Shared Prosthetic Control Based on Multiple Movement Intent Decoders.

SIGNIFICANCE: A number of movement intent decoders exist in the literature that typically differ in the algorithms used and the nature of the outputs generated. Each approach comes with its own advantages and disadvantages. Combining the estimates of multiple algorithms may have better performance than any of the individual methods. OBJECTIVE: This paper presents and evaluates a shared controller framework for prosthetic limbs based on multiple decoders of volitional movement intent. METHODS: An algorithm to combine multiple estimates to control the prosthesis is developed in this paper. The capabilities of the approach are validated using a system that combines a Kalman filter-based decoder with a multilayer perceptron classifier-based decoder. The shared controller's performance is validated in online experiments where a virtual limb is controlled in real-time by amputee and intact-arm subjects. During the testing phase subjects controlled a virtual hand in real time to move digits to instructed positions using either a Kalman filter decoder, a multilayer perceptron decoder, or a linear combination of the two. RESULTS: The shared controller results in statistically significant improvements over the component decoders. Specifically, certain degrees of shared control result in increases in the time-in-target metric and decreases in unintended movements. CONCLUSION: The shared controller of this paper combines the good qualities of component decoders tested in this paper. Herein, combining a Kalman filter decoder with a classifier-based decoder inherits the flexibility of the Kalman filter decoder and the limited unwanted movements from the classifier-based decoder, resulting in a system that may be able to perform the tasks of everyday life more naturally and reliably.

Deep Learning Movement Intent Decoders Trained With Dataset Aggregation for Prosthetic Limb Control.

SIGNIFICANCE: The performance of traditional approaches to decoding movement intent from electromyograms (EMGs) and other biological signals commonly degrade over time. Furthermore, conventional algorithms for training neural network based decoders may not perform well outside the domain of the state transitions observed during training. The work presented in this paper mitigates both these problems, resulting in an approach that has the potential to substantially improve the quality of life of the people with limb loss. OBJECTIVE: This paper presents and evaluates the performance of four decoding methods for volitional movement intent from intramuscular EMG signals. METHODS: The decoders are trained using the dataset aggregation (DAgger) algorithm, in which the training dataset is augmented during each training iteration based on the decoded estimates from previous iterations. Four competing decoding methods, namely polynomial Kalman filters (KFs), multilayer perceptron (MLP) networks, convolutional neural networks (CNN), and long short-term memory (LSTM) networks, were developed. The performances of the four decoding methods were evaluated using EMG datasets recorded from two human volunteers with transradial amputation. Short-term analyses, in which the training and cross-validation data came from the same dataset, and long-term analyses, in which the training and testing were done in different datasets, were performed. RESULTS: Short-term analyses of the decoders demonstrated that CNN and MLP decoders performed significantly better than KF and LSTM decoders, showing an improvement of up to 60% in the normalized mean-square decoding error in cross-validation tests. Long-term analyses indicated that the CNN, MLP, and LSTM decoders performed significantly better than a KF-based decoder at most analyzed cases of temporal separations (0-150 days) between the acquisition of the training and testing datasets. CONCLUSION: The short-term and long-term performances of MLP- and CNN-based decoders trained with DAgger demonstrated their potential to provide more accurate and naturalistic control of prosthetic hands than alternate approaches.

A restrição do crescimento fetal influencia a composição corporal na idade escolar? / Does fetal growth restriction influence body composition at school age?

OBJETIVO: Verificar a influência do baixo peso de crianças nascidas a termo sobre a composição corporal na idade escolar. MÉTODO: Este estudo consistiu de um corte transversal aninhado em uma coorte de 375 crianças recrutadas ao nascimento em 1993-1994 no estado de Pernambuco. Aos 8 anos de idade, 213 crianças tiveram a composição corporal avaliada através da mensuração da espessura das pregas cutâneas tricipital e subescapular e da circunferência do braço. A regressão linear multivariada foi utilizada para identificar a influência do baixo peso ao nascer, das condições socioeconômicas, do estado nutricional materno e morbidade da criança na prega cutânea tricipital. RESULTADOS: As médias das pregas cutâneas tricipital e subescapular, da circunferência do braço e das áreas muscular e de gordura do braço foram menores nas crianças nascidas com baixo peso em relação às nascidas com peso adequado; no entanto, essas diferenças não foram estatisticamente significantes. Na análise de regressão linear multivariada, as variáveis socioeconômicas explicaram o maior percentual da variação da prega cutânea tricipital (12,3 por cento), especialmente a renda familiar per capita (9,1 por cento), seguida da ocorrência de anemia e da hospitalização anterior, que juntas explicaram 5,6 por cento, e do índice de massa corporal materna, que contribuiu com 2,4 por cento dessa variação. O baixo peso ao nascer não influenciou no depósito de gordura subcutânea tricipital nessa faixa etária. CONCLUSÃO: Os fatores socioeconômicos e a morbidade anterior da criança apresentaram uma maior influência na composição corporal de escolares nascidos a termo em detrimento do baixo peso ao nascer.

