Using learning automata in brain emotional learning for speech emotion recognition

We propose an improved version of brain emotional learning (BEL) model trained via learning automata (LA) for speech emotion recognition. Inspiring from the limbic system in mammalian brain, the original BEL model is composed of two neural network components, namely amygdala and orbitofrontal cortex. In this modified BEL model, named brain emotional learning based on learning automata (BELBLA), we have employed the theory of the stochastic LA in error back-propagation to train the BEL model in decreasing the high computational complexity of the traditional gradient method. Hence, the performance of the model can be enhanced. For a speech emotion recognition task, we extract the usual features, such as energy, pitch, formants, amplitude, zero crossing rate and MFCC, from average short-term signals of the emotional Berlin dataset. The experimental results show that the BELBLA outperforms some opponents, like hidden Markov model, Gaussian mixture model, k-nearest neighbor, support vector machines and artificial neural networks, for this application.     

Effect of Tio2 Nanoparticles on the Antibacterial and Physical Properties of Low-Density Polyethylene Film

In this study, TiO₂ nanoparticles were incorporated into low-density polyethylene by melt blending. Morphological properties and dispersion behavior of TiO₂ nanocomposite were characterized through field emission scanning electron microscope, X-ray diffraction, and Fourier transform infrared spectroscopy. Thermal stability of the nanocomposites was determined by thermogravimetric analysis. Moreover, the mechanical properties of nanocomposites were determined. Antimicrobial activity of TiO₂ nanocomposites was investigated by in vitro test. Dispersion of the nanoparticles was good in nanocomposites_. According to thermogravimetric analysis, incorporation of TiO₂ nanoparticles into low-density polyethylene enhanced the thermal stability. Mechanical properties of nanocomposites were improved by TiO₂ nanoparticles. Results showed that the antibacterial effect of low-density polyethylene –TiO₂ nanocomposite was significantly enhanced by TiO₂nanoparticles (p?2 nanoparticles not only can improve the properties of low-density polyethylene but they also have the potential to be used as an active food packaging film.     

An efficient fully bio‐based reactive diluent for epoxy thermosets: 2‐[(Oxiran‐2‐ylmethoxy) methyl] furan versus a petroleum‐based counterpart

Furfuryl alcohol and bio‐based epichlorohydrin were used to prepare a fully bio‐based reactive diluent, 2‐[(oxiran‐2‐ylmethoxy) methyl] furan (FOM). After spectral characterization, FOM was blended with epoxy resin, diglycidylether bisphenol A (DGEBA), at different ratios for reducing the viscosity. For a comparison, Cardura (one of the most common commercial reactive diluents), was separately incorporated to DGEBA. Amine‐curing process of the blends was recorded by FTIR and DSC. Similar trends of curing progression for DGEBA containing the reactive diluents were observed. Thermogravimetric analysis and dynamic mechanical thermal analysis, mechanical (hardness, adhesion, and stress–strain) and morphological properties were also investigated to study characteristics of the epoxy matrices formulated with FOM or Cardura. It was concluded that FOM could be considered as an efficient reactive diluent in formulations of polymer composites, structural adhesives and surface coatings based on epoxy resins. © 2017 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2017 , 134, 44957.     

CBDL: Context‐based distance learning for categorical attributes

Distance learning is an important notion and has played a critical role in success of various machine learning algorithms. Any learning algorithm that requires dissimilarity/similarity measures has to assume some forms of distance functions, either explicitly or implicitly. Hence, in recent years a considerable amount of research has been devoted to distance learning. Despite great achievements in this field, a number of important issues need to be further explored for real world datasets mainly containing categorical attributes. Based on these considerations, the current research presents a Context‐Based Distance Learning approach (CBDL) to advance the state of the art existing researches on distance metric learning for categorical datasets. CBDL is designed and developed based on the idea that distance between two values of a given categorical attribute can be estimated by using information inherently exists within subset of attributes called context. CBDL composes of two main components: context extraction component and distance learning component. Context extraction component is responsible for extracting the relevant subset of feature set for a given attribute, while distance learning component tries to learn distance between each pair of values based on the extracted context. To have a comprehensive analysis, we conduct wide range of experiments in both supervised and unsupervised environments in the presence of noise. Our experimental results reveal that CBDL is the method of choice distance learning approach by offering a comparable or better performance compared to the state of the art existing distance learning schemes according to studied evaluation measures. © 2011 Wiley Periodicals, Inc.     

Dynamically loaded bearings operating with non-Newtonian lubricant films

The behaviour of a laminar non-Newtonian film (power law) was studied for dynamically loaded bearings. The momentum equation for an infinitely long bearing is solved by assuming that the velocity profile is a superposition of couette and Poiseuille flow for power law fluids. An expression for the modified Reynolds equation is obtained for the non-Newtonian fluid film. The load- carrying capacity is obtained for various values of the viscometric exponent of the power law model. It is shown that non-Newtonian lubricants can have a pronounced effect on dynamically loaded bearings.     

