• Food Science and Biotechnology
• /
• v.16 no.2
• /
• pp.238-242
• /
• 2007

Square root models were developed for predicting the kinetics of growth of Listeria monocytogenes in sesame leaves as a function of temperature (4, 10, or $25^{\circ}C$). At these storage temperatures, the primary growth curves fit well ($R^2=0.898$ to 0.980) to a Gompertz equation to obtain lag time (LT) and specific growth rate (SGR). The square root models for natural logarithm transformations of the LT and SGR as a function of temperature were obtained by SAS's regression analysis. As storage temperature ($4-25^{\circ}C$) decreased, LT increased and SGR decreased, respectively. Square root models were identified as appropriate secondary models for LT and SGR on the basis of most statistical indices such as coefficient determination ($R^2=0.961$ for LT, 0.988 for SGR), mean square error (MSE=0.l97 for LT, 0.005 for SGR), and accuracy factor ($A_f=1.356$ for LT, 1.251 for SGR) although the model for LT was partially not appropriate as a secondary model due to the high value of bias factor ($B_f=1.572$). In general, our secondary model supported predictions of the effects of temperature on both LT and SGR for L. monocytogenes in sesame leaves.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.1B
• /
• pp.9-20
• /
• 2012

Recently to overcome limitations of conceptual, hydrological and physics based models for flood stage forecasting, multiple linear regression model as one of data-driven models have been widely adopted for forecasting flood streamflow(stage). The objectives of this study are to compare performance of different multiple linear regression models according to regression coefficient estimation methods and determine most effective multiple linear regression flood stage forecasting models. To do this, the time scale was determined through the autocorrelation analysis of input data and different flood stage forecasting models developed using regression coefficient estimation methods such as LS(least square), WLS(weighted least square), SPW(stepwise) was applied to flood events in Jungrang stream. To evaluate performance of established models, fours statistical indices were used, namely; Root mean square error(RMSE), Nash Sutcliffe efficiency coefficient (NSEC), mean absolute error (MAE), adjusted coefficient of determination($R^{*2}$). The results show that the flood stage forecasting model using SPW(stepwise) parameter estimation can carry out the river flood stage prediction better in comparison with others, and the flood stage forecasting model using LS(least square) parameter estimation is also found to be slightly better than the flood stage forecasting model using WLS(weighted least square) parameter estimation.

• Computers and Concrete
• /
• v.28 no.6
• /
• pp.635-642
• /
• 2021

In this paper, soft learning techniques are used to predict the ultimate torsional capacity of Reinforced Concrete beams strengthened with Fiber Reinforced Polymer. Soft computing techniques, namely Artificial Neural Network, trained by various back propagation algorithms, and Particle Swarm Optimization (PSO) algorithm, have been used to model and predict the torsional strength of Reinforced Concrete beams strengthened with Fiber Reinforced Polymer. The performance of each model has been evaluated by using statistical parameters such as coefficient of determination (R²), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The hybrid PSO NN model resulted in an R² of 0.9292 with an RMSE of 5.35 for training and an R² of 0.9328 with an RMSE of 4.57 for testing. Another model, ANN BP, produced an R² of 0.9125 with an RMSE of 6.17 for training and an R² of 0.8951 with an RMSE of 5.79 for testing. The results of the PSO NN model were in close agreement with the experimental values. Thus, the PSO NN model can be used to predict the ultimate torsional capacity of RC beams strengthened with FRP with greater acceptable accuracy.

• Korean Journal of Agricultural Science
• /
• v.46 no.1
• /
• pp.183-194
• /
• 2019

Adulteration of argan oil with some other cheaper oils with similar chemical compositions has resulted in increasing demands for authenticity assurance and quality control. Fast and simple analytical techniques are thus needed for authenticity analysis of high-priced argan oil. Raman spectroscopy is a potent technique and has been extensively used for quality control and safety determination for food products In this study, Raman spectroscopy in combination with a net analyte signal (NAS)-based methodology, i.e., hybrid linear analysis method developed by Goicoechea and Olivieri in 1999 (HLA/GO), was used to predict the different concentrations of olive oil (0 - 20%) added to argan oil. Raman spectra of 90 samples were collected in a spectral range of $400-400cm^{-1}$, and calibration and validation sets were designed to evaluate the performance of the multivariate method. The results revealed a high coefficient of determination ($R^2$) value of 0.98 and a low root-mean-square error (RMSE) value of 0.41% for the calibration set, and an $R^2$ of 0.97 and RMSE of 0.36% for the validation set. Additionally, the figures of merit such as sensitivity, selectivity, limit of detection, and limit of quantification were used for further validation. The high $R^2$ and low RMSE values validate the detection ability and accuracy of the developed method and demonstrate its potential for quantitative determination of oil adulteration.

