Comparing the efficiency of artificial neural networks in sEMG-based simultaneous and continuous estimation of hand kinematics

Surface Electromyography (sEMG) plays a key role in many applications such as control of Human-Machine Interfaces (HMI) and neuromusculoskeletal modeling. It has strongly nonlinear relations to joint kinematics and reflects the subjects’ intention in moving their limbs. Such relations have been traditionally examined by either integrated biomechanics and multi-body dynamics or gesture-based classification approaches. However, these methods have drawbacks that limit their usability. Different from them, joint kinematics can be continuously reconstructed from sEMG via estimation approaches, for instance, the Artificial Neural Networks (ANNs). The Comparison of different ANNs used in different studies is difficult, and in many cases, impossible. The current study focuses on fairly evaluating four types of ANN over the same dataset and conditions in proportional and simultaneous estimation of 15 hand joint angles from 10 sEMG signals. The presented ANNs are Feedforward, Cascade-Forward, Radial Basis Function (RBFNN), and Generalized Regression (GRNN). Each ANN is applied to its special parametric study. All the methods efficiently solved the regression problem of the complex multi-input multi-output bio-system. The RBFNN has the best performance over the others with a 79.80% mean correlation coefficient over all joints, and its accuracy reaches as high as 92.67% in some joints. Interestingly, the highest accuracy over individual joints is 93.46%, which is achieved via the GRNN. The good accuracy suggests that the proposed approaches can be used as alternatives to the previously adopted ones and can be employed effectively to synchronously control multi-degrees of freedom HMI and for general multi-joint kinematics estimation purposes.     

Implementation of the transformation field analysis for inelastic composite materials

Conclusions The transformation field analysis is a general method for solving inelastic deformation and other incremental problems in heterogeneous media with many interacting inhomogeneities. The various unit cell models, or the corrected inelastic self-consistent or Mori-Tanaka fomulations, the so-called Eshelby method, and the Eshelby tensor itself are all seen as special cases of this more general approach. The method easily accommodates any uniform overall loading path, inelastic constitutive equation and micromechanical model. The model geometries are incorporated through the mechanical transformation influence functions or concentration factor tensors which are derived from elastic solutions for the chosen model and phase elastic moduli. Thus, there is no need to solve inelastic boundary value or inclusion problems, indeed such solutions are typically associated with erroneous procedures that violate (6₂); this was discussed by Dvorak (1992). In comparison with the finite element method in unit cell model solutions, the present method is more efficient for cruder mesches. Moreover, there is no need to implement inelastic constitutive equations into a finite element program. An addition to the examples shown herein, the method can be applied to many other problems, such as those arising in active materials with eigenstrains induced by components made of shape memory alloys or other actuators. Progress has also been made in applications to electroelastic composites, and to problems involving damage development in multiphase solids. Finally, there is no conceptural obstacle to extending the approach beyond the analysis of representative volumes of composite materials, to arbitrarily loaded structures.This work was supported by the Air Force Office of Scienctific Research, and by the Office of Naval Research     

Analyzing and modeling risk exposure of pedestrian children to involvement in car crashes

This paper analyzes the various variables affecting pedestrian children road crashes, placing emphasis on the effect of daily activity patterns and the built environment, including the children's residential neighborhoods and the land use of the places where they conduct their activities. Two complementary data sources from the case study of an Arab town in northern Israel were used to provide a holistic picture of child-pedestrian road crashes: police files providing detailed analyzes of the reason for each crash, its location, and the characteristics of the driver involved; and a survey of 199 households with both involved and not involved children in road crashes, including a one-day travel diary. The study found that a combination of three groups of variables affects child-pedestrian road crashes: socio-economic status, travel patterns, and land use. Most vulnerable are boys from a low socio-economic group who live in areas of high density and mixed land use near a major road and who tend to walk to and from school and additional activities after school.     

