Back Propagation Neural Network Method Research Articles

Implementasi Algoritma Backpropagation Untuk Memprediksi Harga Jual Rumah Berdasarkan Harga Bahan Baku

Housing developers often find it difficult to determine the selling price of the house. One of the main factors to determine the selling price of the house. One of the main factors to determine the selling price of the homes is information regarding the use of raw material prices. Companies need information in prices of row material price fluctuations, air, causing the company is difficult to predict the selling price of the house next period. Forecasting methods used in this system is backpropagation neural network method that refers to a component of time series data forecasting random or random variance with the initial process for determining autocorrelation input variables. This propagation method is proven to predict the selling price of the house.

Optimization and Design of a Railway Wheel Profile Based on Interval Uncertainty to Reduce Circular Wear

Wheel tread wear is a form of wheel damage that can seriously affect the performance of freight vehicles. A new numerical approach to optimizing wheel profiles can reduce circular wear on the LM wheel in the design cycle. This approach considers the influence of different line conditions and speed fluctuation on wheel wear, along with the performance of the wheel and the rail as the materials wear. In this approach, a nonlinear numerical optimization model for the wheel tread profile is built through a backpropagation (BP) neural network method. The multipoint Kik–Piotrowski (KP) contact mechanics model is applied to calculate the wheel/rail normal force, tangential creep force, the stick-slip area, and the size and shape of the contact patch. The optimal profile is obtained through the genetic algorithm (GA) method. In order to better reflect the random characteristics of wheel/rail matching and interval uncertainty, a random sampling technique is used to generate a random data sample at typical operating speeds.

The prediction analysis of properties of recycled aggregate permeable concrete based on back-propagation neural network

The further study on recycled aggregates can promote the standardization and scale of the comprehensive recycling industry of the construction waste and meet the requirements of sustainable development. Therefore, this paper studies the relationship between the material and property and the relationship between properties of recycled aggregate permeable concrete. The test data sets of compressive strength, splitting strength, porosity and permeability coefficient of recycled aggregate permeable concrete are obtained. The results show: after statistical analysis, these four properties approximately follow the normal distribution law, and clearly there is an opposition feature between the strength and permeability. The average relative errors of the unilateral relationship prediction model (between materials and key properties) and the bilateral relationship model (between key properties) based on the Back-Propagation neural network method are both within 7%. The results of this study can provide reference for researchers to evaluate or predict the properties of recycled aggregate permeable concrete as well as reduce the loss of manpower and financial resources during the test.

Forecasting the price of Bitcoin using deep learning

After constructing a feature system with 40 determinants that affect the price of Bitcoin considering aspects of the cryptocurrency market, public attention, and the macroeconomic environment, a deep learning method named stacked denoising autoencoders (SDAE) is utilized to predict the price of Bitcoin. The results show that compared with the most popular machine learning methods, such as back propagation neural network (BPNN) and support vector regression (SVR) methods, the SDAE model performs better in both directional and level prediction, measured using commonly used indicators, i.e., mean absolute percentage error (MAPE), root mean squared error (RMSE), and directional accuracy (DA).

Nondestructive Evaluation of Thermal Barrier Coatings Interface Delamination Using Terahertz Technique Combined with SWT-PCA-GA-BP Algorithm

Thermal barrier coatings (TBCs) are usually subjected to the combined action of compressive stress, tensile stress, and bending shear stress, resulting in the interfacial delamination of TBCs, and finally causing the ceramic top coat to peel off. Hence, it is vital to detect the early-stage subcritical delamination cracks. In this study, a novel hybrid artificial neural network combined with the terahertz nondestructive technology was presented to predict the thickness of interface delamination in the early stage. The finite difference time domain (FDTD) algorithm was used to obtain the raw terahertz time-domain signals of 32 TBCs samples with various thicknesses of interface delamination, not only that, the influence of roughness and the thickness of the ceramic top layer were considered comprehensively when modeling. The stationary wavelet transform (SWT) and principal component analysis (PCA) methods were employed to extract the signal features and reduce the data dimensions before modeling, to make the cumulative contribution rate reach 100%, the first 31 components of the SWT detail data was used as the input data during modeling. Finally, a back propagation (BP) neural network method optimized by the genetic algorithm (GA-BP) was proposed to set up the interface delamination thickness prediction model. As a result, the root correlation coefficient R2 reached over 0.95, the various errors—including the mean square error, mean squared percentage error, and mean absolute percentage error—were less than or equal to 0.53. All these indicators proved that the trained hybrid SWT-PCA-GA-BP model had excellent prediction performance and high accuracy. Finally, this work proposed a novel and convenient interface delamination evaluation method that could also be potentially utilized to evaluate the structural integrity of TBCs.

