Synthesis of Nanostructured Hydroxides and Oxides of Iron: Control Over Morphology and Physical Properties

This paper reports on the surfactant-assisted synthesis of nanotubes and nanorods of β-FeOOH and hence α-Fe₂O₃ (hematite) with remarkable stability against temperature under different reaction conditions. Characterization and a comprehensive study of their nanosized properties are carried out by powder X-ray diffraction, thermal analysis, transmission electron microscope, and vibrating sample magnetometer. Upon calcination at 300°C, β-FeOOH nanostructures transform to α-Fe₂O₃ with some change in morphology. The samples convert to layered rod-like structures and further into some sort of a disc resembling stacked structures upon heat treatment. Even for magnetic fields up to 10 000 G, the magnetization curves for the nanotubes/nanorods of hematite do not attain the saturation magnetization. All the materials exhibit a very low coercivity even at room temperature and hence are potential materials for magnetic applications.     

Structural characterization of FCC feeds from Indian refineries by NMR spectroscopy

Fluid catalytic cracking (FCC) feeds from four Indian refineries are structurally characterized by ¹H, gated-decoupled ¹³C, distortionless enhancement by polarization transfer (DEPT) and 2D ¹H–¹³C HETeronuclear CORrelation (HETCOR) and other 2D nuclear magnetic resonance (NMR) methods. Detailed structural analyses are completely supported by a range of NMR information including chemical shifts of ¹H and ¹³C, CH_n type distributions and ¹H –¹³C connectivities. The average structural parameters like branching sites, average number of branching per molecule, average length of side chains, percentage of saturates, aromatics and naphthenes are obtained from these NMR data. A novel approach based on “multipoint spline base line correction” is employed for estimation of naphthenes and n-paraffins that gives better quantitative estimation than the conventional methods. In this paper, importance is given to the study of those structural parameters that plays a key role in cracking chemistry as well as coke forming tendency of the feedstock. To the best of our knowledge, this is the first attempt to characterize and quantitatively estimate compositions of the high boiling fractions of petroleum feed by NMR methods and especially the complex structure of vacuum gas oil (VGO) fractions used in Indian refineries. The importance of this paper is to help in optimizing the product slate of Indian refineries through proper feedstock blending using few hundreds of million metric tons (MMT) of crude oil consisting of blends of light crudes with different heavy crudes and bottom of the barrel due to escalating cost of crudes.     

KDSAE: Chronic kidney disease classification with multimedia data learning using deep stacked autoencoder network

In recent times, Chronic Kidney Disease (CKD) has affected more than 10% of the population worldwide and millions of people die every year. So, early-stage detection of CKD could be beneficial for increasing the life expectancy of suffering patients and reducing the treatment cost. It is required to build such a multimedia driven model which can help to diagnose the disease efficiently with higher accuracy before leading to worse conditions. Various techniques related to conventional machine learning models have been used by researchers in the past time without involvement of multimodal data-driven learning. This research paper offers a novel deep learning framework for chronic kidney disease classification using stacked autoencoder model utilizing multimedia data with a softmax classifier. The stacked autoencoder helps to extract the useful features from the dataset and then a softmax classifier is used to predict the final class. It has experimented on UCI dataset which contains early stages of 400 CKD patients with 25 attributes, which is a binary classification problem. Precision, recall, specificity and F1-score were used as evaluation metrics for the assessment of the proposed network. It was observed that this multimodal model outperformed the other conventional classifiers used for chronic kidney disease with a classification accuracy of 100%.

     

Least-cost design of singly and doubly reinforced concrete beam using genetic algorithm optimized artificial neural network based on Levenberg–Marquardt and quasi-Newton backpropagation learning techniques

In this work, least-cost design of singly and doubly reinforced beams with uniformly distributed and concentrated load was done by incorporating actual self-weight of beam, parabolic stress block, moment–equilibrium and serviceability constraint besides other constraints. Also, this design expertise was incorporated into a genetically optimized artificial neural network based on steepest descent, Levenberg–Marquardt, and quasi-Newton backpropagation learning techniques. The initial solution for the optimization procedure was obtained using limit state design as per IS: 456-2000.     

