A semantic image classifier based on hierarchical fuzzy association rule mining

One of the major challenges in the content-based information retrieval and machine learning techniques is to-build-the-so-called “semantic classifier” which is able to effectively and efficiently classify semantic concepts in a large database. This paper dealt with semantic image classification based on hierarchical Fuzzy Association Rules (FARs) mining in the image database. Intuitively, an association rule is a unique and significant combination of image features and a semantic concept, which determines the degree of correlation between features and concept. The main idea behind this approach is that any image visual concept has some associated features, so that, there are strong correlations between the concepts and their corresponding features. Regardless of the semantic gap, an image concept appears when the corresponding features emerge in an image and vice versa. Specially, this paper’s contribution was to propose a novel Fuzzy Association Rule for improving traditional association rules. Moreover, it was concerned with establishing a hierarchical fuzzy rule base in the training phase and setup corresponding fuzzy inference engine in order to classify images in the testing phase. The presented approach was independent from image segmentation and can be applied on multi-label images. Experimental results on a database of 6000 general-purpose images demonstrated the superiority of the proposed algorithm.     

Fuzzy logistic regression based on the least squares approach with application in clinical studies

To model fuzzy binary observations, a new model named “Fuzzy Logistic Regression” is proposed and discussed in this study. In fact, due to the vague nature of binary observations, no probability distribution can be considered for these data. Therefore, the ordinary logistic regression may not be appropriate. This study attempts to construct a fuzzy model based on possibility of success. These possibilities are defined by some linguistic terms such as …, low, medium, high…. Then, by use of the Extension principle, the logarithm transformation of “possibilistic odds” is modeled based on a set of crisp explanatory variables observations. Also, to estimate parameters in the proposed model, the least squares method in fuzzy linear regression is used. For evaluating the model, a criterion named the “capability index” is calculated. At the end, because of widespread applications of logistic regression in clinical studies and also, the abundance of vague observations in clinical diagnosis, the suspected cases to Systematic Lupus Erythematosus (SLE) disease is modeled based on some significant risk factors to detect the application of the model. The results showed that the proposed model could be a rational substituted model of an ordinary one in modeling the clinical vague status.     

Colour and ergonomics: On the selection of a “colour of the year”

The key role of colour in ergonomics has been emphasized by a number of researchers and design professionals. Although several research studies have been published regarding the use of colour in ergonomics, there are still some areas that need to be considered. The issue of deciding a “colour of the year” is an example, which represents a new challenge for researchers in the field of ergonomics. This is of particular interest considering the fact that the nature of research on the selection of a “colour of the year” is generally based on user experience. This paper argues that ergonomics should play a more prominent role in this field to ensure better user experience and performance. This paper highlights specific areas that need further study and development.     

Synthesis and characterization of poly(ethylene tetrasulfide)/graphene oxide nanocomposites by in situ polymerization method

Poly(ethylene tetrasulfide) (PSP) is synthesized via interfacial polycondensation of 1,2 dichloroethane and sodium tetrasulfide, in the presence of graphene oxide (GO). This process resulted in homogeneously dispersed PSP/GO nanocomposites. Nanocomposites of 0.3 and 0.5?wt% of GO are synthesized and their morphology, chemical characteristics behavior are studied employing field emission scanning electron microscopy, Fourier transform infrared spectroscopy and X-ray diffraction techniques. Thermal characterization of composites is performed by differential scanning calorimetry and thermogravimetry analysis. Results indicate that the addition of only small amounts (0.5?wt%) of well-dispersed GO can increase the melting point more than 16°C resulting in better thermal properties for the composite. The solubility of nanocomposite is also studied and results show that the solubility depends on solvent concentration in addition to reinforcement (GO) deals.     

Effect of nano-sized calcium carbonate on cure kinetics and properties of polyester/epoxy blend powder coatings