Complexity Analysis of a Four-Dimensional Energy-Economy-Environment Dynamic System

A novel four-dimensional energy, economic, and environmental (3E) under energy reduction constraints chaotic system is proposed. The acquisition of environmental quality data is the key to this paper. During the course of the study, we used Bayesian estimation algorithm to calibrate the environmental quality. Based on the official data, the Levenberg–Marquardt backpropagation neural network method was optimized by genetic algorithm to effectively identify the parameters in the 3E system. The research results show that although increasing energy reduction inputs can improve environmental quality, the effect on energy intensity and overall stability of the system is not obvious. When polluting input in the ecological environment system affects its maximum capacity, the environmental system collapses (i.e., the ecological system can no longer purify the environment through the self-circulation process and will eventually die out). Therefore, it is necessary to correctly grasp the ecological environment protection and the relationship between economic developments and explore synergies to promote ecological priorities and green development new ideas.

Dataset on Insilico approaches for 3,4-dihydropyrimidin-2(1H)-one urea derivatives as efficient Staphylococcus aureus inhibitor.

Series of anti- Staphylococcus aureus were studied via quantum chemical method and several molecular descriptors were obtained which were further used to develop QSAR model using back propagation neural network method using MATLAB. More so, the molecular interaction observed between 3,4-dihydropyrimidin-2(1H)-one Urea Derivatives and Staphylococcus aureus Sortase (PDB ID Code: 2kid) via docking was used as a screening tool for the studied compounds. The observed molecular compounds used in this work was also correlated to Lipinski rule of five and the developed QSAR model using selected descriptors from the optimized compounds was also examined for its predictability. Also, the observed molecular docking revealed the interaction between the studied complex.

System Identification of Neural Signal Transmission Based on Backpropagation Neural Network

The identification method of backpropagation (BP) neural network is adopted to approximate the mapping relation between input and output of neurons based on neural firing trajectory in this paper. In advance, the input and output data of neural model is used for BP neural network learning, so that the identified BP neural network can present the transfer characteristics of the model, which makes the network precisely predict the firing trajectory of the neural model. In addition, the method is applied to identify electrophysiological experimental data of real neurons, so that the output of the identified BP neural network can not only accurately fit the neural firing trajectories of neurons participating in the network training but also predict the firing trajectories and spike moments of neurons which are not involved in the training process with high accuracy.

OPTIMASI CONJUGATE GRADIENT PADA BACKPROPAGATION NEURAL NETWORK UNTUK PREDIKSI HASIL TANGKAP IKAN

The need for fish catch by a company or fisherman in Rembang Regency affects market process and also welfare. The catch made by the fishermen is not on target, due to the weather and type of fishing gear. An accurate method is needed in making predictions and a correlation between catch and weather so that fisherman can get maximum predictions results, so that price adjustment can be made. The research was conducted using an experimental method, to determine the accuracy of the effect of the Conjugate Gradient on the Back Propagation Neural Network in obtaining the best value. Based on the results of the Cycle training test with the Conjugate Gradient Backpropagation Neural Network method, the smallest average value is obtained at the 400th Epoch compared to the Epoch Gradient Descent With Momentum method at Epoch 800.Thus it is proven that using the Conjugate Gradient Backpropagation Neural Network method is better with an average value of- MSE average 0.2223 in three stages of testing Training Cycle, Learning Rate and Hidden Layer.

