Evaluation of effective electrospinning parameters controlling gelatin nanofibers diameter via modelling artificial neural networks

The aim of this work was to evaluate the effective parameters for prediction of the electrospun gelatin nanofibers diameter using artificial neural network (ANN) technique. The various sets of electrospinning process including temperature, applied voltage and polymer and solvent concentrations were designed to produce pure gelatin nanofibers. The obtained results by analyzing Scanning Electron Microscopy (SEM) images indicated that the produced nanofibers diameter was in the range of 85 to 750 nm. Due to the volume of the data, k fold cross-validation method was used for data setting. Data were divided into the five categories and trained and tested using ANN technique. The results indicated that the network including 4 input variables, 3 hidden layers with 10, 18 and 9 nodes in each layers, respectively, and one output layer had the best performance in the testing sets. The mean squared error (MSE) and linear regression (R) between observed and predicted nanofibers diameter were 0.1531 and 0.9424, respectively. The obtained results demonstrated that the selected neural network model had acceptable performance for evaluating involved parameters and prediction of nanofibers diameter.     

Comparison between artificial neural network and response surface methodology in the prediction of the production rate of polyacrylonitrile electrospun nanofibers

This paper focused on using response surface methodology (RSM) and artificial neural network (ANN) to analyze production rate of electrospun nanofibers. The three important electrospinning factors were studied including polymer concentration (wt %), applied voltage (kV) and the nozzle-collector distance (cm). The predicted production rates were in agreement with the experimental results in both ANN and RSM techniques. High regression coefficient between the variables and the response (R ²=0.975) indicates excellent evaluation of experimental data by second-order polynomial regression model. The regression coefficient was 0.988, which indicates that the ANN model was shows good fitting with experimental data. The obtained results indicate that the performance of ANN was better than RSM. It was concluded that applied voltage plays an important role (relative importance of 42.8 %) against production rate of electrospun nanofibers. The RSM model predicted the 2802.3 m/min value of the highest production rate at conditions of 15 wt % polymer concentration, 16 kV of the applied voltage, and 15 cm of nozzle-collector distance. The predicted value showed only 4.4 % difference with experimental results in which 2931.0 m/min at the same setting was observed.     

Artificial neural network approach for predicting colour properties of laser-treated denim fabrics

In this study, artificial neural network (ANN) and linear regression (LR) approaches are proposed for predicting colour properties of laser-treated denim fabrics. Denim fabrics were treated under different combinations of laser processing parameters, including pixel time (μs), resolution (dot per inch) and grayscale (lightness percentage) as inputs. Colour properties, including colour yield (K/S sum value), CIE L*, a* and b* values and yellowness index were predicted as outputs in these approaches. Later, the prediction performances of two approaches were compared and the statistical findings revealed that ANN approach was able to provide more accurate prediction than LR approach, especially for L value. Moreover, among the three input variables, grayscale (lightness percentage) was found to be the most important factor affecting colour properties of laser-treated denim fabrics.     

Comparison of artificial neural network and linear regression models for prediction of ring spun yarn properties. I. Prediction of yarn tensile properties

In this study artificial neural network (ANN) models have been designed to predict the ring cotton yarn properties from the fiber properties measured on HVI (high volume instrument) system and the performance of ANN models have been compared with our previous statistical models based on regression analysis. Yarn count, twist and roving properties were selected as input variables as they give significant influence on yarn properties. In experimental part, a total of 180 cotton ring spun yarns were produced using 15 different blends. The four yarn counts and three twist multipliers were chosen within the range of Ne 20–35 and α _e 3.8–4.6 respectively. After measuring yarn tenacity and breaking elongation, evaluations of data were performed by using ANN. Afterwards, sensitivity analysis results and coefficient of multiple determination (R²) values of ANN and regression models were compared. Our results show that ANN is more powerful tool than the regression models.     

