User-centric hybrid semi-autoencoder recommendation system

Recommendation System is one of such solutions to overcome information overload issues and to identify products most relevant to users and provide suggestions to users for items they might be interested in consuming or elements matching their needs. The significant challenge of several recommendation approaches is that they suggested a huge number of things to the target user. But the exciting items, according to the target user, are seen at the bottom of the recommended list. The proposed approach has improved the quality of recommendations by implementing some of the unique features in the new framework of auto encoder called semi-autoencoder, which contains the rating information as well as some additional information of users. Autoencoder is widely used in the recommender system because it gives the best result for feature extraction, dimensionality reduction, regeneration of data, and a better understanding of the user’s characteristics. The experimental results are compared with some established popular methods using precision, recall, and F-measure evaluation measures. Users generally don’t want to see lots of suggestions. With its six building blocks, the proposed approach gives better performance for the top 10 recommendations compared to other well-known methods.

     

Carbothermal Synthesis of Silicon Nitride: Effect of Reaction Conditions

Conditions for carbothermal synthesis of α-Si₃N₄ are presented with special emphasis on the reaction temperature, C:SiO₂ ratio, and precursor mixing. With pure precursors, the conversion temperature is 1500° to 1550°C. An excess of C is necessary for complete conversion, and a simple sol–gelmixing technique provides excellent intermixing of the precursors. Copious flow of N₂ gas throughout the reactor bed is essential if pure Si₃N₄ is to be produced; small concentrations of CO and O₂ promote SiC and Si₂N₂O, respectively.     

Carbothermal Synthesis of Aluminum Nitride Using Sucrose

Several aluminum oxides (α-Al₂O₃, θ-Al₂O₃, and AIOOH) were examined to study the differences in reaction behavior and powder characteristics during carbothermal nitrida-tion to AIN using sucrose and carbon black. The reaction conditions investigated were carbon-to-alumina ratio, reaction temperature, and time. Carburized sucrose resulted in Full conversion to AIN and produced a uniform powder morphology using a near-istoichiometric ratio of C:Al₂O₃ while carbon black required higher C:Al₂O₃ ratios (i.e., >4:1) for full conversion and led to agglomeration of the AIN powder. The most favorable reaction temperature was 1600°C, with the reaction time to full conversion being dependent on the type of Al₂O₃. The particle and agglomerate size of the AIN powders did not change significantly with reaction time. However, the particle size and morphology were strongly dependent on that of the initial AI₂O₃ with sucrose, whereas agglomeration of the AIN occurs when using carbon black. A solid–solid reaction mechanism is proposed.     

Aromatisation ofn-heptane over ZSM-5 prepared without the aid of a template

ZSM-5 was prepared without the aid of an organic template. Effect of synthesis parameters on its catalytic activity in aromatisation ofn-heptane are discussed. Addition of seed material increased the crystallinity of the ZSM-5 phase. The catalytic activity was comparable with a sample prepared using an organic template. Formation of higher amount of C_9– aromatics was observed over the non-templated zeolite.     

Microwave-assisted green synthesis of hybrid nanocomposite: removal of Malachite green from waste water

Gum xanthan/psyllium-based nanocomposite was prepared by microwave-assisted synthetic method for the removal of toxic Malachite green (MG) dye from aqueous solutions. The nanocomposite was prepared by in situ incorporation of the K₂Zn₃[Fe(CN)₆]·9H₂O nanoparticles into the semi-IPN matrix in the presence of ammonium persulphate and glutaraldehyde as initiator-crosslinker system. Liquid uptake efficacy of the hybrid superabsorbent was enhanced through the optimization of different reaction conditions, including APS = 0.027 mol L^?1; glutaraldehyde = 0.053 × 10^?3 mol L^?1; solvent = 8.0 mL; acrylic acid = 10.928 mol L^?1; pH 7.0; reaction time = 60 s and microwave power = 100 % and its thermal behavior was evaluated using TGA-DTG-DTA technique. Candidate nanocomposite was characterized by FTIR, SEM, XRD and UV–visible spectroscopic methods. Various optimized parameters for the efficient removal (83 %) of the Malachite green were adsorbent dose of 800 mg, 14 mg L^?1 initial dye concentration and contact time of 28 h. Further, Langmuir and Freundlich adsorption isotherms showed good applicability in adsorption process of MG onto the nanocomposite with maximum adsorption efficiency of 3.21 mg g^?1. However, for Freundlich isotherm, R ² was around 0.9947 and value of 1/n was less than 1 for the synthesized nanocomposite which indicated that the Freundlich isotherm was more favorable than Langmuir isotherm model along with its usability for wide range of dye concentrations. The nanocomposite was found to be a potential product for dye removal from waste water and could prove to be a boon for textile sector.     

