A bat-neural network multi-agent system (BNNMAS) for stock price prediction: Case study of DAX stock price

Creating an intelligent system that can accurately predict stock price in a robust way has always been a subject of great interest for many investors and financial analysts. Predicting future trends of financial markets is more remarkable these days especially after the recent global financial crisis. So traders who access to a powerful engine for extracting helpful information throw raw data can meet the success. In this paper we propose a new intelligent model in a multi-agent framework called bat-neural network multi-agent system (BNNMAS) to predict stock price. The model performs in a four layer multi-agent framework to predict eight years of DAX stock price in quarterly periods. The capability of BNNMAS is evaluated by applying both on fundamental and technical DAX stock price data and comparing the outcomes with the results of other methods such as genetic algorithm neural network (GANN) and some standard models like generalized regression neural network (GRNN), etc. The model tested for predicting DAX stock price a period of time that global financial crisis was faced to economics. The results show that BNNMAS significantly performs accurate and reliable, so it can be considered as a suitable tool for predicting stock price specially in a long term periods.     

Design criterion for fatigue strengthening of riveted beams in a 120-year-old railway metallic bridge using pre-stressed CFRP plates

This study presents a design criterion developed for fatigue strengthening of a 120-year-old metallic railway bridge in Switzerland and presents a pre-stressed un-bonded reinforcement (PUR) system developed to apply the strengthening. The PUR system uses carbon fiber reinforced polymer (CFRP) plates; however, unlike conventional pre-stressed CFRP reinforcement methods, preparation of the existing metallic bridge surface is not required. This decreases the time required for on-site strengthening procedures. The principle of the constant life diagram (CLD) and two fatigue failure criteria (Johnson and Goodman) are described. Analytical formulations are developed based on the CLD method to determine the minimum CFRP pre-stress level required to prevent fatigue crack initiation. The PUR system uses an applied pre-stress force to reduce the mean stress level (and stress ratio) to shift an existing fatigue-susceptible metallic detail from the ‘at risk’ finite life regime to the ‘safe’ infinite life regime. The applied CLD method is particularly valuable when the stress history of the detail is not known and it is difficult to assess the remaining fatigue life. Moreover, it is shown that the currently adopted approach in many structural codes which emphasizes stress range as the dominant parameter influencing fatigue life are non-conservative for tension–tension stress patterns (i.e., stress ratios of 0 < R < 1). Analyses show that the modified Johnson formula accurately reflects the combined effect of stress range, mean stress level, and material properties, and offers a relatively easy design procedure. Details of a retrofit field application on members of a riveted wrought iron railway bridge are given. A wireless sensor network (WSN) system is used for long-term monitoring of the on-site CFRP stress levels and temperature of the retrofitted details. WSN measurements indicate that increases in ambient temperature result in increased CFRP pre-stress levels.     

Static and free vibration analysis of functionally graded plates based on a new quasi-3D and 2D shear deformation theories

In this study, two dimensional (2D) and quasi three-dimensional (quasi-3D) shear deformation theories are presented for static and free vibration analysis of single-layer functionally graded (FG) plates using a new hyperbolic shape function. The material of the plate is inhomogeneous and the material properties assumed to vary continuously in the thickness direction by three different distributions; power-law, exponential and Mori–Tanaka model, in terms of the volume fractions of the constituents. The fundamental governing equations which take into account the effects of both transverse shear and normal stresses are derived through the Hamilton's principle. The closed form solutions are obtained by using Navier technique and then fundamental frequencies are found by solving the results of eigenvalue problems. In-plane stress components have been obtained by the constitutive equations of composite plates. The transverse stress components have been obtained by integrating the three-dimensional stress equilibrium equations in the thickness direction of the plate. The accuracy of the present method is demonstrated by comparisons with the different 2D, 3D and quasi-3D solutions available in the literature.     

浅谈氯碱氢的一种深度脱水工艺

概述了氢的主要工业生产方法和实际应用,详细介绍了氯碱氢三级脱水工艺过程,并运用在线分析手段,准确显示了干燥过程中的氯碱氢水分含量变化规律。     

Nonlinear response in glass fibre non-crimp fabric reinforced vinylester composites

This paper addresses the nonlinear stress-strain response in glass fibre non-crimp fabric reinforced vinylester composite laminates subjected to in-plane tensile loading. The nonlinearity is shown to be a combination of brittle and plastic failure. It is argued that the shift from plastic to brittle behaviour in the vinylester is caused by the state of stress triaxiality caused by the interaction between fibre and vinylester. A model combining damage and plasticity is calibrated and evaluated using data from extensive experimental testing. The onset of damage is predicted using the Puck failure criterion, and the evolution of damage is calibrated from the observed softening in plies loaded in transverse tension. Shear loading beyond linear elastic response is observed to result in irreversible strains. A yield criterion is implemented for shear deformation. A strain hardening law is fitted to the stress-strain response observed in shear loaded plies. Experimental results from a selection of laminates with different layups are used to verify the numerical models. A complete set of model parameters for predicting elastic behaviour, strength and post failure softening is presented for glass fibre non-crimped fabric reinforced vinylester. The predicted behaviour from using these model parameters are shown to be in good agreement with experimental results.     