Simulation for response of crop yield to soil moisture and salinity with artificial neural network

In saline fields, irrigation management often requires understanding crop responses to soil moisture and salt content. Developing models for evaluating the effects of soil moisture and salinity on crop yield is important to the application of irrigation practices in saline soil. Artificial neural network (ANN) and multi-linear regression (MLR) models respectively with 10 (ANN-10, MLR-10) and 6 (ANN-6, MLR-6) input variables, including soil moisture and salinity at crop different growth stages, were developed to simulate the response of sunflower yield to soil moisture and salinity. A connection weight method is used to understand crop sensitivity to soil moisture and salt stress of different growth stages. Compared with MLRs, both ANN models have higher precision with RMSEs of 1.1 and 1.6 t ha⁻¹, REs of 12.0% and 17.3%, and R² of 0.84 and 0.80, for ANN-10 and ANN-6, respectively. The sunflower sensitivity to soil salinity varied with the different soil salinity ranges. For low and medium saline soils, sunflower yield was more sensitive at crop squaring stage, but for high saline soil at seedling stage. High soil moisture content could compensate the yield decrease resulting from salt stress regardless of salt levels at the crop sowing stage. The response of sunflower yield to soil moisture at different stages in saline soils can be understood through the simulated results of ANN-6. Overall, the ANN models are useful for investigating and understanding the relationship between crop yield and soil moisture and salinity at different crop growth stages.     

Prediction of CIELab data and wash fastness of nylon 6,6 using artificial neural network and linear regression model

We tried to predict the CIELab data and wash fastness values of scoured nylon 6.6 knitted fabric dyed with 1:2 metal-complex acid dyes and aftertreated using three different methods named as syntan, syntan/cation and full backtan by artificial neural network (ANN) with Levenberg-Marquardt algorithm and regression models. Afterward, the predicting performance of these models was tested and compared with each other using unseen data sets. We were able to achieve to predict the all colorimetric data satisfactorily such as L*, a*, b*, C, h ^o and wash fastness performance using both models. The statistical findings indicated that the regression models provide more accurate prediction for all colour data with an average error of 1% contrast to previous study. In terms of prediction of fastness, artificial neural network is a bit more useful than regression models for prediction of staining value on the nylon part of adjacent multifiber.     

Improving the accuracy of models to map alpine grassland above-ground biomass using Google earth engine

Accurate modelling and mapping of alpine grassland aboveground biomass (AGB) are crucial for pastoral agriculture planning and management on the Qinghai Tibet Plateau (QTP). This study assessed the effectiveness of four popular models (traditional multiple linear regression (MLR), support vector machine (SVM), artificial neural network (ANN), and deep neural network (DNN)) with various input combinations (geospatial variables [GV], vegetation types [VT], field measurements [FM], meteorological variables [MV] and observation time [OT]) for AGB estimation based on a new framework for AGB modelling and mapping using Google Earth Engine. The results showed that the input feature of GV had a poor performance in AGB estimation (0.121 < R² < 0.591). FM improved the accuracy the most when incorporated with GV (0.815 < R² < 0.833). Although MV, VT and OT improved the accuracy (R²) only by 0.112–0.216 with an importance rank order of MV > VT > OT for machine learning models, their outputs could be used to map AGB. Grass AGB was less accurately predicted than shrub AGB, but the pooling of both VTs improved estimation accuracy (R²) by 0.171–0.269. The performance of the models followed the ranked order of DNN > ANN > SVM > MLR. DNN had the highest accuracy (R² = 0.818) using all non-field measured variables (excluding FM) as the inputs, and it was successfully applied to a new dataset (not associated with the data used in the training and testing) with a R² of 0.676. This study presents an effective and operational framework for modelling and mapping grassland AGB. Accordingly, it provides the scientific foundations to determine of sustainable grazing carrying capacity in alpine grasslands.     

