A Bayesian Regularized Neural Network for Analyzing Bitcoin Trends

Classification of data on stacked autoencoder using modified sigmoid activation function

A Neural Network is one of the techniques by which we classify data. In this paper, we have proposed an effectively stacked autoencoder with the help of a modified sigmoid activation function. We have made a two-layer stacked autoencoder with a modified sigmoid activation function. We have compared our autoencoder to the existing autoencoder technique. In the existing autoencoder technique, we generally use the logsigmoid activation function. But in multiple cases using this technique, we cannot achieve better results. In that case, we may use our technique for achieving better results. Our proposed autoencoder may achieve better results compared to this existing autoencoder technique. The reason behind this is that our modified sigmoid activation function gives more variations for different input values. We have tested our proposed autoencoder on the iris, glass, wine, ovarian, and digit image datasets for comparison propose. The existing autoencoder technique has achieved 96% accuracy on the iris, 91% accuracy on wine, 95.4% accuracy on ovarian, 96.3% accuracy on glass, and 98.7% accuracy on digit (image) dataset. Our proposed autoencoder has achieved 100% accuracy on the iris, wine, ovarian, and glass, and 99.4% accuracy on digit (image) datasets. For more verification of the effeteness of our proposed autoencoder, we have taken three more datasets. They are abalone, thyroid, and chemical datasets. Our proposed autoencoder has achieved 100% accuracy on the abalone and chemical, and 96% accuracy on thyroid datasets.

Neural network with NewSigmoid activation function

We increase the power of the Artificial Neural Networks with the help of the Activation Function (AF). The tansig and logsig are widely used AF. But there is still requires some improvement in the AF. So, in this paper, we have proposed a NewSigmoid AF in the neural network. NewSigmoid is also as powerful as tansig and logsig. In multiple cases, the NewSigmoid function gives a better or equivalent performance as compared with both these AF. Like these AF, NewSigmoid is also a smooth S-shape, bounded, continuously differentiable, and zero-centered function. Therefore the NewSigmoid is also suitable for solving non-linear problems. We have tested this AF on iris, cancer, glass, chemical, bodyfat, wine, and ovarian datasets. We use Scaled Conjugate Gradient (SCG), Levenberg-Marquardt (LM), and Bayesian Regularization (BR) algorithms during the optimization of the neural network. Maximum 100% accuracy in the iris dataset while using LM, and BR; 99.9% accuracy in the cancer dataset using BR; 100% accuracy in the glass dataset using BR; 100% accuracy in the chemical and bodyfat dataset using SCG, LM, and BR; 100% accuracy in the wine dataset using LM, and BR; and 99.1% accuracy in the ovarian dataset using BR has been found while working with multilayer neural networks. The NewSigmoid also achieves 100% training and validation accuracy on the mathework-cap image dataset using SCG.

Self-organizing Maps and Bayesian Regularized Neural Network for Analyzing Gasoline and Diesel Price Drifts

Any nation’s growth depends on the trend of the price of fuel. The fuel price drifts have both direct and indirect impacts on a nation’s economy. Nation’s growth will be hampered due to the higher level of inflation prevailing in the oil industry. This paper proposed a method of analyzing Gasoline and Diesel Price Drifts based on Self-organizing Maps and Bayesian regularized neural networks. The US gasoline and diesel price timeline dataset is used to validate the proposed approach. In the dataset, all grades, regular, medium, and premium with conventional, reformulated, all formulation of gasoline combinations, and diesel pricing per gallon weekly from 1995 to January 2021, are considered. For the data visualization purpose, we have used self-organizing maps and analyzed them with a neural network algorithm. The nonlinear autoregressive neural network is adopted because of the time series dataset. Three training algorithms are adopted to train the neural networks: Levenberg-Marquard, scaled conjugate gradient, and Bayesian regularization. The results are hopeful and reveal the robustness of the proposed model. In the proposed approach, we have found Levenberg-Marquard error falls from − 0.1074 to 0.1424, scaled conjugate gradient error falls from − 0.1476 to 0.1618, and similarly, Bayesian regularization error falls in − 0.09854 to 0.09871, which showed that out of the three approaches considered, the Bayesian regularization gives better results.