Table Tennis Tutor: Forehand Strokes Classification Based on Multimodal Data and Neural Networks.

Beginner table-tennis players require constant real-time feedback while learning the fundamental techniques. However, due to various constraints such as the mentor's inability to be around all the time, expensive sensors and equipment for sports training, beginners are unable to get the immediate real-time feedback they need during training. Sensors have been widely used to train beginners and novices for various skills development, including psychomotor skills. Sensors enable the collection of multimodal data which can be utilised with machine learning to classify training mistakes, give feedback, and further improve the learning outcomes. In this paper, we introduce the Table Tennis Tutor (T3), a multi-sensor system consisting of a smartphone device with its built-in sensors for collecting motion data and a Microsoft Kinect for tracking body position. We focused on the forehand stroke mistake detection. We collected a dataset recording an experienced table tennis player performing 260 short forehand strokes (correct) and mimicking 250 long forehand strokes (mistake). We analysed and annotated the multimodal data for training a recurrent neural network that classifies correct and incorrect strokes. To investigate the accuracy level of the aforementioned sensors, three combinations were validated in this study: smartphone sensors only, the Kinect only, and both devices combined. The results of the study show that smartphone sensors alone perform sub-par than the Kinect, but similar with better precision together with the Kinect. To further strengthen T3's potential for training, an expert interview session was held virtually with a table tennis coach to investigate the coach's perception of having a real-time feedback system to assist beginners during training sessions. The outcome of the interview shows positive expectations and provided more inputs that can be beneficial for the future implementations of the T3.

Detecting Mistakes in CPR Training with Multimodal Data and Neural Networks.

This study investigated to what extent multimodal data can be used to detect mistakes during Cardiopulmonary Resuscitation (CPR) training. We complemented the Laerdal QCPR ResusciAnne manikin with the Multimodal Tutor for CPR, a multi-sensor system consisting of a Microsoft Kinect for tracking body position and a Myo armband for collecting electromyogram information. We collected multimodal data from 11 medical students, each of them performing two sessions of two-minute chest compressions (CCs). We gathered in total 5254 CCs that were all labelled according to five performance indicators, corresponding to common CPR training mistakes. Three out of five indicators, CC rate, CC depth and CC release, were assessed automatically by the ReusciAnne manikin. The remaining two, related to arms and body position, were annotated manually by the research team. We trained five neural networks for classifying each of the five indicators. The results of the experiment show that multimodal data can provide accurate mistake detection as compared to the ResusciAnne manikin baseline. We also show that the Multimodal Tutor for CPR can detect additional CPR training mistakes such as the correct use of arms and body weight. Thus far, these mistakes were identified only by human instructors. Finally, to investigate user feedback in the future implementations of the Multimodal Tutor for CPR, we conducted a questionnaire to collect valuable feedback aspects of CPR training.

Psychomotor Behavior: A Practical Approach in Drosophila.

Psychomotor behaviors are governed by fine relationships between physical activity and cognitive functions. Disturbances in psychomotor development and performance are a hallmark of many mental illnesses and often appear as observable and measurable behaviors. Here, we describe a new method called an "equilibrist test," which can be used to quantify psychomotor learning and performance in Drosophila. We also show how this test can be used to quantify motor disturbances at relatively early stages in the development of neurodegenerative diseases.

Os efeitos da aprendizagem psicomotora no controle das atividades de locomoção sobre obstáculos em crianças com deficiência da visão / The effects of psychomotor learning on the control of locomotion during obstacle avoidance in children with low vision

Considerando que a visão é um dos sistemas sensoriais mais importantes na locomoção pois fornece informação tanto do ambiente quanto da postura e dos movimentos corporais, este estudo analisou os efeitos de um programa de treinamento perceptivo-motor no controle das atividades de locomoção em seis crianças com deficiências da visão. Para tanto, realizou-se a avaliação da locomoção durante a transposição de obstáculos com alturas diferentes, utilizando-se indicadores qualitativos: postura / equilíbrio / direção / velocidade / contato visual com o obstáculo / erro na tarefa, e indicadores cinemáticos, obtidos por meio de filmagem (SVHS) através do sistema Peak Motus (Versão 7.0 - Vicon Peak) para medir: a distância do pé de apoio em relação ao obstáculo / a elevação máxima do joelho / a altura do pé em relação à altura do obstáculo. Os indicadores foram novamente avaliados após a realização do programa de treinamento, fornecendo evidências de sua contribuição positiva tanto na estratégia de aproximação quanto na estratégia de ultrapassagem dos obstáculos. Durante a aproximação, a velocidade da locomoção tornou-se mais constante e as passadas foram realizadas de forma mais retilínea. Durante a ultrapassagem, o número de toques no obstáculo diminuiu. Os resultados auxiliam na reflexão sobre a importância da aprendizagem psicomotora nos programas educacionais, particularmente na Educação Física Especial, como uma forma de contribuir para uma melhor qualidade de vida das crianças com baixa visão.

Since vision is one of the most important sensory systems called upon for locomotion because it provides information not only about the environment, but also about posture and movement of corporal segments, this study analyzed the effects of a psychomotor training program on the control of locomotion with six children with low vision. Thus, an assessment of locomotion during obstacle avoidance with different obstacle heights was performed based on the qualitative parameters: posture / balance / direction / velocity / visual contact with the obstacle / error on the task, and on kinematics parameters collected via motion analysis system (Peak Motus - 7.0 - Vicon Peak) to assess: the distance of the base foot in relation to obstacle position / the maximum elevation of the knee / the height of the foot in relation to obstacle height. The parameters were again analyzed after the training program, showing evidence of the positive effect of both the strategy of approximation and the strategy of going over the obstacle. On approximation, the walking velocity became more stable and the subjects walked straighter. During obstacle crossing, there was less contact between the foot and the obstacle. These results will help to understand the importance of psychomotor learning in educational programs, especially on adapted physical education, so as to contribute to better quality of life for children with low vision.