Back-propagation Artificial Neural Network Research Articles

Variations in the streamflow of the Nierji Reservoir Basin and quantification of the influencing factors

Abstract Nierji Reservoir is the largest and most important water conservancy project in the Nenjiang River Basin. A thorough understanding of variations in streamflow and the driving factors of the Nierji Reservoir Basin (NERB) is crucial, but there are still gaps. In this paper, the annual streamflow data of Nierji Reservoir from 1898 to 2013 were applied to detect the changing trend and abruptions using the Mann–Kendall method. Additionally, a Back Propagation-Artificial Neural Network (BP-ANN) model was developed to explore the relationships between the streamflow and its influencing factors and further quantify the relative contribution of each factor to the streamflow change. The results revealed that the annual streamflow of NERB significantly increased from 1898 to 2013 but declined during 1988–2013. Human activities were found to be the primary driver of streamflow decrease during 1988–2013, accounting for nearly 75% of the total change. Specifically, GDP had the largest influence, contributing 32% to the overall variation. Forest area, precipitation, and cultivated area had smaller contributions of 25, 23, and 18%, respectively. Temperature was found to have the least impact, with a relative contribution of 2%. This study provides valuable insights into water resources management in the Nenjiang River Basin, benefiting both agriculture and ecology.

BP neural network predicts the exchange rate of US dollar against gold

Gold and the US dollar are important currencies, and their price changes reflect changes in the world and North American economies. The gold market has become a financial investment market of equal importance to markets such as stocks, foreign exchange, and bonds. In such a situation, the price change of gold has become an important predictive research object. However, due to the changing world landscape, the randomness of gold price changes, and the existence of exchange rate and other influencing factors, it is very difficult to predict. It is crucial to establish a prediction model for exchange rate changes over time. This topic establishes a neural network model for exchange rate changes over time using the newly developed Back Propagation Neural Network in recent years. Finally, after several experiments, the parameters are adjusted to the optimal state to obtain the minimum error result. Through this study, we can determine that the prediction function of the BP artificial neural network can be applied in certain fields of life, but it also has significant limitations, to make it a complete tool for our daily life or work, it is necessary to further improve this technology.

Quality prediction of whole-grain rice noodles using backpropagation artificial neural network.

Whole-grain rice noodles are a kind of healthy food with rich nutritional value, and their product quality has a notable impact on consumer acceptability. The quality evaluation model is of great significance to the optimization of product quality. However, there are few methods that can establish a product quality prediction model with multiple preparation conditions as inputs and various quality evaluation indexes as outputs. In this study, an artificial neural network (ANN) model based on a backpropagation (BP) algorithm was used to predict the comprehensive quality changes of whole-grain rice noodles under different preparation conditions, which provided a new way to improve the quality of extrusion rice products. The results showed that the BP-ANN using the Levenberg-Marquardt algorithm and the optimal topology (4-11-8) gave the best performance. The correlation coefficients (R2) for the training, validation, testing, and global data sets of the BP neural network were 0.927, 0.873, 0.817, and 0.903, respectively. In the validation test, the percentage error in the quality prediction of whole-grain rice noodles was within 10%, indicating that the BP-ANN could accurately predict the quality of whole-grain rice noodles prepared under different conditions. This study showed that the quality prediction model of whole-grain rice noodles based on the BP-ANN algorithm was effective, and suitable for predicting the quality of whole-grain rice noodles prepared under different conditions. © 2024 Society of Chemical Industry.

Predicting the classification of high vowel sound by using artificial neural network: a study in forensic linguistics

<span lang="EN-US">One of the tasks in forensic linguistics, especially forensic phonetics, is evaluating the speech sounds in the recordings. The speech evaluation aims at identifying and verifying speakers to predict if the sound were spoken by the suspect or not. The common problem in the task is determining which acoustic features of the speech sounds are reliable for the speaker identification and verification. The purpose of this research is studying formant frequencies to predict high vowel sounds /i/, and /u/ by using artificial neural network (ANN). Using three various normalization methods (i.e., softmax, z-score and sigmoid), we utilized multilayer perceptron on backpropagation ANN with the architectural models of 4-5-2, 4-10-2 and 4-20-2. The results show that the z-score normalization method provides higher accuracy than the other two in all formations and the 4-10-2 formation has shown the highest accuracy (92.26%).</span>

QSPR Models Based on Multiple Linear Regression and Back-Propagation Artificial Neural Network for Predicting Electrical Conductivity of Ionic Liquids

QSPR Models Based on Multiple Linear Regression and Back-Propagation Artificial Neural Network for Predicting Electrical Conductivity of Ionic Liquids

