RESUMEN

Recognizing user intention in reach-to-grasp motions is a critical challenge in rehabilitation engineering. To address this, a Machine Learning (ML) algorithm based on the Extreme Learning Machine (ELM) was developed for identifying motor actions using surface Electromyography (sEMG) during continuous reach-to-grasp movements, involving multiple Degrees of Freedom (DoFs). This study explores feature extraction methods based on time domain and autoregressive models to evaluate ELM performance under different conditions. The experimental setup encompassed variations in neuron size, time windows, validation with each muscle, increase in the number of features, comparison with five conventional ML-based classifiers, inter-subjects variability, and temporal dynamic response. To evaluate the efficacy of the proposed ELM-based method, an openly available sEMG dataset containing data from 12 participants was used. Results highlight the method's performance, achieving Accuracy above 85%, F-score above 90%, Recall above 85%, Area Under the Curve of approximately 84% and compilation times (computational cost) of less than 1 ms. These metrics significantly outperform standard methods (p < 0.05). Additionally, specific trends were found in increasing and decreasing performance in identifying specific tasks, as well as variations in the continuous transitions in the temporal dynamics response. Thus, the ELM-based method effectively identifies continuous reach-to-grasp motions through myoelectric data. These findings hold promise for practical applications. The method's success prompts future research into implementing it for more reliable and effective Human-Machine Interface (HMI) control. This can revolutionize real-time upper limb rehabilitation, enabling natural and complex Activities of Daily Living (ADLs) like object manipulation. The robust results encourages further research and innovative solutions to improve people's quality of life through more effective interventions.

RESUMEN

Tufted capuchin monkeys (Sapajus spp.) are the only Neotropical Primates that regularly use tools in the wild, but only one population of bearded capuchin monkeys (Sapajus libidinosus) is known to habitually use sticks as probes. In this population, males are typically the only sex to use stick tools, something unexpected, since there are no obvious physical constraints, and females do use stone tools in the wild and sticks in experimental conditions. We investigated the development of probe tool use in eight infants to clarify whether social influences on learning varied between the sexes, as tool use learning by capuchin monkeys is a socially biased process. We found that in the first 10 months of age, females manipulate sticks as much as males, but after 10-12 months of age, males begin to manipulate them at higher frequencies. We examined if social connections-as opportunities for social learning-could explain this difference and verified that, on close distance social networks, infant males and females have similar connections with older males. However, males observe probe tool use events more often than females when close to such events. The higher frequency of manipulation of sticks, as well as the higher rates of probe tool use observation, appear to be the key to understand why only males are probe tool users in this population. Since there are only male potential models of probe use, a sex motivational bias could explain the sex difference in observation; a bias in observation could explain the differences in manipulation-and manipulation rates would certainly influence the chances of individual, trial-and-error learning (a case of "local/stimulus enhancement").

Asunto(s)

RESUMEN

OBJECTIVE: To assess hand function and grip force (GF) control in non-neuropathic diabetic individuals using traditional hand function tests and instrumented handles that provide information about the underlying neural mechanisms controlling simple manipulation tasks. METHODS: Twelve diabetic individuals (31-60 years-old) without neuropathy and 12 controls performed traditional functional tests (i.e., nine hole peg test, Jebsen-Taylor test, and maximum grip strength test) and were tested for GF control in two situations: holding a free moving instrumented handle and isometrically pulling fixed handles. Task performance in the tests and safety margin (SM - percentage of GF above the minimum needed to hold the handle) were the main dependent variables assessed. RESULTS: There was no difference between diabetics and controls in any functional test and in SM in isometric pulling task. However, diabetics presented around twice lower SM than controls in the free holding task. CONCLUSIONS: Diabetics showed no impairment in functional manipulation tasks. However, they presented a lower SM than healthy controls. SIGNIFICANCE: This lower SM suggests that diabetics may present sensory impairment that could put them at risk of losing objects during its manipulation. Also, it suggests that the applied experimental procedure is sensitive to detect mild sensory impairment in diabetics.

Asunto(s)

RESUMEN

El objetivo del estudio fue describir el patrón temporal de ira y de dos comportamientos con función reguladora (autotranquilización y manipulación de un objeto) en función de un entrenamiento para el uso de reglas de despliegue emocional (RDE) en una muestra de 12 niños (M= 9.5 años). Como efecto de la intervención se estabilizó la tasa de autotranquilización en participantes y grupos; la manipulación de objeto parece no tener una función reguladora. Los puntajes de uso de RDE no mostraron diferencias significativas pre y post intervención, pero se discuten los cambios en autotranquilización y manipulación de objeto en función de patrones específicos de uso de RDE.

The aim of this study was to describe the temporary pattern of anger and two regulatory behaviors (self-soothing, object manipulation) as a function of training in the use of emotional display rules (EDR) in a sample of 12 boys (M= 9.5 years-old). As an outcome of,this intervention the rate of self-soothing amongst subjects and groups became stable whereas object manipulation seemed to have no regulatory function. Scores in EDR did not show significant differences pre and post intervention, but changes in self-soothing and object manipulation are discussed in function of specific patterns of EDR enactment.

O objetivo deste estudo foi descrever o padrão temporal de ira e de dois comportamentos reguladores (auto-tranquilização e manipulação de um objeto) com base em um treinamento para o uso de regras de exibição emocional (REE) em uma amostra de 12 crianças (M = 9,5 anos). A intervenção estabilizou a taxa de auto-tranquilização nos participantes e grupos. A manipulação de objetos parece não ter uma função reguladora. Os escores de utilização de REE não mostraram diferença significativa antes e depois a intervenção, mas são discutidas as mudanças em auto-tranquilização e manipulação de objetos com base em padrões específicos de uso do REE.

Asunto(s)