Neural network techniques for monotonic nonlinear models

Changes on the CIELab values of the dyed materials after the different chemical finishing treatments using artificial neural network (ANN) and linear regression (LR) models have been predicted. The whole structural properties of fabrics and some process data which were from fiber to the finishing parameters were accepted as inputs in these models. The networks having different structures were established, and it was also focus on the parameters which could affect the performance of the established networks. It was determined that we could successfully predict the color differences values occurring on the material after the finishing applications. In addition, we realized that some ANN parameters affected the prediction performance while establishing the models. After training ANN models, the prediction of the color difference values was also tried by linear regression models. Then, extra ANN models were established for all outputs using the parameters as inputs in the LR equations, and the prediction performances of both established models were compared. According to the results, the neural network model gives a more accurate prediction performance than the LR models.

این مطالعه به منظور بررسی پیش بینی شاخص های عملکرد تولیدی در مرغان تخم گذار با استفاده از شبکه های عصبی مصنوعی و رگرسیون غیرخطی چندگانه انجام شد. بررسی بر روی اطلاعات چهار دوره متوالی پرورش در یک واحد پرورش مرغ تخم گذار صورت گرفت. روش های داده-کاوی شامل رگرسیون خطی و غیر خطی، شبکه عصبی پرسپترون سه لایه، شبکه عصبی پرسپترون چهار لایه و شبکه عصبی با تابع پایه ای شعاعی بود. در این مدل ها از متغیرهای سن گله، میزان خوراک مصرفی و فصل تولید به عنوان متغیر پیشگو و شاخص های عملکرد تولیدی شامل درصد تخم-گذاری، وزن توده ای تخم مرغ تولیدی و ضریب تبدیل غذایی به عنوان متغیر پاسخ استفاده شد. نتایج نهایی رگرسیون های خطی نشان داد که برای تمامی متغیرهای وابسته مورد مطالعه متغیر مستقل سن گله معنی دار می باشد. بنابراین رگرسیون غیر خطی شاخص های عملکرد تولیدی در مقابل سن برای مقایسه با شبکه های عصبی مختلف مورد بررسی قرار گرفت و برای مقایسه کلیه مدل ها از ضریب تعیین (R2) و میانگین قدر مطلق خطا (MAE) استفاده شد. نتایج نشان داد بین شبکه های عصبی مصنوعی مختلف مورد مطالعه، شبکه با تابع پایه ای شعاعی بهتر از سایر مدل های در پیش‌بینی شاخص های عملکرد تولیدی مرغان تخم گذار عمل می کند.

A comparison of 4 predictive models of calving assistance and difficulty in dairy heifers and cows

Performance comparison of artificial neural network and multiple regression models for wire electrical discharge machining of haste alloy

Background: Nowadays, forecasting models based on nonparametric models have been developed in many branches of science such as mathematics and economics. However, the relatively complicated structure of these models has made them less practical in medical sciences. Objectives: In this study, we investigated the application of a nonparametric regression model to predict the psychological symptoms appearing six months after mild traumatic brain injury. We also made a comparison between the performance of nonparametric regression and artificial neural network models in predicting the psychological symptoms. Methods: In a six-month period during 2015 - 2017, information of 100 mild traumatic patients was included in a prospective cohort study. The data were then divided randomly into two groups of training (n = 50) and testing (n = 50) for 100 times. In the training group, the focus was on 100 artificial neural network and nonparametric regression models. However, in the testing group, a comparison was made between the values obtained using the two final models. To compare the models, the ROC curve and the accuracy rate were finally applied. Results: According to the obtained results, the nonparametric regression model showed an accuracy rate of 91.25% while the neural network model had an accuracy rate of 85.34%. In the experimental set for both neural network and nonparametric regression models, the area under the ROC curve appeared to be 81.51% and 85.73 %, respectively. Conclusions: The nonparametric regression model appeared to be more powerful than the neural network model in predicting psychological symptoms.

Particulate atmospheric pollution in urban areas is considered to have significant impact on human health. Therefore, the ability to make accurate predictions of particulate ambient concentrations is important to improve public awareness and air quality management. This study examines the possibility of using neural network methods as tools for daily average particulate matter with aerodynamic diameter <10 µm (PM10) concentration forecasting, providing an alternative to statistical models widely used up to this day. Based on a data inventory, in a fixed central site in Athens, Greece, ranging over a two-year period, and using mainly meteorological variables as inputs, neural network models and multiple linear regression models were developed and evaluated. Comparison statistics used indicate that the neural network approach has an edge over regression models, expressed both in terms of prediction error (root mean square error values lower by 8.2–9.4%) and of episodic prediction ability (false alarm rate values lower by 7–13%). The results demonstrate that artificial neural networks (ANNs), if properly trained and formed, can provide adequate solutions to particulate pollution prognostic demands.

