• Environmental Engineering Research
• /
• v.25 no.1
• /
• pp.114-122
• /
• 2020

This study was aimed at using the Central Composite Design (CCD) and Box-Behnken Design (BBD) to compare the efficiency and to elucidate the main interacting parameters in the upflow anaerobic sludge blanket (UASB) reactor, namely: Organic Loading Rate (OLR), Hydraulic Retention Times (HRT) and pH at a constant temperature of 35℃. Optimum HRT (15 h), OLR (3.5 kg.m^-3.d^-1) and pH (7) resulted in biogas production of 5,800 mL/d and COD removal of 80.8%. BBD produced a higher desirability efficiency of 94% as compared to the CCD which was 92%. The regression quadratic models developed with high R² values of 0.961 and 0.978 for both CCD and BBD, respectively, demonstrated that the interaction models could be used to pilot the design space. BBD model developed was more reliable with a higher prediction of biogas production (5,955.4 ± 225.3 mL/d) and COD removal (81.5 ± 1.014%), much close to the experimental results at a 95% confidence level. CCD model predictions was greater in terms of COD removal (82.6 ± 1.06% > 80.8%) and biogas production (4,636.31 mL/d ± 439.81 < 5,800 mL/d) which was less than the experimental results. Therefore, RSM can be adapted for optimizing various wastewater treatment processes.

• Journal of Microbiology and Biotechnology
• /
• v.17 no.4
• /
• pp.644-649
• /
• 2007

Response surface model was developed for predicting the growth rates of Salmonella enterica sv. Typhimurium in tryptic soy broth (TSB) medium as a function of combined effects of temperature, pH, and NaCl. The TSB containing six different concentrations of NaCl (0, 2, 4, 6, 8, and 10%) was adjusted to an initial of six different pH levels (pH 4, 5, 6, 7, 8, 9, and 10) and incubated at 10 or $20^{\circ}C$. In all experimental variables, the primary growth curves were well $(r^2=0.900\;to\;0.996)$ fitted to a Gompertz equation to obtain growth rates. The secondary response surface model for natural logarithm transformations of growth rates as a function of combined effects of temperature, pH, and NaCl was obtained by SAS's general linear analysis. The predicted growth rates of the S. Typhimurium were generally decreased by basic (9, 10) or acidic (5, 6) pH levels or increase of NaCl concentrations (0-8%). Response surface model was identified as an appropriate secondary model for growth rates on the basis of coefficient determination $(r^2=0.960)$, mean square error (MSE=0.022), bias factor $(B_f=1.023)$, and accuracy factor $(A_f=1.164)$. Therefore, the developed secondary model proved reliable predictions of the combined effect of temperature, NaCl, and pH on growth rates for S. Typhimurium in TSB medium.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.2
• /
• pp.98.2-98.2
• /
• 2012

We firstly present the unified Far-UV continuum map of the Taurus-Auriga-Perseus (TPA) complex, one of the largest local associations of dark cloud located in (l, b)=([154,180], [-28, -2]), by merging both FIMS and GALEX. The FUV continuum map shows that dust extinction correlate well with the FUV around the complex. It shows strong absorption in FUV toward the dense Taurus cloud while it does not in California cloud. It turned out that it is related to the relative location of each cloud and Perseus OB2 association. We also present some results of dust scattering simulation based on Monte Carlo Radiative Transfer technique (MCRT). Through this dust scattering simulation, we have derived the scattering parameter for this region, albedo(a)=$0.42^{+0.05}{_{-0.05}}$, asymmetry factor(g)=$0.47^{+0.11}{_{-0.27}}$. The optical parameters we obtained seem reasonable compared to the theoretical model values ~0.40 and ~0.65 for the albedo and the phase function though the phase function is rather small. Using the result of simulation, we figured out the geometries of each cloud in the complex region, especially their distances and thicknesses. Our predictions from the results are in good agreement with the previous studies related to the TPA complex. For example, the Taurus cloud is within ~200pc from the Sun and the Perseus seems to be multi-layered, at least two. The California cloud is more distant than the other cloud on average at ~350 pc and Auriga cloud seems to be between the Taurus cloud and the eastern end of the California cloud. We figured out that across the TPA complex region, there might be some correlation between the LSR velocity and the distance to each cloud in the complex.