• Korean Journal of Soil Science and Fertilizer
• /
• v.43 no.2
• /
• pp.174-179
• /
• 2010

In order to interpret yield response of sugar beet to nitrogen fertilizer, and pig manure compost in saline-sodic soil of reclaimed tidal land, 4 kinds of response model, i.e., quadratic, exponential, square root, and linear response, and plateau model, are applied. The root fresh yield of sugar beet decreased exponentially with the increase of soil EC. The root fresh yield of sugar beet to nitrogen fertilizer was fitted best to the linear response, and plateau model among 4 yield response models with highly significant determination coefficient ($R^2=0.92^{**}$). The optimum N rate determined on the model was 138 kg N $ha^{-1}$. The root fresh yield of sugar beet to pig manure compost was fitted best to the quadratic model among 4 yield response models with highly significant determination coefficient ($R^2=0.99^{**}$). The maximum N rate determined on the model was 9.17 ton $ha^{-1}$. In conclusion, the proper model to interpret the yield of sugar beet in saline-sodic soil differs with the kinds of nutrient, linear response, and plateau model for fertilizer nitrogen, and quadratic model to pig manure compost.

• Computers and Concrete
• /
• v.32 no.2
• /
• pp.149-163
• /
• 2023

One of the main design parameters traditionally utilized in projects of geotechnical engineering is the uniaxial compressive strength. The present paper employed three artificial intelligence methods, i.e., the stochastic fractal search (SFS), the multi-verse optimization (MVO), and the vortex search algorithm (VSA), in order to determine the compressive strength of concrete (CSC). For the same reason, 1030 concrete specimens were subjected to compressive strength tests. According to the obtained laboratory results, the fly ash, cement, water, slag, coarse aggregates, fine aggregates, and SP were subjected to tests as the input parameters of the model in order to decide the optimum input configuration for the estimation of the compressive strength. The performance was evaluated by employing three criteria, i.e., the root mean square error (RMSE), mean absolute error (MAE), and the determination coefficient (R²). The evaluation of the error criteria and the determination coefficient obtained from the above three techniques indicates that the SFS-MLP technique outperformed the MVO-MLP and VSA-MLP methods. The developed artificial neural network models exhibit higher amounts of errors and lower correlation coefficients in comparison with other models. Nonetheless, the use of the stochastic fractal search algorithm has resulted in considerable enhancement in precision and accuracy of the evaluations conducted through the artificial neural network and has enhanced its performance. According to the results, the utilized SFS-MLP technique showed a better performance in the estimation of the compressive strength of concrete (R²=0.99932 and 0.99942, and RMSE=0.32611 and 0.24922). The novelty of our study is the use of a large dataset composed of 1030 entries and optimization of the learning scheme of the neural prediction model via a data distribution of a 20:80 testing-to-training ratio.

