Predicting the performance of multi-media filters using artificial neural networks

The impact of flow rate and turbidity on the performance of multi-media filtration has been studied using an artificial neural network (ANN) based model. The ANN model was developed and tested based on experimental data collected from a pilot scale multi-media filter system. Several ANN models were tested, and the best results with the lowest errors were achieved with two hidden layers and five neurons per layer. To examine the significance and efficiency of the developed ANN model it was compared with a linear regression model. The R2 values for the actual versus predicted results were 0.9736 and 0.9617 for the ANN model and the linear regression model, respectively. The ANN model showed an R-squared value increase of 1.22% when compared to the linear regression model. In addition, the ANN model gave a significant reduction of 91.5% and 97.9% in the mean absolute error and the root mean square error, respectively when compared to the linear regression model. The proposed model has proven to give plausible results to model complex relationships that can be used in real life water treatment plants.

Download Full-text

Physico-Chemical Analysis of Groundwater and Effect of Climatic Change in Angul-Talcher Area

International Journal of Emerging Research in Management and Technology ◽

10.23956/ijermt.v6i12.31 ◽

2018 ◽

Vol 6 (12) ◽

pp. 26

Author(s):

Aliva Bera ◽

D.P. Satapathy

Keyword(s):

Water Resources ◽

Linear Regression ◽

Regression Model ◽

Climatic Change ◽

Linear Regression Model ◽

Ann Model ◽

Quality Of Water ◽

Physico Chemical ◽

Simulation Based

In this paper, the linear regression model using ANN and the linear regression model using MS Excel were developed to estimate the physico-chemical concentrations in groundwater using pH, EC, TDS, TH, HCO3 as input parameters and Ca, Mg and K as output parameters. A comparison was made which indicated that ANN model had the better ability to estimate the physic-chemical concentrations in groundwater. An analytical survey along with simulation based tests for finding the climatic change and its effect on agriculture and water bodies in Angul-Talcher area is done. The various seasonal parameters such as pH, BOD, COD, TDS,TSS along with heavy elements like Pb, Cd, Zn, Cu, Fe, Mn concentration in water resources has been analyzed. For past 30 years rainfall data has been analyzed and water quality index values has been studied to find normal and abnormal quality of water resources and matlab based simulation has been done for performance analysis. All results has been analyzed and it is found that the condition is stable.

Download Full-text

Artificial neural network, predictor variables and sensitivity threshold for DNA methylation-based age prediction using blood samples

Scientific Reports ◽

10.1038/s41598-021-81556-2 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Zhonghui Thong ◽

Jolena Ying Ying Tan ◽

Eileen Shuzhen Loo ◽

Yu Wei Phua ◽

Xavier Liang Shun Chan ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Regression Model ◽

Sensitivity Threshold ◽

Ann Model ◽

Blood Samples ◽

Ann Models ◽

Artificial Neural ◽

The Impact ◽

Age Prediction

AbstractRegression models are often used to predict age of an individual based on methylation patterns. Artificial neural network (ANN) however was recently shown to be more accurate for age prediction. Additionally, the impact of ethnicity and sex on our previous regression model have not been studied. Furthermore, there is currently no age prediction study investigating the lower limit of input DNA at the bisulfite treatment stage prior to pyrosequencing. Herein, we evaluated both regression and ANN models, and the impact of ethnicity and sex on age prediction for 333 local blood samples using three loci on the pyrosequencing platform. Subsequently, we trained a one locus-based ANN model to reduce the amount of DNA used. We demonstrated that the ANN model has a higher accuracy of age prediction than the regression model. Additionally, we showed that ethnicity did not affect age prediction among local Chinese, Malays and Indians. Although the predicted age of males were marginally overestimated, sex did not impact the accuracy of age prediction. Lastly, we present a one locus, dual CpG model using 25 ng of input DNA that is sufficient for forensic age prediction. In conclusion, the two ANN models validated would be useful for age prediction to provide forensic intelligence leads.

