Diabetes Prediction Algorithm Using Recursive Ridge Regression L2

At present, the prevalence of diabetes is increasing because the human body cannot metabolize the glucose level. Accurate prediction of diabetes patients is an important research area. Many researchers have proposed techniques to predict this disease through data mining and machine learning methods. In prediction, feature selection is a key concept in preprocessing. Thus, the features that are relevant to the disease are used for prediction. This condition improves the prediction accuracy. Selecting the right features in the whole feature set is a complicated process, and many researchers are concentrating on it to produce a predictive model with high accuracy. In this work, a wrapper-based feature selection method called recursive feature elimination is combined with ridge regression (L2) to form a hybrid L2 regulated feature selection algorithm for overcoming the overfitting problem of data set. Overfitting is a major problem in feature selection, where the new data are unfit to the model because the training data are small. Ridge regression is mainly used to overcome the overfitting problem. The features are selected by using the proposed feature selection method, and random forest classifier is used to classify the data on the basis of the selected features. This work uses the Pima Indians Diabetes data set, and the evaluated results are compared with the existing algorithms to prove the accuracy of the proposed algorithm. The accuracy of the proposed algorithm in predicting diabetes is 100%, and its area under the curve is 97%. The proposed algorithm outperforms existing algorithms.     

Dynamic characterization of the thickness-tapered laminated plant fiber-reinforced polymer composite plates

Evolution of the laminated woven natural fiber fabric-reinforced polymer composite structures makes a way to the development of the non-uniform laminated composite structures in order to achieve the stiffness variation throughout the structure. An attempt is made in this work to carry out the experimental and numerical investigations on the dynamic characteristics of the thickness-tapered laminated woven jute/epoxy and woven aloe/epoxy composite plates. The governing differential equations of motion for the thickness-tapered laminated composite plate are developed using the h-p version FEM based on higher order shear deformation theory. The validation of the present finite element formulation is carried out by comparing the natural frequencies obtained using the finite element formulation with those natural frequencies determined experimentally. The developed model is further validated with the available literature works on tapered composite plate to confirm the efficiency of h-p version FEM. This work also explores the study of the vibrational characteristics of composite plates under the influence of plant fiber’s transverse isotropic material characteristics and porosity associated with plant fiber composites through the elastic constants evaluated in the author’s previous work. Also the influences of aspect ratios, ply orientations, and taper angles under various end conditions on the natural frequencies of the woven jute/epoxy composite plate are studied using the present finite element formulation. The forced vibration response of the thickness-tapered laminated woven jute/epoxy composite plate under the harmonic force excitation is carried out considering CFCF and CFFF end conditions.     

X-ray,electrical conductivity and magnetic hysteresis studies of the chalcogenide system Zn1−xCuxCr2Se4

X-ray diffraction studies performed here indicated solid-solution formation between ZnCr₂Se₄ and CuCr₂Se₄, and all the compounds could be indexed on the basis of cubic spinel lattice. The compositions between 0 x 0.8 showed semi-conducting behaviour, while CuCr₂Se₄ (x=1.0) exhibited metallic conductivity. Seebeck measurements showd P-type behaviour for 0 x 1. Magnetic hysteresis indicated a ferromagnetic nature for all the compounds except ZnCr₂Se₄ (x=0). The shapes of/ _i plotted againstT exhibited single domain behaviour, and Curie temperatures showed an increase with increasing copper concentration.     

Study of Cation Ordering in Ba(Yb1/2Ta1/2)O3 by X-Ray Diffraction and Raman Spectroscopy

The complex perovskite Ba(Yb_1/2Ta_1/2)O₃ has been prepared by the two-stage solid-state reaction method. Rietveld' refinement analysis indicates cubic perovskite phase with space group     . The 1:1 cation ordering at the B-site is revealed by the presence of (111) superlattice reflection in the X-ray diffraction pattern and further evidenced by the presence of A_1g and F_2g vibrational modes in the Raman spectra. The dielectric constant is measured to be 29.1, the product of quality factor and resonant frequency ( Q × f ) is found to be 32,000 GHz and the temperature coefficient of resonant frequency (τ_f) is 135 (ppm/°C) in the temperature range 30–70°C.     

Investigation on effect of blocking layer in perovskite sensitized pure and aluminium doped ZnO photoanode solar cell

ZnO is a promising candidate as low cost, porous semiconductor material for photoanodes in a dye sensitized solar cell. In this work, we investigate the performance of pure ZnO nanoparticles (ZNPs), Al₂O₃ doped ZnO (Al@ZNPs) and ZnO/Nb₂O₅ core–shell structure of photoanode material. These electrodes were sensitized with a pervoskite CH₃NH₃SnCl₃ sensitizer. To study the effect of the Al₂O₃, Nb₂O₅ treatment with ZnO, the J–V and EIS parameters, the current density (Jsc),Open circuit voltage (Voc), fill factor (FF), electron life time (τ_n), electron mobility (µ) and charge collection efficiency (?_cc) are calculated for the fabricated solar cells and the results are compared. It was found that the Al₂O₃ doped ZnO with the sensitizer CH₃NH₃Sncl₂ showed the highest efficiency of 9.41% under 100 mW/cm² irradiation. The electron impedance spectroscopy revealed that the charge collection efficiency (?_cc) of the solar cells is in the order of PSSC3?>?PSSC4?>?PSSC2?>?PSSC1. In this work, the effect of blocking layer (Ta₂O₅) is also discussed. From the J–V and EIS analysis, the effect of blocking layer is appreciable and it is useful to increase the efficiency of the solar cell by the way of reducing the recombination of charge carriers process. Therefore, the increase of photocurrent is mainly due to the combined effect of the sensitizer competence and blocking layer.     

