Face recognition using a fuzzy fisherface classifier

In this study, we are concerned with face recognition using fuzzy fisherface approach and its fuzzy set based augmentation. The well-known fisherface method is relatively insensitive to substantial variations in light direction, face pose, and facial expression. This is accomplished by using both principal component analysis and Fisher's linear discriminant analysis. What makes most of the methods of face recognition (including the fisherface approach) similar is an assumption about the same level of typicality (relevance) of each face to the corresponding class (category). We propose to incorporate a gradual level of assignment to class being regarded as a membership grade with anticipation that such discrimination helps improve classification results. More specifically, when operating on feature vectors resulting from the PCA transformation we complete a Fuzzy K-nearest neighbor class assignment that produces the corresponding degrees of class membership. The comprehensive experiments completed on ORL, Yale, and CNU (Chungbuk National University) face databases show improved classification rates and reduced sensitivity to variations between face images caused by changes in illumination and viewing directions. The performance is compared vis-à-vis other commonly used methods, such as eigenface and fisherface.     

Cholesterol removal from homogenized milk with beta-cyclodextrin

This study was carried out to determine optimum conditions of five different factors (beta-cyclodextrin concentration, mixing temperature, mixing time, centrifugal force, and centrifugation time) in reduction of cholesterol in 3.6% fat, homogenized milk by application of beta-cyclodextrin. beta-Cyclodextrin at 0.5 to 1.5% provided 92.2 to 95.3% removal of cholesterol when mixed at 10 degrees C for 10 min. Among other factors, mixing time (5 to 20 min) did not significantly affect cholesterol removal. Removal was enhanced with increasing centrifugal forces up to 166x g (95.9%) but decreased thereafter. Various centrifugation times (5 to 20 min) did not have significant effects. Based on these results, we suggest that the optimum conditions for the process are addition of 1.5% beta-cyclodextrin, mixing temperature of 10 degrees C, 10-min mixing time, and centrifugation at 166x g for 10 min.     

Analytic and experimental method for making magnesium alloy products based on an injection moulding process

Magnesium alloys are very attractive materials for the machinery industry, where a lighter weight and a higher strength are needed. Due to the higher ratio of strength versus weight and stiffness versus weight, various magnesium alloys have been tried to make a light and strong product through an extrusion or a die-casting process. However, it was very difficult to achieve these objectives with conventional processes. So, a new process was considered. An injection moulding technology is rising as an alternative solution. In this study, a computer simulation and experiments based upon the injection moulding process were conducted for the AZ91D magnesium alloy. Filling time and melt front temperature were obtained by the simulation. From the injection moulding experimentation, a successful product was made and the product test was conducted.     

A Simulated transportation problem for improved operational planning: An application in the trucking industry

This paper demonstrates the use of a simulated transportation method as an approach to developing an instructional guide that is operationally flexible and feasible for planning truck rental needs in a way to minimize costs. The informational impact of this approach aids not only the internal operations, but also external relations with truck renting companies by providing a more accurate measure of the anticipated demand on rental equipment, thus allowing the rental companies an opportunity to meet this demand.The results of the research conducted indicate the simulated transportation method is a reliable and valid planning instrument for minimizing transportation cost and generating useful information for management decision making.     

Hierarchical community classification and assessment of aquatic ecosystems using artificial neural networks

Benthic macroinvertebrate communities in stream ecosystems were assessed hierarchically through two-level classification methods of unsupervised learning. Two artificial neural networks were implemented in combination. Firstly, the self-organizing map (SOM) was used to reduce the dimension of community data, and secondly, the adaptive resonance theory (ART) was subsequently applied to the SOM to further classify the groups in different scales. Hierarchical grouping in community data efficiently reflected the impact of the environmental factors such as topographic conditions, levels of pollution, and sampling location and time across different scales. New community data not included in the training process were used to test the trained network model. The input data were appropriately grouped at different hierarchical levels by the trained networks, and correspondingly revealed the impact of environmental disturbances and temporal dynamics of communities. The hierarchical clusters based on a two-level classification method could be useful for assessing ecosystem quality and community variations caused by environmental disturbances.     