Download Full-text

Cognition predicts days-alive-out-of-hospital after LVAD implantation

The International Journal of Artificial Organs ◽

10.1177/03913988211018484 ◽

2021 ◽

pp. 039139882110184

Author(s):

Marykay A Pavol ◽

Amelia K Boehme ◽

Melana Yuzefpolskaya ◽

Mathew S Maurer ◽

Jesus Casida ◽

...

Keyword(s):

Linear Regression ◽

Regression Model ◽

Linear Regression Model ◽

Left Ventricular ◽

Motor Speed ◽

Ventricular Assist ◽

Hospitalization Rates ◽

Left Ventricular Assist ◽

Patient Groups ◽

The Impact

Objective: Cognition influences hospitalization rates for a variety of patient groups but this association has not been examined in heart failure (HF) patients undergoing left ventricular assist device (LVAD) implantation. We used cognition to predict days-alive-out-of-hospital (DAOH) in patients after LVAD surgery. Methods: We retrospectively identified 59 HF patients with cognitive assessment prior to LVAD. Cognitive tests of attention, memory, language, and visual motor speed were averaged into one score. DAOH was converted to a percentage based on total days from LVAD surgery to either heart transplant or 900 days post-LVAD. Variables significantly associated with DAOH in univariate analyses were included in a linear regression model to predict DAOH. Results: A linear regression model including LVAD type (continuous or pulsatile flow) and cognition significantly predicted DAOH (F(2,54) = 6.44, p = 0.003, R2 = .19). Inspection of each variable revealed that cognition was a significant predictor in the model (β = .11, SE = .04, p = 0.007) but LVAD type was not ( p = 0.08). Conclusions: Cognitive performance assessed prior to LVAD implantation predicted how much time patients spent out of the hospital following surgery. Further studies are warranted to identify the impact of pre-LVAD cognition on post-LVAD hospitalization.

Download Full-text

A Linear Regression Model for THD Sensitivity in PV Based Microgrid with Varying Insolation Levels

International Journal of Advanced Research in Science, Communication and Technology ◽

10.48175/ijarsct-2257 ◽

2022 ◽

pp. 179-186

Author(s):

Yuvraj Praveen Soni ◽

Eugene Fernandez

Keyword(s):

Linear Regression ◽

Regression Model ◽

Linear Regression Model ◽

Solar Irradiance ◽

Harmonic Distortion ◽

System Control ◽

Solar Pv ◽

Pv System ◽

Simulink Model ◽

The Impact

Solar PV systems can be used for powering small microgrids in rural area of developing countries. Generally, a solar power microgrid consists of a PV array, an MPPT, a dc-dc converter and an inverter, particularly as the general loads are A.C in nature. In a PV system, reactive current, unbalancing in currents, and harmonics are generated due to the power electronics-based converters as well as nonlinear loads (computers induction motors etc). Thus, estimation of the harmonics levels measured by the Total Harmonic Distortion (THD) is an essential aspect of performance assessment of a solar powered microgrid. A major issue that needs to be examined is the impact of PV system control parameters on the THD. In this paper, we take up this assessment for a small PV based rural microgrid with varying levels of solar irradiance. A Simulink model has been developed for the study from which the THD at equilibrium conditions is estimated. This data is in turn used to design a generalized Linear Regression Model, which can be used to observe the sensitivity of three control variables on the magnitude of the THD. These variables are: Solar Irradiance levels, Power Factor (PF) of connected load magnitude of the connected load (in kVA) The results obtained show that the greatest sensitivity is obtained for load kVA variation.

