Efficacy of classical manual material handling (MMH) training interventions on back pain prevention at the workplace has been called into question. The way that observation (self-observation or hetero-observation) is used in other areas to create feedback addressed to modify motor activities can justify innovative components for these interventions. However, their implementation and evaluation cannot be done without tackling the methodological challenge of developing a reliable observational instrument to measure manual handling practice during the training process. The aims of this study were: (1) justify and develop an hetero-observation (H-O) instrument to assess changes in the worker behavioral patterns with a level of analysis convenient to derive a parallel version for the systematic self-observation (S-O) during training on MMH; (2) provide evidence on the inter-rater reliability of the H-O instrument; (3) provide evidence on the usability of the S-O instrument and its perceived usefulness; and (4) provide evidence on the benefits that can be derived with the use of the H-O instrument to create feedback based on T-pattern and polar coordinate analysis. A mixed method approach mainly grounded on systematic observation was used. A convenience sample composed by blue-collar workers participated in the study. Based on literature review and expert opinion, the H-O instrument proposed was composed by six dimensions (feet, knee joints, back, elbow joints, load position, and interaction between back tilt and displacement) plus a structural dimension which defined MMH phases. The inter-rater reliability of this instrument was almost perfect for all dimensions using a tolerance level of 2 s (the range of time-unit kappa was from 0.93 to 0.97 and the range of event-based kappa was from 0.82 to 0.9). The usability and usefulness of the S-O instrument was highly valued by workers. Regarding the way to use hetero-observations to create feedback, the paper shows the great potential of T-pattern and polar coordinate analysis. The observational instruments developed combined with these techniques make it possible to characterize the body positions adopted during manual handling performance, and this is crucial to create feedback on performance instead of only feedback on results.
Multimodal natural behavior of humans presents a complex yet highly coordinated set of interacting processes. Providing robots with such interactive skills is a challenging and worthy goal and numerous such efforts are currently underway; evaluating the progress in this direction, however, continues to be a challenge. General methods for measuring the performance of artificially intelligent systems would be of great benefit to the research community. In this paper1 we describe an approach to evaluating human-robot multimodal natural behavior. The approach is based on a detailed scoring and spatio-temporal analysis of the structure and patterning of live behavior, at multiple temporal scales, down to the decisecond level. The approach is tested in a case study involving an early virtual robot prototype, Gandalf, which is capable of real-time verbal and non-verbal interaction with people. Our analysis includes a comparison to a comparable human-human dyadic interaction scenario. Our main objective is to develop a methodology for comparing the quality and effectiveness of human-robot interaction between a wide variety of such systems. Early results indicate that our approach holds significant promise as a future methodology for evaluating complex systems that have a natural counterpart
27 November 2023 in Ágora para la Educación Física y el Deporte
El sistema de puntuación basado en la acumulación-desacumulación comporta un trasiego en la puntuación de los equipos. En el juego de tríada estudiado se confirma el efecto ambivalente de las situaciones motrices y cómo reduce las diferencias entre los equipos que revierten en el marcador. El análisis se realiza a través de la frecuencia de roles, tasa de actuación, y todo ello en tres momentos del desarrollo del juego; además, se aplica una prueba T-Patterns, para conocer las diferencias a través de los patrones temporales. Se establece una reflexión paralela acerca del mensaje social y la repercusión pedagógica que emana del sistema de puntuación estudiado.