Ensemble Learning Based Collaborative Filtering with Instance Selection and Enhanced Clustering

Recommender system is a tool to suggest items to the users from the extensive history of the user's feedback. Though, it is an emerging research area concerning academics and industries, where it suffers from sparsity, scalability, and cold start problems. This paper addresses sparsity, and scalability problems of model-based collaborative recommender system based on ensemble learning approach and enhanced clustering algorithm for movie recommendations. In this paper, an effective movie recommendation system is proposed by Classification and Regression Tree (CART) algorithm, enhanced Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) algorithm and truncation method. In this research paper, a new hyper parameters tuning is added in BIRCH algorithm to enhance the cluster formation process, where the proposed algorithm is named as enhanced BIRCH. The proposed model yields quality movie recommendation to the new user using Gradient boost classification with broad coverage. In this paper, the proposed model is tested on Movielens dataset, and the performance is evaluated by means of Mean Absolute Error (MAE), precision, recall and f-measure. The experimental results showed the superiority of proposed model in movie recommendation compared to the existing models. The proposed model obtained 0.52 and 0.57 MAE value on Movielens 100k and 1M datasets. Further, the proposed model obtained 0.83 of precision, 0.86 of recall and 0.86 of f-measure on Movielens 100k dataset, which are effective compared to the existing models in movie recommendation.     

Analysis and classification of malignancy in pancreatic magnetic resonance images using neural network techniques

Computer-aided diagnosis (CAD) is a computerized way of detecting tumors in MR images. Magnetic resonance imaging (MRI) has been generally used in the diagnosis and detection of pancreatic tumors. In a medical imaging system, soft tissue contrast and noninvasiveness are clear preferences of MRI. Inaccurate detection of tumor and long time consumption are the disadvantages of MRI. Computerized classifiers can greatly renew the diagnosis activity, in terms of both accuracy and time necessity by normal and abnormal images, automatically. This article presents an intelligent, automatic, accurate, and robust method to classify human pancreas MRI images as normal or abnormal in terms of pancreatic tumor. It represents the response of artificial neural network (ANN) and support vector machine (SVM) techniques for pancreatic tumor classification. For this, we extract features from MR images of pancreas using the GLCM method and select the best features using JAFER algorithm. These features are analyzed by five classification techniques: ANN BP, ANN RBF, SVM Linear, SVM Poly, and SVM RBF. We compare the results with benchmark data set of MR brain images. The analytical outcome presents that the two best features used to classify the MR images using ANN BP technique have 98% classification accuracy.     

Erratum to: Malaria infected erythrocyte classification based on a hybrid classifier using microscopic images of thin blood smear

Multimedia Tools and Applications -     

Synthesis and characterization of moisture‐cured polyurethane membranes and their applications in pervaporation separation of ethyl acetate/water azeotrope at 30°C

NCO‐terminated polyurethane membranes were prepared using diisocyanate, diol, and trimethylolpropane (TMP) using an NCO/OH ratio of 1.6 : 1. Prepolymer was chain‐extended using cellulose acetate butyrate (CAB) in the ratios of 2 : 1, 4 : 1, and 3 : 1 of NCO/OH. Polyurethane (PU) membranes were characterized by differential scanning calorimeter (DSC) and thermogravimetry (TGA) to investigate their thermal properties. Equilibrium sorption studies were carried out at 30°C in water and ethyl acetate media as well as in their binary mixtures. The influence of CAB on pervaporation (PV) separation of an ethyl acetate/water (92/8, w/w, i.e., azeotropic composition) mixture was investigated. Membranes in this study showed a selectivity of 42.42 with a flux value of 0.187 kg/m/h for 3 : 1% NCO/OH containing PU membrane. In order to gain a more detailed picture of the molecular transport phenomenon, we performed the sorption gravimetric experiments at 30°, 35°, 40°, and 50°C to compute diffusion, swelling, sorption, and permeability coefficients of PU membranes in the azeotropic mixture of ethyl acetate and water. Activation parameters for diffusion and permeation were computed from the Arrhenius equation to understand the polymer/solvent interactions. Sorption trends and diffusion anomalies were established through an empirical equation after estimating the diffusion parameters. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 103: 3405–3414, 2007     

Oligomeric Composition of Polyols From Fatty Acid Methyl Ester: The Effect of Ring‐Opening Reactants of Epoxide Groups

