A new hybrid method with data‑characteristic‑driven analysis for artificial intelligence and robotics index return forecasting

Forecasting returns for the Artificial Intelligence and Robotics Index is of great significance for financial market stability,and the development of the artificial intelligence industry.To provide investors with a more reliable reference in terms of artificial intelligence index investment,this paper selects the NASDAQ CTA Artificial Intelligence and Robotics(AIRO)Index as the research target,and proposes innovative hybrid methods to forecast returns by considering its multiple structural characteristics.Specifically,this paper uses the ensemble empirical mode decomposition(EEMD)method and the modified iterative cumulative sum of squares(ICSS)algorithm to decompose the index returns and identify the structural breakpoints.Furthermore,it combines the least-square support vector machine approach with the particle swarm optimization method(PSO-LSSVM)and the generalized autoregressive conditional heteroskedasticity(GARCH)type models to construct innovative hybrid forecasting methods.On the one hand,the empirical results indicate that the AIRO index returns have complex structural characteristics,and present time-varying and nonlinear characteristics with high complexity and mutability;on the other hand,the newly proposed hybrid forecasting method(i.e.,the EEMD-PSO-LSSVM-ICSS-GARCH models)which considers these complex structural characteristics,can yield the optimal forecasting performance for the AIRO index returns.

Optimization of fused deposition modeling process parameters using a fuzzy inference system coupled with Taguchi philosophy

Fused deposition modeling （FDM） is an additive manufacturing technique used to fabricate intricate parts in 3D, within the shortest possible time without using tools, dies, fixtures, or human intervention. This article empiri- cally reports the effects of the process parameters, i.e., the layer thickness, raster angle, raster width, air gap, part orientation, and their interactions on the accuracy of the length, width, and thicknes, of acrylonitrile-butadiene- styrene （ABSP 400） parts fabricated using the FDM tech- nique. It was found that contraction prevailed along the directions of the length and width, whereas the thickness increased from the desired value of the fabricated part. Optimum parameter settings to minimize the responses, such as the change in length, width, and thickness of the test specimen, have been determined using Taguchi＇s parameter design. Because Taguchi＇s philosophy fails to obtain uniform optimal factor settings for each response, in this study, a fuzzy inference system combined with the Taguchi philosophy has been adopted to generate a single response from three responses, to reach the specific target values with the overall optimum factor level settings. Further, Taguchi and artificial neural network predictive models are also presented in this study for an accuracy evaluation within the dimensions of the FDM fabricated parts, subjected to various operating conditions. The pre- dicted values obtained from both models are in good agreement with the values from the experiment data, with mean absolute percentage errors of 3.16 and 0.15, respectively. Finally, the confirmatory test results showed an improvement in the multi-response performance index of 0.454 when using the optimal FDM parameters over the initial values.