Classifying Coal Mine Pillar Stability Areas with Multiclass SVM on Ensemble Learning Models

Pillars are key structural components in coal mining. The safety requirements of underground coal mines are non-negotiable. Accurately classifying the areas of pillar stability helps ensure safety in coal mines. This study aimed to classify new pillar stability categories and their stability areas. The multiclass support vector machine (SVM) method was implemented with two types of kernel functions (polynomial and radial basis function (RBF) kernels) on pillar stability data with four new categories: failed or intact, either with or without an appropriate safety factor. This classification uses three basic ensemble learning models: Artificial Neural Network-Backpropagation Rectified Linear Unit, Artificial Neural Network-Backpropagation Exponential Linear Unit, and Artificial Neural Network-Backpropagation Gaussian Error Linear Unit. The results with four data proportions and ten experiments had an average accuracy and standard deviation of 92.98% and 0.56%-1.64% respectively. The accuracies of the multiclass SVM method using the polynomial kernel and the RBF kernel with Bayesian parameter optimization to classify the areas of pillar stability were 91% and 92%, respectively. The multiclass SVM method with the RBF kernel captured 96.6% of potentially dangerous pillars. The visualization of classification areas showed that areas with intact pillars may also have failed pillars.

Prediction and visualization of moisture content in Tencha drying processes by computer vision and deep learning.

It is important to monitor and control the moisture content throughout the Tencha drying processing procedure so that its quality is ensured. Workers often rely on their senses to perceive the moisture content, leading to relative subjectivity and low reproducibility. Traditional drying methods, which are used for measuring moisture content, are destructive to samples. This research was conducted using computer vision combined with deep learning to detect moisture content during the Tencha drying process. Different color space components of Tencha drying sample images were first extracted by computer vision. The color components were preprocessed using MinMax and Z score. Subsequently, one-dimensional convolutional neural networks (1D-CNN), partial least squares, and backpropagation artificial neural networks models were built and compared. The 1D-CNN model and Z scorepreprocessing achieved superior predictive accuracy, with correlation coefficient of prediction (Rp) = 0.9548 for moisture content. The migration of moisture content during the Tencha drying process was eventually visualized by mapping its spatial and temporal distributions. The results indicated that computer vision combined with 1D-CNN was feasible for moisture prediction during the Tencha drying process. This study provides technical support for the industrial and intelligent production of Tencha. © 2024 Society of Chemical Industry.

The Prediction of Flow Stress in the Hot Compression of a Ni-Cr-Mo Steel Using Machine Learning Algorithms

The constitutive model refers to the mapping relationship between the stress and deformation conditions (such as strain, strain rate, and temperature) after being loaded. In this work, the hot deformation behavior of a Ni-Cr-Mo steel was investigated by conducting isothermal compression tests using a Gleeble-3800 thermal simulator with deformation temperatures ranging from 800 °C to 1200 °C, strain rates ranging from 0.01 s−1 to 10 s−1, and deformations of 55%. To analyze the constitutive relation of the Ni-Cr-Mo steel at high temperatures, five machine learning algorithms were employed to predict the flow stress, namely, back-propagation artificial neural network (BP-ANN), Random Committee, Bagging, k-nearest neighbor (k-NN), and a library for support vector machines (libSVM). A comparative study between the experimental and the predicted results was performed. The results show that correlation coefficient (R), root mean square error (RMSE), mean absolute value error (MAE), mean square error (MSE), and average absolute relative error (AARE) obtained from the Random Committee on the testing set are 0.98897, 8.00808 MPa, 5.54244 MPa, 64.12927 MPa2 and 5.67135%, respectively, whereas the metrics obtained via other algorithms are all inferior to the Random Committee. It suggests that the Random Committee can predict the flow stress of the steel more effectively.

Classification of Banana Types Based on The Geometrical Attributes using Artificial Neural Network Method

Banana (Musa paradisiaca) is one of the important horticultural commodities. This study aims to measure the physical and geometrical parameters of three different bananas (Muli, Ambon, and Kepok) and to develop prediction equations using an Artificial Neural Network (ANN) model. In this study the backpropagation ANN model with supervised learning method was used. The ANN model had one output node, two hidden layers, and network architecture of 8 inputs, namely fruit weight and volume, projected area and roundness of the fruit, cross section, peel color, and geometric mean fruit cross section diameter. The data for building the model and testing the model were respectively 70% and 30% of the 150 data number in total. The results showed that the best ANN model structure for estimating Muli, Ambon and Kepok bananas was purelin-logsig-logsig with an RMSE value of 0.0077 and an R2 of 0.9999. This shows that the ANN model is highly robust to predict the banana types. Using the built model, the accuracy of the prediction results is 100%. Keywords: Artificial Neural Network, Banana fruits, Geometry attribute.