A hybrid short-term load forecasting model and its application in ground source heat pump with cooling storage system

This paper proposed a hybrid hour-ahead forecast model, which combines multiple superimposed long and short term memory (LSTM) network and back-propagation neural network (BPNN), for the purpose of the load forecast on a building-level. The model (hybrid LSTM-BPNN) takes full consideration of the influence of the meteorological information, time information, the information of persons and devices and indoor thermal parameters. A method (LSTM-BPNN + BPNN) is further developed based on the forecasting advantages of sensible heat by hybrid LSTM-BPNN and latent heat by BPNN, in which the cooling load was split into sensible heat and latent heat to forecast separately. The results show that the method achieves the best performance for hour-ahead load forecasting compared with several classic forecasting models. An operation strategy based on the proposed LSTM-BPNN + BPNN method and LSTM model is applied to an improved ground source heat pump system integrated with cooling storage (GSHPs-CS) which was equipped with two storage tanks to achieve the variable volume control of stored chilled water. The system model is established by TRNSYS. Compared to conventional GSHPs-CS, the energy consumption and operating cost of the improved GSHPs-CS system were reduced by 11.5% and 7.5%, respectively. • A hybrid short-term load forecasting model and method is proposed. • Proposed model improved forecasting accuracy than classical models. • The forecasting models and method were applied to an improved GSHP-CS system. • The forecasting model can achieve a predictive control and realize energy saving.

Detection of Cholesterol Levels by Analyzing Iris Patterns using Backpropagation Neural Network

Detecting cholesterol levels with iridology can be an alternative method for checking human’s health. Iridology analyzes diseases and weaknesses of the body based on the shape and structure of the iris. This study uses image processing to analyze patterns in the outer portion of the iris bordering the sclera. Colored iris images are converted to grayscale to facilitate image processing. The results of color conversion still contain noise so that the Median Filter is used to eliminate noise in the image. The iris image which is still in the form of polar is transformed into a rectangular shape. This is used to facilitate the taking of the area to be analyzed. Next, the iris image is filtered using a Gaussian Filter to get smooth results. This is used to remove lines on the iris image after being converted into a rectangular shape. From the filtered image, the statistical value is calculated using the Gray Level Co-Occurance Matrix (GLCM). This is a comparison method which will produce several statistical characteristics, namely Energy, Correlation, Contrast, and Homogeneity. The four statistical characteristics will be used as input data for training using the Backpropagation Neural Network method that will produce output in the form of normal cholesterol or high cholesterol. The results of experiments on thirty images obtained an accuracy of 96.67%.

Modeling of Prediction Bandwidth Density with Backpropagation Neural Network (BPNN) Methods

Using computer networks in campus area which is open access will cause some problems at the speed to access the information. The allocation of bandwidth that provided sometimes does not match the needs of the client, so it takes an accurate prediction of bandwidth usage. This research obtained that Neural Network backpropagation modeling can solve the problem. The stages of research conducted the stage of training and testing phase. Data training is traffic data weekly and conducted by feed-forward back method, with max error 0.001, max hidden layer neuron 5000, constant momentum 0.95 and increase ratio 0.1. Before the data train is conducted, the scaling of the input and target values in the range of 0.1-0.9, then resumes the denormalization after the data train to return the data into Kb form. The results obtained from the training process in the form of comparison data, training performance, and regression. Furthermore, data testing, conducted by using a network that has been developed from the previous results. The test results are shown in the form of real data and predictive data using 8 input layers. In the prediction process, the mean square error generated is 0.0031792 which indicates a low error rate, so it can be stated that the resulting modeling has a level of output accuracy in predicting the use of computer network bandwidth is very high.

Expert System of Diagnosing Building Damage due to Earthquake using Backpropagation Artificial Neural Network Method

Earthquake is one of the most destructive natural disasters. After the earthquake, experts were deployed to survey the damage that occurred. One of the main objectives of the assessment task carried out by experts is to evaluate and classify buildings into several categories based on the level of damage that occurs. In this study, an expert system that could facilitate the assessment of building damage due to the earthquake was made using Backpropagation neural network method. The testing techniques used in this system are blackbox, accuracy and Mean Opinion Score (MOS) testing. MOS testing conducted by 30 respondents produced an MOS value of 4.54 from a scale of 5. While the average accuracy of the system obtained is 82.22% of the 30 case cases tested by 3 building damage experts.

