background: intervertebral disc herniation has two common types, extrusion and protrusion, which may affect the adjacent vertebrae.in addition, it is associated with significant signal changes in t1 mri (short tr/te) and t2 mri (long tr/te).   methods: the present study is a cross-sectional analytic one, in which sampling was performed retrospectively. cases were randomly selected from the pati...

This paper aims to develop a writing robot by recognizing the speech signal from the user. The robot arm constructed mainly for the disabled people who can’t perform writing on their own. Here, dynamic time warping (DTW) algorithm is used to recognize the speech signal from the user. The action performed by the robot arm in the environment is done by reducing the redundancy which frequently fac...

In this paper artificial neural networks and support vector machines are used to reduce the amount of vibration data that is required to estimate the Time Domain Average of a gear vibration signal. Two models for estimating the time domain average of a gear vibration signal are proposed. The models are tested on data from an accelerated gear life test rig. Experimental results indicate that the...

This paper presents a fast center weighted rank order filtering algorithm with logarithmic worst case time complexity with respect to the window size. The method is based on a data structure, called an unbalanced “double heap” which naturally supports partition of the window samples into two different “heaps”, greater and smaller than the rth sample. The algorithm is designed for any window siz...

Time-over-threshold measurements of the output of a first order integration amplifier can be used as a cheap way to estimate the charge deposited on a wire in an MWPC. Even if the time scale of the first order system is seemingly much larger than the signal development time, we noticed experimentally a significant deviation from the relationship of time-over-threshold and the charge, as would b...

The discrete-time system of multilayer composite plate is modeled using neural network (NN) to produce a nonlinear exogenous autoregressive moving-average model (NARMAX). The model is implemented by training a NN with input-output experimental data. Each damaged sample can be modeled by a parameter governed by the propagation behaviors of the NN. A residual signal is evaluated from the differen...

In this paper we consider the problem of worst-case simulation for a discrete-time system with structured uncertainty. The approach is based on the recursive computation of ellipsoids of conndence for the system state, based on semideenite programming.