Fast and high performance image subsampling using feedforwardneural networks

We introduce a fast and high performance image subsampling method using feedforward artificial neural networks (FANNs). Our method employs a pattern matching technique to extract local edge information within the image, in order to select the FANN desired output values during the supervised training stage. Subjective and objective evaluations of experimental results using still images and video frames show that our method, while less computationally intensive, outperforms the standard lowpass filtering and subsampling method.     

Changes in the structure and properties of aluminum alloys solidified in an ultrasonic field

An ultrasonic field was applied to melted metal alloys during their solidification with the aim of obtaining their microstructure in a solid state characterized by small-sized grains. In this paper, the results of experimental research are presented, obtained under the application of an ultrasonic field of 100–350 W during the solidification of an ATC Si₁₀Cu₄ alloy cast in a mold.     

Feedforward neural network design with tridiagonal symmetryconstraints

This paper introduces a pruning algorithm with tridiagonal symmetry constraints for feedforward neural network (FANN) design. The algorithm uses a reflection transform applied to the input-hidden weight matrix in order to reduce it to its tridiagonal form. The designed FANN structures obtained by applying the proposed algorithm are compact and symmetrical. Therefore, they are well suited for efficient hardware and software implementations. Moreover, the number of the FANN parameters is reduced without a significant loss in performance. We illustrate the complexity and performance of the proposed algorithm by applying it as a solution to a nonlinear regression problem. We also compare the results of our proposed algorithm with those of the optimal brain damage algorithm     

Modification of mechanical characteristics of 10TiNiCr180 stainless steel tubes in the process of drawing under the action of ultrasonic vibrations

The paper presents the results of the experimental research concerning modification of mechanical characteristics of resistance and plasticity in the process of drawing of 10TiNiCr180 stainless steel tubes with and without ultrasonic vibrations. The experiments were performed in the framework of the CEEX project (Excelence Research Program, Ministry of Education, Research and Innovation of Romania), Contract no. 293/2006. Modification of mechanical characteristics of resistance and plasticity is analyzed for the tube samples processed using the classical technology (CT) or ultrasonic vibration drawing (UVD) depending on the relative drawing velocity $ (v_{dr} /\bar v_v ) $ (v_{dr} /\bar v_v ) .     

High-order image subsampling using feedforward artificial neuralnetworks

We propose a method for high-order image subsampling using feedforward artificial neural networks (FANNs). In our method, the high-order subsampling process is decomposed into a sequence of first-order subsampling stages. The first stage employs a tridiagonally symmetrical FANN, which is obtained by applying the design algorithm introduced by Dumitras and Kossentini (see IEEE Trans. Signal Processing, vol.48, p.1446-55, 2000). The second stage employs a small fully connected FANN. The algorithm used to train both FANNs employs information about local edges (extracted using pattern matching) to perform effective subsampling of both high detail and smooth image areas. We show that our multistage first-order subsampling method achieves excellent speed-performance tradeoffs, and it consistently outperforms traditional lowpass filtering and subsampling methods both subjectively and objectively.     

Experimental research on ultrasonic softening in cold-rolled steel strips

The possibility of obtaining the effect of ultrasonic softening through laboratory experiments in hardened cold-rolled steel strips has been shown. The rolling of metal strips using ultrasonic activation is promising for increasing the deformation degree in comparison with conventional rolling as well as for the growth of the rolling rate, which supposes greater productivities. The text was submitted by the authors in English.     

Determining the force and pressure at the extrusion of union nuts from cylindrical semiproducts

The paper aims to determine by experiment the total force and pressure of deformation as a function of the punch stroke and the deformation degree at the indirect extrusion of steel union nuts from cylindrical semiproducts. The text was submitted by the authors in English.