A Wide Learning Approach for Interpretable Feature Recommendation for 1-D Sensor Data in IoT Analytics

Machine Intelligence Research - This paper presents a state of the art machine learning-based approach for automation of a varied class of Internet of things (IoT) analytics problems targeted on...     

Impact behavior of unidirectional polyethylene–glass fibers: PMMA hybrid composite laminates

Unidirectional (UD) hybrid laminates based on glass fibers (GF) and high performance polyethylene fibers (PEF) were prepared with partially polymerized methyl methacrylate (MMA) at room temperature followed by heating at 55°C (well below the softening point of PEF) for 2 h. Izod impact strength of the composites was then measured. An interesting observation of the study was the change in impact strength that was largely dependent on the position of GF and PEF ply/plies present within the hybrid laminates. When the ply/plies of PEF were at the impacted surface, the impact strength showed a higher value than that of the case when GF ply/plies were at the impacted surface of the hybrid laminates. © 1996 John Wiley & Sons, Inc.     

COSMO-RS based predictions for the desulphurization of diesel oil using ionic liquids: Effect of cation and anion combination

Ionic Liquids ILs provide an important alternative in removing aromatic sulphur compounds by Liquid-Liquid Extraction (LLE). A total of 28 anions and 6 cations resulting in 168 possible combinations were screened via COSMO-RS (COnductor Like Screening MOdel for Real Solvents). Initially benchmarking was performed to predict the infinite dilution activity coefficients of thiophene in ionic liquids. Comparison with literature values involving 8 ILs with 20 points gave the average root mean square deviation (RMS) to be 11%. Thereafter artificial simulated diesel, aromatic sulphur compound and the cation and anion combination was used to predict the capacity (C) and selectivity (S) at infinite dilution. In general the selectivities were found to decrease in the following order: thiophene (4-24) > benzothiophene (2-12)> dibenzothiophene (1-7). The different hetero atom (N,S,O) and its location in the cation structure strongly influenced the selectivity and capacity at infinite dilution for all the three aromatic sulphur compounds. It was found that the cation without the aromatic ring combined with anions having sterical shielding effect such as [SCN], [CH₃SO₃], [CH₃COO], [Cl], and [Br] proved to be the most favourable IL for desulphurization. [EMMOR][SCN] proved to be the most viable IL for the removal of all the three aromatic sulphur compounds.     

Development of a knowledge based hybrid neural network (KBHNN) for studying the effect of diafiltration during ultrafiltration of whey

The membrane surface dynamics is very difficult to predict and can be roughly estimated by the available models but a true depiction is always difficult since the magnitude and direction of driving forces change as a function of time. The present study is an effort to address the issue, so that the combinatorial approach of deterministic and stochastic modelling might present a better understanding of membrane dynamics. The effect of diafiltration has also been incorporated to investigate the effects it has on the membrane. A stochastic model developed by a knowledge based hybrid neural network (KBHNN) was trained using the Levenberg–Marqurt algorithm where the film layer model was used as the deterministic layer, called the first principle model (FPM). Present work employs two different types of KBHNN architecture with an effort to understand the suitability and applicability of the hybrid network in case of predictions for an ultrafiltration (UF) process. In one sort of architecture neural part was in series with the FPM and in the other one it was in parallel with the FPM. The high correlation coefficient (R²) value portrays the correctness and preciseness of the underlining assumptions and establishes the validity of the developed network.     

Innovative Utilization of Improved n-doped μc-SiOx:H Films to Amplify the Performance of Micromorph Solar Cells

Silicon - Due to in-situ deposition process doped SiOx material attracts the PV community as intermediate reflecting layer (IRL) for the less hazardous deposition process. Previously we have been...     

Studies of mechanical and moisture regain properties of methyl methacrylate grafted silk fibers

The mechanical properties such as the tenacity, breaking extension, initial modulus, elastic and work recovery, and stress relaxation behavior of methyl methacrylate (MMA) grafted silk fibers prepared under different conditions were measured and explained in terms of the relative dominance of the stress concentration, reduction in the interchain cohesion, and fiber matrix stiffening at different grafting percentages. The moisture regain characteristics of fibers grafted in the presence of different solvents were also studied and compared. The grafting of MMA on silk was found to improve the recovery properties significantly without affecting the stress relaxation behavior. The moisture regain studies indicate that moisture regain is reduced with increasing length of the grafted poly(MMA) chains. © 2002 Wiley Periodicals, Inc. J Appl Polym Sci 84: 969–974, 2002; DOI 10.1002/app.10202