Analysis and prediction of contact characteristics of rock fracture surfaces under normal loading

The real contact area of rock fractures is smaller than the nominal area, and actual stresses on contacts are significantly higher. Evaluating contact characteristics and predicting potential contact areas are crucial for understanding mechanical and hydraulic properties of geological fractures under compression or shear. We measured the real contact area of mated tensile fractures using pressure-sensitive films and studied their contact characteristics and evolution under different normal stresses through point cloud analysis. It is revealed that the initial aperture of mated tensile fractures determines the contact state. Under conditions of low normal stress, regions exhibiting higher mean curvature are more susceptible to contact formation, particularly when aperture sizes are comparable. This propensity is further influenced by the directional orientation of the normal vector components within these regions. Increasing normal stress leads to faster development of new contacts in regions with smaller initial apertures. Additionally, we predicted contact characteristics and real contact area of tensile fractures using back propagation artificial neural network. Comparison between predictions and laboratory measurements demonstrated accurate prediction of contact distribution and area values by the neural network. Our findings enable the prediction of real stress states, potential failure areas, and hydraulic conductivity of rock fractures in slope and underground rock engineering.

Gliding Footprint Calculation Method for Aircraft with Thrust Failure Based on Six-Degree-of-Freedom Flight Envelope and Back-Propagation Artificial Neural Network

In hostile environments, engine damage is of particular concern since the engine is the only component to generate thrust that affects survivability. For an aircraft suffering thrust failure, the forced landing sites should be identified within the gliding footprint, which is the reachable region on the ground. This paper proposes two calculation methods to obtain the gliding footprint by finding a series of boundary points with maximum gliding distance around the aircraft. Method 1 models the thrust-failed aircraft with six-degree-of-freedom (6-DOF) flight dynamics and adopts a novel 6-DOF unpowered-flight envelope to characterize its maneuvering capabilities. Given the initial altitude when thrust failure occurs, Method 1 determines all feasible gliding distances around the aircraft based on the constructed 6-DOF flight envelope and selects the landing points of maximum gliding distances along different radial directions as the boundary points. Method 2 employs the Back-Propagation Artificial Neural Network (BP-ANN) to predict the boundary points. Using the well-trained BP-ANN, this method can estimate the maximum gliding distances with only the initial altitude and radial directions. Simulations are conducted to analyze these two methods. Compared with conventional methods using point-mass flight dynamics, Method 1 considers more flight constraints, and the gliding footprint area is reduced by 20.79%. These results are relatively conservative and can improve the safety threshold of forced landing sites. Method 2 can estimate the gliding footprints (encircled by the boundary points under the entire operational altitude and full radial direction) in real time, which reserves more response and action time for aircraft forced landing.

Wrist EMG Monitoring Using Neural Networks Techniques

In rehabilitation, the correct performance of the exercises the specialist prescribes wrist movement is crucial. However, this may have the disadvantage of the patient’s subjectivity. Moreover, recent studies show that feedback through electrostimulation devices is beneficial during the process that leads to neuromotor rehabilitation. Besides, the electromyographic (EMG) signals give information about the actual degree of rehabilitation. This work examines whether temporal features can be used to classify wrist movements using back-propagation artificial neural networks and superficial EMG (sEMG) signals. The data for the evaluation were based on the information acquired from sEMG signals of two forearm muscles: the flexor carpi ulnaris (FCU) and the brachioradialis (B). These sEMG signals were analyzed to find the most critical parameters for classifying the wrist’s movement and to configure a multilayer perceptron (MLP) capable of classifying such movements.

Application of Northern Goshawk Back-Propagation Artificial Neural Network in the Prediction of Monohydroxycarbazepine Concentration in Patients with Epilepsy.

A northern goshawk back-propagation artificial neural network (NGO-BPANN) model was established to predict monohydroxycarbazepine (MHD) concentration in patients with epilepsy. The data were collected from 108 Han Chinese patients with epilepsy on oxcarbazepine monotherapy. The results of 14 genotype variates were selected as the input layer in the first BPANN model, and the variables that had a more significant impact on the plasma concentration of MHD were retained. With demographic characteristics and clinical laboratory test results, the genotypes of SCN1A rs2298771 and SCN2A rs17183814 were used to construct the BPANN model. The BPANN model was comprehensively validated and used to predict the MHD plasma concentration of five patients with epilepsy in our hospital. The model demonstrated favorable fitness metrics, including a mean squared error of 0.00662, a gradient magnitude of 0.00753, an absence of validation tests amounting to zero, and a correlation coefficient of 0.980. Sex, BMI, and the genotype SCN1A rs2298771 were ranked highest by the absolute mean impact value (MIV), which is primarily associated with the concentration of MHD. The test group exhibited a range of - 20.84% to 31.03% bias between the predicted and measured values, with a correlation coefficient of 0.941 between the two. With BPANN, the MHD nadir concentration could be predicted precisely. The NGO-BPANN model exhibits exceptional predictive capability and can be a practical instrument for forecasting MHD concentration in patients with epilepsy. www.chiCTR-OOC-17012141 .

