THERAPY OF UPPER LIMBS BY MEANS OF VIRTUAL REALITY TECHNOLOGIES

This paper deals with an approach to upper limbs therapy that uses virtual reality technologies. The previous methods and subsequent improvements of these procedures by means of a skeletal model of the upper limb in a virtual environment are presented here. So, main focus of the paper is on the description of calculation related to the bone rotation system within appropriate skeletal model. The therapist can add either more virtual upper limb objects or more virtual training objects to the virtual environment and thus expand/change the scene or the therapy complexity. The functions used in the limb movement calculations are useful for creating additional animations with various objects. With this system, the patient can be stimulated under the supervision of a therapist to practice certain rehabilitation procedures. Due to the use of collaborative web-based virtual reality, the therapy can be also applied in a remote form. The way in which the underlying idea of rehabilitation process is implemented and it is also described. In the conclusion are the some notes about system testing and evaluation including description of a therapist interface.

Reinforcement learning control of a biomechanical model of the upper extremity

Among the infinite number of possible movements that can be produced, humans are commonly assumed to choose those that optimize criteria such as minimizing movement time, subject to certain movement constraints like signal-dependent and constant motor noise. While so far these assumptions have only been evaluated for simplified point-mass or planar models, we address the question of whether they can predict reaching movements in a full skeletal model of the human upper extremity. We learn a control policy using a motor babbling approach as implemented in reinforcement learning, using aimed movements of the tip of the right index finger towards randomly placed 3D targets of varying size. We use a state-of-the-art biomechanical model, which includes seven actuated degrees of freedom. To deal with the curse of dimensionality, we use a simplified second-order muscle model, acting at each degree of freedom instead of individual muscles. The results confirm that the assumptions of signal-dependent and constant motor noise, together with the objective of movement time minimization, are sufficient for a state-of-the-art skeletal model of the human upper extremity to reproduce complex phenomena of human movement, in particular Fitts’ Law and the $$\frac{2}{3}$$ 2 3 Power Law. This result supports the notion that control of the complex human biomechanical system can plausibly be determined by a set of simple assumptions and can easily be learned.

Enhancing Pupils' Understanding of the Human Skeleton Using a Designed Human Skeletal Model

The research was necessitated due to the researcher's experience of the difficulty of pupils of Pepease Presbyterian Basic Six in the understanding of the human skeleton. The total number of thirty-three pupils in this class, Pepease Presbyterian Basic Six was the population of this study which employed an action research method. The study revealed that pupils performed better in a lesson on the human skeleton aided by the skeletal model designed by the researcher than when presented theoretically. The research instruments employed in this study were interview, test and questionnaire. The model of the human skeleton, designed teaching and learning material used served its purpose so well and this reflected in pupils' performance which had improved remarkably after the intervention. The present study, therefore, recommends intermittent in-service training for Science Teachers especially those in the remote areas on how to design improvised materials for the various topics in the Basic Schools Science Syllabus.

Two-Dimensional versus Three-Dimensional Symmetric Lifting Motion Prediction Models: A Case Study

Symmetric lifting is a common manual material handling strategy in daily life and is the main cause of low back pain. In the literature, symmetric lifting is mainly simulated by using two-dimensional (2D) models because of their simplicity and low computational cost. In practice, however, symmetric lifting can generate asymmetric kinetics especially when the lifting weight is heavy and symmetric lifting based on 2D models miss this important asymmetric kinetics information. Therefore, three-dimension (3D) models are necessary for symmetric lifting simulation to capture asymmetric kinetics. The purpose of this single subject case study is to compare the optimization formulations and simulation results for symmetric lifting by using 2D and 3D human models and to identify their pros and cons. In this case study, a 10 degrees of freedom (DOFs) 2D skeletal model and a 40 DOFs 3D skeletal model are employed to predict the symmetric maximum weight lifting motion, respectively. The lifting problem is formulated as a multi-objective optimization (MOO) problem to minimize the dynamic effort and maximize the box weight. An inverse dynamic optimization approach is used to determine the optimal lifting motion and the maximum lifting weight considering dynamic joint strength. Lab experiments are carried out to validate the predicted motions. The predicted lifting motion, ground reaction forces (GRFs), and maximum box weight from the 2D and 3D human models for Subject #8 are compared with the experimental data. Recommendations are given.

Recognition of Russian and Indian sign languages used by the deaf people

In our paper, we consider approaches towards the recognition of sign languages used by the deaf people in Russia and India. The structure of the recognition system for individual gestures is proposed based on the identification of its five components: configuration, orientation, localization, movement and non-manual markers. We overview the methods applied for the recognition of both individual gestures and continuous Indian and Russian sign languages. In particular we consider the problem of building corpuses of sign languages, as well as sets of training data (datasets). We note the similarity of certain individual gestures in Russian and Indian sign languages and specify the structure of the local dataset for static gestures of the Russian sign language. For the dataset, 927 video files with static one-handed gestures were collected and converted to JSON using the OpenPose library. After analyzing 21 points of the skeletal model of the right hand, the obtained reliability for the choice of points equal to 0.61, which was found insufficient. It is noted that the recognition of individual gestures and sign speech in general is complicated by the need for accurate tracking of various components of the gestures, which are performed quite quickly and are complicated by overlapping hands and faces. To solve this problem, we further propose an approach related to the development of a biosimilar neural network, which is to process visual information similarly to the human cerebral cortex: identification of lines, construction of edges, detection of movements, identification of geometric shapes, determination of the direction and speed of the objects movement. We are currently testing a biologically similar neural network proposed by A.V. Kugaevskikh on video files from the Russian sign language dataset.