Feature Reduction via Generalized Uncorrelated Linear Discriminant Analysis

High-dimensional data appear in many applications of data mining, machine learning, and bioinformatics. Feature reduction is commonly applied as a preprocessing step to overcome the curse of dimensionality. Uncorrelated Linear Discriminant Analysis (ULDA) was recently proposed for feature reduction. The extracted features via ULDA were shown to be statistically uncorrelated, which is desirable for many applications. In this paper, an algorithm called ULDA/QR is proposed to simplify the previous implementation of ULDA. Then, the ULDA/GSVD algorithm is proposed, based on a novel optimization criterion, to address the singularity problem which occurs in undersampled problems, where the data dimension is larger than the sample size. The criterion used is the regularized version of the one in ULDA/QR. Surprisingly, our theoretical result shows that the solution to ULDA/GSVD is independent of the value of the regularization parameter. Experimental results on various types of data sets are reported to show the effectiveness of the proposed algorithm and to compare it with other commonly used feature reduction algorithms.     

Obtaining high defect coverage for frequency-dependent defects in complex ASICs

Structured delay tests have been around for years, but how effectively do they identify defective silicon, even at reduced frequency? How much overkill is associated with their use? The authors present data from industrial circuits aimed at these and other aspects of speed testing.     

Transmission line analysis of nonlinear slot coupled microstrip antenna

The transmission line method is used for the analysis of microstrip antennas fed by several nonlinear slots with 'H' shapes or new geometries. This analysis allows the input impedance of nonlinear slot coupled microstrip antennas to be calculated for the four different structures.<>     

Drying of Chestnuts (Castanea sativa Mill.) after Osmotic Dehydration with Sucrose and Glucose Solutions

Chestnuts were dehydrated by using a combined method of osmotic dehydration followed by air drying. Samples were osmotically pretreated with sucrose (60% w/w) and glucose (56% w/w) for 8 h, air-dried at temperatures of 45, 55, and 65°C, at a relative humidity of 30% and at a velocity of 2.7 m·s^-1 and the experimental data of the drying kinetics were obtained. Whole samples were dried with different peelings: (a) removal of endocarp and pericarp (peeled) and (b) additionally the internal rough surface (cut). In all cases, cut chestnuts show greater drying rates than peeled samples, indicating that a significant mass transfer resistance in the layer nearest to the surface takes place. Peeled samples pretreated with sucrose solutions behave in a similar way to untreated samples. For the rest of the samples, the cut samples osmotically treated with sucrose solutions and all the samples treated with the glucose solution, the drying rates decrease during drying. Drying kinetics are successfully modeled by employing a diffusional model that takes the shrinkage into account. The effective coefficient of water diffusion was evaluated and correlated with temperature. The quality of the final product was monitored by color change. In spite of the fact that the total color difference is not modified by the osmotic treatment, the L*, a*, and b* color coordinates of cut samples treated with sucrose and glucose solutions do undergo changes; the L* and a* coordinates change less than the b*.     

CAL delivery selection criteria and authoring systems

Abstract  In the past, authoring systems have been used to generate computer-assisted learning materials that have often followed the rather restrictive programmed learning format. A number of innovative ways of using recently developed systems to develop CAL packages that include a wider range of learning activities (access to data bases, simulations, interactive video, etc.) are described. Analogous to the concept of a media selection model, a computer delivery mode selection model is presented as an aid to decision making for designers. This increase in flexibility should broaden the applicability of computerassisted learning (CAL) to a wider range of educational objectives and raise the level of the cognitive emphasis in learning packages, as well as facilitate the implementation of visually appealing materials. The paper also implies a standard of acceptability for authoring systems.     

A strain hardening failure assessment diagram derived from carbon-manganese steel compact tension specimens

A failure assessment diagram is derived from carbon-manganese steel compact tension specimens. The diagram has been determined from an elastic-plastic finite element analysis of a compact tension specimen geometry. The diagram has been validated by using experimental fracture toughness data obtained on the same steel and specimen geometry modelled in the finite element analysis. The plastic collapse load has been determined empirically for this geometry.It is shown that a non-work-hardening failure assessment diagram is not a good representation of the experimental data and that the computed failure assessment diagram is more appropriate for describing the behaviour of the carbon-manganese steel specimens.