Search

Bridges are playing a major role in the socio-economic development of any country over the world. Suspension bridges are one of the most sensitive structures to various external influences and loads. Therefore, the need for structural monitoring system, maintenance and deformation prediction for these types of structures is important and vital. Time of observations for the purpose of structural deformation can vary from a few hours, days to several months or even years. This paper investigates the performance of several soft computing techniques for point displacement modeling using GNSS technique during the process of monitoring the structural deformation of suspension highway bridge, taking into consideration the effect of wind, temperature, humidity and traffic loads during the operational and short-term measurements. Due to the availability of a large amount of positions data generated from GNSS data positions for monitoring the deformation of such structure, artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS) should be chosen. One of the main objectives of this paper is to investigate the optimum predictive soft computing model for processing GNSS positions and points displacement prediction. Several mathematical models and two cases of data amount (66.67% and 50% of all available data) for dynamic and kinematic state are applied and compared for prediction of suspension bridge displacement with confidence interval with a probability ρ = 0.95, Δ = ± 2σ. The resulting point displacement values by applying ANNs and ANFIS, which used a confidence interval with a probability of ρ = 0.95, Δ = ± 2σ when using 66.67% of all data, are more accurate and reliable than any other applied methods, and therefore, ANNs and ANFIS can provide a significant improvement of understanding and predicting the structure deformation values where conventional mathematical modeling techniques were not as accurate or capable especially in dynamic prediction of displacements. [ABSTRACT FROM AUTHOR]

The soft computing models used for predicting land surface temperature (LST) changes are very useful to evaluate and forecast the rapidly changing climate of the world. In this study, four soft computing techniques, namely, multivariate adaptive regression splines (MARS), wavelet neural network (WNN), adaptive neurofuzzy inference system (ANFIS), and dynamic evolving neurofuzzy inference system (DENFIS), are applied and compared to find the best model that can be used to predict the LST changes of Beijing area. The topographic change is considered in this study to accurately predict LST; furthermore, Landsat 4/5 TM and Landsat 8OLI_TIRS images for four years (1995, 2004, 2010, and 2015) are used to study the LST changes of the research area. The four models are assessed using statistical analysis, coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) in the training and testing stages, and MARS is used to estimate the important variables that should be considered in the design models. The results show that the LST for the studied area increases by 0.28°C/year due to the urban changes in the study area. In addition, the topographic changes and previously recorded temperature changes have a significant influence on the LST prediction of the study area. Moreover, the results of the models show that the MARS, ANFIS, and DENFIS models can be used to predict the LST of the study area. The ANFIS model showed the highest performances in the training (R2 = 0.99, RMSE = 0.78°C, MAE = 0.55°C) and testing (R2 = 0.99, RMSE = 0.36°C, MAE = 0.16°C) stages; therefore, the ANFIS model can be used to predict the LST changes in the Beijing area. The predicted LST shows that the change in climate and urban area will affect the LST changes of the Beijing area in the future. [ABSTRACT FROM AUTHOR]