Predicting properties of single jersey fabrics using regression and artificial neural network models

In our previous works, we had predicted cotton ring yarn properties from the fiber properties successfully by regression and ANN models. In this study both regression and artificial neural network has been applied for the prediction of the bursting strength and air permeability of single jersey knitted fabrics. Fiber properties measured by HVI instrument and yarn properties were selected as independent variables together with wales’ and courses’ number per square centimeter. Firstly conventional ring yarns were produced from six different types of cotton in four different yarn counts (Ne 20, Ne 25, Ne 30, and Ne 35) and three different twist multipliers (α _e 3.8, α _e 4.2, and α _e 4.6). All the yarns were knitted by laboratory circular knitting machine. Regression and ANN models were developed to predict the fabric properties. It was found that all models can be used to predict the single jersey fabric properties successfully. However, ANN models exhibit higher predictive power than the regression models.     

Using artificial neural network to predict colour properties of laser-treated 100% cotton fabric

In this paper, artificial neural network (ANN) model was used for predicting colour properties of 100 % cotton fabrics, including colour yield (in terms of K/S value) and CIE L, a, and b values, under the influence of laser engraving process with various combination of laser processing parameters. Variables examined in the ANN model included fibre composition, fabric density (warp and weft direction), mass of fabric, fabric thickness and linear density of yarn (warp and weft direction). The ANN model was compared with a linear regression model where the ANN model produced superior results in prediction of colour properties of laser engraved 100 % cotton fabrics. The relative importance of the examined factors influencing colour properties was also investigated. The analysis revealed that laser processing parameters played an important role in affecting the colour properties of the treated 100 % cotton fabrics.     

An artificial neural network approach to prediction of the colorimetric values of the stripped cotton fabrics

This paper presents an artificial neural network (ANN) modeling by Levenberg-Marquardt (LM) algorithm for predicting the colorimetric values of the stripped cotton fabrics dyed using commercial reactive dyes. Achieving the expected efficiency in the application of stripping process is a very important aspect for the success of the reproduction. In the study, the predictions of L* and ΔE colorimetric values of stripped cotton samples for different stripping applications by artificial neural network are reported. We set up different network structures with different number of nodes in the hidden layer, the number of inputs and MSE of results as stopping criteria in order to get the best fitting model. According to the result of the best neural network models predicting L* and ΔE, we achieved 97 % of R for both of them. We are able to predict the L* value of the stripped samples using some working parameters as inputs with only 1.2 % error. We think that our results are very promising and the predictions of L* and ΔE values of stripped samples before applying any process are possible using the ANN model set up in the study, especially for L*.     

A scanner based neural network technique for color matching of dyed cotton with reactive dye

Conventional theory for color matching is Kubelka-Munk, but it fails in some situations. New intelligent procedures such as neural networks could learn the behavior of a complex system and produce accurate prediction. This paper investigates the ability of MLP (multiple layer perceptron) neural network for color matching of cotton fabric. Three reactive dyes, namely Levafix Red CA, Levafix Yellow CA and Levafix Blue CA were used for experiments. The dyed samples were scanned and L * a * b * histogram were extracted. Different neural networks were trained and tested using L * a * b * histogram of fabric’s images and also L * a * b * values (D65, 10°) of fabrics. The results were encouraging. For neural networks including the L * a * b * histogram in input vector, colorants and their concentration were predicted with a mean square error (MSE) less than 10^?5 and an average value of color difference (CMC (1:2)) less than 1.5 for approximately 80 % of testing data.     

