scholarly journals Development of a Low-Cost Optical Sensor to Detect Eutrophication in Irrigation Reservoirs

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7637
Author(s):  
Javier Rocher ◽  
Lorena Parra ◽  
Jose M. Jimenez ◽  
Jaime Lloret ◽  
Daniel A. Basterrechea
Keyword(s):  
Multiple Regression ◽  
Regression Models ◽  
Low Cost ◽  
Absolute Error ◽  
Alternative Methods ◽  
Validation Phase ◽  
Massive Growth ◽  
Multiple Regression Models ◽  
Artificial Neural ◽  
Irrigation Infrastructure

In irrigation ponds, the excess of nutrients can cause eutrophication, a massive growth of microscopic algae. It might cause different problems in the irrigation infrastructure and should be monitored. In this paper, we present a low-cost sensor based on optical absorption in order to determine the concentration of algae in irrigation ponds. The sensor is composed of 5 LEDs with different wavelengths and light-dependent resistances as photoreceptors. Data are gathered for the calibration of the prototype, including two turbidity sources, sediment and algae, including pure samples and mixed samples. Samples were measured at a different concentration from 15 mg/L to 4000 mg/L. Multiple regression models and artificial neural networks, with a training and validation phase, are compared as two alternative methods to classify the tested samples. Our results indicate that using multiple regression models, it is possible to estimate the concentration of alga with an average absolute error of 32.0 mg/L and an average relative error of 11.0%. On the other hand, it is possible to classify up to 100% of the samples in the validation phase with the artificial neural network. Thus, a novel prototype capable of distinguishing turbidity sources and two classification methodologies, which can be adapted to different node features, are proposed for the operation of the developed prototype.

Prediction of Cotton Ring Yarn Evenness Properties from Process Parameters by Using Artificial Neural Network and Multiple Regression Analysis

2011 ◽  
Vol 366 ◽  
pp. 103-107 ◽  
Author(s):  
Bo Zhao
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Multiple Regression ◽  
Process Parameters ◽  
Regression Models ◽  
Absolute Error ◽  
Multiple Regression Model ◽  
Ring Yarn ◽  
Multiple Regression Models ◽  
Artificial Neural

The artificial neural network and multiple regression models have been developed to predict the evenness of cotton ring yarn with process parameters such as front roller speed, spindle speed, nip gauge, back draft zone time and roving twist. The efficiencies of prediction of the two models have been experimentally verified, and the predicted evennesses of cotton ring yarns from both the models have been compared statistically. An attempt has been made to study the effect of process parameters on yarn evenness. The MSE and mean absolute error of ANN modelare lower than that of multiple regression model. The results show that the performances of prediction of ANN models are more accurate than those of multiple regression models.

Estimation of Calorific Values of Some of the Turkish Lignites by Artificial Neural Network and Multiple Regressions

2020 ◽  
Vol 10 (2) ◽  
pp. 154-162
Author(s):  
Engin Özdemir ◽  
Didem Eren Sarici
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Multiple Regression ◽  
Regression Models ◽  
Calorific Value ◽  
Volatile Matter ◽  
Ash Content ◽  
Percentage Error ◽  
Multiple Regression Models ◽  
Artificial Neural

Background: The calorific value is the most important and effective factors of lignites in terms of energy resources. Humidity, ash content, volatile matter and sulfur content are the main factors affecting lignite's calorific values. Objective: Determination of calorific value is a process that takes time and cost for businesses. Therefore, estimating the calorific value from the developed models by using other parameters will benefit enterprises in term of time, cost and labor. Method: In this study calorific values were estimated by using artificial neural network and multiple regression models by using lignite data of 30 different regions. As input parameters, humidity, ash content and volatile matter values are used. In addition, the mean absolute percentage error and the significance coefficient values were determined. Results: Mean absolute percentage error values were found to be below 10%. There is a strong relationship between calorific values and other properties (R2> 90). Conclusion: As a result, artificial neural network and multiple regression models proposed in this study was shown to successfully estimate the calorific value of lignites without performing laboratory analyses.

scholarly journals Multiple regression models and Artificial Neural Network (ANN) as prediction tools of changes in overall quality during the storage of spreadable processed Gouda cheese

2019 ◽  
Vol 245 (11) ◽  
pp. 2539-2547 ◽  
Author(s):  
J. Stangierski ◽  
D. Weiss ◽  
A. Kaczmarek
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Multiple Regression ◽  
Regression Models ◽  
Principal Component ◽  
Multiple Regression Models ◽  
Gouda Cheese ◽  
Artificial Neural ◽  
Validation Set ◽  
Artificial Neural Network Ann

Abstract The aim of the study was to compare the ability of multiple linear regression (MLR) and Artificial Neural Network (ANN) to predict the overall quality of spreadable Gouda cheese during storage at 8 °C, 20 °C and 30 °C. The ANN used five factors selected by Principal Component Analysis, which was used as input data for the ANN calculation. The datasets were divided into three subsets: a training set, a validation set, and a test set. The multiple regression models were highly significant with high determination coefficients: R2 = 0.99, 0.87 and 0.87 for 8, 20 and 30 °C, respectively, which made them a useful tool to predict quality deterioration. Simultaneously, the artificial neural networks models with determination coefficient of R2 = 0.99, 0.96 and 0.96 for 8, 20 and 30 °C, respectively were built. The models based on ANNs with higher values of determination coefficients and lower RMSE values proved to be more accurate. The best fit of the model to the experimental data was found for processed cheese stored at 8 °C.