Relaxation behavior in polarized PVDF films under the influence of mechanical and thermal multistresses above glass-transition temperature

The discharging currents in cast-prepared PVDF films are measured under the influence of mechanical and thermal multistresses. Analysis of the experimental data in the framework of the Kohlrausch-Williams-Watt's function is carried out. A linear relationship between the logarithm of the relaaxation time and the applied stress is verified, which is displayed as the mechanical offset stress increases. With the aid of the rate theory and the concept of the free volume, the activation volume , υ*, has been determined and is consistent with the reported value. © 1998 John Wiley & Sons, Inc. J. Appl. Polym. Sci. 70: 859–864, 1998     

Finite element modelling of an energy-storing prosthetic foot during the stance phase of transtibial amputee gait

Energy-storing prosthetic feet are designed to store energy during mid-stance motion and to recover it during late-stance motion. Gait analysis is the most commonly used method to characterize prosthetic foot behaviour during walking. In using this method, however, the foot is generally modelled as a rigid body. Therefore, it does not take into account the ability of the foot to deform. However, the way this deformation occurs is a key parameter of various foot properties under gait conditions. The purpose of this study is to combine finite element modelling and gait analysis in order to calculate the strain, stress and energy stored in the foot along the stance phase for self-selected and fast walking speeds. A finite element model, validated using mechanical testing, is used with boundary conditions collected experimentally from the gait analysis of a single transtibial amputee. The stress, strain and energy stored in the foot are assessed throughout the stance phase for two walking speed conditions: a self-selected walking speed (SSWS), and a fast walking speed (FWS). The first maximum in the strain energy occurs during heel loading and reaches 3J for SSWS and 7J for FWS at the end of the first double support phase. The second maximum appears at the end of the single support phase, reaching 15J for SSWS and 18J for FWS. Finite element modelling combined with gait analysis allows the calculation of parameters that are not obtainable using gait analysis alone. This modelling can be used in the process of prosthetic feet design to assess the behaviour of a prosthetic foot under specific gait conditions.     

Synthesis,structural characterization and luminescent properties of Tb3+-doped AgLaP2O7 phosphors

Silver lanthanum diphosphates doped with terbium, AgLa_1-xTb_xP₂O₇ (x=0%, 1%, 5%, 10%, 15% and 20%), were prepared by solid state reaction at T=500°. The obtained compounds were investigated by means of a multi-methodological approach, involving the Scanning Electron Microscopy (SEM) equipped with energy dispersive X-Ray spectroscopy (EDS) for morphological investigation and semi-quantitative chemical analysis, respectively; powder X-ray diffraction (PXRD) for structural characterization and Rietveld refinement; Fourier Transform InfraRed (FTIR) and Raman spectroscopies for qualitative study. Finally, emission spectra were collected in order to detect the fluorescence properties of the compounds.The unit cell parameters and the space group of all the family members were determined by PXRD data. The compounds crystallize in the orthorhombic Pnma space group, with the AgLaP₂O₇ cell constants equal to: a?=?8.6706(1) Å, b?=?5.3218(1) Å, c?=?12.8839(1) Å and cell volume V?=?594.51(1) ų. A decreasing trend for unit cell parameters was observed at increase of dopant concentration. For the pure phase, the investigation was completed with the structure solution via Direct Methods and Rietveld refinement. The crystal structure consists of compact layers of LaO₉ polyhedra, down the c axis, bridged by P₂O₇ diphosphate groups and by zig-zag chains of AgO₉ polyhedra down b.The FTIR and Raman analysis supports the chemical structure, highlighting the deformation (δPO₃) and stretching (νPO₃) vibration of PO₃ groups, and the characteristic bands of P₂O₇^4- groups attributed to the symmetric and asymmetric stretching (ν_s and ν_as) of P-O-P bridge, respectively.The luminescence properties of Tb³⁺ activating ion in AgLa_1-xTb_xP₂O₇ (x=1%, 5%, 10%, 15% and 20%) were also examined. No concentration quenching of the main ⁵D₄-→⁷F₅ emission, responsible for the well known green emission of Tb³⁺ ion, was observed in the studied concentration range, whereas a concentration quenching of the emission from ⁵D₃ level, due to ⁵D₃^-→⁵D₄ cross relaxation process, was revealed.