Evolving an Accurate Decision Tree-Based Model for Predicting Carbon Dioxide Solubility in Polymers

Solubility is one of the most indispensable physicochemical properties determining the compatibility of components of a blending system. Research has been focused on the solubility of carbon dioxide in polymers as a significant application of green chemistry. To replace costly and time-consuming experiments, a novel solubility prediction model based on a decision tree, called the stochastic gradient boosting algorithm, was proposed to predict CO₂ solubility in 13 different polymers, based on 515 published experimental data lines. The results indicate that the proposed ensemble model is an effective method for predicting the CO₂ solubility in various polymers, with highly satisfactory performance and high efficiency. It produces more accurate outputs than other methods such as machine learning schemes and an equation of state approach.     

Social collaborative filtering using local dynamic overlapping community detection

The Journal of Supercomputing - Recommender systems play an important role in dealing with the problems caused by the great and growing amount of information, and the collaborative filtering method...     

Modification of glassy carbon electrode with multi-walled carbon nanotubes and iron(III)-porphyrin film: Application to chlorate, bromate and iodate detection

In this study, multi-wall carbon nanotubes (MWCTs) is evaluated as a transducer, stabilizer and immobilization matrix for the construction of amperometric sensor based on iron-porphyrin. 5,10,15,20-Tetraphenyl-21H,23H-porphine iron(III) chloride (Fe(III)P) adsorbed on MWCNTs immobilized on the surface of glassy carbon electrode. Cyclic voltammograms of the Fe(III)P-incorporated-MWCNTs indicate a pair of well-defined and nearly reversible redox couple with surface confined characteristics at wide pH range (2-12). The surface coverage (Γ) and charge transfer rate constant (k_s) of Fe(III)P immobilized on MWCNTs were 7.68 × 10⁻⁹ mol cm⁻² and 1.8 s⁻¹, respectively, indicating high loading ability of MWCNTs for Fe(III)P and great facilitation of the electron transfer between Fe(III)P and carbon nanotubes immobilized on the electrode surface. Modified electrodes exhibit excellent electrocatalytic activity toward reduction of ClO₃⁻, IO₃⁻ and BrO₃⁻ in acidic solutions. The catalytic rate constants for catalytic reduction of bromate, chlorate and iodate were 6.8 × 10³, 7.4 × 10³ and 4.8 × 10² M⁻¹ s⁻¹, respectively. The hydrodynamic amperometry of rotating-modified electrode at constant potential versus reference electrode was used for detection of bromate, chlorate and iodate. The detection limit, linear calibration range and sensitivity for chlorate, bromate and iodate detections were 0.5 μM, 2 μM to 1 mM, 8.4 nA/μM, 0.6 μM, 2 μM to 0.15 mM, 11 nA/μM, and 2.5 μM, 10 μM to 4 mM and 1.5 nA/μM, respectively. Excellent electrochemical reversibility of the redox couple, good reproducibility, high stability, low detection limit, long life time, fast amperometric response time, wide linear concentration range, technical simplicity and possibility of rapid preparation are great advantages of this sensor. The obtained results show promising practical application of the Fe(III)P-MWCNTs-modified electrode as an amperometric sensor for chlorate, iodate and bromate detections.     

TVD-MRDL: traffic violation detection system using MapReduce-based deep learning for large-scale data

Maintaining a fluid and safe traffic is a major challenge for human societies because of its social and economic impacts. Various technologies have considerably paved the way for the elimination of traffic problems and have been able to effectively detect drivers’ violations. However, the high volume of the real-time data collected from surveillance cameras and traffic sensors along with the data obtained from individuals have made the use of traditional methods ineffective. Therefore, using Hadoop for processing large-scale structured and unstructured data as well as multimedia data can be of great help. In this paper, the TVD-MRDL system based on the MapReduce techniques and deep learning was employed to discover effective solutions. The Distributed Deep Learning System was implemented to analyze traffic big data and to detect driver violations in Hadoop. The results indicated that more accurate monitoring automatically creates the power of deterrence and behavior change in drivers and it prevents drivers from committing unusual behaviors in society. So, if the offending driver is identified quickly after committing the violation and is punished with the appropriate punishment and dealt with decisively and without negligence, we will surely see a decrease in violations at the community level. Also, the efficiency of the TVD-MRDL performance increased by more than 75% as the number of data nodes increased.

