored. One hundred thirty-five patients with due to treated a local tertiary hospital during period March 2021–September 2023 selected as study subjects, they separated into three groups control group 1, 2 research randomization method, 45 each group. Control 1 was diagnosed using MRI (Magnetic Resonance Imaging); used conventional...

High density (HD) haptic interfaces have become increasingly common for entertainment thanks to advancements in virtual reality technology, however their flexibility may make them a useful sensory substitution interface motor rehabilitation. Yet little research has explored how users interpret different feedback encoding methods. Therefore, this study's objective was evaluate the effectiveness of various methods conveying information based on existing strategies, one being line motion...

In this paper, we designed a prototype of powered above-knee prosthesis. Compared with other prototypes available in the literature, our prosthetic leg employs redundant actuator concept to overcome challenge faced by single-motor transmission systems. The also enables prosthesis be partially functional when loses power. Finally, order provide optimal control parameters for perform smooth level-ground walking task, an inverse dynamic model based on Kane’s method is constructed.

In this study, we developed and tested a novel adaptive controller for powered transfemoral prostheses. Adaptive dynamic programming (ADP) was implemented within the prosthesis control to complement existing finite state impedance (FS-IC) in prototypic active-transfemoral (ATP). The ADP interacts with human user-prosthesis system, observes user's states during walking, learns personalize user performance properties via online adaptation meet individual objectives. new preliminarily on one...

Machines and humans become mechanically coupled when lower limb amputees walk with powered prostheses, but these two control systems differ in adaptability. We know little about how they interact faced real-world physical demands (e.g. carrying loads). Here, we investigated each system (i.e. amputee prosthesis) responds to changes the prosthesis mechanics gravitational load. Five transfemoral walked without load weighted backpack) a knee pre-programmed controller settings for no load)....

Nowadays, since the resources of remanufacturing are 'cores', uncertainty in quantity and quality 'cores' is an obstacle engineering. To solve this problem, production management design for have been discussed former studies. However, current mode, which carried out end life cycle, reactive. delimit concept proactive presented paper. And one issue to identify timing. In beginning, reactive timing introduced. Then, characterise remanufacturability components, residual strength proposed....

The tuning process for a robotic prosthesis is challenging and time-consuming task both users clinicians. An automatic approach using reinforcement learning (RL) has been developed knee to address the challenges of manual methods. algorithm tunes optimal control parameters based on provided joint profile that expected replicate during gait safely. This paper presents an intuitive interface designed clinicians choose preferred use autotuner in prosthesis. interface-based validated by...