Performance evaluation of multiple adaptive regression splines, teaching–learning based optimization and conventional regression techniques in predicting mechanical properties of impregnated wood

Tiryaki, Sebahattin; Tan, Hüseyin; Bardak, Selahattin; Kankal, Murat; Nacar, Sinan; Peker, Hüseyin

doi:10.1007/s00107-019-01416-9

Cited by 16 publications

(5 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The endpoints of these splines are called knots. Partial curves formed between the two knots are called basic functions [52]. This strategy made the MARS method more advantageous and flexible than the other statistical methods in multivariate modeling studies [53].…”

Section: Multivariate Adaptive Regression Splines (Mars) Methodsmentioning

confidence: 99%

“…Following the input combination and modeling process, the MARS method was applied to identify the equations that produced the results closest to the measured LDO concentration, by using the Salford Predictive Modeler 8.0 software. Then, three different regression functions, i.e., exponential, power, and linear, were used for the TLBO and CRA methods, which were chosen to optimize the unknown coefficients (w i ) of the independent variables (x i ) [52]. The equations of exponential, power, and linear functions are given below;…”

Section: Model Development Applicationsmentioning

confidence: 99%

“…where t i is the monitored value, t is the mean of monitored values, td i is the predicted value, and N is the total number of monitored values [52]. The TLBO algorithm parameters were used for the same values for all functions employed in the study.…”

Section: Normalized Value =mentioning

confidence: 99%

See 2 more Smart Citations

Spatial Forecasting of Dissolved Oxygen Concentration in the Eastern Black Sea Basin, Turkey

Nacar

Bayram

BAKİ

et al. 2020

Water

Self Cite

View full text Add to dashboard Cite

The aim of this study was to model, as well as monitor and assess the surface water quality in the Eastern Black Sea (EBS) Basin stream, Turkey. The water-quality indicators monitored monthly for the seven streams were water temperature (WT), pH, total dissolved solids (TDS), and electrical conductivity (EC), as well as luminescent dissolved oxygen (LDO) concentration and saturation. Based on an 18-month data monitoring, the surface water quality variation was spatially and temporally evaluated with reference to the Turkish Surface Water Quality Regulation. First, the teaching–learning based optimization (TLBO) algorithm and conventional regression analysis (CRA) were applied to three different regression forms, i.e., exponential, power, and linear functions, to predict LDO concentrations. Then, the multivariate adaptive regression splines (MARS) method was employed and three performance measures, namely, mean absolute error (MAE), root means square error (RMSE), and Nash Sutcliffe coefficient of efficiency (NSCE) were used to evaluate the performances of the MARS, TLBO, and CRA methods. The monitoring results revealed that all streams showed the same trend in that lower WT values in the winter months resulted in higher LDO concentrations, while higher WT values in summer led to lower LDO concentrations. Similarly, autumn, which presented the higher TDS concentrations brought about higher EC values, while spring, which presented the lower TDS concentrations gave rise to lower EC values. It was concluded that the water quality of the streams in the EBS basin was high-quality water in terms of the parameters monitored in situ, of which the LDO concentration varied from 9.13 to 10.12 mg/L in summer and from 12.31 to 13.26 mg/L in winter. When the prediction accuracies of the three models were compared, it was seen that the MARS method provided more successful results than the other methods. The results of the TLBO and the CRA methods were very close to each other. The RMSE, MAE, and NSCE values were 0.2599 mg/L, 0.2125 mg/L, and 0.9645, respectively, for the best MARS model, while these values were 0.4167 mg/L, 0.3068 mg/L, and 0.9086, respectively, for the best TLBO and CRA models. In general, the LDO concentration could be successfully predicted using the MARS method with various input combinations of WT, EC, and pH variables.

show abstract

Section: Multivariate Adaptive Regression Splines (Mars) Methodsmentioning

confidence: 99%

Section: Model Development Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Spatial Forecasting of Dissolved Oxygen Concentration in the Eastern Black Sea Basin, Turkey

Nacar

Bayram

BAKİ

et al. 2020

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…Wang investigated the parameter optimization based on the grain shadow motion estimation algorithm for the ignition process [8]. Tiryaki et al investigated performance evaluation in terms of predicting the mechanical properties of impregnated wood based on teaching-based optimization and traditional regression techniques [9]. But the cost of their research is relatively high.…”