Formation and prediction of heterocyclic amines and N-nitrosamines in smoked sausages using back propagation artificial neural network.

Heterocyclic amines (HAs) and N-nitrosamines (NAs) are formed easily during the thermal processing of food, and epidemiological studies have demonstrated that consuming HAs and NAs increases the risk of cancer. However, there are few studies on the application of back propagation artificial neural network (BP-ANN) models to simultaneously predict the content of HAs and NAs in sausages. This study aimed to investigate the effects of cooking time and temperature, smoking time and temperature, and fat-to-lean ratio on the formation of HAs and NAs in smoked sausages, and to predict their total content based on the BP-ANN model. With an increase in processing time, processing temperature and fat ratio, the content of HAs and NAs in smoked sausages increased significantly, while the content of HA precursors and nitrite residues decreased significantly. The optimal network topology of the BP-ANN model was 5-11-2, the correlation coefficient values for training, validation, testing and all datasets were 0.99228, 0.99785, 0.99520 and 0.99369, respectively, and the mean squared error value of the best validation performance was 0.11326. The bias factor and the accuracy factor were within acceptable limits, and the predicted values approximated the true values, indicating that the model has good predictive performance. The contents of HAs and NAs in smoked sausages were significantly influenced by the cooking conditions, smoking conditions and fat ratio. The BP-ANN model has high application value in predicting the contents of HAs and NAs in sausages, which provides a theoretical basis for the suppression of carcinogen formation. © 2024 Society of Chemical Industry.

Machine Learning Backpropagation Prediction and Analysis of the Thermal Degradation of Poly (Vinyl Alcohol).

Thermogravimetric analysis (TGA) is crucial for describing polymer materials' thermal behavior as a result of temperature changes. While available TGA data substantiated in the literature significantly focus attention on TGA performed at higher heating rates, this study focuses on the machine learning backpropagation analysis of the thermal degradation of poly (vinyl alcohol), or PVA, at low heating rates, typically 2, 5 and 10 K/min, at temperatures between 25 and 600 °C. Initial TGA analysis showed that a consistent increase in heating rate resulted in an increase in degradation temperature as the resulting thermograms shifted toward a temperature maxima. At degradation temperatures between 205 and 405 °C, significant depths in the characterization of weight losses were reached, which may be attributed to the decomposition and loss of material content. Artificial neural network backpropagation of machine learning algorithms were used for developing mathematical descriptions of the percentage weight loss (output) by these PVA materials as a function of the heating rate (input 1) and degradation temperature (input 2) used in TGA analysis. For all low heating rates, modelling predictions were observably correlated with experiments with a 99.2% correlation coefficient and were used to interpolate TGA data at 3.5 and 7.5 K/min, indicating trends strongly supported by experimental TGA data as well as literature research. Thus, this approach could provide a useful tool for predicting the thermograms of PVA materials at low heating rates and contribute to the development of more advanced PVA/polymer materials for home and industrial applications.

Prediction of Wear Resistance of In-situ Zinc Matrix Composites Reinforced by Silicon Phase Based on Neural Network

Silicon phase reinforced zinc-aluminium alloy composites were prepared by in-situ method. The effect of silicon content and external load on the wear resistance of in-situ zinc--aluminium composites was studied by BP artificial neural network. The test results show that the silicon phase, as a hard material, plays the role of supporting load and improves the wear resistance of the alloy. With the increase of Si content, the wear resistance of in-situ zinc--aluminium composites increased first and then decreased. When the amount of silicon added exceeds 2.5-3%, the wear resistance will be reduced, which is related to the silicon phase aggregation and the easy separation of large silicon phases from the matrix. With the increase of external load, the relative wear continues to increase, which is related to the increase of friction. The neural network platform can successfully predict the general trend of wear resistance with the change of silicon content and load.