scholarly journals Application of Artificial Neural Networks for estimating index floods

2012 ◽  
Vol 42 (4) ◽  
pp. 295-311 ◽  
Author(s):  
Viliam Šimor ◽  
Kamila Hlavčová ◽  
Silvia Kohnová ◽  
Ján Szolgay
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Multiple Regression ◽  
Regression Models ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Activation Function ◽  
Multiple Regression Models ◽  
Artificial Neural ◽  
Hidden Layer

Abstract This article presents an application of Artificial Neural Networks (ANNs) and multiple regression models for estimating mean annual maximum discharge (index flood) at ungauged sites. Both approaches were tested for 145 small basins in Slovakia in areas ranging from 20 to 300 km2. Using the objective clustering method, the catchments were divided into ten homogeneous pooling groups; for each pooling group, mutually independent predictors (catchment characteristics) were selected for both models. The neural network was applied as a simple multilayer perceptron with one hidden layer and with a back propagation learning algorithm. Hyperbolic tangents were used as an activation function in the hidden layer. Estimating index floods by the multiple regression models were based on deriving relationships between the index floods and catchment predictors. The efficiencies of both approaches were tested by the Nash-Sutcliffe and a correlation coefficients. The results showed the comparative applicability of both models with slightly better results for the index floods achieved using the ANNs methodology.

scholarly journals 242 Effect of trucking distance on sale price of beef calf and feeder cattle lots sold through video auctions from 2010 through 2018

2020 ◽  
Vol 98 (Supplement_3) ◽  
pp. 10-11
Author(s):  
Esther D McCabe ◽  
Mike E King ◽  
Karol E Fike ◽  
Maggie J Smith ◽  
Glenn M Rogers ◽  
...  
Keyword(s):  
Multiple Regression ◽  
Regression Models ◽  
Average Weight ◽  
Sale Price ◽  
Feeder Cattle ◽  
A Value ◽  
Multiple Regression Models ◽  
Determine Effect

Abstract The objective was to determine effect of trucking distance on sale price of beef calf and feeder cattle lots sold through Superior Livestock Video Auctions from 2010 through 2018. Data analyzed were collected from 211 livestock video auctions. There were 42,043 beef calf lots and 19,680 feeder cattle lots used in these analyses. Six states (Colorado, Iowa, Kansas, Nebraska, Oklahoma, and Texas) of delivery comprised 70% of calf lots and 83% of feeder cattle lots and were used in these analyses. All lot characteristics that could be accurately quantified or categorized were used to develop multiple regression models that evaluated effects of independent factors using backwards selection. A value of P < 0.05 was used to maintain a factor in the final models. Based upon reported state of origin and state of delivery, lots were categorized into one of the following trucking distance categories: 1) Within-State, 2) Short-Haul, 3) Medium-Haul, and 4) Long-Haul. Average weight and number of calves in lots analyzed was 259.2 ± 38.4 kg BW and 100.6 ± 74.3 head, respectively. Average weight and number of feeder cattle in lots analyzed was 358.4 ± 34.3 kg BW and 110.6 ± 104.1 head, respectively. Beef calf lots hauled Within-State sold for more ($169.24/45.36 kg; P < 0.0001) than other trucking distance categories (Table 1). Long-Haul calf lots sold for the lowest (P < 0.0001) price ($166.70/45.36 kg). Within-State and Short-Haul feeder cattle lots sold for the greatest (P < 0.0001) price ($149.96 and $149.81/45.36 kg, respectively; Table 2). Long-Haul feeder cattle lots sold for the lowest (P < 0.0001) price, $148.43/45.36 kg. These results indicate there is a price advantage for lots expected to be hauled shorter distances, likely because of cost and risk associated with transportation.

scholarly journals Prediction of Blended Yarn Evenness and Tensile Properties by Using Artificial Neural Network and Multiple Linear Regression

2016 ◽  
Vol 16 (2) ◽  
pp. 43-50 ◽  
Author(s):  
Samander Ali Malik ◽  
Assad Farooq ◽  
Thomas Gereke ◽  
Chokri Cherif
Keyword(s):  
Neural Networks ◽  
Linear Regression ◽  
Multiple Linear Regression ◽  
Tensile Properties ◽  
Regression Models ◽  
Prediction Models ◽  
Research Work ◽  
Absolute Error ◽  
Knowledge Domain ◽  
Artificial Neural

Abstract The present research work was carried out to develop the prediction models for blended ring spun yarn evenness and tensile parameters using artificial neural networks (ANNs) and multiple linear regression (MLR). Polyester/cotton blend ratio, twist multiplier, back roller hardness and break draft ratio were used as input parameters to predict yarn evenness in terms of CVm% and yarn tensile properties in terms of tenacity and elongation. Feed forward neural networks with Bayesian regularisation support were successfully trained and tested using the available experimental data. The coefficients of determination of ANN and regression models indicate that there is a strong correlation between the measured and predicted yarn characteristics with an acceptable mean absolute error values. The comparative analysis of two modelling techniques shows that the ANNs perform better than the MLR models. The relative importance of input variables was determined using rank analysis through input saliency test on optimised ANN models and standardised coefficients of regression models. These models are suitable for yarn manufacturers and can be used within the investigated knowledge domain.

Sign in / Sign up

Export Citation Format

Share Document