Minakhi Rout

Stock indices prediction using radial basis function neural network

Aim of the paper is to efficiently predict the stock market data for future days ahead using Radial Basis Function (RBF) neural network. DJIA and S&P 500 stock indices have been taken to simulate the RBF model and also comparison has been done with results obtained from Functional Link Artificial Neural Network(FLANN) and Multilayer Perceptron, (MLP). From the simulation result it is observed that the proposed model is giving better results than other two neural network models interms of prediction accuracy.

Efficient recognition of Odiya numerals using low complexity neural classifier

The paper develops an efficient but simple adaptive nonlinear classifier for recognition of handwritten Odiya numerals. The standard gradient and curvature features are extracted and nonlinearly mapped by sine/cosine expansions. These nonlinear inputs are fed to a low complexity classifier. The simulation results show excellent classification accuracy when test features are used.

Novel Stock Market Prediction Using a Hybrid Model of Adptive Linear Combiner and Differential Evolution

The paper proposes a novel forecasting model for efficient prediction of small and long range predictions of stock indices particularly the DJIA and S&P500. The model employs an adaptive structure containing a linear combiner with adjustable weights implemented using differential evolution. The learning algorithm using DE is dealt in details. The key features of known stock time series are extracted and used as inputs to the model for training its parameters. Exhaustive simulation study indicates that the performance of the proposed model with test input is quite satisfactory and superior to those provided by previously reported GA and PSO based forecasting models.

An artificial bee colony algorithm based efficient prediction model for stock market indices

The ABC algorithm is a new meta-heuristic approach, having the advantages of memory, multi-characters, local search, and a solution improvement mechanism. It can be used to identify a high quality optimal solution and offer a balance between complexity and performance, thus optimizing forecasting effectiveness. This paper proposes an efficient prediction model for forecasting of short and long range stock market prices of two well know stock indices, S&P 500 and DJIA using a simple adaptive linear combiner (ALC), whose weights are trained using artificial bee colony (ABC) algorithm. The Model is simulated in terms of mean square error (MSE) and extensive simulation study reveals that the performance of the proposed model with the test input patterns is more efficient, accurate than the PSO and GA based trained models.

Experimental Comparison of Sampling Techniques for Imbalanced Datasets Using Various Classification Models

Imbalanced dataset is a dataset, in which the number of samples in different classes is highly uneven, which makes it very challenging for classification, i.e., classification becomes very tough as the result may get biased by the dominating class values. But misclassification of minor class sample or interested samples is very much costlier. So to provide solution to this problem, various studies have been made out of which sampling techniques are successfully adopted to preprocess the imbalance datasets. In this paper, experimental comparison of two pioneering sampling techniques SMOTE and MWMOTE is simulated using the classification models SVM, RBF, and MLP.

TLBO Based Hybrid Forecasting Model for Prediction of Exchange Rates

The teacher-learning based optimization (TLBO) algorithm is a new meta-heuristic approach, having the ability to solve non-linear problem and free from algorithm parameters. This paper proposes an efficient prediction model for forecasting currency exchange rate in term of 1 US Dollar to Indian Rupees, Singapore Dollar and Canadian Dollar using FLANN (Functional Link Artificial Neural Network). The teaching and learning algorithm has been used to optimize the weights of the forecasting models. The mean absolute percentage error (MAPE) is used to find out the performance of the model. The performance of the model is evaluated through simulation study and the results have been compared with FLANN-PSO and FLANN-DE forecasting models. It is observed that the model gives better performance result.

Performance evaluation of protein structural class prediction using artificial neural networks

Prediction of protein structural class has been a new area of research in the scientific community in the last decade. Various approaches has been adopted and analysed. However representing the raw amino acid sequence to preserve the property of proteins has posed a great challenge. Chous pseudo amino acid composition feature representation method has fetched wide attention in this regard. In Chous representation each protein molecule is represented as the combination of amino acid composition information, the amphiphillic correlation factors and the spectral characteristics of the protein. This method preserves both the sequence order and length information of the raw amino acid sequence and this plays a significant role in prediction. A set of exhaustive simulation studies with functional link artificial network(FLANN) demonstrates high success rate of classification. The self-consistency and jackknife test on the benchmark datasets has been performed and a comparison has been done with the results of radial basis function (RBF) neural network. It indicates that the FLANN models accuracy is little less than RBF, but its complexity is very less whereas the accuracy of RBF is little higher, but its complexity is high in comparison to FLANN.