Effect of reaction pH on the photodegradation of model melanoidins

The effect was studied of the pH of the amino-carbonyl reaction on the photodegradation of model melanoidins. Nondialyzable model melanoidins were prepared from glucose and lysine with or without initial pH control to 7.0.: 2 mol/l phosphate buffer (buffer-melanoidin) and pH adjustment at the reaction start with NaHCO₃ (NaHCO₃-melanoidin). Melanoidin was also prepared from glucose and the lysine-Cu²⁺complex to investigate the difference of complexes between melanoidin and Cu²⁺ (Cu²⁺-melanoidin). Each melanoidin solution was irradiated with a Xe or tungsten-halogen lamp under dissolved oxygen or by the continuous supply of oxygen in a Cu²⁺/O₂ or ascorbic acid/Cu²⁺/O₂ system. The effects of the concentrations of Cu²⁺ and melanoidin, reaction pH value, and metal ion species on the decolorization rate in the Cu²⁺/O₂ system were investigated. The most effective factor for decolorization was found to be the melanoidin concentration. The decolorization rate was negligible when 14 g/l of Cu²⁺-melanoidin was photodegraded in the ascorbic acid/Cu²⁺/O₂ system under dissolved oxygen, although depolymerization was observed. Photodegradation of NaHCO₃-melanoidins in the Cu²⁺/O₂ system by the continuous supply of oxygen resulted in an increased decolorization rate, decreased molecular mass, production of low-molecular-weight compounds, release of free lysine, and pI change. The buffer- and Cu²⁺-melanoidins did not show changes in chemical characteristics similar to those of the NaHCO₃-melanoidin.     

Robust optimization using a gradient index: MEMS applications

This paper discusses a simple and effective robust optimization formulation and illustrates its application to MicroElectroMechanical Systems (MEMS) devices. The proposed formulation improves robustness of the objective function by minimizing a gradient index (GI), defined as a function of gradients of performance functions with respect to uncertain variables. The level of constraint feasibility is also enhanced by adding a term determined by a constraint value and the gradient index. In the robust optimal design procedure, a deterministic optimization for performance improvement is followed by a sensitivity analysis with respect to uncertainties such as MEMS fabrication errors and changes of material properties. During the process of the deterministic optimization and sensitivity analysis, dominant performances and critical uncertain variables are identified to define the GI. Our approach for robust design requires no statistical information on the uncertainties and yet achieves robustness effectively. Two MEMS application examples including a micro accelerometer and a resonant-type micro probe are presented.     

Functional properties of cholesterol-removed whipping cream treated by beta-cyclodextrin

The present study was carried out to examine the changes in functional properties of cholesterol-removed whipping cream by beta-cyclodextrin (beta-CD) treatment. The cholesterol removal rate reached over 90% in cream before whipping in all conditions (different stirring time and speed) applied. The apparent viscosity of beta-CD treated cream after whipping increased with increased stirring time and speed. Comparatively, the overrun percentage reached to 150%, and foam instability was measured as 2.5 ml deformed cream with lower stirring time (10 min) and speed (400 rpm). The thiobarbituric acid value of cholesterol-removed whipping cream increased from 0.08 to 0.14 stored at 4 degrees C during 4 wk; however, no difference was found compared with that of control. Above results indicated that beta-CD treatment process for cholesterol removal did not show a profound adverse effect on functional properties of cream after whipping.     

A finite element prediction of ferroelectric switching behavior using a regular dodecahedron RVE

Some piezoelectric ceramic materials do behave in a nonlinear way when they are subjected to large electric or mechanical stress fields. This macroscopic nonlinearity comes from microscopic domain switchings during which one type of variant switches to other types of variants under large electromechanical fields. This switchable piezoelectric ceramic materials are called ferroelectric ceramics. In the present paper, a typical ferroelectric material particle is represented by a regular dodecahedron representative volume element (RVE) which includes twenty distinct types of variants, and a finite element analysis is carried out on a cubic specimen subjected to both a constant compressive stress and an electric field cycling. The calculation results are compared with experimental observations and isotropy of the responses is discussed.The authors gratefully acknowledge the support of the Agency for Defense Development through Grant ADD 01-05-01.