Investigation of Hydrodynamics Characteristics of Fluidized Bed with back propagation Artificial Neural Network (BPANN)

Correlations have also been developed with system parameters by using dimensional analysis and an artificial neural network approach. The paper describes an investigation for the thermal design of a fluidized bed cooler and prediction of heat transfer rate among the media categories. It is devoted to the thermal design of such equipment and their application in the industrial fields. In the present work, an extensive ANN by using back propagation (BP) has been carried out to correlate the expansion ratio, fluctuation ratio in gas-solid fluidized bed. Back propagation network is the most well-known and widely used among the current types of neural network system, several applications of ANN for modeling of nonlinear process systems and subsequent control were reported. In back-propagation, different ANN structures (I×H×O) with varying number of neurons in the hidden layer were used as a tool for training input and output data for prediction value of hydrodynamic characteristics of the bed system. It was noted that ring models are the best ones in reducing bed expansion ratio and fluctuation ratio around (25%) and (23.22%).

The erosion rate prediction for the elbow in shale gas gathering and transportation system: RSM and GA-BP-ANN modeling

Elbow erosion caused by sand mixed in shale gas is a significant issue faced by shale gas gathering and transportation systems, posing a serious threat to the safe and stable production of shale gas. In this paper, the factors affecting elbow erosion in the shale gas gathering and transportation system are identified. The computational fluid dynamics (CFD) two-way coupling Euler-Lagrange method is used to investigate the single-action of various parameters on particle trajectory, erosion morphology, and maximum erosion rate, including pipe inner diameter, pipe R/D ratio, pipe bending angle, pipe bending orientation, solid particle velocity, solid particle size, and solid particle mass flow rate. Subsequently, the response surface methodology (RSM) is employed to quantitatively explore the synergistic interactions between these factors that affect the maximum erosion rate of the elbow, and a surrogate model for simple and rapid evaluation of the maximum erosion rate for elbows at the engineering level is proposed. Finally, the backpropagation artificial neural network (BP-ANN) optimized by genetic algorithm (GA) is used to train the samples obtained by Latin hypercube sampling (LHS) in the multi-factor range. By comparison, the RSM surrogate model and the GA-BP-ANN model reveal a favorable level of agreement with the experimental data, while considering various influential factors. It is important to note that each method possesses distinct advantages, limitations, and specific application environments. This research can provide quantitative references for preventing and controlling erosion within the shale gas gathering and transportation system.

Predictive Quality Analytics of Surface Roughness in Turning Operation Using Polynomial and Artificial Neural Network Models

The variability of the material properties of steel from different suppliers causes problems in achieving the required surface quality after turning. Therefore, the manufacturer needs to estimate the resulting quality before starting production, especially if it is an expensive, small-batch production from stainless steel. Predictive models will make it possible to estimate the surface roughness from the mechanical properties of steel and thus support decision making about supplier selection or acceptance of a material supply. This research presents a step-by-step decision-making procedure, which enables the trained staff to make quick decisions based on commonly available information in the Mill Test Certificate (MTC). A new multivariate second-order polynomial model and feedforward backpropagation artificial neural network (ANN) models have been developed using input variables from the MTC: Tensile Strength, Yield Strength, Elongation, and Hardness. Models were used to enhance the methodological robustness in formulating the decision if the predicted surface roughness is outside the required range, even before accepting the delivery. Both models can accurately predict surface roughness, while the ANN model is more accurate than the polynomial model; however, the predictive model is sensitive to the accuracy of the input data, and the model’s prediction is valid only under precisely defined conditions.

Comparison of machine learning and statistical approaches to estimate rock tensile strength

Tensile strength is very important in drilling operations. The main objective of this study was to assess petrography, physical, and mechanical properties and predict the Brazilian tensile strength of sedimentary rocks by leveraging key parameters such as Schmidt hardness, compressional wave velocity, density, and porosity. A diverse array of predictive models was employed, encompassing simple regression, multivariate linear and nonlinear regression, backpropagation artificial neural network, gaussian process regression, classification and regression tree, K-nearest neighbor, random forest, and support vector regression. Based on thin section analysis and X-ray diffraction, the samples were identified. The sandstone samples were meticulously categorized into two distinct groups: arenite and litharenite. Additionally, the limestone samples were stratified into the categories of packstone to mudstone based on texture. The highest failure mode frequency of the samples under the Brazilian tensile strength test was identified as central fracturing. Upon meticulous examination, it was discerned that compressional wave velocity exerted the most substantial influence on Brazilian tensile strength estimates, while density exhibited the least impact. Comparing the outcomes derived from the diverse modeling techniques, it was unequivocally established that the support vector regression model showcased the highest level of performance for forecasting Brazilian tensile strength. This was evidenced by the remarkable coefficient of determination of 0.99 along with an impressively low root mean square error of 0.03.