Journal of Hotel and Business Management
Open Access

Abstract

Prediction of environmental indicators in land leveling using artificial intelli- gence techniques

Isham Alzoubi

Land leveling is one of the most significant strides in soil planning and development. Despite the fact that land leveling with machines requires significant measure of vitality, it conveys a reasonable surface incline with negligible decay of the dirt and harm to plants and different living beings in the dirt. In any case, specialists during late years have attempted to decrease petroleum derivative utilization and its pernicious symptoms utilizing new procedures, for example, Artificial Neural Network (ANN),Imperialist Competitive Algorithm – ANN (ICA- ANN), and relapse and Adaptive Neuro-Fuzzy Inference System (ANFIS) and Sensitivity Analysis that will prompt a perceptible improvement in the earth. In this examination impacts of different soil properties, for example, Embankment Volume, Soil Compressibility Factor, Specific Gravity, Moisture Content, Slope, Sand Percent, and Soil Swelling Index in vitality utilization were researched. The examination was comprised of 90 examples were gathered from 3 unique areas. The lattice size was set 20 m in 20 m (20*20) from a farmland in Karaj territory of Iran. The point of this work was to decide best direct model Adaptive Neuro- Fuzzy Inference System (ANFIS) and Sensitivity Analysis so as to anticipate the vitality utilization for land leveling. As indicated by the aftereffects of Sensitivity Analysis, just three boundaries; Density, Soil Compressibility Factor and, Embankment Volume Index had critical impact on fuel utilization. As per the aftereffects of relapse, just three boundaries; Slope, Cut-Fill Volume (V) and, Soil Swelling Index (SSI) had huge impact on vitality utilization. utilizing versatile neuro-fluffy derivation framework for forecast of work vitality, fuel vitality, complete apparatus cost, and all out hardware vitality can be effectively illustrated. In correlation with ANN, all ICA-ANN models had higher exactness in forecast by their higher R2 worth and lower RMSE esteem.

Published Date: 2021-03-30; Received Date: 2021-03-16