A method is proposed for gesture recognition and humanoid imitation based on Functional Principal Component Analysis (FPCA). FPCA is a statistical technique of functional data analysis that has never been applied before for humanoid imitation. In functional data analysis data (e.g. gestures) are functions that can be considered as observations of a random variable on a functional space. FPCA is an extension of multivariate PCA that provides functional principal components which describe the modes of variation in the data. In the proposed approach FPCA is used for both unsupervised clustering of training data and gesture recognition.In this work we focus on arm gesture recognition. Human hand paths in Cartesian space are reconstructed from inertial sensors. Recognized gestures are reproduced by a small humanoid robot. The FPCA algorithm has also been compared to a state of the art algorithm for gesture classification based on Dynamic Time Warping (DTW). Results indicate that, in this domain, the FPCA algorithm achieves a comparable recognition rate while it outperforms DTW in terms of efficiency in execution time.
The paper focuses on the gait analysis for the investigation of the typical events occurring in human movements and validate its use as a method for musculoskeletal disease evaluation and for the improvement of athletic training. In the present research the motion capture system is combined with an in-house developed prototype of uniaxial force plates for the measurement of the vertical component of ground reaction forces during movement. While similar techniques are implemented for gait, this equipment can be employed to investigate running, thus, covering a larger number of possible applications and providing a deeper insight either of the athlete performance or the disease analysis. For the prevention and the treatment of those events occurring during running, a thorough understanding of its mechanisms is critical; therefore, a method for evaluating both the kinematic behavior of the human body and the ground reaction forces combined to a model for determining the muscle forces is proposed. An infrared motion capture technique is adopted for measuring accurately the body motion and a multiple force-plate system is used to calculate the force exerted by the ground and sub-divided in the three components by an ad-hoc developed routine. Moreover, the data are used as input parameters for the OpenSim software to derive muscles forces. Finally, the potential of the proposed protocol is determined by an experimental campaign on healthy subjects and a significant database of muscle forces is constructed for different running speeds.
The lung is the human organ mainly affected by severe coronavirus disease (COVID-19) caused by the novel coronavirus SARS-CoV-2. In this pathology, the dynamic lung function and the respiratory mechanics are compromised, leading to the development of the ARDS (acute respiratory distress syndrome). The resulting damage is the progressive reduction of gas exchange and death in the most critical patients. For these reasons, it is important to study and analyze how this virus adversely affects lung dynamics. The main objective of the present paper is to propose a modeling methods of SARS-CoV-2 virus particles spread in the 23rd generation of lung tree and the mechanical estimation of how a severe stage of Covid-19 characterized by pulmonary fibrosis affects the alveolar sac expansion and hence the breathing capability of the sick person. In this context, the dynamic analysis of the influence of SARS-CoV-2 spread on human lung under real conditions has been shown by means of a numerical approach. Therefore, a multiphase three-dimensional computational fluid dynamics (CFD) study is performed to estimate the Covid-19 virus particles dispersion throughout a simplify model of the 23rd generation of bronchial tree, at the alveolar region. Then, a fully coupled fluid-structure interaction (FSI) with the mesh morphing technique and solid displacement characteristics are used to obtain and evaluate a realistic wall displacement during the expansion of the alveolar sac. A comparison is made between a healthy and a diseased lung. These phases are studied under cyclic steady-state conditions The novelties of this analysis are: firstly, the innovative CFD method proposed in order to model the particles spread inside the alveolar region, and secondly the evaluation of how the presence of Sars-Cov-2 can affect the mechanical properties of the alveolar sac and damage the lung function of a sick person at an advanced stage of infection, such as a person affected by pulmonary fibrosis.
The paper focuses on the methodology for the analysis of the physiological and biomechanical efficiency of a professional athlete for integrating the standard preparation routine. The proposed methodology combines an in-house developed prototype of multiple uniaxial force plates for the measurement of the vertical component of ground reaction forces during movement and an infrared motion capture technique is adopted for measuring accurately the body motion. The procedure is applied on a top level professional volley player and integrates the working routines used for the training over an entire season. The dynamic performance of the athlete is measured in terms of fatigue threshold and the aerobic workload. The proposed methodology demonstrates to be an accurate and reliable instrument for quantifying, for both slow and fast movements, the efficiency with which the athlete reaches the defined training targets and the precision achieved in developing an exercises’ routine. Furthermore, the dynamic response of the athlete is also measured by evaluating the position of the body during the workload as well as the speed of the movements and the corresponding interaction with the ground. This analysis verifies if an asymmetrical loading of the lower limbs and the power exerted during the impulsive contact phase with the ground. The measurements carried out during the analysis provide a map of the athlete performances during an entire season training and the mono- and bi-podalic movements could be associated with the time evolution of the athletic results, such as jumping length and height, speed, precision. Therefore, inefficiencies in the postural and technical aspects during the training can be measured and thus corrected leading to an improvement of the performance and to a reduction of the possibility for injuries onset.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.