• Ocean and Polar Research
• /
• v.38 no.1
• /
• pp.1-19
• /
• 2016

Recently, there has been a growing interest in physical-biological ocean-modeling systems by communities in the fields of science and business. In this paper, we present preliminary results from a coupled physical-biological model for the Northwestern Pacific marginal seas. The ocean circulation component is an implementation of the Regional Ocean Modeling System (ROMS), and the lower trophic level ecosystem component is a Nutrient-Phytoplankton-Zooplankton-Detritus (NPZD) model. The ROMS-NPZD coupled system, with a 25 km resolution, is forced by climatological atmospheric data and predicts the physical variables and concentrations of nitrate, phytoplankton, zooplankton, and detritus. Model results are compared with remote-sensed sea surface temperature and chlorophyll, and with climatological sea surface salinity and nitrate. Our model adequately reproduces the observed spatial distribution and seasonal variability of nitrate and chlorophyll concentrations as well as physical variables, showing a high correlation in the East Sea (ES) and Kuroshio/Oyashio Extension (KOE) region but relatively low correlation in the Yellow Sea (YS) and East China Sea (ECS). Although some deficiencies were found in the biological components, such as the over/underestimation of the intensity of phytoplankton blooms in the ES and KOE/the YS and ECS, our system demonstrates the capability of the model to capture and record dominant seasonal variability in physical-biological processes and this holds out the promise of coming to a better understanding of such processes and making better predictions .

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• Journal of Environmental Science International
• /
• v.25 no.10
• /
• pp.1369-1379
• /
• 2016

This research assessed the disparity in anion generation according to the vertical structure of a Zelkova Serrata tree for the purpose of creating a pleasant and green city environment. Measurements for the study were conducted between July and August of 2014 in Chung-ju in the central region of the Republic of Korea. The average anion generation of vertical structure trees during active photosynthesis periods was: L Section ($839.0ea/cm^3$) > M Section ($664.6ea/cm^3$) > U Section ($472.0ea/cm^3$). According to DMRT analysis, significant difference was found in the average between the L, or M Locations and the U Locations. During dormant photosynthesis periods, records showed that the anion production at the M Location ($1,212.5ea/cm^3$) > L Location ($1,050.4ea/cm^3$) > H Location ($844.1ea/cm^3$), According to DMRT analysis, the difference within each location was significant for ${\alpha}=0.05$. In a comprehensive analysis of the weather factors in each vertical structure, anion generation during active photosynthesis periods showed a positive correlation with solar radiation and a negative correlation with wind speed. Dormant photosynthesis periods showed negative correlations with both solar radiation and temperature, and positive correlations with relative humidity and wind speed. Predictions from a multicenter retrospective study showed that during active photosynthesis periods, $Y_1=282.443X_1+512.07$, and $Y_2=314.337X_1+16.913X_2$, while during dormant photosynthesis periods, $Y_1=391.009X_1+840.043$, and $Y_2=351.412X_1+32.765X_2$.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.3
• /
• pp.202-211
• /
• 2017

In this study, numerical simulations were performed using the ${\gamma}-Re_{\theta}$ transition model of KFLOW for the transitional flow over the KARI-11-180 airfoil. Numerical results of KFLOW were compared with experimental data and two other numerical results of XFoil and MSES. Fully turbulence model was predicted high skin friction drag than transition model because fully turbulence model could not solve the transitional flow. Numerical predictions using the ${\gamma}-Re_{\theta}$ model of KFLOW show a good agreement with experimental data and other numerical results. Present numerical results were confirmed the state of drag bucket due to dramatic changing of the transition location on the airfoil surface.