OBJECTIVE: To assess the influence of low birth weight in full-term infants on body composition at school age. METHOD: This is a cross-sectional study nested in a cohort of 375 infants recruited at birth between 1993 and 1994 in the state of Pernambuco, Brazil. At 8 years of age, the body composition of 213 children from this cohort was assessed by measurement of triceps and subscapular skinfold thickness and mid upper arm circumference. Multivariable linear regression analysis was used to identify the influence of low birth weight, socioeconomic condition, maternal nutritional status, and child morbidity on triceps skinfold thickness. RESULTS: Mean triceps and subscapular skinfold thickness, mid upper arm circumference, and upper arm muscle and fat areas were lower in children born at term with low weight than in those with appropriate birth weight. However, these differences were not statistically significant. Multivariable linear regression analysis showed that the relative majority of variance in triceps skinfold thickness (12.3 percent) was explained by socioeconomic variables, particularly per capita family income (9.1 percent), followed by anemia and past hospitalization (which, together, explained 5.6 percent of variance) and maternal body mass index, which contributed toward 2.4 percent of this variance. Low birth weight had no influence on triceps subcutaneous fat deposition in this age group. CONCLUSION: Socioeconomic factors and a history of morbidity had a greater influence on body composition than low birth weight in schoolchildren born at term.

Does fetal growth restriction influence body composition at school age?

OBJECTIVE: To assess the influence of low birth weight in full-term infants on body composition at school age. METHOD: This is a cross-sectional study nested in a cohort of 375 infants recruited at birth between 1993 and 1994 in the state of Pernambuco, Brazil. At 8 years of age, the body composition of 213 children from this cohort was assessed by measurement of triceps and subscapular skinfold thickness and mid upper arm circumference. Multivariable linear regression analysis was used to identify the influence of low birth weight, socioeconomic condition, maternal nutritional status, and child morbidity on triceps skinfold thickness. RESULTS: Mean triceps and subscapular skinfold thickness, mid upper arm circumference, and upper arm muscle and fat areas were lower in children born at term with low weight than in those with appropriate birth weight. However, these differences were not statistically significant. Multivariable linear regression analysis showed that the relative majority of variance in triceps skinfold thickness (12.3%) was explained by socioeconomic variables, particularly per capita family income (9.1%), followed by anemia and past hospitalization (which, together, explained 5.6% of variance) and maternal body mass index, which contributed toward 2.4% of this variance. Low birth weight had no influence on triceps subcutaneous fat deposition in this age group. CONCLUSION: Socioeconomic factors and a history of morbidity had a greater influence on body composition than low birth weight in schoolchildren born at term.

Da avaliaçäo na Disciplina de Neonatologia e Puericultura do Departamento Materno Infantil do Centro de Ciências da Saúde da Universidade Federal de Pernambuco / Evaluation in the Department of Neonatology and Puericulture of the Department Materno Infantil do Centro de Ciências da Saúde da Universidade Federal de Pernambuco

Säo apresentadas as diversas formas de avaliaçäo utilizadas na Disciplina de Neonatologia e Puericultura do Departamento Materno Infantil do Centro de Ciências da Saúde da Universidade Federal de Pernambuco (UFPE). Enfatiza-se a importância de avaliar o aprendizado de um modo global, numa tentativa de atingir as diversas áreas do conhecimento: cognitiva, afetiva e psicomotora. Relata-se a experiência da retroalimentaçäo contínua do sistema, para modificaçäo do comportamento. Especial importância é dada à avaliaçäo diária do aluno, através de seminário, estudo dirigido e prática ambulatorial