Recently, fast and practical inverse kinematics (IK) methods for complicated human models have gained considerable interest owing to the spread of convenient motion-capture or human-augmentation technologies. Although IK algorithms developed in robotics can also be applied humans, they experience computational speed issues, especially real-time applications. This paper presents a new algorithm ...

The main goal of the presented work is to analyse the performance of the Multi-Layer Perceptron (MLP) neural network for flow regime classification based on sets of simulated Electrical Capacitance Tomography (ECT) data. Normalised ECT data have been used to separately train several MLPs employing various commonly used back-propagation learning algorithms, namely the Levenberg-Marquardt (LM), Q...

In this study, a Neural Network (NN) based data fusion and estimation algorithm is developed, which could be applied in monitoring and detection applications that use measurements coming from multiple sensors. For NN based applications, a fast training approach which can also guarantee the global minimum is highly desirable and is subject for ongoing research. For this purpose, in this study, a...

Artificial neural networks have emerged as a good candidate to mathematical wear models, due to their capabilities of handling nonlinear behavior, learning from experimental data and generalization. In the present work the potential of using neural networks for the prediction of abrasive wear properties of unfilled and graphite filled carbon fabric reinforced epoxy composite under various testi...

In this study, 40 healthy control group and 40 patients with rheumatoid arthritis (RA) and Doppler signal from radial artery of the left and right hand were recorded. This non-parametric Welch Periodogram method to signal attributes of the signs were removed and the artificial neural network (ANN) classification method was utilized in order to recognize diseased and healthy control group indivi...

The design of an optimized near-perfect reconstruction (NPR) type trans-multiplexer has been proposed. Cosine modulation has been used to design the synthesis and analysis sections of the trans-multiplexer. The design of transmultiplexer was reduced to design of single low-pass prototype FIR filter which is designed using variable window function (Kaiser, Cosh and DolphChebyshev). An unconstrai...

Back-propagation Artificial Neural Networks (ANN) were tested with the aim of modelling the occurrence of benthic macroinvertebrate families in a south Brazilian river. The dataset, consisting of 67 sets of observations of macroinvertebrate abundance (families Hydrobiidae, Tubificidae, Chironomidae, Baetidae and Leptophlebiidae) and water quality variables (pH, temperature, dissolved oxygen, bi...

The combination of angle-resolved X-ray photoelectron spectroscopy (ARXPS) and a modified Levenberg-Marquardt (LM) fit procedure has been used to study a native oxide layer on a clean Si(100) substrate. Numerical calculations show that with an aperture of 3 o or 9 o of the electron analyser, the photoelectron take-off angle should not exceed 80 o or 70 o, respectively, as compared to normal tak...

In this paper we develop further a method for detecting unstable periodic orbits (UPOs) by stabilising transformations, where the strategy is to transform the system of interest in such a way that the orbits become stable. The main difficulty of using this method is that the number of transformations, which were used in the past, becomes overwhelming as we move to higher dimensions [5, 19, 20]....

0957-4174/$ see front matter 2013 Elsevier Ltd. A http://dx.doi.org/10.1016/j.eswa.2013.01.060 ⇑ Tel.: +385 1 4561191. E-mail address: [email protected] The main disadvantage of self-organizing polynomial neural networks (SOPNN) automatically structured and trained by the group method of data handling (GMDH) algorithm is a partial optimization of model weights as the GMDH algorithm optimizes on...