Predicting Stock Market Price Using Neural Network Model

The present article predicts the movement of daily Indian stock market (S&P CNX Nifty) price by using Feedforward Neural Network Model over a period of eight years from January 1st 2008 to April 8th 2016. The prediction accuracy of the model is accessed by normalized mean square error (NMSE) and sign correctness percentage (SCP) measure. The study indicates that the predicted output is very close to actual data since the normalized error of one-day lag is 0.02. The analysis further shows that 60 percent accuracy found in the prediction of the direction of daily movement of Indian stock market price after the financial crises period 2008. The study indicates that the predictive power of the feedforward neural network models reasonably influenced by one-day lag stock market price. Hence, the validity of an efficient market hypothesis does not hold in practice in the Indian stock market. This article is quite useful to the investors, professional traders and regulators for understanding the effectiveness of Indian stock market to take appropriate investment decision in the stock market.

Artificial Neural Network Model Prediction of Bitumen/Light Oil Mixture Viscosity under Reservoir Temperature and Pressure Conditions as a Superior Alternative to Empirical Models

Herein, we show the prediction of the viscosity of a binary mixture of bitumen and light oil using a feedforward neural network with backpropagation model, as compared to empirical models such as the reworked van der Wijk model (RVDM), modified van der Wijk model (MVDM), and Al-Besharah. The accuracy of the ANN was based on all of the samples, while that of the empirical models was analyzed based on experimental results obtained from rheological studies of three binary mixtures of light oil (API 32°) and bitumen (API 7.39°). The classical Mehrotra–Svrcek model to predict the viscosity of bitumen under temperature and pressure, which estimated bitumen results with an %AAD of 3.86, was used along with either the RVDM or the MVDM to estimate the viscosity of the bitumen and light oil under reservoir temperature and pressure conditions. When both the experimental and literature data were used for comparison to an artificial neural network (ANN) model, the MVDM, RVDM and Al-Besharah had higher R2 values.

Using the modified k-mean algorithm with an improved teaching-learning-based optimization algorithm for feedforward neural network training

In this paper we proposed a novel procedure for training a feedforward neural network. The accuracy of artificial neural network outputs after determining the proper structure for each problem depends on choosing the appropriate method for determining the best weights, which is the appropriate training algorithm. If the training algorithm starts from a good starting point, it is several steps closer to achieving global optimization. In this paper, we present an optimization strategy for selecting the initial population and determining the optimal weights with the aim of minimizing neural network error. Teaching-learning-based optimization (TLBO) is a less parametric algorithm rather than other evolutionary algorithms, so it is easier to implement. We have improved this algorithm to increase efficiency and balance between global and local search. The improved teaching-learning-based optimization (ITLBO) algorithm has added the concept of neighborhood to the basic algorithm, which improves the ability of global search. Using an initial population that includes the best cluster centers after clustering with the modified k-mean algorithm also helps the algorithm to achieve global optimum. The results are promising, close to optimal, and better than other approach which we compared our proposed algorithm with them.

A 24-sectors direct power control-feedforward neural network method of DFIG integrated to dual-rotor wind turbine

<p class="Abstract">In this work, a 24-sector direct power control (24-sector DPC) of a doubly-fed induction generator (DFIG) based dual-rotor wind turbine (DRWT) is studied. The major disadvantage of the 24-DPC control is the steady-state ripples in reactive and active powers. The use of 24 sectors of rotor flux, a feedforward neural network (FNN) algorithm is proposed to improve traditional 24-sector DPC performance and minimize significantly harmonic distortion (THD) of stator current and reactive/active power ripple. The proposed method is modeled and simulated by using MATLAB/Simulink software under different tests and compared with conventional 24-sector DPC.</p>

Estimation of Depth of Discharge of Li-ion Battery Using Neural Network

This paper deals with the estimation of depth of discharge for Li-ion batteries. Estimation is based on the knowledge of discharging curves measured for discrete values of loading currents. The estimator of the depth of discharge is a form of feedforward neural network which is trained with the measured data of discharge curves. Accuracy of estimation of the depth of discharge is shown for arbitrary generated and measured loading characteristics, where the depth of discharge is estimated by the designed neural network and measured by using the Coulomb counting method.

Generalised Regression Neural Network (GRNN) Architecture-Based Motion Planning and Control of an E-Puck Robot in V-REP Software Platform

This article focuses on the motion planning and control of an automated differential-driven two-wheeled E-puck robot using Generalized Regression Neural Network (GRNN) architecture in the Virtual Robot Experimentation Platform (V-REP) software platform among scattered obstacles. The main advantage of this GRNN over the feedforward neural network is that it provides accurate results in a short period with minimal error. First, the designed GRNN architecture receives real-time obstacle information from the Infra-Red (IR) sensors of an E-puck robot. According to IR sensor data interpretation, this architecture sends the left and right wheel velocities command to the E-puck robot in the V-REP software platform. In the present study, the GRNN architecture includes the MIMO system, i.e., multiple inputs (IR sensors data) and multiple outputs (left and right wheel velocities). The three-dimensional (3D) motion and orientation results of the GRNN architecture-controlled E-puck robot are carried out in the V-REP software platform among scattered and wall-type obstacles. Further on, compared with the feedforward neural network, the proposed GRNN architecture obtains better navigation path length with minimum error results.