Copper Extraction Kinetics by Beta-Diketone Derivatives (Acylpyrazolones and Acylisoxazolones) in Water/Chloroform Biphasic System

Abstract

Copper(II) extraction and back-extraction rates were determined in a water/chloroform system using a bell-shaped transport cell. Various 1-phenyl-3-methyl-4-acyl-pyrazol-5-ones (with acyl = benzoyl, 2-thenoyl, octadecanoyl, p-tert-butylbenzoyl, 3-phenyl-propanoyl, and iso-nonanoyl) and 3-phenyl-4-acylisoxazol-5-ones (with acyl = benzoyl and p-tert-butylbenzoyl) were considered. The back-extraction rate is shown to be limited by the diffusion of the complex in the organic unstirred layer, whatever the stirring speed and whatever the ligand considered. At low stirring speed, the extraction rate appears to be limited by the diffusion of either a complex or a ligand species in the unstirred layers, depending on the pH. At high stirring speed, the extraction rate is limited by the interfacial complexation. The extraction rate dependence on side-group variation cannot be correlated with hydrophobicity or acidity of the extractants and may be explained by structural differences of the CO vicinal group of the acyl.     

In vivo study of anti‐epidermal growth factor receptor antibody‐based iron oxide nanoparticles (anti‐EGFR‐SPIONs) as a novel MR imaging contrast agent for lung cancer (LLC1) cells detection

Superparamagnetic iron oxide nanoparticles (SPIONs) conjugated with anti‐epidermal growth factor receptor monoclonal antibody (anti‐EGFR‐SPIONs) were characterised, and its cytotoxicity effects, ex vivo and in vivo studies on Lewis lung carcinoma (LLC1) cells in C57BL/6 mice were investigated. The broadband at 679.96 cm⁻¹ relates to Fe–O, which verified the formation of the anti‐EGFR‐Mab with SPIONs was obtained by the FTIR. The TEM images showed spherical shape 20 and 80 nm‐sized for nanoparticles and the anti‐EGFR‐SPIONs, respectively. Results of cell viability at 24 h after incubation with different concentrations of nanoprobe showed it has only a 20% reduction in cell viabilities. The synthesised nanoprobe administered by systemic injection into C57BL/6 mice showed good Fe tumour uptake and satisfied image signal intensity under ex vivo and in vivo conditions. A higher concentration of nanoprobe was achieved compared to non‐specific and control, indicating selective delivery of nanoprobe to the tumour. It is concluded that the anti‐EGFR‐SPIONs was found to be as an MR imaging contrast nanoagent for lung cancer (LLC1) cells detection.Inspec keywords: toxicology, biomedical MRI, lung, magnetic particles, biomedical materials, nanofabrication, nanomagnetics, transmission electron microscopy, nanomedicine, superparamagnetism, nanoparticles, iron compounds, proteins, cellular biophysics, molecular biophysics, cancer, tumours, Fourier transform infrared spectraOther keywords: MR imaging contrast agent, LLC1, superparamagnetic iron oxide nanoparticles, Lewis lung carcinoma cells, ex vivo conditions, cell viability, antiepidermal growth factor receptor antibody‐based iron oxide nanoparticles, antiEGFR‐SPION, lung cancer cell detection, antiepidermal growth factor receptor monoclonal antibody, cytotoxicity effects, C57BL‐6 mice, antiEGFR‐Mab, FTIR spectra, TEM, spherical shape, incubation, nanoprobe concentrations, systemic injection, Fe tumour uptake, image signal intensity, in vivo conditions, time 24.0 hour, Fe₃ O₄      

Facile microwave‐assisted synthesis of NiO nanoparticles and its effect on soybean (Glycine max)

NiO nanoparticles in high purity, 15 ± 0.5 nm in size, were prepared via solid‐state microwave irradiation. The [Ni(NH₃)₆](NO₃)₂ complex as a novel source was decomposed in the presence of microwave irradiation for a short time (10 min). The present method is facile, safe, and low‐cost. This method exhibits other advantages; there is no need of a solvent, fuel, surfactant, expensive material, or complex instrument. Synthesised NiO nanoparticles were determined by various analyses. Also, for the first time, NiO nanoparticle effects on biochemical factors in soybean were investigated. Seeds of soybean were grown in the Murashige and Skoog agar medium containing different concentrations of NiO nanoparticles (0, 200, and 400 mg/L) for 21 days under growth chamber conditions. Estimates of malondialdehyde, hydrogen peroxide contents, and antioxidant enzymes (catalase and ascorbate peroxidase) under treatment of NiO nanoparticles were assayed. The result showed that by significantly increasing the concentration of NiO nanoparticles, the activity of catalase and ascorbate peroxidase enzymes was enhanced. Malondialdehyde and hydrogen peroxide contents significantly increased in the presence of NiO nanoparticles. In this study, the increasing activity of catalase and ascorbate peroxidase was not enough for radical oxygen species detoxification.Inspec keywords: nickel compounds, molecular biophysics, biotechnology, microorganisms, nanoparticles, biochemistry, microwave materials processing, hydrogen compounds, enzymes, cellular biophysicsOther keywords: solid‐state microwave irradiation, synthesised NiO nanoparticles, soybean, facile microwave‐assisted synthesis, biochemical factors, Murashige, Skoog agar medium, malondialdehyde, hydrogen peroxide contents, antioxidant enzymes, ascorbate peroxidase enzymes, radical oxygen species detoxification, NiO, [Ni(NH₃)₆](NO₃)₂