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...     

Supply chain network design using an integrated neuro-fuzzy and MILP approach: A comparative design study

In this study, an integrated supply chain (SC) design model is developed and a SC network design case is examined for a reputable multinational company in alcohol free beverage sector. Here, a three echelon SC network is considered under demand uncertainty and the proposed integrated neuro-fuzzy and mixed integer linear programming (MILP) approach is applied to this network to realize the design effectively. Matlab 7.0 is used for neuro-fuzzy demand forecasting and, the MILP model is solved using Lingo 10.0. Then Matlab 7.0 is used for artificial neural network (ANN) simulation to supply a comparative study and to show the applicability and efficiency of ANN simulation for this type of problem. By evaluating the output data, the SC network for this case is designed, and the optimal product flow between the factories, warehouses and distributors are calculated. Also it is proved that the ANN simulation can be used instead of analytical computations because of ensuring a simplified representation for this method and time saving.     

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.     

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.     

Microelectromechanical System for Controlling Flow Past an Airfoil: Pressure Transducers

A technology is developed for making single-chip diaphragm pressure sensors with polycrystalline-silicon piezoresistive elements on a monocrystalline-silicon substrate. It allows one to produce piezoresistive elements with a conductivity–temperature characteristic that neutralizes the temperature dependence of piezoresistive sensitivity. Sensors with a 1.8 × 1.8-mm² diaphragm are designed and fabricated by the above technology for pressures ranging from 1 to 10⁵ Pa, showing a maximum sensitivity of 10^–6 Pa^–1. The sensors are tested in aerodynamic experiments on monitoring the flow past a model wing of finite span at angles of attack close to the stall angle.     

Thermal pressure coefficient of a polyhedral oligomeric silsesquioxane (POSS)‐reinforced epoxy resin

The thermal pressure coefficients of a neat, unfilled, epoxy resin and a 10 wt % POSS (polyhedral oligomeric silsesquioxane)‐filled epoxy nanocomposite have been measured using a thick‐walled tube method. It is found that just below the glass transition temperature the thermal pressure coefficient is ～ 20% smaller for the polymer composite containing 10% POSS than for the neat, unfilled resin. The thermal expansion coefficient and thermal pressure coefficient of the uncured POSS itself are also reported. © 2009 Wiley Periodicals, Inc. J Appl Polym Sci, 2010     

Drying kinetics,colour, total phenolic content and antioxidant capacity properties of kiwi dried by different methods

This study analysed the convective (60, 70 and 80° C), microwave (120 and 350 W) and freeze drying methods in terms of their effects on the drying characteristics, colour, total phenolic content (TPC) and antioxidant capacity of kiwi slices. Nine different mathematical models were applied to experimental data to achieve the most accurate calculation for drying curves. The Midilli et al. and Wang and Singh models proved to be the most suitable at explaining the drying kinetics of kiwi samples as compared to other models according to the statistical tests. Each drying method was significantly affected by colour parameters (L*, a*, b*, C, α and ΔE). The dried samples exhibited respectively 5–49 % and 10–47 % less TPC and antioxidant capacity compared to the fresh sample. According to the correlation analysis conducted between TPC and antioxidant capacity for kiwi slices, there is a positive correlation (R ²  = 0.7796). Microwave dried samples at 120 W particularly had the lowest TPC and antioxidant capacity. Freeze drying method yielded the closest values with respect to colour values, total phenol content and antioxidant capacity to those of fresh samples when compared to the other methods.     

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     

Telepresence feedback and input systems for a twin armed mobilerobot

Complex tasks in unstructured/hazardous environments often require teleoperation. The telepresence robot featured here has “user friendly” limb linked output and feedback systems. The mechanism design and sensory feedback of visual, audio and multi-functional tactile (pressure, texture/slip and thermal parameters) are described