In this article, a rainfall forecasting model using monthly historical rainfall data and climate indices is developed by incorporating wavelet analysis (WA) and second order volterra nonlinear model. The monthly rainfall time series and large-scale climate index time series are decomposed using wavelets into a certain number of component subseries at different temporal scales. The lag relationship between the rainfall anomaly and each potential predictor is identified by cross correlation analysis with a lag time of at least 1 month at different temporal scales. The components of predictor variables with known lag times are then integrated using a second order Volterra model. Further, orthogonal least squares method is used to reduce the redundant variables and select the significant variables to be included into the final forecast model. The proposed multivariate wavelet nonlinear rainfall forecasting method is examined with over three places in India, and compared to the traditional ANN model based on the original time series and linear wavelet regression model. The models are trained with data from the 1916 to 1968 period and then tested in the 1968–1989 period. The results show that the proposed wavelet nonlinear model provides considerably more accurate monthly rainfall forecasts for the three selected places in India than the traditional regression model, neural networks model and the wavelet based linear model. It was seen that for the proposed models and other models also, both the past rainfall and the large-scale climate signals were useful in forecasting the future.

The goal of the research was to develop a new predictive tool for assessing the performance of traffic sign retroreflectivity and to compare the developed tool with the existing linear regression models. Retroreflectivity decreases as sign sheeting ages. Currently Louisiana Department of Transportation and Development (LADOTD) replace signs with low reflectivity based on driver complaints. This practice might have resulted in premature sign replacement (removal of signs with several years of in-service life still remaining) or in non-replacement of signs that are not in compliance with LADOTD minimum reflectivity standards. In this study, both neural network models and regression models were developed to predict reflectivity of Engineering and High Intensity Grade signs. The LADOTD traffic sign inventory data of Ascension Parish traffic signs were used for model development, validation and comparison. The performance of the developed neural network models (NN models) was compared to the developed regression models (R2 models) and also to the existing retroreflectivity regression models (R1 models) developed by Wolshon et al. The R1 models were developed for traffic signs placed along Interstate and State Highway routes in the districts of New Orleans, Baton Rouge, Lafayette, and Shreveport. Also, the usability of the neural network models developed in the study was analyzed based on the data collected by Wolshon et al to develop the linear regression R1 models. The results of this study demonstrated the feasibility of using ANNs in predicting the retroreflectivity of Type I and Type III sign sheeting. The independent variables found to be statistically significant variables in explaining the performance of traffic signs retroreflectivity included age of the sign, sheeting type, and background color of sign sheeting. A comparison of the models developed with two different specifications involving different sets of independent variables showed that the models including all the variables (i.e., Age, Edge of Pavement Distance, Sign Orientation, Sign Background Color, and Sheeting Type) increased the explanatory power of the models by little. However, it was recommended to use of all deterioration variables whose effects are not non-existent.

Different chemical attributes, measured via total soluble solids (TSS), acidity, vitamin C (VitC), total sugars (Tsugar), and reducing sugars (Rsugar), were determined for three groups of citrus fruits (i.e., orange, mandarin, and acid); each group contains two cultivars. Artificial neural network (ANN) and multiple linear regression (MLR) models were developed for TSS, acidity, VitC, Tsugar, and Rsugar from fresh citrus fruits by applying different independent variables, namely the dimensions of the fruits (length (FL) and diameter (FD)), fruit weight (FW), yield/tree, and soil electrical conductivity (EC). The results of ANN application showed that a feed-forward back-propagation network type with four input neurons (Yield/tree, FW, FL, and FD) and eight neurons in one hidden layer provided successful modeling efficiencies for TSS, acidity, VitC, Tsugar, and Rsugar. The effect of the EC variable was not significant. The hyperbolic tangent of both the hidden layer and the output layer of the developed ANN model was chosen as the activation function. Based on statistical criteria, the ANN developed in this study performed better than the MLR model in predicting the chemical attributes of fresh citrus fruits. The root mean square error of TSS, acidity, VitC, Tsugar, and Rsugar ranged from 0.064 to 0.453 and 0.068 to 0.634, respectively, for the ANN model, and 0.568 to 4.768 and 0.550 to 4.830, respectively, for the MLR model using training and testing datasets. In addition, the relative errors obtained through the ANN approach provided high model predictability and feasibility. In chemical attribute modeling, the FD and FL variables exhibited high contribution ratios, resulting in a reliable predictive model. The developed ANN model generally showed a good level of accuracy when estimating the chemical attributes of fresh citrus fruit.