An effective implementation and assessment of a random forest classifier as a soil spatial predictive model

Mapping the spatial distribution of soil classes is important for informing soil use and management decisions. This study aimed to effectively implement Random Forest (RF) model and to evaluate the behaviour and performance of the model for soil classification of Indian districts. Soil-forming factors, known as ‘scorpan,’ are selected as environmental covariates to tune RF model to classify 11 different soil categories. Thirty-five digital layers are prepared using different satellite data [ALOS (Advanced Land Observing Satellite) digital elevation model, Landsat-8, Moderate Resolution Imaging Spectroradiometer normalized difference vegetation index product, RISAT-1 (Radar Imaging Satellite-1), Sentinel-1A] and climatic data (precipitation and temperature) to represent scorpan environmental covariates in the study area. The RF parameters corresponding to highest Cohen’s kappa coefficient (κ) value and lowest number of random split variables are considered optimum values for RF model. Model behaviour evaluation is based on mapping accuracy, sensitivity to data set size, and noise. Two other machine-learning methods, CART (Classification and Regression Tree) decision tree (CDT) and CART ensemble bagger (CEB), are used to provide the comparative study. To access behaviour of models to the false data set, noise in training set is produced by assigning a false class to the training set in 5% increment. Comparative performance of RF model is based on quality assessment measures. To evaluate the performance of models, marginal rates, F-measure, and Jaccard’s coefficient of the community, classification success index and agreement coefficients are selected under quality assessment measures. The score is calculated to rank the algorithm. RF model shows high stability against data set reduction in comparison to other methods. The results show that the abrupt change in accuracy is only observed after 60% training data reduction in RF model; however, significant decrease in accuracy can be noted after 45% and 25% data reduction in CEB and CDT, respectively. The RF model shows comparatively the greater resistance to noise. Overall, RF model has performed better than CDT and CEB to classify soil categories in the study area. The results of this research provide new insights into the performance of RF in the context of soil class mapping.     

Investigation of optical and thermally stimulated properties of SiO2 nanoparticles‐filled polycarbonate

Polycarbonate nanocomposite containing silicon oxide nanoparticles average size of 5 nm at different weight ratio has been prepared by solution mixing method. The dispersion of nanoparticles in polymer matrix was studied by transmission electron microscopy (TEM). The optical and thermally stimulated behavior of nanocomposites were analyzed by energy dispersive X‐ray spectra (EDX), X‐ray diffraction pattern (XRD), UV–vis spectroscopy, differential scanning calorimetry (DSC), and thermally stimulated discharge current (TSDC). TEM images show the dispersion and size of the nanoparticles, however, EDX indicate the presence of SiO₂ on the surface of the nanocomposite film. An XRD result reveals that the crystallinity increases with increase in concentration of SiO₂ nanoparticles in polymer matrix. The direct and indirect optical energy band gaps decreased and number of carbon atom increased with concentration of SiO₂ nanoparticles. We have observed that the increase of SiO₂ nanoparticles in PC significantly reduces the refractive index. DSC and TSDC show that glass transition temperature increases according to SiO₂ weight ratio. The TSDC of nanocomposites samples could be understand in terms of non‐Debye theory of charge relaxation and co‐tunneling mechanism of charge transport. © 2012 Wiley Periodicals, Inc. J Appl Polym Sci, 2012     

Effect of nano ZnO on the phase mixing of polyurethane hybrid dispersions

In the present study series of aqueous polyurethane (PU)/ZnO hybrid dispersions were prepared using dimethylolpropionic acid (bis-MPA) as an ionic center. For this, NCO terminated PU prepolymers with pendent acid groups were prepared first, then different concentrations of nano ZnO powder was incorporated into the PU matrix. The hybrid dispersions were prepared by adding required amount of triethylamine (TEA), water and chain extender. The prepared PU/ZnO hybrid dispersions were casted in a Teflon petri dish and the dried films were used for TGA, DMTA, SEM, gel content and contact angle measurements. The phase mixing behavior was studied from FT-IR peak deconvolution technique and DMTA analysis and the result suggests that phase mixing increases with ZnO content. The DMTA data suggest that the phase mixing and soft segment glass transition increases but storage modulus decreases with increasing with ZnO content. The FT-IR deconvolution result supports to the DMTA analysis. The coating properties like adhesive strength, water absorption, contact angle, gel content and corrosion resistance of the hybrid coatings were also evaluated.     

Rapid analysis of scattering from periodic dielectric structures using accelerated Cartesian expansions

The analysis of fields in periodic dielectric structures arise in numerous applications of recent interest, ranging from photonic bandgap structures and plasmonically active nanostructures to metamaterials. To achieve an accurate representation of the fields in these structures using numerical methods, dense spatial discretization is required. This, in turn, affects the cost of analysis, particularly for integral-equation-based methods, for which traditional iterative methods require O(N2) operations, N being the number of spatial degrees of freedom. In this paper, we introduce a method for the rapid solution of volumetric electric field integral equations used in the analysis of doubly periodic dielectric structures. The crux of our method is the accelerated Cartesian expansion algorithm, which is used to evaluate the requisite potentials in O(N) cost. Results are provided that corroborate our claims of acceleration without compromising accuracy, as well as the application of our method to a number of compelling photonics applications.