Download Full-text

Modified One-Parameter Liu Estimator for the Linear Regression Model

Modelling and Simulation in Engineering ◽

10.1155/2020/9574304 ◽

2020 ◽

Vol 2020 ◽

pp. 1-17

Author(s):

Adewale F. Lukman ◽

B. M. Golam Kibria ◽

Kayode Ayinde ◽

Segun L. Jegede

Keyword(s):

Linear Regression ◽

Regression Model ◽

Linear Regression Model ◽

Ridge Regression ◽

Real Life ◽

Liu Estimator ◽

Real Life Data ◽

Squared Prediction Error ◽

Simulation Results ◽

Better Than

Motivated by the ridge regression (Hoerl and Kennard, 1970) and Liu (1993) estimators, this paper proposes a modified Liu estimator to solve the multicollinearity problem for the linear regression model. This modification places this estimator in the class of the ridge and Liu estimators with a single biasing parameter. Theoretical comparisons, real-life application, and simulation results show that it consistently dominates the usual Liu estimator. Under some conditions, it performs better than the ridge regression estimators in the smaller MSE sense. Two real-life data are analyzed to illustrate the findings of the paper and the performances of the estimators assessed by MSE and the mean squared prediction error. The application result agrees with the theoretical and simulation results.

Download Full-text

A Multi Linear Regression Model to Derive Dust PM10 in the Sahel Using AERONET Aerosol Optical Depth and CALIOP Aerosol Layer Products

Remote Sensing ◽

10.3390/rs12183099 ◽

2020 ◽

Vol 12 (18) ◽

pp. 3099

Author(s):

Jean-François Léon ◽

Nadège Martiny ◽

Sébastien Merlet

Keyword(s):

Linear Regression ◽

Regression Model ◽

Aerosol Optical Depth ◽

Optical Depth ◽

Linear Regression Model ◽

Population Exposure ◽

Aerosol Layer ◽

Multi Linear Regression ◽

Sun Photometer ◽

The Impact

Due to a limited number of monitoring stations in Western Africa, the impact of mineral dust on PM10 surface concentrations is still poorly known. We propose a new method to retrieve PM10 dust surface concentrations from sun photometer aerosol optical depth (AOD) and CALIPSO/CALIOP Level 2 aerosol layer products. The method is based on a multi linear regression model that is trained using co-located PM10, AERONET and CALIOP observations at 3 different locations in the Sahel. In addition to the sun photometer AOD, the regression model uses the CALIOP-derived base and top altitude of the lowermost dust layer, its AOD, the columnar total and columnar dust AOD. Due to the low revisit period of the CALIPSO satellite, the monthly mean annual cycles of the parameters are used as predictor variables rather than instantaneous observations. The regression model improves the correlation coefficient between monthly mean PM10 and AOD from 0.15 (AERONET AOD only) to 0.75 (AERONET AOD and CALIOP parameters). The respective high and low PM10 concentration during the winter dry season and summer season are well produced. Days with surface PM10 above 100 μg/m3 are better identified when using the CALIOP parameters in the multi linear regression model. The number of true positives (actual and predicted concentrations above the threshold) is increased and leads to an improvement in the classification sensitivity (recall) by a factor 1.8. Our methodology can be extrapolated to the whole Sahel area provided that satellite derived AOD maps are used in order to create a new dataset on population exposure to dust events in this area.

Download Full-text

Prediction of Carcass Meat Percentage in Young Pigs Using Linear Regression Models and Artificial Neural Networks

Annals of Animal Science ◽

10.1515/aoas-2015-0057 ◽

2016 ◽

Vol 16 (1) ◽

pp. 275-286 ◽

Cited By ~ 1

Author(s):

