A new deep intuitionistic fuzzy time series forecasting method based on long short-term memory

The Journal of Supercomputing - In recent years, deep artificial neural networks can have better forecasting performance than many other artificial neural networks. The long short-term memory...     

An ERP software selection process with using artificial neural network based on analytic network process approach

An enterprise resource planning (ERP) software selection is known to be multi attribute decision making (MADM) problem. This problem has been modeled according with analytic network process (ANP) method due to fact that it considers criteria and sub criteria relations and interrelations in selecting the software.Opinions of many experts are obtained while building ANP model for the selection ERP then opinions are reduced to one single value by methods like geometric means so as to get desired results. To use ANP model for the selection of ERP for a new organization, a new group of expert’s opinions are needed. In this case the same problem will be in counter. In the proposed model, when ANP and ANN models are setup, an ERP software selection can be made easily by the opinions of one single expert. In that case calculation of geometric mean of answers that obtained from many experts will be unnecessary. Additionally the effect of subjective opinion of one single decision maker will be avoided. In terms of difficulty, ANP has some difficulties due to eigenvalue and their limit value calculation.An ANN model has been designed and trained with using ANP results in order to calculate ERP software priority. The artificial neural network (ANN) model is trained by results obtained from ANP. It seems that there is no any major difficulty in order to predict software priorities with trained ANN model. By this results ANN model has been come suitable for using in the selection of ERP for another new decision.     

Dynamic soil–structure interaction analysis of layered unbounded media via a coupled finite element/boundary element/scaled boundary finite element model

In this paper, a coupled model based on finite element method (FEM), boundary element method (BEM) and scaled boundary FEM (SBFEM) (also referred to as the consistent infinitesimal finite element cell method) for dynamic response of 2D structures resting on layered soil media is presented. The SBFEM proposed by Wolf and Song (Finite‐element Modelling of Unbounded Media. Wiley: England, 1996) and BEM are used for modelling the dynamic response of the unbounded media (far‐field). The standard FEM is used for modelling the finite region (near‐field) and the structure. In SBFEM, which is a semi‐analytical technique, the radiation condition at infinity is satisfied exactly without requiring the fundamental solution. This method, also eliminates the need for the discretization of interfaces between different layers. In both SBFEM and BEM, the spatial dimension is decreased by one. The objective of the development of this coupled model is to combine advantages of above‐mentioned three numerical models to solve various soil–structure interaction (SSI) problems efficiently and effectively. These three methods are coupled (FE–BE–SBFEM) via substructuring method, and a computer programme is developed for the harmonic analyses of SSI systems. The coupled model is established in such a way that, depending upon the problem and far‐field properties, one can choose BEM and/or SBFEM in modelling related far‐field region(s). Thus, BEM and/or SBFEM can be used efficiently in modelling the far‐field. The proposed model is applied to investigate dynamic response of rigid and elastic structures resting on layered soil media. To assess the proposed SSI model, several problems existing in the literature are chosen and analysed. The results of the proposed model agree with the results presented in the literature for the chosen problems. The advantages of the model are demonstrated through these comparisons. Copyright © 2004 John Wiley & Sons, Ltd.     

Sources and mitigation of methane emissions by sectors: A critical review

The environmental community rightly recognizes global warming as one of the gravest threats to the planet. Methane (CH₄), one of the greenhouse gases causing global warming, is emitted from a variety of sources and its concentration in atmosphere has increased dramatically over the last few centuries. Therefore, the increasing concentrations of methane are of special concern because of its effects on climate and atmospheric chemistry. Anthropogenic sources of methane can be collected under the titles of agriculture, energy, waste and industry on the basis of sectors. This paper aims at examining the past trends in emissions, the sources and mitigation strategies of the methane. As a result of the study, it is determined that the agricultural sector is the biggest source of methane emissions among the sectors. The energy, waste and industry follow the agricultural sources respectively.     