基于等距拆分和随机森林算法的皖北小麦始花期气象预报

为探讨基于等距拆分和随机森林算法用于皖北小麦始花期气象预报的可行性，利用1980-2019年皖北地区7个农业气象观测站的冬小麦始花期原位观测物候数据和平行观测的气象数据，采用相关系数法，筛选影响始花期早迟的特征变量，采用有序等距离抽样法，拆分出训练集和测试集。基于随机森林算法（RF），从4月10日到4月15日，每日训练1个预报模型，实现小麦始花期逐日滚动气象预报，并与基于类神经网络（ANN）、线性支撑向量机（LSVM）、多元回归（RG）和支持向量机（SVM）4种算法训练的预报模型进行比较。结果表明，由平均气温、最高气温、日照时数3类气象要素构成的40个关键气象因子与小麦始花期早迟密切相关；训练出的6个始花期逐日气象预报模型中，4月10-14日5个模型入选特征变量均为40个，4月15日模型入选特征变量为39个；6个气象预报模型训练集与测试集的平均正确率分别为93.3%和80.4%，平均均方根误差（RMSE）分别为1.860～1.960和2.510～2.709，平均决定系数分别为0.944和0.841；基于RF算法训练的预报模型3项检验指标均优于ANN、LSVM、RG和SVM算法训练的预报模型；利用RF算法模型在2020年和2021年进行预报，提前7～9 d准确预报出当年始花期。由此可见，采用有序等距离抽样拆分出训练集，再基于RF算法构建的皖北地区小麦花期气象预报模型，能够以较高精度对小麦始花期进行预报。     

Prediction of cotton yarn properties using support vector machine

This paper presents a support vector machine (SVM) regression approach to forecast the properties of cotton yarns produced on ring and rotor spinning technologies from the fibre properties measured by HVI and AFIS. Prediction performance of SVM models have been compared against those of the artificial neural network (ANN) models. A k-fold cross validation technique is applied to assess the expected generalization accuracies of both SVM and ANN models. The investigation indicates that the yarn properties can be predicted with a very high degree of accuracy using SVM models and the prediction performance of SVM models are better than that of ANN models.     

Prediction of water quality effect on saturated hydraulic conductivity of soil by artificial neural networks

This study was conducted to investigate the impact of water salinity (EC_w) and sodicity (SAR_w) on saturated (K_s) and relative (K_r) hydraulic conductivities in two clay (C) and sandy clay loam (SCL) soils. The results showed that the K_s decreased with increasing SAR_w, and in all of water quality treatments, the K_s of SCL soil was higher than that of the C soil. Sodicity effect (even at high SAR_w) on the K_r of clay soil was minimized by high salinity. Although K_r of both soils similarly responded to EC_w and SAR_w, microstructure of clay soil was more sensitive to water quality. Effect of EC_w on soil structure was greater than that of SAR_w. In order to assess the applicability of artificial neural networks (ANNs) in estimating K_s and K_r, two types of FFBP and CFBP ANNs and two training algorithms, namely Levenberg–Marquardt (LM) and Bayesian regulation, were employed with two strategies of uniform threshold and different threshold functions. Multiple linear regressions were also used for K_s and K_r prediction. Based on the ANN results of second strategy, best topology (4–5–4–1) was belonged to CFBP network with LM algorithm, LOGSIG–LOGSIG–TANSIG threshold functions, and values of MAE and R² are equal to 0.1761 and 0.9945, respectively. Overall, the efficacy of ANNs is much greater than regression method for K_s prediction.     

Effects of Nitrogen Fertilizer Level on Chlorophyll Fluorescence Characteristics in Flag Leaf of Super Hybrid Rice at Late Growth Stage

To compare the effects of slow-release nitrogen fertilizer at six different levels on the flag leaf chlorophyll fluorescence characteristics of super hybrid rice,a field fertilization experiment was conducted with super hybrid rice Y Liangyou 1 as a test material.The photosynthetic electron transport rate (ETR),effective quantum yield (EQY),photochemical quenching coefficient (q P),and non-photochemical quenching coefficient (NPQ) of flag leaves were measured at the initial heading,full heading,10 d after full heading and 20 d after full heading stages.Results showed that the values of ETR,EQY and q P increased with rice development from initial heading to 20 d after full heading,whereas the NPQ decreased.During the measured stages,ETR,EQY and q P increased initially and then decreased as nitrogen application amount increased,but they peaked at different nitrogen fertilizer levels.The maximum ETR and EQY values appeared at the treatment of 135 kg/hm 2 N.In conclusion,the optimum nitrogen amount for chlorophyll fluorescence characteristics of super hybrid rice was 135 180 kg/hm 2.     