New fault diagnostic strategies for refrigerant charge fault in a VRF system using hybrid machine learning method

Fault diagnosis of a refrigerant charge is significant for the stable operation of a variable refrigerant flow (VRF) air conditioning system. At present, machine learning methods are widely used to diagnose faults associated with the model training. However, new faults that are not associated with the process are rarely considered for diagnosis. On this basis, this study presents two strategies using hybrid back propagation neural network (BPNN) and decision tree (DT) methods, namely, distinguish threshold-based and vector similarity principle-based strategies. This study aims to construct a diagnostic model that can diagnose new faults for a VRF system. The data of the refrigerant charge amount fault are employed to verify the strategies and are divided into training, validating, and testing datasets. The training dataset simply constituting known faults is first employed to train the proposed hybrid model. The validating dataset is employed to evaluate the diagnostic performance of a hybrid model. In a well-trained hybrid model, the BPNN is responsible for diagnosing known and new faults from the testing dataset. Meanwhile, the DT is responsible for diagnosing the specific fault type from the known faults. Results show that the hybrid model using the proposed strategies possesses good diagnostic performance. The hit rates of the new faults can yield 94.47% and 97.44%. The correct rates of the testing dataset can yield 95.2% and 96.63%.

Diagnosis of Blade Icing Using Multiple Intelligent Algorithms

The icing problem of wind turbine blades in northern China has a serious impact on the normal and safe operation of the unit. In order to effectively predict the icing conditions of wind turbine blades, a deep fully connected neural network optimized by machine learning (ML) algorithms based on big data from the wind farm is proposed to diagnose the icing conditions of wind turbine blades. This study first uses the random forest model to reduce the features of the supervisory control and data acquisition (SCADA) data that affect blade icing, and then uses the K-nearest neighbor (KNN) algorithm to enhance the active power feature. The features after the random forest reduction and the active power mean square error (MSE) feature enhanced by the KNN algorithm are combined and used as the input of the fully connected neural network (FCNN) to perform and an empirical analysis for the diagnosis of blade icing. The simulation results show that the proposed model has better diagnostic accuracy than the ordinary back propagation (BP) neural network and other methods.

Impact of correlation of plug load data, occupancy rates and local weather conditions on electricity consumption in a building using four back-propagation neural network models

This study explores approaches to evaluates correlation how significantly plug load data, occupancy rates, and local weather factors affect the actual electricity consumption of a commercial building in seasonal changes and it predicts electricity usage in buildings using four Back-propagation neural network (BP-NN) algorithms: Levenberg–Marquardt Back-propagation (LMBP), Quasi-Newton Back-propagation (QNBP), scaled conjugate gradient (SCG), and Bayesian regularization (BR). In order to evaluate the impact performance of each input parameter, an impact value was used for these experimental datasets. The results demonstrated that the artificial neural network (ANN) model using the LMBP algorithm has better performance in forecasting electricity consumption in a building. Compared to the other three ANN method results, the LMBP model represented better performance with a lower error rate of 1.07–2.23%. Through impact factor analysis, plug load data were found to highly impact the electricity consumption, and temperature had a significant impact in the summer. However, temperature did not largely influence the results in the winter because the gas boiler heating systems used in the building had little impact on the actual electricity consumption. These methods are helpful in analyzing input factors how each element influences energy consumption. The four proposed BP-NN methods can be used as reliable approaches.

An ultrafast and high accuracy calculation method for gas radiation characteristics using artificial neural network

In this work, a new approach to efficient gas radiation characteristics calculating is proposed to satisfy the demand for high accuracy and efficient calculation in many applications. This approach establishes a mapping relationship between gas condition parameters and radiation characteristics using a back-propagation neural network (BPNN). The line by line (LBL) model is utilized for the generation of training samples in the BPNN model. The values of pressure, temperature and component concentration are taken as input, and absorption coefficient values are taken as output. A case study of CO2 transmittance at 2250–2350 cm− 1 band is presented. The comparison and analysis of the results indicated that the BPNN model has a high accuracy of LBL fitting and is insensitive to the input. Although the training time of BPNN is long, once the training is completed, the computational efficiency is very high. Compared to the look-up table method or other accelerated methods using parameter pre-calculation, the BPNN method occupies much less storage space. It can replace the LBL model to a certain extent when dealing with the needs of high precision and high-speed computing.

