No abstract

Abstract-In this paper, we provide a robust forecasting model to predict phone prices in European markets using Long Short-Term Memory (LSTM) neural network and Support Vector Regression (SVR). We propose a comparison study of time series forecasting models for these two techniques. LSTM, due to its architecture, is considered as the perfect solution to problems not resolvable by classic Recurrent Neural Networks (RNNs). On the other hand, Support Vector Machines (SVMs) are a very powerful machine learning method for both classification and regression. After studying and comparing several univariate models, SVR and LSTM neural networks appear to be the most accurate ones. In addition, we compared multivariate models for both these techniques. Considering the multivariate approach, by introducing more variables, we obtain better prediction performance. In fact, the SVR model is able to predict the next day price with an root mean squared error (RMSE) of 33.43 euros with the univariate model. However, using multivariate models, LSTM RNN gives the most accurate prediction for the next day's price with an RMSE of 23.640 euros.Index Terms-Time series forecasting, LSTM neural network, support vector regression, e-commerce data, machine learning, deep learning.

No abstract

This communication presents a novel approach to contour segmentation of Computed Tomography (CT) images. Image segmentation is achieved by means of the snake algorithm and the dynamic programming (DP) optimization technique. Based upon the edge preserving gradient vector flow (EPGVF) field, a new strategy for contour points initialization and splitting is presented. Contour initialization is carried out from EPGVF magnitude thresholding. In the multi-object image segmentation, the delineation of all the image objects is done through the splitting of the contour at the divergent points in the image. The proposed technique can attain a good solution without the need of an operator intervention. Some experiences on synthetic and CT medical images show that the proposed algorithm gives good results.

No abstract