Characterization of fuzzy clustering algorithms in terms of entropy of probabilistic sets

We discuss a method of evaluating fuzzy clustering algorithms. Each of them generates a partition matrix of a data set with the entries lying in the [0, 1] interval and expressing the grade of belonging of the object to the clusters detected. Membership functions of the same cluster are interpreted as probabilistic sets in the sense of Hirota. This makes it possible to characterize the clusters by means of the entropy of the corresponding probabilistic sets. Moreover, the mutual entropy of pairs of probabilistic sets provides an index for evaluating the degree of interaction between clusters.     

An efficient accelerator for attribute reduction from incomplete data in rough set framework

Feature selection (attribute reduction) from large-scale incomplete data is a challenging problem in areas such as pattern recognition, machine learning and data mining. In rough set theory, feature selection from incomplete data aims to retain the discriminatory power of original features. To address this issue, many feature selection algorithms have been proposed, however, these algorithms are often computationally time-consuming. To overcome this shortcoming, we introduce in this paper a theoretic framework based on rough set theory, which is called positive approximation and can be used to accelerate a heuristic process for feature selection from incomplete data. As an application of the proposed accelerator, a general feature selection algorithm is designed. By integrating the accelerator into a heuristic algorithm, we obtain several modified representative heuristic feature selection algorithms in rough set theory. Experiments show that these modified algorithms outperform their original counterparts. It is worth noting that the performance of the modified algorithms becomes more visible when dealing with larger data sets.     

Assessment of the Influence of the Selected Range of Visible Light Radiation on the Durability of the Gel with Ascorbic Acid and Its Derivative

(1) Background: Depending on the type of hydrophilic polymer used, different types of hydrogels may be chemically stable or may degrade and eventually disintegrate, or dissolve upon exposure to sunlight. Many over-the-counter medications are now stored with a limited control of temperature, humidity and lighting. Therefore, in this study, the photostability of a gel made of cross-linked polyacrylic acid (PA), methylcellulose (MC) and aristoflex (AV) was assessed, and the interaction between the polymers used and ascorbic acid and its ethylated derivative was investigated. (2) Methods: The samples were continuously irradiated at constant temperature for six hours. The stability of the substance incorporated into the gels was assessed using a UV-Vis spectrophotometer. FTIR-ATR infrared spectroscopy was used to measure changes during the exposure. (3) Results: Ascorbic acid completely decomposed between the first and second hours of illumination in all samples. The exception is the preparation based on polyacrylic acid with glycerol, in which the decomposition of ascorbic acid slowed down significantly. After six hours of irradiation, the ethylated ascorbic acid derivative decomposed in about 5% for the polyacrylic acid-based gels and aristoflex, and in the methylcellulose gel it decomposed to about 2%. In the case of ascorbic acid, the most stable formulation was a gel based on polyacrylic acid and polyacrylic acid with glycerol, and in the case of the ethyl derivative, a gel based on methylcellulose. (4) Conclusions: The experiment showed significant differences in the decomposition rate of both compounds, resulting from their photostability and the polymer used in the hydrogel.     

SDF classifier revisited

This paper is addressing problems related to the construction of classifiers based on the Similarity Discriminant Function (SDF), in which the traditional vector representation of a pattern is replaced with matrix data. We introduce potential modifications of the matrix data structure and propose new variants of the SDF. The algorithms that we present were tested on images of handwritten digits and on photographs of human faces, taken from the ORL and CMU‐PIE databases. The results of experiments show that our modifications significantly improved the performance of the original SDF classifier.     

Thermal,hydrolytic, anticorrosive,and tribological properties of alkyd‐silicone hyperbranched resins with high solid content

Novel alkyd hyperbranched resins (AHBRs) modified with a Z‐6018 silicone (a polysiloxane intermediate) and with high solid content were synthesized by etherification reaction using an acid catalyst. Different molar ratios of AHBR to silicone were used. Structural, thermal, hydrolytic, anticorrosive, and tribological properties were studied using infrared (IR) analysis, nuclear magnetic resonance (NMR), vapor pressure osmometry (VPO), thermogravimetric analysis (TGA), acid value, electrochemical impedance spectroscopy (EIS), and pin‐on‐disk friction. IR and NMR provide evidence of grafting of the silicone on AHBR; the efficiency of grafting was quantified by TGA. Thermal stability was studied also by acid value analysis. Grafting increases the number average molecular mass, enhances thermal stability, and improves significantly hydrolytic stability. Corrosion resistance on steel is improved by two orders of magnitude, hence our modified materials can be used as highly effective anticorrosion coatings. Grafting lowers dynamic friction dramatically, more so at higher concentrations of silicone. © 2011 Wiley Periodicals, Inc. J Appl Polym Sci, 2012     

A Comparative Study of Mechanical Properties,Thermal Conductivity,Residual Stresses,and Wear Resistance of Aluminum-Alumina Composites Obtained by Squeeze Casting and Powder Metallurgy

Squeeze casting and powder metallurgy techniques were employed to fabricate AlSi12/Al₂O₃ composites, which are lightweight structural materials with potential applications in the automotive industry. The impact of the processing route on the material properties was studied. Comparative analyses were conducted for the Vickers hardness, flexural strength, fracture toughness, thermal conductivity, thermal residual stresses, and frictional wear. Our results show that the squeeze cast composite exhibits superior properties to those obtained using powder metallurgy.

     

Tribological properties of ethylene–propylene–diene rubber + polypropylene + thermal‐shock‐resistant ceramic composites

This work is part of a program on composites used in thermoelectric devices. Tribological properties of dynamic vulcanizate blends of polypropylene and ethylene‐propylene‐diene rubber filled with 5 wt% of microscale powder have been studied. The microscale thermal‐shock‐resistant ceramic filler contains α‐Al₂O₃, mullite (3Al₂O₃ · 2SiO₂ or 2Al₂O₃SiO₂), β‐spodumene glass‐ceramic and aluminium titanate. We found that our ceramic particles are abrasive; they cause strong abrasion of softer steel ball surfaces during dry sliding friction. To overcome the difficulty of particle dispersion and adhesion, the filler was modified through grafting using three types of organic molecules. Dry sliding friction was measured using four types of counter‐surfaces: tungsten carbide, Si₃N₂, 302 steel and 440 steel. Thermoplastic vulcanizate filled with neat ceramic powder shows the lowest friction compared to composites containing the same but surface‐treated powder. We introduce a ‘bump’ model to explain the tribological responses of our composites. ‘Naked’ or untreated ceramic particles protrude from the polymer surface and cause a decrease of the contact area compared to neat polymer. The ball partner surface has only a small contact area with the bumps. As contact surface area decreases, so does friction and the amount of heat generated during sliding friction testing. Chemical coupling of the ceramic to the matrix smoothens the bumps and increases the contact surface, giving a parallel increase in friction. Copyright © 2012 Society of Chemical Industry