Ilija Svalina

An adaptive network-based fuzzy inference system (ANFIS) for the forecasting: The case of close price indices

The close price prediction model of the Zagreb Stock Exchange Crobex(R) index is presented in this paper. For the input/output data plan modeling the Crobex(R) index close price historical data are retrieved from the Zagreb Stock Exchange official internet pages. The prediction model is created in the way that for each of 5days in advance it predicts the Crobex(R) close price. The prediction model is generated based on the input/output data plan by means of the adaptive neuro-fuzzy inference system method, representing the fuzzy inference system. It is of the essence to point out that for each day a separate fuzzy inference system is created by means of the adaptive neuro-fuzzy inference system method based on the same set of input/output data, the only difference being that for every separate fuzzy inference system different subsets for training and checking are used so that input variables are differently created. The input/output data set represents the historical data of the Crobex(R) index close price from 4 November 2010 to 24 January 2012 and the Crobex(R) index close price is predicted for the subsequent 5days, the first day of prediction being 25 January 2012. After that the above mentioned input/output data set is shifted 5days in advance and the Crobex(R) index close price is predicted in advance for the next 5days starting with the last day of the input/output data set. In that way the Crobex(R) index close prices are predicted until 19 October 2012 based on the Crobex(R) index close price historical data. At the end of the paper qualitative and quantitative estimates are presented for the given approach of predicting the Crobex(R) index close price showing that the approach is useful for predicting within its limits.

MACHINED SURFACE ROUGHNESS PREDICTION USING ADAPTIVE NEUROFUZZY INFERENCE SYSTEM

This work considers the effect of the depth of cut, feed, and number of revolutions on the roughness of the machined surface. The results obtained by experimentally investigating the workpiece “diving manifold” were used to model the input/output data plan for the adaptive neurofuzzy inference system (ANFIS). Those data were used to generate a fuzzy inference system that made it possible to predict the output (surface roughness) based on the given inputs (feed, number of revolutions, and depth of cut). The surface roughness results obtained by the fuzzy inference system (FIS) were compared with the surface roughness results obtained by neural networks, moving linear least square method and moving linear least absolute deviation method on the same set of experimental data. These methods and systems for prediction of surface roughness are helpful when solving practical technological problems in a manufacturing process, first by determining the cutting parameter values that will add to the demanded quality of a product, and later when optimizing the technological process.

Estimation of Machining Time for CNC Manufacturing using Neural Computing

An approach to solving the problem of machining time estimation in production of complex products within CNC machining systems is presented in the paper. Heuristic analysis of the process is used to define the attributes of influence to machining time. For the problem of estimating machining time the following „Neural Computing techniques“ are used: Back-Propagation Neural Network, Modular Neural Network, Radial Basis Function Neural Network, General Regression Neural Network and Self-Organizing Map Neural Network. Real data from the technological process obtained by measuring are used to design the model used in investigation. The established model is used to carry out the investigation aimed at learning and testing different algorithms of neural networks and the results are given by the RMS error. The best results in the validation phase were achieved by Modular Neural Network (RMSE: 1.89 %) and Back-Propagation Neural Network (RMSE: 2.03 %) while the worst results were achieved by Self-Organizing Map Neural Network (RMSE: 10.05 %). (Received in January 2016, accepted in June 2016. This paper was with the authors 3 months for 1 revision.)