• Journal of Biosystems Engineering
• /
• v.43 no.2
• /
• pp.148-159
• /
• 2018

Purpose: Unmanned air vehicle (UAV) remote sensing was applied to test various vegetation indices and make prediction models of protein content of rice for monitoring grain quality and proper management practice. Methods: Image acquisition was carried out by using NIR (Green, Red, NIR), RGB and RE (Blue, Green, Red-edge) camera mounted on UAV. Sampling was done synchronously at the geo-referenced points and GPS locations were recorded. Paddy samples were air-dried to 15% moisture content, and then dehulled and milled to 92% milling yield and measured the protein content by near-infrared spectroscopy. Results: Artificial neural network showed the better performance with $R^2$ (coefficient of determination) of 0.740, NSE (Nash-Sutcliffe model efficiency coefficient) of 0.733 and RMSE (root mean square error) of 0.187% considering all 54 samples than the models developed by PR (polynomial regression), SLR (simple linear regression), and PLSR (partial least square regression). PLSR calibration models showed almost similar result with PR as 0.663 ($R^2$) and 0.169% (RMSE) for cloud-free samples and 0.491 ($R^2$) and 0.217% (RMSE) for cloud-shadowed samples. However, the validation models performed poorly. This study revealed that there is a highly significant correlation between NDVI (normalized difference vegetation index) and protein content in rice. For the cloud-free samples, the SLR models showed $R^2=0.553$ and RMSE = 0.210%, and for cloud-shadowed samples showed 0.479 as $R^2$ and 0.225% as RMSE respectively. Conclusion: There is a significant correlation between spectral bands and grain protein content. Artificial neural networks have the strong advantages to fit the nonlinear problem when a sigmoid activation function is used in the hidden layer. Quantitatively, the neural network model obtained a higher precision result with a mean absolute relative error (MARE) of 2.18% and root mean square error (RMSE) of 0.187%.

• Nuclear Engineering and Technology
• /
• v.53 no.12
• /
• pp.4179-4188
• /
• 2021

This study identifies efficient earthquake intensity measures (IMs) for seismic performances and fragility evaluations of the reactor containment building (RCB) in the advanced power reactor 1400 (APR1400) nuclear power plant (NPP). The computational model of RCB is constructed using the beam-truss model (BTM) for nonlinear analyses. A total of 90 ground motion records and 20 different IMs are employed for numerical analyses. A series of nonlinear time-history analyses are performed to monitor maximum floor displacements and accelerations of RCB. Then, probabilistic seismic demand models of RCB are developed for each IM. Statistical parameters including coefficient of determination (R²), dispersion (i.e. standard deviation), practicality, and proficiency are calculated to recognize strongly correlated IMs with the seismic performance of the NPP structure. The numerical results show that the optimal IMs are spectral acceleration, spectral velocity, spectral displacement at the fundamental period, acceleration spectrum intensity, effective peak acceleration, peak ground acceleration, A95, and sustained maximum acceleration. Moreover, weakly related IMs to the seismic performance of RCB are peak ground displacement, root-mean-square of displacement, specific energy density, root-mean-square of velocity, peak ground velocity, Housner intensity, velocity spectrum intensity, and sustained maximum velocity. Finally, a set of fragility curves of RCB are developed for optimal IMs.

• Korean Journal of Agricultural Science
• /
• v.38 no.4
• /
• pp.761-767
• /
• 2011

The objective of this study was to predict total bacteria count of pork meats by using the portable electronic nose systems developed throughout two stages of the prototypes. Total bacteria counts were measured for pork meats stored at $4^{\circ}C$ for 21days and compared with the signals of the electronic nose systems. PLS(Partial least square), PCR (Principal component regression), MLR (Multiple linear regression) models were developed for the prediction of total bacteria count of pork meats. The coefficient of determination ($R_p{^2}$) and root mean square error of prediction (RMSEP) for the models were 0.789 and 0.784 log CFU/g with the 1st system for the pork loin, 0.796 and 0.597 log CFU/g with the 2nd system for the pork belly, and 0.661 and 0.576 log CFU/g with the 2nd system for the pork loin respectively. The results show that the developed electronic system has potential to predict total bacteria count of pork meats.

• Journal of Biosystems Engineering
• /
• v.29 no.1
• /
• pp.59-64
• /
• 2004

This study was performed to determine drying equations of sarcodon aspratus. Drying tests for sarcodon aspratus were conducted in an experimental dryer equiped with an air conditioning unit. The drying tests were performed at three air temperatures of 30$^{\circ}C$, 40$^{\circ}C$ and 50$^{\circ}C$, and two relative humidities of 30% and 50%. Measured moisture ratio data were fitted with the selected four drying models(Page, Thompson, Lewis and simplified diffusion models) using stepwise multiple regression analysis. When the coefficients of determination and root mean square errors of moisture ratio were evaluated for four drying models, the Page model was found to fit adequately to all the drying test data with coefficient of determination of 0.9996 and RMSE of 0.00523.