Effect of electrolyte storage layer on performance of PPy-PVDF-PPy microactuators

Trilayer electroactive conducting polymer actuators comprising of two active polymer layers separated by an electrolyte storage layer in between are capable of working in air. Ions are shuttled between the two active layers via the middle inactive layer during electrochemical switching, which leads to a bending motion like the bending of a cantilever beam under a load. Performance of these types of cantilevered actuators greatly depends on the middle electrolyte storage layer, which holds electrolyte and eliminates the necessity of an external electrolyte reservoir, as required by their predecessors. In this paper, we used different types of poly(vinylidene fluoride) (PVDF) films as an electrolyte reservoir and compared bending displacement performance of the actuators made from such PVDF films. The results indicate that the thickness of the PVDF layer has significant effect on the tip displacement of the actuators. With a reduction in the PVDF thickness, the bending stress generated by the actuator decreases while the free tip displacement increases. Several types of PVDF thin films were also compared. As expected, porous PVDF thin films retained more liquid electrolyte and produced larger actuation than non-porous films of the same thickness. It was also found that addition of the electrolyte salt directly to the PVDF film during its spin casting increased the film conductivity and actuation tip displacement.     

Robust identification of nonlinear complex systems using low complexity ANN and particle swarm optimization technique

The paper introduces a novel method of adaptive robust identification of complex nonlinear dynamic plants including Box Jenkin, Mackey Glass and Sunspot series under the presence of strong outliers in the training samples. The identification model consists of a low complexity single layer functional link artificial neural network (FLANN) in the feed forward path and another on the feedback path. The connecting weights are iteratively adjusted by a population based particle swarm optimization technique so that a robust cost function (RCF) of the model-error is minimized. To demonstrate robust identification performance up to 50% random samples of the plant output is contaminated with strong outliers and are employed for training the model using PSO tool. Identification of wide varieties of benchmark complex static and dynamic plants is carried out through simulation study and the performance obtained are compared with those obtained from using standard squared error norm as CF. It is in general observed that, the Wilcoxon norm provides best identification performance compared to squared error and other RCFs based models.     

Water management — A tool for methane mitigation from irrigated paddy fields

Water drainage is considered to be one of the important practices that reduce the CH₄ efflux from paddy fields. In this study, four different drainage systems (continuous flooding, tillering stage drainage, mid-season drainage and multiple drainage) were compared to find out the best one, for attenuation of CH₄ emission from rice fields. Except for continuous flooding, from all the other three drainage systems, irrigation water from the paddy fields was drained out at the different stages of the crop cycle. Highest efflux of the methane was recorded from continuously flooded plots (346.6 mg/m²/day), followed by 9% less CH₄ efflux from tillering stage drainage (315.1 mg/m²/day), 36.7% less efflux from mid-season drainage (219.3 mg/m²/day) and the least 41% CH₄ efflux from multiple drainage plots (204.7 mg/m²/day). Among all the four different drainage systems applied, mid-season drainage and multiple drainage were found to be highly effective in mitigating methane efflux. Redox potential of the soil of the drainage system was found to be inversely proportional to the methane efflux from all the treatments.     

Financial time series prediction using distributed machine learning techniques

Neural Computing and Applications - The financial time series is inherently nonlinear and hence cannot be efficiently predicted by using linear statistical methods such as regression. Hence,...     

含石浆粉废弃物工程胶结复合材料的性能

工程胶结复合材料中使用的大多数材料的晶粒尺寸细小,有较好的韧性.石浆粉(SSP)是石工业中的一种惰性材料副产品,对环境产生有害影响.本文研究了用不同含量(25％和50％)SSP部分替代硅砂(SS)和细砂(FS)来制备工程胶结复合材料.根据强度、拉伸应变、中跨度偏转能力、超声波脉冲速度和微观结构对其性能进行了评价.在两种...