Abstract In this study, wavelet support vector machine (WSWM) model is proposed for daily suspended sediment (SS) prediction. The WSVM model is achieved by combination of two methods; discrete wavelet analysis and support vector machine (SVM). The developed model was compared with single SVM. Daily discharge (Q) and SS data from Yadkin River at Yadkin College, NC station in the USA were used. I...

We asses the ability of a distance correlation coefficient (DiCC), calculated from distance covariance, for detecting long-range concerted motion in proteins. We establish a set of criteria for ideal correlation coefficient values based on the coefficient of determination in multi-dimension, R2. We compare in detail DiCC and conventional coefficients against these criteria. We demonstrate that ...

Assessing the accuracy of predictive models is critical because predictive models have been increasingly used across various disciplines and predictive accuracy determines the quality of resultant predictions. Pearson product-moment correlation coefficient (r) and the coefficient of determination (r2) are among the most widely used measures for assessing predictive models for numerical data, al...

Key-words: Artificial neural networks, random forests, native fish, species richness, Mediterranean rivers Machine learning (ML) techniques have become important to support decision making in management and conservation of freshwater aquatic ecosystems. Given the large number of ML techniques and to improve the understanding of ML utility in ecology, it is necessary to perform comparative studi...

The purpose of this paper was to investigate the early water stress in maize using leaf-level measurements of chlorophyll fluorescence and temperature. In this study, a series of diurnal measurements, such as leaf chlorophyll fluorescence (Fs), leaf spectrum, temperature and photosynthetically active radiation (PAR), were conducted for maize during gradient watering and filled watering experime...

We present a new atom type classification system for use in atom-based calculation of partition coefficient (log P) and molar refractivity (MR) designed in part to address published concerns of previous atomic methods. The 68 atomic contributions to log P have been determined by fitting an extensive training set of 9920 molecules, with r2 ) 0.918 and σ ) 0.677. A separate set of 3412 molecules ...

preparation of the topographic factor (ls) map in rusle model is a very tedious step because of the complicated effects of topography on soil loss. the objective of this study was to determine the suitable cell size of digital elevation model (dem) for computing ls factor by the method of moore and wilson (1992) in a 5326 ha area, northwest of tehran province. towards this end, cell sizes of 30...

in this research, papaya slices with dimensions of 0.5×2×5 cm3 were dried at 45 °c using a cabinet dryer in which drying air velocity and relative humidity were 0.9 m/s and 30%, respectively. the moisture diffusion coefficient of papaya was determined in this drying condition. mass transfer equation with its boundary conditions was solved based on finite difference method. finally, coefficient ...

A series of 3and 4-substituted 7-hydroxycoumarins analogues were analyzed for structure–activity relationship using sphere exclusion algorithm method. The QSAR studies were analyzed and the structural features contributing to the enhancement of activity were identified. 2D-QSAR statistically significant model with coefficient of determination (r2) of 0.8291 and cross validated correlation coeff...