Magdalena Szyndler-Nędza ◽

Robert Eckert ◽

Tadeusz Blicharski ◽

Mirosław Tyra ◽

Artur Prokowski

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Linear Regression ◽

Regression Model ◽

Linear Regression Model ◽

Performance Testing ◽

Regression Equations ◽

Young Pigs ◽

Marquardt Algorithm ◽

Artificial Neural

Abstract One of the approaches to improving performance testing of pigs is to look for mathematical solutions to increase the accuracy of calculations. This is mainly done through improvement of linear regression equations based on current data on performance tested pigs in Poland. The advances in computer technology and the improvements in mathematical analysis have made it possible to use artificial neural networks (ANNs) for prediction of carcass meat percentage in young pigs. The aim of the study was to compare the potential for live estimation of carcass meat percentage in pigs using two computational methods: linear regression equations and ANNs. The experiment used 654 gilts of six breeds, which were subjected to performance testing and slaughter analysis at the Pig Performance Testing Station (SKURTCh). The collected data were used to train ANNs to estimate carcass meat percentage in young pigs. Training was performed using the Levenberg- Marquardt algorithm. Next, meatiness estimated by ANNs was compared with the results obtained using linear modelling. It is concluded that based on the fattening and slaughter performance test results of live pigs, artificial neural networks (SSN23) are significantly more accurate in estimating carcass meat percentage in young pigs compared to the three-variable linear regression model 1. The difference in meatiness estimation between SSN23 and the four-variable linear regression model 2 was statistically non-significant in most of the breeds except Duroc and Pietrain, where the meatiness of young animals was estimated more accurately by the linear regression model.

Download Full-text

Influence of the key account manager in the provisioning management: Evidence from staple companies during the events of COVID-19

Accounting ◽

10.5267/j.ac.2021.7.006 ◽

2022 ◽

Vol 8 (2) ◽

pp. 161-170 ◽

Cited By ~ 1

Author(s):

Luis-Ricardo Flores-Vilcapoma ◽

Cynthia-Paola A lbengrin-Mendoza ◽

Gabriela-Briggite Gomez-Rojas ◽

Yuri Sánchez-Solis ◽

Wagner Vicente-Ramos

Keyword(s):

Experimental Design ◽

Linear Regression ◽

Correlation Analysis ◽

Regression Model ◽

Multiple Linear Regression ◽

Linear Regression Model ◽

Multiple Linear Regression Model ◽

Cross Sectional ◽

Key Account ◽

The Impact

The purpose of this research was to evaluate the degree of influence exercised by the Key Account Manager in the provisioning management in the main companies called Staple in Peru, during the events of COVID-19. The research was of type quantitative, cross-sectional and temporal, with a non-experimental design, using a multiple linear regression model and correlation analysis to determine the impact that exists between the variables. The data belongs to the Industrias San Miguel company, distributed in a weekly period from June 2019 to March 2021, which gives 88 observations. The results allow us to conclude that the Key Account Manager is an important manager of the supply of goods during the crisis caused by COVID-19 in staple companies.

Download Full-text

Extreme return, extreme volatility and investor sentiment

Filomat ◽

10.2298/fil1615949g ◽

2016 ◽

Vol 30 (15) ◽

pp. 3949-3961 ◽

Cited By ~ 7

Author(s):

Xu Gong ◽

Fenghua Wen ◽

Zhifang He ◽

Jia Yang ◽

Xiaoguang Yang ◽

...

Keyword(s):

Linear Regression ◽

Quantile Regression ◽

Regression Model ◽

Least Squares ◽

Linear Regression Model ◽

Investor Sentiment ◽

Generalized Least Squares ◽

Regression Methods ◽

Leading Role ◽

The Impact

The extreme return and extreme volatility have great influences on the investor sentiment in stock market. However, few researchers have taken the phenomenon into consideration. In this paper, we first distinguish the extreme situations from non-extreme situations. Then we use the ordinary generalized least squares and quantile regression methods to estimate a linear regression model by applying the standardized AAII, the return and volatility of SP 500. The results indicate that, except for extremely negative return, other return sequences can cause great changes in investor sentiment, and non-extreme return plays a leading role in affecting the overall American investor sentiment. Extremely positive (negative) return can rapidly improve (further reduce) the level of investor sentiment when investors encounter extremely pessimistic situations. The impact gradually decreases with improvement of the sentiment until the situation turns optimistic. In addition, we find that extreme and non-extreme volatility cannot a_ect the overall investor sentiment.

Download Full-text