Adaptive BP Neural Network Research Articles

Analysis on the construction of sports match prediction model using neural network

To grasp the development of sports events in time and adjust the strategy in the process of match in time, the traditional back-propagation neural network (BPNN) algorithm was improved, and the match prediction model was constructed by using the adaptive BPNN. Taking the football match data of the Union of European Football Associations Champions League 2016–2017 as the prediction sample, the match was predicted. Moreover, taking some match data of Barcelona in 2016–2017 as an example, the fitting accuracy of the improved adaptive BPNN prediction model, multiple linear regression (MLR) model and grey degree prediction model were compared and analyzed. The research results showed that the prediction model built by the improved adaptive BPNN algorithm had smaller prediction error after rolling prediction. By comparing with the fitting accuracy of MLR model and grey prediction model, it was also found that the prediction error of the prediction model proposed was almost zero, and the error of the other two models was large. It showed that the prediction model proposed had high accuracy and reliability. Therefore, applying neural network to build a sports match prediction model and then predict the match results can provide a certain theoretical basis for sports match practice and the prediction and analysis of the match results.

Smart data driven quality prediction for urban water source management

A water supply system that integrates water source management, treatment and distribution is a critical infrastructure in urban areas. Traditional water quality research mostly focused on separate aspects, lacking a comprehensive coverage of all aspects, which undermines the prediction accuracies.In this paper, we propose a smart data analysis scheme to analyze and predict the water quality, considering all the water quality standard indicators. Instead of data output from water treatment, we collect the raw water data directly from water sources. We design two models to predict the water quality: (1) adaptive learning rate BP neural network (ALBP) and (2) 2-step isolation and random forest (2sIRF). We applied these models in the practical urban water supply systems of Oslo and Bergen in Norway. The results show that ALBP is theoretically simple and easy to implement. 2sIRF considers the risk distribution and shows higher prediction accuracy. In addition, we perform the correlation analysis of all the indicators and the importance analysis over different indicators. The domain experts have confirmed that this work is meaningful for future risk control and decision support in urban water supply systems.

Analysis of the Smart Player’s Impact on the Success of a Team Empowered with Machine Learning

The innovation and development in data science have an impact in all trades of life. The commercialization of sport has encouraged players, coaches, and other concerns to use technology to be in better position than r their opponents. In the past, the focus was on improved training techniques for better physical performance. These days, sports analytics identify the patterns in the performance and highlight strengths and weaknesses of potential players. Sports analytics not only predict the performance of players in the near future but it also performs predictive modeling for a particular behavior of a player in the past. The impact of a smart player on the success of a team is always a big question mark before the start of a match. The fans always want to know performance analysis of these superstar players and they always are interested to get to know more about their favorite player and they always have high hopes from their favorite player. Machine learning (ML) based techniques help in predicting the performance of an individual player as well as for the whole team. The statistics are very vital and useful for management, fans, and expert analysis. In our proposed framework, the adaptive back propagation neural network (ABPNN) model is used for the prediction of a player’s performance. The data is collected from football websites, and the results are stored in the cloud for fast fetching of data. They can be retrieved anywhere in the world through cloud storage. The results are computed with 94% accuracy and the performance of the smart player is formulated for the success of a team.

Application of Improved BPNN Algorithm in GIS Insulation Defect Type Identification

In this paper, a new BP neural network has been built with GA algorithm, which possesses high effectivity, parallel processing ability and global search feature, in order to overcome the original shortcomings such as the low convergence rate and the confusion of local minimum points. Ten parameters of partial discharge characteristics are obtained as input of BPNN to identify four typical insulation defect physical models designed in this paper for the purpose of measuring the recognition accuracy of the improved BPNN. Experiments show that the improved BPNN has a better performance of convergence speed and recognition accuracy than that of adaptive momentum BP neural network.

An adaptive fractional-order BP neural network based on extremal optimization for handwritten digits recognition

The optimal generation of initial connection weight parameters and dynamic updating strategies of connection weights are critical for adjusting the performance of back-propagation (BP) neural networks. This paper presents an adaptive fractional-order BP neural network abbreviated as PEO-FOBP for handwritten digit recognition problems by combining a competitive evolutionary algorithm called population extremal optimization and a fractional-order gradient descent learning mechanism. Population extremal optimization is introduced to optimize a large number of initial connection weight parameters and fractional-order gradient descent learning mechanism is designed to update these connection weight parameters adaptively during the evolutionary process of fractional-order BP neural network. The extensive experimental results for a well-known MNIST handwritten digits dataset have demonstrated that the proposed PEO-FOBP outperforms the original fractional-order BP neural network and the traditional integer-order BP neural network in terms of training and testing accuracies.

