An expert system to classify microarray gene expression data using gene selection by decision tree

Gene selection can help the analysis of microarray gene expression data. However, it is very difficult to obtain a satisfactory classification result by machine learning techniques because of both the curse-of-dimensionality problem and the over-fitting problem. That is, the dimensions of the features are too large but the samples are too few. In this study, we designed an approach that attempts to avoid these two problems and then used it to select a small set of significant biomarker genes for diagnosis. Finally, we attempted to use these markers for the classification of cancer. This approach was tested the approach on a number of microarray datasets in order to demonstrate that it performs well and is both useful and reliable.     

Automated thermal fuse inspection using machine vision and artificial neural networks

Machine vision is an excellent tool for inspecting a variety of items such as textiles, fruit, printed circuit boards, electrical components, labels, integrated circuits, machine tools, etc. This paper presents an intelligent system that incorporates machine vision with artificial intelligent networks to automatically inspect thermal fuses. An effective inspection flow is proposed to detect four commonly seen defects, including black-dot, small-head, bur, and flake during the production of thermal fuses. Backpropagation neural networks and learning vector quantization performance is compared in detecting the bur defect because of its illegibility. Different numbers of defective samples were screened out from a production line in a case study company and used to demonstrate the efficacy of the proposed system. Currently, the proposed inspection system is operating at the case study company, replacing four to six human inspectors. The system not only ensures the quality of the thermal fuses produced, but also reduced the cost of manual visual inspection.     

A simple algorithm for checking compatibility among discrete conditional distributions

A distribution is said to be conditionally specified when only its conditional distributions are known or available. The very first issue is always compatibility: does there exist a joint distribution capable of reproducing all of the conditional distributions? We review five methods-mostly for two or three variables-published since 2002, and we conclude that these methods are either mathematically too involved and/or are too difficult (and in many cases impossible) to generalize to a high dimension. The purpose of this paper is to propose a general algorithm that can efficiently verify compatibility in a straightforward fashion. Our method is intuitively simple and general enough to deal with any full-conditional specifications. Furthermore, we illustrate the phenomenon that two theoretically equivalent conditional models can be different in terms of compatibilities, or can result in different joint distributions. The implications of this phenomenon are also discussed.     

Feature extraction in carpal-bone analysis

Hand-bone analysis with image processing techniques using a digital radiograph can be used to assess skeletal age. The analysis consists of two steps: phalangeal and carpal bone analysis. The carpal bone analysis is discussed. First, the carpal bone region of interest (CROI) is defined using a standard thresholding technique to separate the hand from the background. Then, a dynamic thresholding method with variable window sizes is used to differentiate between the bones and the soft tissue. Next, the radius, ulna, and metacarpals intersecting the borders of the CROI are removed by using mathematical morphology. Finally, all objects included in the corrected CROI are separated and described in terms of features. These features describe the size, shape, and location and include some gray-scale pixel value information. On the basis of this analysis, the separation of the noncarpal bone objects from the carpal bone is possible. The feature selection step removes features of low discriminant power and reduces the space dimension. The remaining carpal bone parameters are used for further analysis leading to skeletal age assessment.     

Application of cuprous oxide synthesized from copper-containing waste liquid to treat aqueous reactive dye

Cuprous oxide that was prepared from Cu-containing waste liquid from a printed circuit board manufacturer was used to carry out Fenton-like and photo-Fenton-like oxidation reactions to decolorize a reactive dye (RB19). A microwave hydrothermal method was applied in the synthesis. The highest recovery rate of Cu from wastewater was 87% and was obtained when the synthesis was performed at a power of 200 W for 15 min. An RB19 decolorization efficiency of 99.9% was achieved when the Fenton-like reaction was conducted with 50 mmol/L H(2)O(2) and 0.9 g/L of Cu(2)O. The decolorization of RB19 was more effective when the system was irradiated with visible light than with UV light. Under irradiation, the decolorization rate was the highest when the decolorization was performed in the RB19 solution that contained 50 mmol/L H(2)O(2) and 0.9 g/L CuO(2) in the Fenton-like and the 365 nm-irradiated photo-Fenton-like reactions. In the case of irradiation under 410 nm visible light, the system was operated with lower H(2)O(2) (30 mmol/L) and Cu(2)O (0.5 g/L) to achieve a decolorization rate higher than 365 nm-irradiated photo-Fenton-like reactions.     

Is cheating a human function? The roles of presence,state hostility,and enjoyment in an unfair video game

In sports and board games, when an opponent cheats, the other players typically greet it with disdain, anger, and disengagement. However, work has yet to fully address the role of the computer cheating in video games. In this study, participants played either a cheating or a non-cheating version of a modified open-source tower-defense game. Results indicate that when a computer competitor cheats, players perceive the opponent as being more human. Cheating also increases player aggravation and presence, but does not affect enjoyment of the experience. Additionally, players that firmly believed that their opponent was controlled by the computer exhibited significantly less state hostility compared to players that were less certain of the nature of their competitor. Game designers can integrate subtle levels of cheating into computer opponents without any real negative responses from the players. The results indicate that minor levels of cheating might also increase player engagement with video games.     

Modeling and Simulation of Variable-Reluctance Step Motors with Application to a High-Performance Printer System

Basic information on modeling and digital computer simulation of variable-reluctance (VR) step motors is provided. The nonlinear equations of the system are derived, and a method for implementing them on a digital computer is presented. As an example, a typical printer with a step motor is designed with this approach. The problem is defined by giving the desired system performance criteria and the step motor parameters and characteristics. The specification of the control schemes determined the design. Computer simulation runs are made to determine the optimal control parameters of the system. The case study demonstrates the advantages of the computer-aided design, before the physical construction of the experimental system.     

Organoclay effect on transverse compressive strength of glass/epoxy nanocomposites

This research focuses on the fabrication of glass fiber/epoxy nanocomposites containing organoclay as well as understanding the organoclay effect on the transverse compressive strength of nanocomposites. To demonstrate the organoclay effect, three different loadings of organoclay were dispersed, respectively, in the epoxy resin using a mechanical mixer followed by sonication. The corresponding glass/epoxy nanocomposites were produced by impregnating dry glass fiber with organoclay epoxy compound through a vacuum hand lay-up procedure. Unidirectional block specimens were employed for transverse compression tests on a hydraulic MTS machine. Experimental observations indicate that glass/epoxy nanocomposites containing organoclay exhibit higher transverse compressive strength than conventional composites. Furthermore, the failure mechanisms for all tested specimens were found to be fiber and matrix debonding. Therefore, results indicate that the increasing characteristic in transverse failure stress may be ascribed to the enhanced fiber/matrix adhesion modified by the organoclay.     

Detection and classification of defect patterns on semiconductor wafers

The detection of process problems and parameter drift at an early stage is crucial to successful semiconductor manufacture. The defect patterns on the wafer can act as an important source of information for quality engineers allowing them to isolate production problems. Traditionally, defect recognition is performed by quality engineers using a scanning electron microscope. This manual approach is not only expensive and time consuming but also it leads to high misidentification levels. In this paper, an automatic approach consisting of a spatial filter, a classification module and an estimation module is proposed to validate both real and simulated data. Experimental results show that three types of typical defect patterns: (i) a linear scratch; (ii) a circular ring; and (iii) an elliptical zone can be successfully extracted and classified. A Gaussian EM algorithm is used to estimate the elliptic and linear patterns, and a spherical-shell algorithm is used to estimate ring patterns. Furthermore, both convex and nonconvex defect patterns can be simultaneously recognized via a hybrid clustering method. The proposed method has the potential to be applied to other industries.