Commercial availability of fatty acid methyl ester (FAME) from palm oil targeted for biodiesel offers a good feedstock for the production of structurally well‐defined polyols for polyurethane applications. The effect of molecular weight (MW), odd and even carbon numbers, and the linear and branched structure reactants used in the ring‐opening reaction of epoxidized fatty acid methyl ester (E‐FAME) on the properties of polyols was investigated. Conversions of E‐FAME to PolyFAME polyols were confirmed by Fourier transform infrared analysis, oxirane oxygen content, and hydroxyl number. Gel permeation chromatography (GPC) calibrated against polyether polyols as a standard and vapor pressure osmometry were used for MW determination. GPC chromatograms of PolyFAME polyols clearly demonstrated the formation of oligomers during ring‐opening reactions. MW, and odd and even carbon numbers in a structure of linear diols and branched diol used in the syntheses of PolyFAME polyols did not have an effect on crystallinity, glass transition, or melt temperatures measured using Differential scanning calorimetry (DSC). PolyFAME polyols ring‐opened with water, methanol, and 1,2‐propanediol contained secondary hydroxyl groups, whereas PolyFAME polyols ring‐opened with linear diols contained a mixture of primary and secondary hydroxyl groups. It was found that the concentration of primary hydroxyl groups increased significantly by increasing the number of carbons from C2 to C3 in the linear diols. The viscosity of PolyFAME polyols also increased with the MW of linear diols used in the E‐FAME ring‐opening reaction. These findings would be beneficial for formulators in choosing the most cost effective polyols for polyurethane formulations.     

Biological decolourization of C.I. Direct Black 38 by E. gallinarum

In the present study, an Enterococcus gallinarum strain was isolated from effluent treatment plant of a textile industry based on its ability to decolourize C.I. Direct Black 38 (DB38), a benzidine-based azo dye. Effects of dye concentration and medium composition on dye decolourization were studied. The strain was found to decolourize DB38 even under aerobic conditions. Kinetics of DB38 decolourization was also examined, and V(max) and K(s) of decolourization were found to be higher in Luria broth (12.8 mg l(-1)h(-1) and 490.6 mg l(-1)) than in minimal medium (4.09 mg l(-1)h(-1) and 161.84 mg l(-1)). However, decolourization rate/biomass was found to be higher in minimal medium than in Luria broth, indicating greater decolourization efficiency of biomass in the former. The study also revealed biodegradation of DB38 to benzidine and its further deamination to 4-aminobiphenyl (4-ABP) by the culture. Ammonia released during this process was used as nitrogen source for growth of the culture.     

Effect of SBS and HDPH polymer on rheological properties of asphalt

The present work discusses the combined effect of High Density Polyethylene Homo polymer and Styrene-Butadiene-Styrene on properties of Viscosity Grade 30 asphalt commonly used in India. Six blends of binders were prepared using varying percentages of both polymers and were evaluated for rheological properties. Use of both polymers leads to higher viscosity, while blending with HDPH polymer only leads to marginal increase in viscosity when compared to unmodified binder. Comparison of dynamic modulus and phase angle master curves indicated, significant differences were found among master curves obtained with different aging conditions when compared to unaged condition especially at lower reduced frequencies.     

Thermo-mechanical treatments of Sc- and Mg-modified Al–Cu alloy welds

High-strength heat-treatable aluminum alloy AA2219 finds application in aerospace industries. Though it has good weldability, with alternating current–tungsten inert gas welding, the joint efficiency obtained is only 40%, particularly in thicker plates. In the present study, an attempt has been made to improve the weld metal properties by modifying the chemistry of fusion zone and post-weld thermo-mechanical treatments. Fillers were made through casting route by melting conventional 2319 filler with Sc and Mg. Two levels of Sc (0.3% and 0.6%) and four levels of Mg (0.3% to 0.6%) were varied. Compressive deformation was done on the fusion zone of the weld to get three levels of percentage of reduction (4%, 8%, and 12%). As welded specimens and welds after compressive deformation, those were subjected to post-weld aging treatments at 190ºC for different periods up to 100 h. Compressive deformation on the welds made with modified filler of 2319 with Sc and Mg resulted in significant improvement in the weld metal strength.     

Kinetic Alfven Waves Excited by Cometary Newborn Ions with Large Perpendicular Energies

Stability of the kinetic Alfven wave in a plasma of hydrogen, oxygen and electrons is studied. Each species is modeled by drifting ring distributions in the direction parallel to the magnetic field, while in the perpendicular direction the distribution is simulated with a loss cone type distribution obtained through the subtraction of two Maxwellian distributions with different temperatures. It is found that for frequencyw^* < Ｗ_Hwith w^* andＷ_H the Doppler shifted and hydrogen ion gyro-frequencies, respectively, the growth rate of the kinetic Alfven wave increases with the increase in propagation angles and density of oxygen ions. On the other hand, for frequencies w^* < Ｗ_OwithＷ_Othe oxygen ion gyro-frequency the growth rate is independent of the oxygen ion density.