Today's strict environmental laws pose significant challenges for coating's formulators to look for eco-friendly products. Powder coatings, particularly polyester/epoxy blends have demonstrated their ability as alternatives to traditional solvent-borne coatings. Recently, the use of nanoparticles such as nano-CaCO₃ (nCaCO₃) has been suggested as a beneficial strategy towards powder coating application with improved properties. Here, we study the effect of nCaCO₃ on morphology, cure behavior, adhesion and hardness of polyester/epoxy systems. The nanoparticles shape, size and dispersion state were investigated through X-ray diffraction (XRD), transmission electron microscopy (TEM) and scanning electron microscopy (SEM) methods. Furthermore, isothermal cure characterization of the neat and filled systems was performed using a torque rheometer. The most important finding based on the rheological studies was the catalytic effect of nCaCO₃ on cure reaction of polyester/epoxy, leading to the shorter curing time. Moreover, the kinetic analyses of rheograms revealed a marked decrease in the activation energy of the cure process upon raising nCaCO₃ content. Interestingly, pull-off adhesion and hardness tests showed that the hardness and adhesion strength were dramatically increased by the addition of nCaCO₃ into the polyester/epoxy system compared to pure blend resin. Therefore, considering the strong competition in powder coating market, the use of nCaCO₃ as a commercial and inexpensive nanofiller is necessary not only to reduce the dwell time which has benefits in terms of the energy consumption and economics, but also to improve the performance of final polyester/epoxy coating.     

The effect of MWNTs concentration and nanofiber orientation on mechanical properties of PAA nanocomposite nanofibrous web

In this research, nanocomposite nanofibrous webs of poly(acrylic acid) (PAA)/multi‐walled carbon nanotubes (MWNTs) were obtained via electrospinning. The effect of MWNTs concentration on the morphology and mechanical properties of PAA/MWNTs nanofibers was investigated by changing the MWNTs content from 0 to 5 wt%. The results showed that average diameter of nanofibers increased with increasing the MWNTs concentration and presence of MWNTs led to the enhancement of mechanical properties. Also, the results revealed that the strength, modulus, and elongation at break of samples increased 3.22, 2.70, and 4.27 fold, respectively, after adding 3 wt% of MWNTs. In addition, the effect of rotating speed of collector on the orientation of PAA nanofibers and its effect on mechanical properties was investigated. Scanning electron microscopy (SEM) studies demonstrated that the degree of nanofibers orientation increased with the augmentation of drum speed to 25 rps. Moreover, the average nanofibers diameter decreased with the increase of drum speed. Improvement of nanofiber orientation resulted in superior mechanical properties that is, higher strength and modulus of aligned nanofiber layers were obtained in comparison to nonaligned layers (12.6 and 26.6 fold, respectively). POLYM. COMPOS., 37:3149–3159, 2016. © 2015 Society of Plastics Engineers     

Using Taguchi method to determine optimum process conditions for flue gas desulfurization through an amine scrubber

This study was done to determine the optimum process conditions for absorption of sulfur dioxide in a mixture of flue gases. Using a selective amine-based absorber; a high amount of SO₂ was absorbed in the scrubbing process. The process was designed to reduce the amount of sulfur dioxide. The pilot plant was designed and set up in the Research Center of Petroleum University of Technology, containing absorption and desorption stages. This paper reports an investigation of the effect and optimization of parameters that improve the efficiency of the whole process. The experiments were conducted under varying levels of desorption temperature, pH of the absorber solution, concentration of SO₂ inlet gas, and flow rate of the absorbing solution. Using Taguchi experimental design method, the optimum conditions were identified for the absorption process. An efficiency of more than 99 % could be obtained by varying the parameters in which all the released SO₂ gas was absorbed from the inlet flue gas; an achievement that is much favorable for industrial purposes.     

Study of macromolecular interactions in low‐fat brined cheese modified with Zedu gum

The functionality of Zedu gum as a fat mimetic in low‐fat brined cheese was studied. The physicochemical, textural, rheological, microstructural and sensory properties of cheese samples modified with 0.1% and 0.25% of Zedu gum were compared to those of control cheeses (low‐fat and full‐fat cheeses with no fat mimetic) during ripening. To obtain further information about the cheeses' structure and interactions between macromolecules (casein protein and Zedu gum), other parameters were analysed by differential scanning calorimetry and Fourier transform infrared (FTIR) spectroscopy. Incorporation of Zedu gum into low‐fat cheese caused an open microstructure and softer texture in comparison with the control low‐fat cheese. The thermal properties and FTIR spectra of the cheeses were influenced by both fat mimetic and ripening time. On days 1 and 60 of ripening time, the lower value of enthalpy of the low‐fat cheese with 0.25 g of Zedu gum/kg of milk (AS 0.25) in comparison with control low‐fat cheese could have been due to the electrostatic nature of the interactions between Zedu gum and casein protein. On both days, the FTIR spectrum of AS 0.25 showed a well separated absorption at 1746 cm^?1 possibly due to the formation of ester groups as a result of the interaction of the carbonyl groups in Zedu gum with the hydroxyl groups of some amino acids in casein.