     

Fault detection and diagnosis of an industrial steam turbine using a distributed configuration of adaptive neuro-fuzzy inference systems

The issue of fault detection and diagnosis (FDD) has gained widespread industrial interest in process condition monitoring applications. An innovative data-driven FDD methodology has been presented in this paper on the basis of a distributed configuration of three adaptive neuro-fuzzy inference system (ANFIS) classifiers for an industrial 440 MW power plant steam turbine with once-through Benson type boiler. Each ANFIS classifier has been developed for a dedicated category of four steam turbine faults. A preliminary set of conceptual and experimental studies has been conducted to realize such fault categorization scheme. A proper selection of four measured variables has been configured to feed each ANFIS classifier with the most influential diagnostic information. This consequently leads to a simple distributed FDD system, facilitating the training and testing phases and yet prevents operational deficiency due to possible cross-correlated measured data effects. A diverse set of test scenarios has been carried out to illustrate the successful diagnostic performances of the proposed FDD system against 12 major faults under challenging noise corrupted measurements and data deformation corresponding to a specific fault time history pattern.     

Homotopy perturbation method for motion of a spherical solid particle in plane couette fluid flow

He’s homotopy perturbation method is applied to obtain exact analytical solutions for the motion of a spherical particle in a plane couette flow. It is demonstrated that the applied analytical method is very straightforward in comparison with existing techniques. Furthermore, it is decidedly effectual in terms of accuracy and rapid convergence. The formulation of the problem is presented in the text as well as the analytical and numerical procedures. The current results can be used in different areas of particulate flows.     

A computational method of forecasting based on high-order fuzzy time series

This paper presents a computational method of forecasting based on high-order fuzzy time series. The developed computational method provides a better approach to overcome the drawback of existing high-order fuzzy time series models. Its simplicity lies with the use of differences in consecutive values of various orders as forecasting parameter and a w-step fuzzy predictor in place of complicated computations of fuzzy logical relations. The objective of the present study is to examine the suitability of various high-order fuzzy time series models in forecasting. The general suitability of the developed method has been tested by implementing it in the forecasting of student enrollments of the University of Alabama and in the forecasting of crop (Lahi) production, a case of high uncertainty in time series data. The results obtained have been compared in terms of average error of forecast to show superiority of the proposed model.     

Blockwise conjugate gradient methods for image reconstruction in volumetric CT

Cone beam computed tomography (CBCT) enables volumetric image reconstruction from 2D projection data and plays an important role in image guided radiation therapy (IGRT). Filtered back projection is still the most frequently used algorithm in applications. The algorithm discretizes the scanning process (forward projection) into a system of linear equations, which must then be solved to recover images from measured projection data. The conjugate gradients (CG) algorithm and its variants can be used to solve (possibly regularized) linear systems of equations Ax=b and linear least squares problems minx∥b-Ax∥(2), especially when the matrix A is very large and sparse. Their applications can be found in a general CT context, but in tomography problems (e.g. CBCT reconstruction) they have not widely been used. Hence, CBCT reconstruction using the CG-type algorithm LSQR was implemented and studied in this paper. In CBCT reconstruction, the main computational challenge is that the matrix A usually is very large, and storing it in full requires an amount of memory well beyond the reach of commodity computers. Because of these memory capacity constraints, only a small fraction of the weighting matrix A is typically used, leading to a poor reconstruction. In this paper, to overcome this difficulty, the matrix A is partitioned and stored blockwise, and blockwise matrix-vector multiplications are implemented within LSQR. This implementation allows us to use the full weighting matrix A for CBCT reconstruction without further enhancing computer standards. Tikhonov regularization can also be implemented in this fashion, and can produce significant improvement in the reconstructed images.     

A three-dimensional inverse finite-element method applied to experimental eddy-current imaging data

Eddy-current techniques can be used to create electrical conductivity mapping of an object. The eddy-current imaging system in this paper is a magnetic induction tomography (MIT) system. MIT images the electrical conductivity of the target based on impedance measurements from pairs of excitation and detection coils. The inverse problem here is ill-posed and nonlinear. Current state-of-the-art image reconstruction methods in MIT are generally based on linear algorithms. In this paper, a regularized Gauss-Newton scheme has been implemented based on an edge finite-element forward solver and an efficient formula for the Jacobian matrix. Applications of Tikhonov and total variation regularization have been studied. Results are presented from experimental data collected from a newly developed MIT system. The paper also presents further progress in using an MIT system for molten metal flow visualization in continuous casting by applying the proposed algorithm in a real experiment in a continuous casting pilot plant of Corus RD&T, Teesside Technology Centre.