Application of higher order spectral features and support vector machines for bearing faults classification

Condition monitoring and fault diagnosis of rolling element bearings timely and accurately are very important to ensure the reliability of rotating machinery. This paper presents a novel pattern classification approach for bearings diagnostics, which combines the higher order spectra analysis features and support vector machine classifier. The use of non-linear features motivated by the higher order spectra has been reported to be a promising approach to analyze the non-linear and non-Gaussian characteristics of the mechanical vibration signals. The vibration bi-spectrum (third order spectrum) patterns are extracted as the feature vectors presenting different bearing faults. The extracted bi-spectrum features are subjected to principal component analysis for dimensionality reduction. These principal components were fed to support vector machine to distinguish four kinds of bearing faults covering different levels of severity for each fault type, which were measured in the experimental test bench running under different working conditions. In order to find the optimal parameters for the multi-class support vector machine model, a grid-search method in combination with 10-fold cross-validation has been used. Based on the correct classification of bearing patterns in the test set, in each fold the performance measures are computed. The average of these performance measures is computed to report the overall performance of the support vector machine classifier. In addition, in fault detection problems, the performance of a detection algorithm usually depends on the trade-off between robustness and sensitivity. The sensitivity and robustness of the proposed method are explored by running a series of experiments. A receiver operating characteristic (ROC) curve made the results more convincing. The results indicated that the proposed method can reliably identify different fault patterns of rolling element bearings based on vibration signals.     

基于多项式变换的参数估计方法

本文给出一种采用DPT估计SNCK信号时宽—带宽积的方法,并通过仿真该估计方法的性能与其它估计方法进行比较.首先给出SNCK信号参数估计的一般过程.为了便于计算和理论推导,根据估计出的中心频率将接收到的SNCK信号搬移到零频,从而进一步估计其它参数,如采用DPT估计SNCK信号时宽带宽积.本文将重点研究采用DPT算法估计SNCK信号值的方法.     

气液螺旋环状流压降特性研究

考虑旋流衰减的影响，对气液螺旋环状流的压降特性进行研究并推导出了螺旋环状流压降预测模型。定义压降旋-直比系数为气液两相螺旋环状流和气液两相直流的压降之比，以此来表征旋流衰减对压降的影响。基于量纲分析的方法对压降旋-直比系数进行分析，推导出其表达式，压降旋-直比系数依赖于Lockhart-Martinelli 参数和气相Froude数变化。最终，得出了气液两相螺旋环状流的压降预测模型。在50 mm内径的水平管内对螺旋环状流的压降特性进行了实验研究，其中气相表观流速变化范围为10~16 m/s，体积含液率（LVF）变化范围为0.6%~4.8%。通过与实验数据进行对比，压降预测模型的相对误差在±15%以内，为工程应用提供了参考。     

Improving the prediction of petroleum reservoir characterization with a stacked generalization ensemble model of support vector machines

The ensemble learning paradigm has proved to be relevant to solving most challenging industrial problems. Despite its successful application especially in the Bioinformatics, the petroleum industry has not benefited enough from the promises of this machine learning technology. The petroleum industry, with its persistent quest for high-performance predictive models, is in great need of this new learning methodology. A marginal improvement in the prediction indices of petroleum reservoir properties could have huge positive impact on the success of exploration, drilling and the overall reservoir management portfolio. Support vector machines (SVM) is one of the promising machine learning tools that have performed excellently well in most prediction problems. However, its performance is a function of the prudent choice of its tuning parameters most especially the regularization parameter, C. Reports have shown that this parameter has significant impact on the performance of SVM. Understandably, no specific value has been recommended for it. This paper proposes a stacked generalization ensemble model of SVM that incorporates different expert opinions on the optimal values of this parameter in the prediction of porosity and permeability of petroleum reservoirs using datasets from diverse geological formations. The performance of the proposed SVM ensemble was compared to that of conventional SVM technique, another SVM implemented with the bagging method, and Random Forest technique. The results showed that the proposed ensemble model, in most cases, outperformed the others with the highest correlation coefficient, and the lowest mean and absolute errors. The study indicated that there is a great potential for ensemble learning in petroleum reservoir characterization to improve the accuracy of reservoir properties predictions for more successful explorations and increased production of petroleum resources. The results also confirmed that ensemble models perform better than the conventional SVM implementation.