Fruit fly optimization based least square support vector regression for blind image restoration

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.

Download Full-text

Hybrid Machine Learning Model of Support Vector Machine and Fruit Fly Optimization Algorithm for Prediction of Remaining Service Life of Flexible Pavement

10.20944/preprints201910.0238.v1 ◽

2019 ◽

Author(s):

Nader Karballaeezadeh ◽

Adrienn Dineva ◽

Amir Mosavi ◽

Narjes Nabipour ◽

Shahaboddin Shamshirband ◽

...

Keyword(s):

Service Life ◽

Support Vector Regression ◽

Optimization Algorithm ◽

Fruit Fly ◽

Flexible Pavement ◽

Support Vector ◽

Fruit Fly Optimization Algorithm ◽

Fruit Fly Optimization ◽

Remaining Service Life ◽

Non Destructive

Remaining service life (RSL) of pavement, as a sign of future pavement performance, has always received growing attention from pavement engineers. The RSL describes the time from the moment of pavement inspection until such a time when a major repair or reconstruction is required. The conventional approach to determining RSL involves using non-destructive tests. These tests, in addition to being costly, interfere with traffic flow and compromise users' safety. In this paper, surface distresses of pavement have been used to estimate the pavement’s RSL in order to eliminate the aforementioned problems and challenges. To implement the proposed theory, 105 flexible pavement segments were taken from Shahrood-Damghan Highway (Highway 44) in Iran. For each pavement segment, the type, severity, and extent of surface damage and pavement condition index (PCI) were determined. The pavement RSL was then estimated using non-destructive tests include Falling Weight Deflectometer (FWD) and Ground Penetrating Radar (GPR). After completing the dataset, the modeling was conducted to predict RSL using three techniques include Support Vector Regression (SVR), Support Vector Regression Optimized by Fruit Fly Optimization Algorithm (SVR-FOA), and Gene Expression Programming (GEP). All three techniques estimated the RSL of the pavement by selecting the PCI as input. The Correlation Coefficient (CC), Nash-Sutcliffe efﬁciency (NSE), Scattered Index (SI), and Willmott’s Index of agreement (WI) criteria were used to examine the performance of the three techniques adopted in this study. In the end, it was found that GEP with values of 0.874, 0.598, 0.601, and 0.807 for CC, SI, NSE, and WI criteria, respectively, had the highest accuracy in predicting the RSL of pavement.

Download Full-text

Support Vector Regression Integrated with Fruit Fly Optimization Algorithm for River Flow Forecasting in Lake Urmia Basin

10.20944/preprints201905.0361.v1 ◽

2019 ◽

Author(s):

Saeed Samadianfard ◽

Salar Jarhan ◽

Ely Salwana ◽

Amir Mosavi ◽

Shahaboddin Shamshirband

Keyword(s):

Support Vector Regression ◽

Optimization Algorithm ◽

River Flow ◽

Fruit Fly ◽

Support Vector ◽

Fruit Fly Optimization Algorithm ◽

Lake Urmia ◽

River Flows ◽

Fruit Fly Optimization ◽

River Flow Forecasting

Adequate knowledge about the development and operation of the components of water systems is of high importance in order to optimize them. For this reason, forecasting of future events becomes greatly significant due to making the appropriate decision. Moreover, operational river management severely depends on accurate and reliable flow forecasts. In this regard, current study inspects the accuracy of support vector regression (SVR), and SVR regulated with fruit fly optimization algorithm (FOASVR) and M5 model tree (M5), in river flow forecasting. Monthly data of river flow in two stations of the Lake Urmia Basin (Vaniar and Babarud stations on the Aji Chay and the Barandouz Rivers) were utilized in the current research. Additionally, the influence of periodicity (π) on the forecasting enactment was examined. To assess the performance of mentioned models, different statistical meters were implemented, including root mean squared error (RMSE), mean absolute error (MAE), correlation coefficient (R), and Bayesian information criterion (BIC). Results showed that the FOASVR with RMSE (4.36 and 6.33 m3/s), MAE (2.40 and 3.71 m3/s) and R (0.82 and 0.81) values had the best performances in forecasting river flows in Babarud and Vaniar stations, respectively. Also, regarding BIC parameters, Qt-1 and π were selected as parsimonious inputs for predicting river flow one month ahead. Overall findings indicated that, although both FOASVR and M5 predicted the river flows in suitable accordance with observed river flows, the performance of FOASVR was moderately better than the M5 and periodicity noticeably increased the performances of the models; consequently, FOASVR can be suggested as the accurate method for forecasting river flows.

Download Full-text

Support vector regression with fruit fly optimization algorithm for seasonal electricity consumption forecasting

Energy ◽

10.1016/j.energy.2016.09.065 ◽

2016 ◽

Vol 115 ◽

pp. 734-745 ◽

Cited By ~ 63

Author(s):

Guohua Cao ◽

Lijuan Wu

Keyword(s):

Support Vector Regression ◽

Optimization Algorithm ◽

Electricity Consumption ◽

Fruit Fly ◽

Support Vector ◽

Fruit Fly Optimization Algorithm ◽

Fruit Fly Optimization

Download Full-text

Support Vector Regression Integrated with Fruit Fly Optimization Algorithm for River Flow Forecasting in Lake Urmia Basin

Water ◽

10.3390/w11091934 ◽

2019 ◽

Vol 11 (9) ◽

pp. 1934 ◽

Cited By ~ 14

Author(s):

Saeed Samadianfard ◽

Salar Jarhan ◽

Ely Salwana ◽

Amir Mosavi ◽

Shahaboddin Shamshirband ◽

...

Keyword(s):

Machine Learning ◽

Support Vector Regression ◽

Optimization Algorithm ◽

River Flow ◽

Fruit Fly ◽

Support Vector ◽

Fruit Fly Optimization Algorithm ◽

River Flows ◽

Fruit Fly Optimization ◽

Flow Prediction

Advancement in river flow prediction systems can greatly empower the operational river management to make better decisions, practices, and policies. Machine learning methods recently have shown promising results in building accurate models for river flow prediction. This paper aims to identify models with higher accuracy, robustness, and generalization ability by inspecting the accuracy of a number of machine learning models. The proposed models for river flow include support vector regression (SVR), a hybrid of SVR with a fruit fly optimization algorithm (FOA) (so-called FOASVR), and an M5 model tree (M5). Additionally, the influence of periodicity (π) on the forecasting enactment was examined. To assess the performance of the proposed models, different statistical meters were implemented, including root mean squared error (RMSE), mean absolute error (MAE), correlation coefficient (R), and Bayesian information criterion (BIC). Results showed that the FOASVR with RMSE (4.36 and 6.33 m3/s), MAE (2.40 and 3.71 m3/s) and R (0.82 and 0.81) values had the best performance in forecasting river flows at Babarud and Vaniar stations, respectively. Also, regarding BIC parameters, Qt−1 and π were selected as parsimonious inputs for predicting river flow one month ahead. Overall findings indicated that, although both the FOASVR and M5 predicted the river flows in suitable accordance with observed river flows, the performance of the FOASVR was moderately better than the M5 and periodicity noticeably increased the performance of the models; consequently, FOASVR can be suggested as the most accurate method for forecasting river flows.

Download Full-text