Automatic Pesticide Spray Based on Digital Image Processing in Chili Plants by Classification Backpropagation Neural Network Method

In Indonesia demand for chili still quite high and as if it has become a basic necessity for the community. Along with the world in the food processing industry, there has been an increase in the need for chillies, in addition to the high demand and the selling price of chilli peppers, it has encouraged the interest of the community to cultivate chili plants. However, biotic disorders that cause obstacles in efforts to increase chili production. On the leaves and fruit of the chili plant is a part of body the plant that allows the identification process of disease in the chili plant, because there will be changes in color and texture. The process of disease detection in chili plants through digital image processing using the feature extraction method, which has previously been done pre-processing. Then at the segmen-tation stage a thresholding operation is carried out to separate the healthy / diseased leaves / chili. For the classifi-cation of diseases using BPNN (Backpropagation Neural Network) method. The identification process will results five types of diseases, namely fusarium wilt, bacterial wilt, leaf foliage, curly leaves, and anthracnose. From this data will be sent by smartphone via IoT to the automatic sprayer to spray the type of pesticide in accordance with the dose and type of disease identified. Based on the results of testing using 150 samples of leaf and fruit images on chili plants obtained a success percentage of 43% in the leaves and 83.33% in the chilli fruit.

Backpropagation artificial neural network for prediction plant seedling growth

Prediction of the growth of plant seedlings is one of the important problems in the world in order to fulfill the availability of food for all residents. At this time Greenhouse technology has been developed which is one of the technologies that support plant growth. Unfortunately, prediction technology is still done manually so the results are not accurate. This paper proposes the Neural Network Backpropagation method to evaluate the growth of plant seedlings in the greenhouse area. Data collected from the internet network system from temperature sensors, soil humidity, environmental humidity, light intensity and cameras to monitor growth. Seedling prediction is done by building a computer program using the neural network backpropagation algorithm based on time series that has input layer, hidden layer and output prediction architecture. Training data is used to carry out the training process before the program is used to perform predictions. Furthermore, the program is used to make predictions. The results of applying the neural network backpropagation algorithm to predict the growth of plant seedlings in the greenhouse get good results based on the first iteration Mean Squared Error (MSE) of 0.0112, with computing time 0.0193 seconds and data accuracy of 92.79%, which means that the prediction generated approximates actual data for the application of backpropagation neural network algorithms to the evaluation of plant seedling growth.

Coal Resource Security Assessment in China: A Study Using Entropy-Weight-Based TOPSIS and BP Neural Network

Energy security has become a worldwide issue in recent years. Coal resources security (CRS), an important part of energy security, has been an emerging concern in many countries, due to the diminishing fossil energy reserve and unbalanced energy structure. However, there is no universally agreed method of constructing indicator system for CRS assessment. Subjectivity in the process of evaluation also affects the results of assessment. Moreover, CRS is a complex system that should be evaluated scientifically under diverse methods. Therefore, we constructed an indicator system and evaluation model of CRS and used a case study of China and 31 provinces in its mainland to evaluate CRS at both national and provincial levels. The indicator system included two subsystems—long-term CRS and short-term CRS. We also chose a few elements and factors that are consistent with China’s reality. Different research methods were used: the entropy-weight-based TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) method is applied to evaluate the degree of CRS, which avoids the subjectivity of weight determination and reflects the relative merit of each indicator; the BP (Back-Propagation) Neural Network method is used to analyze the sensitivity of CRS to each index. The results show that the national level of CRS dropped in the early years but slowly picked up with the help of government intervention. Investment in coal industry development resulted in the immediate effect of improving CRS. The positive impact of maintaining environmental sustainability is stable over either the short, medium, or long term. The degrees of CRS vary significantly across provinces, even between those with similar coal stock levels. Extra attention should be paid to the transportation of coal resources among provinces and intervention to balance supply and demand within the regions.