Training Back-Propagation Neural Network Using Hybrid Fruit Fly Optimization Algorithm

2016 ◽  
Vol 13 (5) ◽  
pp. 3212-3221 ◽  
Author(s):  
Fei Cai ◽  
Jian Cui ◽  
Bing Dong ◽  
Jin Li ◽  
Xiaoming Li
Keyword(s):  
Neural Network ◽  
Optimization Algorithm ◽  
Back Propagation ◽  
Fruit Fly ◽  
Back Propagation Neural Network ◽  
Fruit Fly Optimization Algorithm ◽  
Fruit Fly Optimization

scholarly journals Determinants of Tourism Stocks During the COVID-19: Evidence From the Deep Learning Models

2021 ◽  
Vol 9 ◽  
Author(s):  
Wen-Tsao Pan ◽  
Qiu-Yu Huang ◽  
Zi-Yin Yang ◽  
Fei-Yan Zhu ◽  
Yu-Ning Pang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Stock Returns ◽  
Optimization Algorithm ◽  
Prediction Models ◽  
Back Propagation ◽  
Fruit Fly ◽  
Back Propagation Neural Network ◽  
Fruit Fly Optimization Algorithm ◽  
Learning Models ◽  
Fruit Fly Optimization

This paper examines the determinants of tourism stock returns in China from October 25, 2018, to October 21, 2020, including the COVID-19 era. We propose four deep learning prediction models based on the Back Propagation Neural Network (BPNN): Quantum Swarm Intelligence Algorithms (QSIA), Quantum Step Fruit-Fly Optimization Algorithm (QSFOA), Quantum Particle Swarm Optimization Algorithm (QPSO) and Quantum Genetic Algorithm (QGA). Firstly, the rough dataset is used to reduce the dimension of the indices. Secondly, the number of neurons in the multilayer of BPNN is optimized by QSIA, QSFOA, QPSO, and QGA, respectively. Finally, the deep learning models are then used to establish prediction models with the best number of neurons under these three algorithms for the non-linear real stock returns. The results indicate that the QSFOA-BPNN model has the highest prediction accuracy among all models, and it is defined as the most effective feasible method. This evidence is robust to different sub-periods.

A Mutual Fund Investment Method Using Fruit Fly Optimization Algorithm and Neural Network

2014 ◽  
Vol 571-572 ◽  
pp. 318-325 ◽  
Author(s):  
Tsu Hua Huang ◽  
Yung Ho Leu
Keyword(s):  
Neural Network ◽  
Mutual Funds ◽  
Optimization Algorithm ◽  
Mutual Fund ◽  
Fruit Fly ◽  
Fruit Fly Optimization Algorithm ◽  
Fruit Fly Optimization ◽  
Asset Value ◽  
Net Asset Value ◽  
Fund Portfolio

This paper presents a method to construct a profitable portfolio of mutual funds for investors. This method comprises two stages. In the first stage, the DEA, Sharpe and Treynor indices of mutual funds and the monthly rates of return (ROR) of mutual funds are used to select a mutual fund portfolio. In the second stage, the linear regression model, the Fruit Fly Optimization Algorithm (FOA) and the General Regression Neural Network (GRNN) are used to construct a prediction model for the net asset values of each of the constituent mutual funds of the portfolio. The trade decision of a selected mutual fund is then made based on the rise or fall of its net asset value. The empirical results showed that, compared to other combinations, the combination of using Sharpe index for portfolio selection and the GRNN optimized with FOA for net asset value prediction offered the best accumulated return rate for the mutual fund portfolio investment.

Prediction Research on the Failure of Steam Turbine Based on Fruit Fly Optimization Algorithm Support Vector Regression

2012 ◽  
Vol 614-615 ◽  
pp. 409-413 ◽  
Author(s):  
Zhi Biao Shi ◽  
Ying Miao
Keyword(s):  
Neural Network ◽  
Support Vector Regression ◽  
Optimization Algorithm ◽  
Optimal Solution ◽  
Fruit Fly ◽  
Support Vector ◽  
Fruit Fly Optimization Algorithm ◽  
Global Optimal Solution ◽  
Fruit Fly Optimization ◽  
Global Optimal

In order to solve the blindness of the parameter selection in the Support Vector Regression (SVR) algorithm, we use the Fruit Fly Optimization Algorithm (FOA) to optimize the parameters in SVR, and then propose the optimization algorithm on the parameters in SVR based on FOA to fitting and simulate the experimental data of the turbine’s failures. This algorithm could optimize the parameters in SVR automatically, and achieve ideal global optimal solution. By comparing with the commonly used methods such as Support Vector Regression and Radial Basis Function neural network, it can be shown that the forecast results of FOA_SVR more accurate and the forecast speed is the fastest.

Sign in / Sign up

Export Citation Format

Share Document