Section: Related Workmentioning

confidence: 99%

Parameter Optimization and State Evaluation of Basketball Teaching Based on BPNN

Wang

2022

Mobile Information Systems

View full text Add to dashboard Cite

BPNN is a multi-layer network with forward and backward error algorithms. It is currently the most widely used NN. Especially when it is applied to the basketball teaching scene, it can improve the research on the parameter optimization and state evaluation of the BP neural network in the teaching scene. This paper is mainly to study how to optimize the parameters of basketball teaching scene to improve the teaching effect and to evaluate the state. This paper improves the BPNN technology to study the basketball teaching scene and then proposes a genetic algorithm on the basis of the BPNN. It optimizes the parameters of basketball teaching scene through genetic algorithm and then analyzes the experimental data. The experimental results of this paper show that the BPNN is not as good as the BPNN based on the genetic algorithm in optimizing the parameters of the basketball teaching scene. The BPNN based on genetic algorithm has a successful recognition rate of more than 93% for basketball dribbling and shooting, which is 7-8% higher than that of the BPNN.

show abstract

“…In order to increase the prediction capability of this model, the second stage, in other words, the backward process is started. In this process, the model is pruned by removing the ineffective basis functions from the model (Samui 2013;Khuntia et al 2015;Tiryaki et al 2019). More detailed information about the MARS statistical downscaling method and its applications can be found in (Friedman 1991).…”

Section: Multivariate Adaptive Regression Spline (Mars)mentioning

confidence: 99%

Climate Change Projections of Temperature and Precipitation in the Eastern Black Sea Basin, Turkey by using Multivariate Adaptive Regression Splines Statistical Downscaling Method

Nacar

Kankal

Okkan

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Climate change has recently become one of the most important issue discussed by scientists around the world. The purpose of this study is to investigate the possible effects of climate change on temperature and precipitation variables, which are among the most major climate variables in terms of their environmental and economic impact for the rainiest region of Turkey. General circulation models (GCMs) under different emission scenarios are widely used in determining possible changes in the climate system. However, the coarse resolutions of these models are unsuitable for the climate impact/adaptation studies at basin scale. In this paper, the future monthly mean temperature and precipitation for 12 station in the Eastern Black Sea Basin, Turkey were projected for three periods 2030s (2021–2050), 2060s (2051–2080), and 2090s (2081–2100) from the three GCMs, namely CNRM-CM5.1, HadGEM2-ES, and MPI-ESM-MR, under RCP4.5 (optimistic) and RCP8.5 (pessimistic) scenarios using the multivariate adaptive regression splines (MARS) statistical downscaling method. The statistical downscaling models were set up between the 12 potential predictor, obtained from ERA-Interim reanalysis data set, and the local station data. For evaluating and the performance of the downscaling models four performance statistics namely root means square error, scatter index, mean absolute error, and the Nash Sutcliffe coefficient of efficiency, were used. Thereafter, the calibrated and validated models were applied to downscale future scenarios of the GCMs. The results obtained from the study proved that the downscale temperature and precipitation values correlated well with the observation values for the training (1981–2004) and test (2005–2010) periods. An average increase of 2.5 and 2.0°C is foreseen according to the optimistic scenario and an average increase of 3.5 and 3.0°C is foreseen according to the pessimistic scenario in the southern and northern parts of the basin, respectively. As to precipitation, a decrease is expected in the southern part of the basin but a significant increase is expected especially in spring at the stations located in the western and coastal parts of the basin.

show abstract

Performance evaluation of multiple adaptive regression splines, teaching–learning based optimization and conventional regression techniques in predicting mechanical properties of impregnated wood

Cited by 16 publications

References 36 publications

Spatial Forecasting of Dissolved Oxygen Concentration in the Eastern Black Sea Basin, Turkey

Spatial Forecasting of Dissolved Oxygen Concentration in the Eastern Black Sea Basin, Turkey

Parameter Optimization and State Evaluation of Basketball Teaching Based on BPNN

Climate Change Projections of Temperature and Precipitation in the Eastern Black Sea Basin, Turkey by using Multivariate Adaptive Regression Splines Statistical Downscaling Method

Contact Info

Product

Resources

About