Investigations of ductile damage during the process chains of toothed functional components manufactured by sheet-bulk metal forming

Sheet-bulk metal forming processes combine conventional sheet forming processes with bulk forming of sheet semi-finished parts. In these processes the sheets undergo complex forming histories. Due to in- and out-of-plane material flow and large accumulated plastic strains, the conventional failure prediction methods for sheet metal forming such as forming limit curve fall short. As a remedy, damage models can be applied to model damage evolution during those processes. In this study, damage evolution during the production of two different toothed components from DC04 steel is investigated. In both setups, a deep drawn cup is upset to form a circumferential gearing. However, the two final products have different dimensions and forming histories. Due to combined deep drawing and upsetting processes, the material flow on the cup walls is three-dimensional and non-proportional. In this study, the numerical and experimental investigations for those parts are presented and compared. Damage evolution in the process chains is simulated with a Lemaitre damage criterion. Microstructural analysis by scanning electron microscopy is performed in the regions with high mechanical loading. It is observed that the evolution of voids in terms of void volume fraction is strongly dependent on the deformation path. The comparison of simulation results with microstructural data shows that the void volume fraction decreases in the upsetting stage after an initial increase in the drawing stage. Moreover, the concurrent numerical and microstructural analysis provides evidence that the void volume fraction decreases during compression in sheet-bulk metal forming.     

Magnetic Properties of Zn1?x Ni x O (0.25≤x≤ 0.50) Prepared by Solid-State Reactions

In this study the origin of ferromagnetism in ZnO-based bulk systems has been investigated using Ni-doped ZnO samples, Zn_1−x Ni _x O with 0.25≤x≤0.50, prepared by solid-state reactions. The structural characterizations indicated that the Ni²⁺ ions almost uniformly distributed in all the samples, and the samples have hexagonal wurtzite structure; however, when x is increased toward 0.50, a new NiO phase is formed. A ferromagnetism (FM) has been observed for all the samples at and below the room temperature. In other words, the room temperature results of (M–H) curves show that the FM observed is intrinsic for all the Ni-doped ZnO samples. However, the saturated magnetizations decrease gradually with increasing Ni concentration. This indicates that, in addition to FM, the excessive doping of Ni in ZnO also causes an antiferromagnetic (AFM) contribution which increases with increasing Ni amount. This result is also supported by the magnetization against temperature measurements. Furthermore, the trend of the ac-susceptibility (χ) versus temperature curves, measured under an ac-magnetic field of 100 Oe, also support our conclusion about the antiferromagnetic contribution to ferromagnetism in our samples.     

Reflective light modulator based on epsilon-GaSe crystal

We report the results of investigating a low-voltage, polarization-insensitive, reflective-type modulator based on an epsilon-GaSe crystal and operated at the 1.960-eV line of a He-Ne laser. We demonstrate that the modulation in an Al-epsilon-GaSe-Cu device results mainly from the Franz-Keldysh effect. Relatively high speed and low operating voltage could make these modulators with Schottky-barrier contacts attractive devices in the red range of the spectrum.     

Automated adaptive 3D forming simulation processes

In this study, an automated adaptive mesh control scheme, based on local mesh modifications, is developed for the finite element simulations of 3D metal-forming processes. Error indicators are used to control the mesh discretization errors, and an h-adaptive procedure is conducted. The mesh size field used in the h-adaptive procedure is processed to control the discretization and geometric approximation errors of the evolving workpiece mesh. Industrial problems are investigated to demonstrate the capabilities of the developed scheme.     

Detection of seizures from small samples using nonlinear dynamicsystem theory

The electroencephalogram (EEG), like many other biological phenomena, is quite likely governed by nonlinear dynamics. Certain characteristics of the underlying dynamics have recently been quantified by computing the correlation dimensions (D₂) of EEG time series data. In this paper, D₂ of the unbiased autocovariance function of the scalp EEG data was used to detect electrographic seizure activity. Digital EEG data were acquired at a sampling rate of 200 Hz per channel and organized in continuous frames (duration 2.56 s, 512 data points). To increase the reliability of D₂ computations with short duration data, raw EEG data were initially simplified using unbiased autocovariance analysis to highlight the periodic activity that is present during seizures. The D₂ computation was then performed from the unbiased autocovariance function of each channel using the Grassberger-Procaccia method with Theiler's box-assisted correlation algorithm. Even with short duration data, this preprocessing proved to be computationally robust and displayed no significant sensitivity to implementation details such as the choices of embedding dimension and box size. The system successfully identified various types of seizures in clinical studies