Ozone-oxygen gas enhanced passivation of pure iron

Pure iron samples were passivated in borate buffer solution and were exposed to ozone-oxygen gas to study the possibility of improving the surface nanostructure such as atomically flat terrace structure. The treated samples were analyzed with spectroscopic ellipsometry and scanning tunneling microscopy, and the test of corrosion resistance was also carried out. The thickness of the oxide film increased by passivation at 800 mV (Ag/AgCl) and increased by ozone-oxygen gas exposure, but the oxidation film thickness decreased in air due to the reconstruction after rapid growth of oxides by passivation. The reconstruction of the oxide film was estimated by the change of the film thickness and compositions which were analyzed by spectroscopic ellipsometry using several layer models of Fe(OH)₃, γ-Fe₂O₃ and Fe₃O₄ and so on. The widest terrace width of the oxidation film was obtained on large particles based on the reconstruction after the combination treatment of passivation at 800 mV as well as subsequent ozone-oxygen gas treatment. The terrace width of the oxide film after passivation and ozone-oxygen gas treatment was three times larger than that of air-formed oxide film. The terrace width with atomic scale flatness was correlated with the corrosion resistance except for the increase in oxide film thickness.     

Morphology controlled synthesis of ZnO nanostructures by varying pH

ZnO nanostructures have been synthesized in a controlled manner by varying the pH of the precursor solution using hydrothermal technique. The morphological changes of the prepared ZnO nanostructures have been investigated in the range of pH 5–10. Radial hexagonal rod-like shape is formed at lower pH values of 5 and 6 whereas, flower-like shape is obtained for higher pH values of 9 and 10. Flake-like structure is observed at moderate pH of 8. The prepared ZnO nanostructures have been characterized using X-ray diffraction technique (XRD), energy dispersive X-ray analysis, scanning electron microscope and FTIR spectroscopy. XRD results show that the prepared ZnO nanostructures exhibit hexagonal wurtzite structure. The growth mechanism suggests that the supersaturation of the precursor results in various nucleation habits, which induce the formation of ZnO nanostructures with different morphologies. UV–Vis spectroscopy and photoluminescence were applied to study the optical properties. The photoluminescence spectrum demonstrated two emission bands, a near band edge emission in the UV region and a strong deep band emission in the visible region. The change in pH from 5 to 10 results in band gap variations of 3.47–3.97 eV and blue-shift in the peak emission of visible PL from 560 to 460 nm.     

Customized blends of polypropylene for extrusion based additive manufacturing

Filament-based material extrusion (MatEx) additive manufacturing has garnered great interest due to its simplicity, customizability, and cost-effectiveness. However, MatEx of semicrystalline polymers is still largely relegated to prototyping applications. Major issues involving volumetric shrinkage and warpage of the printed parts must be addressed in order to employ them for printing functional parts. Moreover, the crystallization behavior and rheology of the polymer are dependent on the MatEx processing conditions. In the current work, the printability of blends of isotactic polypropylene with a soft, low crystallinity propylene based homopolymer is evaluated. Addition of the homopolymer resulted in an increase in the crystallization window of the blends by ~6°C that had a profound impact on the interlayer adhesion and residual stress state. The shear-dependent melt flow behavior inside the printing nozzle as well as the interlayer chain diffusion and interlayer welding on the print bed were investigated. Rheological characterizations also indicate sufficient dispersion and miscibility of the homopolymer in the neat polypropylene matrix. The incorporation of the homopolymer as an additive significantly improved the dimensional accuracy of the printed parts through better dissipation of the entrapped residual stresses during MatEx. Moreover, the degree of mechanical anisotropy of the parts was significantly lower than that obtained using many 3D printable grade polymers. The findings from this study can be leveraged in toolpath planning, process parameter optimization, and new feedstock development, highlighting current limitations as well as providing valuable insights into necessary processing modifications in order to enable MatEx of next generation semicrystalline polymers.     

Functionalization of electrochemically prepared titania nanotubes with Pt for application as catalyst for fuel cells

Titania nanotubes (TiNTs) were prepared by electrochemical anodization and were used as a support for depositing Pt. After annealing the TiNTs changed to crystalline anatase phase and were doped with carbon. The TiNTs/Pt/C was tested as electrode for electrochemical catalysis of methanol oxidation. The composite catalyst activities were measured by cyclic voltammetry in 1 M CH₃OH + 1 M H₂SO₄. The results demonstrated that TiNTs/Pt/C can greatly enhance the catalytic activity of methanol oxidation. The CO stripping led to the increase in the current peak of methanol oxidation due to activating the catalyst surface by point defect formation. Moreover, the higher ratio of the forward anodic peak current to the reverse anodic peak current indicates more effective removal of the poisonous species.     

Automatic identification of sound recordings

We have designed an automatic song identification component of a digital rights management (DRM) system for music, called MusicDNA. The details of MusicDNA are presented and the process by which we arrived at the final system configuration is outlined. This paper documents our experiences so that it can serve as a reference to those seeking to build a complete DRM system for music.