• Geomechanics and Engineering
• /
• v.31 no.2
• /
• pp.129-147
• /
• 2022

The properties of soil are naturally highly variable and thus, to ensure proper safety and reliability, we need to test a large number of samples across the length and depth. In pile foundations, conducting field tests are highly expensive and the traditional empirical relations too have been proven to be poor in performance. The study proposes a state-of-art Particle Swarm Optimization (PSO) hybridized Artificial Neural Network (ANN), Extreme Learning Machine (ELM) and Adaptive Neuro Fuzzy Inference System (ANFIS); and comparative analysis of metaheuristic models (ANN-PSO, ELM-PSO, ANFIS-PSO) for prediction of bearing capacity of pile foundation trained and tested on dataset of nearly 300 dynamic pile tests from the literature. A novel ensemble model of three hybrid models is constructed to combine and enhance the predictions of the individual models effectively. The authenticity of the dataset is confirmed using descriptive statistics, correlation matrix and sensitivity analysis. Ram weight and diameter of pile are found to be most influential input parameter. The comparative analysis reveals that ANFIS-PSO is the best performing model in testing phase (R² = 0.85, RMSE = 0.01) while ELM-PSO performs best in training phase (R² = 0.88, RMSE = 0.08); while the ensemble provided overall best performance based on the rank score. The performance of ANN-PSO is least satisfactory compared to the other two models. The findings were confirmed using Taylor diagram, error matrix and uncertainty analysis. Based on the results ELM-PSO and ANFIS-PSO is proposed to be used for the prediction of bearing capacity of piles and ensemble learning method of joining the outputs of individual models should be encouraged. The study possesses the potential to assist geotechnical engineers in the design phase of civil engineering projects.

• Horticultural Science & Technology
• /
• v.30 no.6
• /
• pp.709-717
• /
• 2012

To establish the standard of ripe kiwifruit sorting, near infrared (NIR) spectroscopy was performed on kiwifruit sampled from three farms. Destructive measurements of flesh firmness, soluble solids content (SSC), and acidity were performed and compared to measurement using NIR reflectance spectrums from 408 to 2,492 nm. NIR predictions of those quality factors were calculated using the modified partial least square regression method. Flesh firmness was predicted with a standard error of prediction (SEP) of 3.32 N and with a correlation coefficient ($R^2$) of 0.88. SSC was predicted with SEP of $0.49^{\circ}Brix$ and with $R^2$ of 0.98. Acidity was predicted with SEP of 0.28% and with $R^2$ of 0.91. Kiwifruit ripened at $20^{\circ}C$ for 15 days showed uneven qualities with normal distribution. Considering the SEP of each parameter, kiwifruit after ripening treatment could be non-destructively predicted their qualities and sorted by flesh firmness or soluble solids content through NIR prediction.

• Journal of Positioning, Navigation, and Timing
• /
• v.13 no.1
• /
• pp.111-115
• /
• 2024

This study builds a machine learning model optimized for clocks among various techniques in the field of artificial intelligence and applies it to clock stabilization or synchronization technology based on atomic clock noise characteristics. In addition, the possibility of providing stable source clock data is confirmed through the characteristics of machine learning predicted values during holdover of atomic clocks. The proposed machine learning model is evaluated by comparing its performance with the AutoRegressive Integrated Moving Average (ARIMA) model, an existing statistical clock prediction model. From the results of the analysis, the prediction model proposed in this study (MSE: 9.47476) has a lower MSE value than the ARIMA model (MSE: 221.2622), which means that it provides more accurate predictions. The prediction accuracy is based on understanding the complex nature of data that changes over time and how well the model reflects this. The application of a machine learning prediction model can be seen as a way to overcome the limitations of the statistical-based ARIMA model in time series prediction and achieve improved prediction performance.