This paper presents generation of a compact thermal model of a Ball Grid Array (BGA) based on experimental test results obtained from infrared (IR) camera system. The model is optimized so that the steady state and transient thermal behaviors of the package may be predicted with required accuracy. The optimization algorithm is based on Gauss-Newton and Levenberg-Marquardt methods which are well...

Drusens are indicators of macular degeneration, a disease characterized by accumulations of extra cellular materials under retina. The automatic study of the quantitative evolution of Drusen spots throughout a medical treatment constitutes a useful tool for ophthalmologists. Until now, drusen evaluation was done manually, based only on qualitative aspects. Also the analyses depended on the opht...

We propose a new family of Newton-type methods for the solution of constrained systems of equations. Under suitable conditions, that do not include differentiability or local uniqueness of solutions, local, quadratic convergence to a solution of the system can be established. We show that as particular instances of the method we obtain inexact versions of both a recently introduced LP-based New...

We present an iterative multiresolution algorithm for the translational and rotational alignment of digital images. An image is represented by an interpolating spline. Coarser versions of this continuous image model are obtained by using spline approximations at various scales (polynomial spline pyramid). We use a coarse-to-fine updating strategy to compute the alignment parameters iteratively,...

To actively maneuver a robotic capsule for interactive diagnosis in the gastrointestinal tract, visualizing accurate position and orientation of the capsule when it moves in the gastrointestinal tract is essential. A possible method that encloses the circuits, batteries, imaging device, etc into the capsule looped by an axially magnetized permanent-magnet ring is proposed. Based on expression o...

Traditional learning algorithms with gradient descent based technique, such as back-propagation (BP) and its variant Levenberg-Marquardt (LM) have been widely used in the training of multilayer feedforward neural networks. The gradient descent based algorithm may converge usually slower than required time in training, since many iterative learning step are needed by such learning algorithm, and...

Training neural networks to capture an intrinsic property of a large volume of high dimensional data is a difficult task, as the training process is computationally expensive. Input attributes should be carefully selected to keep the dimensionality of input vectors relatively small. Technical indexes commonly used for stock market prediction using neural networks are investigated to determine i...

This paper applied a new Kalman Filter Recurrent Neural Network (KFRNN) topology and a recursive Levenberg-Marquardt (L-M) learning algorithm capable to estimate parameters and states of highly nonlinear unknown plant in noisy environment. The proposed KFRNN identifier, learned by the Backpropagation and L-M learning algorithm, was incorporated in a direct and indirect adaptive neural control s...

We describe a generalized Levenberg-Marquardt method for computing critical points of the Ginzburg-Landau energy functional which models superconductivity. The algorithm is a blend of a Newton iteration with a Sobolev gradient descent method, and is equivalent to a trust-region method in which the trustregion radius is defined by a Sobolev metric. Numerical test results demonstrate the method t...