Search results

The stock indexes are an important issue for investors, and in this paper good trading strategies will be aimed to be adopted according to the accurate prediction of the stock indexes to chase high returns.

To avoid the problem of insufficient financial data for daily stock indexes prediction during modeling, a data augmentation method based on time scale transformation (DATT) was introduced. After that, a new deep learning model which combined DATT and NGRU (DATT-nested gated recurrent units (NGRU)) was proposed for stock indexes prediction. The proposed models and their competitive models were used to test the stock indexes prediction and simulated trading in five stock markets of China and the United States.

The experimental results demonstrated that both NGRU and DATT-NGRU outperformed the other recurrent neural network (RNN) models in the daily stock indexes prediction.

A novel RNN with NGRU and data augmentation is proposed. It uses the nested structure to increase the depth of the deep learning model.

The purpose of this paper is to develop an interval method for vehicle allocation and route planning in case of an evacuation.

First, the evacuation route planning system is described and the notations are defined. An inexact programming model is proposed. The goal of the model is to achieve optimal planning of vehicles allocation with a minimized system time under the condition of inexact information. The constraints of the model include four types: number of vehicles constraint, passengers balance constraints, maximum capacity of links constraints and no negative constraints. The model is solved through the decomposition of the inexact model. A hypothetical case is developed to illustrate the proposed model.

The paper finds that the interval solutions are feasible and stable for evacuation model in the given decision space, and this may reduce the negative effects of uncertainty, thereby improving evacuation managers' estimates under different conditions.

This method entails incorporation of uncertainties existing as interval values into model formulation and solution procedure, and application of the developed model and the related solution algorithm in a hypothetical case study.

This paper aims to study the frictional performance of reciprocating pair with high velocity by using hydrodynamic lubrication principle and fish scale textured piston model.

Based on the idea of function characteristic approximation and coordinate change, a mathematical representation model of imitating fish scale texture pit section is established. According to the principle of dynamic pressure lubrication of the textured fluid, a three-dimensional numerical model of flow field for fish scale texture is established without considering cavitation. Numerical analysis of the model carp scale texture unit by orthogonal experimental design and FLUENT software is carried out.

Effects of fish scale pit texture on friction properties for a reciprocating pair piston surface with high velocity (impact piston) are acquired. Effects of texture characterization parameters and flow rate on the surface friction performance for impact piston are found. Effects of different characteristic parameters combination of imitating fish scale texture on friction performance for impact piston surface are obtained.

The model is an effective tool to study the friction and wear of reciprocating pair with high velocity. The effects of fish scale textured piston pair supply a theory lead to design the reciprocating pair with better friction performance.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-09-2019-0398

The purpose of this paper is to present an efficient model for project buffer sizing by taking failure mode and effects analysis (FMEA) into account to reach a more realistic schedule.

In the first phase of the project, several turbines were installed according to the primary schedule with an average duration of 142 days. Then, some of critical chain project management algorithms were separately applied in the implementation and installation of the other wind turbines. The adaptive procedure with resource tightness (APRT) method turned out to be the best method in terms of obtaining a more realistic schedule in this case study. Finally, FMEA was simultaneously applied with APRT.

Applying the hybrid method to the scheduling of the wind turbines, yielded the more realistic schedule than traditional.

The proposed hybrid APRT-FMEA algorithm was implemented on a real wind farm construction project which was completed with 37 percent shorter duration than the initial estimation; in spite of the initial estimation of 142 days, the project completed in 103 days.

Introducing and implementing a new algorithm which is a combination of buffer sizing algorithms and one of the well-known and mostly used risk assessment methods in order to provide the more realistic project schedule in the construction of wind turbines.

Introducing and implementing a novel algorithm which is a combination of conventional buffer sizing method and one of the efficient risk assessment methods in order to make the schedule more realistic.