Islanding fault detection based on data-driven approach with active developed reactive power variation

The fluctuation of grid frequency can cause a pseudo islanding phenomenon (PIP) which cannot be avoided by the conventional detection method and the false alarm would be made. In order to reduce the reactive power variation (RPV) which is used by the conventional active islanding detection method (IDM) and avoid the false alarm, a novel data-driven IDM combines adaptive back propagation neural network data fusion and support vector machine (ABPS) is presented by taking PIP into consideration. The feature datasets (frequency, RPV) are selected to detect the islanding event. The proposed method involves two steps: first, k-means cluster and logic operation techniques are used to process the offline data for training ABPS; second, the online testing data are classified into two categories by ABPS: islanding and non-islanding. Compared with the conventional active IDM, the proposed method could detect islanding event by using less RPV, and the false alarm caused by PIP is significantly avoided. Then, a case study of the single-phase-inverter is used to prove the proposed method is more capable of islanding detection than the conventional active IDM.

Multi user detection using fuzzy logic empowered adaptive back propagation neural network

Multi user detection using fuzzy logic empowered adaptive back propagation neural network

Evaluation of borrower's credit of P2P loan based on adaptive particle swarm optimisation BP neural network

Evaluation of borrower's credit of P2P loan based on adaptive particle swarm optimisation BP neural network

Evaluation of borrower's credit of P2P loan based on adaptive particle swarm optimisation BP neural network

Personal credit assessment is the main method to reduce the credit risk of P2P online loans. In this paper, after the adaptive mutation operator is used to reinitialise the particles with a certain probability and the global search capability of the particle swarm optimisation algorithm is used to optimise the weights and thresholds of the BP neural network, a method which adopts adaptive mutation particle swarm combined with BP neural network model is proposed to evaluate borrower's credit of P2P network loan. Result of simulation experiment shows that AMPSO-BP neural network model has higher prediction accuracy, smaller error variation range, better fitting ability and robustness than the BP neural network model in P2P network loan borrower credit evaluation applications.

Evaluation of University Project Based on Partial Least Squares and Dynamic Back Propagation Neural Network Group

In this paper, aiming at the more objective evaluation of university scientific research projects, an evaluation model based on partial least squares and dynamic back propagation neural network group (PLS-DBPG) algorithm is put forward. First, the reasonable index system of project evaluation is designed. For evaluation indexes, the PLS algorithm is used to reduce the feature dimension of original data. As the input of BP neural network, low dimensional data can simplify network structure. Then in view of the slow convergence of traditional BP algorithm, a dynamic adaptive BP neural network group algorithm is proposed. By introducing dynamic proportion factors, the update of each BP neural network is affected by both itself and the optimal network. And, the contribution of each network for group study is constantly adjusted. Finally, in this paper, the simulation results show that the improved algorithm for evaluating the project proposed has valuable applications with the merits of the fast convergence and high precision.

Nondestructive detection of chilled mutton freshness based on multi-label information fusion and adaptive BP neural network

Nondestructive detection of mutton freshness based on a single indicator has limitations and poor applicability. Hyperspectral imaging technology can detect a variety of information in the process of mutton freshness changes, but the establishments of spectral feature extraction and evaluation model have greater impacts on the final evaluation results. To improve the applicability and accuracy of nondestructive detection of mutton freshness, this paper proposes a multi-indicator correlation maximization spectral feature extraction algorithm and self-adaptive BP neural network classification model to detect mutton freshness nondestructively. In the experiments, 400–1000 nm hyperspectral images are collected from 140 mutton samples, and the standard values of total volatile basic nitrogen (TVB-N) and total aerobic plate count (TAC) are determined by laboratory methods. The representative spectra of mutton samples are extracted in the region of interests (ROIs). The spectral feature information is extracted using the feature of multi-indicator correlation maximization, which is proposed in this paper. The samples of calibration set and the prediction set are divided at a ratio of 3:1, and the improved three-layer BP neural network is used to evaluate the freshness of mutton. The results show that the final overall classification accuracy (OA) is 0.9378, the Kappa coefficient is 0.9096, and the AUC values for the three freshness classification results are 0.8192, 0.6766 and 0.7483, respectively. The root means square error (RMSE) of the evaluation results is 0.279. The research shows that the method proposed in this paper can achieve more accurate nondestructive detection of mutton freshness. Moreover, the research provides a new method to obtain spectral information of multiple detection indicators with hyperspectral imaging technology, which can improve the applicability and robustness of the evaluation model of single indicator.

Adaptive GMM and BP Neural Network Hybrid Method for Moving Objects Detection in Complex Scenes

Moving foreground objects detection in complex scenes is a tough job because it requires high recognition accuracy. Adaptive Gaussian mixture model (AGMM) can be used to extract the foreground objects and it shows good performance, however, the detection quality of the foreground objects under complex scenes is not excellent. In this paper, an AGMM and BP neural network hybrid method is proposed, which is used to extract the foreground objects in complex scenes such as, dynamic backgrounds, illumination changes and moving shadows. In this method, an improved BP neural network is used to post-process the images of the foreground objects that are extracted from the AGMM. The neural network has strong robustness by learning the statistical features of the images. Momentum term and adaptive learning rate are added in the BP neural network algorithm to improve the training speed and robustness of the network. The experimental results show that the proposed AGMM and BP neural network hybrid method can extract the complete foreground objects effectively when compared with some other moving objects detection algorithms.