Hairiness is a very important yarn quality parameter for high speed weaving. This paper presents a comparative analysis of two modeling methodologies for the prediction of ring and rotor yarn hairiness. Cotton fibre properties measured by a high volume instrument (HVI) and yarn count have been used as inputs for artificial neural network (ANN) and linear regression models. The prediction accuracy for both of the models is found to be good as the correlation coefficient is higher than 0.92 and mean absolute error is less than 4%. However, ANN models have an edge over the regression model particularly for ring yarn hairiness prediction. The importance of the cotton fibre properties on yarn hairiness has also been analysed by the developed ANN and regression models. For ring spun yarns, the ranking of cotton fibre properties given by the ANN and regression models are generally in agreement although some disparities exist in the ranking of length properties. Both models yield almost identical ranking of cotton fibre properties for rotor yarn hairiness.

This paper aims to detect the periodic coefficients of a Linear Regression model with Panel Data. Nonparametric locally and asymptotically optimal tests are proposed for testing the null hypothesis of a traditional linear regression model, against an alternative of a Periodic Coefficient Regression model. The Uniform Local Asymptotic Normality (ULAN) property is established for Periodic Linear Regression (PLR) model, to construct Locally asymptotically optimal tests. The rank-based version of the optimal parametric test is provided in particular cases. The performance of the proposed tests is valid with numerical simulations using the Monte Carlo study. Real data was studied for applying the periodic linear regression model which compared to both traditional regression and random coefficient regression models.

Background: Data mining (DM) is an approach used in extracting valuable information from environmental processes. This research depicts a DM approach used in extracting some information from influent and effluent wastewater characteristic data of a waste stabilization pond (WSP) in Birjand, a city in Eastern Iran. Methods: Multiple regression (MR) and neural network (NN) models were examined using influent characteristics (pH, Biochemical oxygen demand [BOD 5 ], temperature, chemical oxygen demand [COD], total suspended solids [TSS], total dissolved solid [TDS], electrical conductivity [EC] and turbidity) as the regression input vectors. Models were adjusted to input attributes, effluent BOD 5 (BODout) and COD (CODout). The models performances were estimated by 10-fold external cross-validation. An internal 5-fold cross-validation was also used for the training data set in NN model. The models were compared using regression error characteristic (REC) plot and other statistical measures such as relative absolute error (RAE). Sensitivity analysis was also applied to extract useful knowledge from NN model. Results: NN models (with RAE = 78.71 ± 1.16 for BODout and 83.67 ± 1.35 for CODout) and MR models (with RAE = 84.40% ± 1.07 for BODout and 88.07 ± 0.80 for CODout) indicate different performances and the former was better (P < 0.05) for the prediction of both effluent BOD 5 and COD parameters. For the prediction of CODout the NN model with hidden layer size (H) = 4 and decay factor = 0.75 ± 0.03 presented the best predictive results. For BODout the H and decay factor were found to be 4 and 0.73 ± 0.03, respectively. TDS was found as the most descriptive influent wastewater characteristics for the prediction of the WSP performance. The REC plots confirmed the NN model performance superiority for both BOD and COD effluent prediction. Conclusion: Modeling the performance of WSP systems using NN models along with sensitivity analysis can offer better understanding on exploring the most significant parameters for the prediction of system performance. The findings of this study could build the foundation for prospective work on the characterization of WSP operations and optimization of their performances with a view to conducting statistical approaches.

Multi-Regional Surrogate Model Selection (MRSMS) approach for the analysis and optimal fitting of univariate responses

Evaluation of data driven models for river suspended sediment concentration modeling

This paper deals with a new approach of non-invasive glucose monitoring based on near infrared spectroscopy. The proposed approach is coupled with a regression analysis in order to improve the predictive capacity of the designed device. Basic spectral data is a comparison that has been established between linear and non-linear machine learning regression algorithms. The experimental results show that feed forward backpropagation neural network improves more the performance of the designed prototype than partial least square models. The squared correlation coefficient and the Root Mean Square Error (RMSE) of the Artificial Neural Network (ANN) regression model built were 0.9804 and 0.0784 respectively. The ANN regression model was then used in the validation step using 300 human serums with a concentration range of 08-297 mg/dl. Clarke Error Grid Analysis (EGA) showed that 97% of the measured concentrations fall within the clinically acceptable regions. Results showed that the created model can open a new path to a non-invasive glucose monitoring.