Prediction of the changes on the CIELab values of fabric after chemical finishing using artificial neural network and linear regression 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.     

Prediction of mechanical properties of aging B.mori silk fabric based on grey neural network model

This paper presents a grey neural network model for the prediction of mechanical properties of aging B.mori silk fabric. In the experiment, we obtained outdoor natural aging breaking strength of B.mori silk fabric from 8 samples. Then, a grey neural network GNNM (1,1) model is proposed by the means of combining GM (1,1) model with BP artificial neural network to predict mechanical properties of B.mori silk fabric. At the same time, this paper analyzed and compared the GM (1,1) model and GNNM (1,1) model by using prediction error such as the relative percentage error (RPE) and the root mean square error (RMSE). The experimental results show that the RMSE of GNNM (1,1) model is 0.0284 well below 6.1786, which is the RMSE of GM (1,1) model. It indicates the GNNM (1,1) model were better than the normal grey GM (1,1) model, when taken the prediction error as evaluation parameter.     

A neural network model for prediction of strength loss in threads during high speed industrial sewing

In this paper artificial neural network (ANN) model has been designed to predict the strength loss in threads during high speed industrial sewing. Four different types of threads (Mercerized cotton, polyester staple spun, polyester-cotton core spun and polyester-polyester core spun) were taken for the study. The other input parameters include thread linear density, fabric area density, number of fabric layers, stitch density and needle size. In order to reduce the dependency of the results on a specific partition of the data into training and testing sets, a four-way cross validation tests were performed, i.e. total data was divided into training and testing set in four different ways. The predicted tenacity loss was correlated to the experimental tenacity loss and correlation coefficient between the actual and predicted tenacity loss obtained. It was observed that the neural network system is able to predict the tenacity loss of threads after sewing with good correlation and less average error. The relative contribution of each parameter to the overall prediction of the tenacity loss was studied by carrying out the sensitivity analysis of the test data set. The results of sensitivity analysis show that thread type is the most important input parameter followed by thread linear density, number of fabric layers, fabric area density, needle size and the stitch density.     

Artificial Neural Network Modelling of Leaf Water Potential for Potatoes Using RGB Digital Images: A Greenhouse Study

Plant water status information of potato (Solanum tuberosum L. cv. Russet Burbank) is needed at the farm level for irrigation scheduling. This research investigated the feasibility of using a 5-megapixel digital camera to determine the leaf water potential (Ψ_L) of potato plants by capturing red, green, blue (RGB) digital images in the visible region of the electromagnetic spectrum. A greenhouse experiment was conducted in containerized cv. Russet Burbank potato plants subjected to five soil nitrate-nitrogen (N) levels and four soil water content levels. An artificial neural network (ANN) model, built with RGB images, RGB image transformations, RGB vegetation indices, and principal components analysis, found that for the validation data set, the measured Ψ_L and predicted Ψ_L results were from common populations. Other results showed: (1) a linear trend between soil nitrate-N levels and leaf reflectance in the G image band, (2) that the RG image bands were more suitable than the B image band for classifying leaf pigment from leaf shadow and leaf damage, (3) soil nitrate-N interacted with leaf greenness, affecting Ψ_L prediction, and (4) some image variables were more important than others in the ANN model. Although this greenhouse research shows promise, further field-based research is required to validate the selection of input neurons used and also validate the use of ANN modelling to determine Ψ_L at the plant canopy level with cv. Russet Burbank and other cultivars. In addition, an image acquisition method needs to be developed to obtain periodic representative sample coverage over a field.