A New Approach to Modeling and Controlling a Pneumatic Muscle Actuator-Driven Setup Using Back Propagation Neural Networks

Pneumatic muscle actuators (PMAs) own excellent compliance and a high power-to-weight ratio and have been widely used in bionic robots and rehabilitated robots. However, the high nonlinear characteristics of PMAs due to inherent construction and pneumatic driving principle bring great challenges in applications acquired accurately modeling and controlling. To tackle the tricky problem, a single PMA mass setup is constructed, and a back propagation neural network (BPNN) is employed to identify the dynamics of the setup. An offline model is built up using sampled data, and online modifications are performed to further improve the quality of the model. An adaptive controller based on BPNN is designed using gradient descent information of the built-up model. Experiments of identifying the PMA setup using BPNN and position tracking by adaptive BPNN controller are performed, and results demonstrate the good capacity in accurate controlling of the PMA setup.

Deriving Bathymetry From Optical Images With a Localized Neural Network Algorithm

We present a localized neural network algorithm for water depth estimation from optical remote sensing images. Our new model is called a locally adaptive back-propagation neural network (LABPNN). In an LABPNN, the neural networks were trained at regularly distributed normative sites. For each unit of LABPNN, training data samples were identified by a specified search radius from the normative sites. Water depth was estimated by an ensemble of LABPNNs, with weights assigned inversely by their distances to the point of estimation. The water depth prediction accuracy from the LABPNN models doubled compared to the regular back-propagation network that uses all of the samples without considering nonstationarity. We also compared the LABPNN model with the regression-based inversion model with the localization feature. The prediction error of LABPNN is less by about 5% in the first case study, and 7% less in the second case study. It is because of the better performance of neural networks than that of the regression models when the sample data are relatively sparse. The experiments suggest that the LABPNN model is a viable solution to water depth retrieval from optical images.

Reconstruction of missing color-channel data using a three-step back propagation neural network

Demosaicking aims to approximate missing color pixels through analysis of the geometric structure between given color pixels and missing color pixels. In this paper, we introduce an efficient adaptive demosaicking method based on back propagation (BP) neural network (BP-NN). We firstly reconstruct the green channel using one BPNN, and then refine the green channel utilizing another BPNN based on the color difference. With the whole green channel interpolated, we reconstruct the red/blue channel using the color difference between the green channel and red/blue channel in a local region. Finally, we refine the red/blue channel using the third BPNN. Regarding the interpolation issue, different image features have completely different properties, such as smooth regions, edges, and textures. Consequently, it is necessary to identify an adaptive model to estimate the relation among neighboring color pixels. We provide the adaptive BP-NN based demosaicking algorithm which can reduce blurring through recovery of missing pixels by a learning process, and also use a pre-trained fixed network to reduce computational complexity. Experimental results demonstrate that the proposed method outperforms extant approaches in PSNR, computational complexity, and visual quality.

Prediction algorithm of PM2.5 mass concentration based on adaptive BP neural network

PM2.5 hadn’t received much attention until 2013 when people started to understand its dreadful impacts to human health. According to the meteorological monitoring data of PM2.5 from September 9, 2016 to September 9, 2017 in Fuling district, Chongqing, this paper analyzed the impact of temperature, humidity and the power of wind on PM2.5. Using the mathematical model of BP neural networks, a prediction model based on satellite remote sensing data for the pollutant concentration in regional scale was explored, and the forecast for Fuling 3-h PM2.5 concentration was realized. The algorithm effectively establishes the correlation between AOD and PM2.5 concentration, and it suppresses the overfitting phenomenon very well, as well as it makes up the limitation of machine learning for single site prediction.

Estimation of Mechanical Properties of PAN Nanofibers Based on Polymeric Structural Characteristics by Artificial Intelligence Modeling

Introduction: Today, nanofibers are commonly used in filtration, composites, tissue engineering, drug delivery systems and many scientific and industrial applications. Here, investigating of nanofiber mechanical properties is important. Measuring mechanical properties of thin nanofiber is very difficult, time consuming and expensive. In this research, mechanical properties of nanofibers have been studied based on their structural characteristics. Method: From the presented experiments, polymeric structural parameters and mechanical properties of parallel PAN nanofibers were measured for 150 samples in five categories of electrospinning conditions. After that, adaptive back propagation neural network was designed and optimized by genetic algorithm for experimental data. Result: The results presented 0.89% and 0.006% for test and train errors which were acceptable for mechanical properties estimation. Conclusion: The presented intelligent modeling method can be an accurate choice for mechanical properties estimation of nanofibers especially, where the experimental measuring is difficult or unavailable. Also, sensitivity test presented that distance between crystal in L1020 and polymeric crystal size had more effect on the strength of the nanofibers. Keywords: Nanofiber, mechanical properties, neural network, algorithm genetic, structural parameters, electrospinning.

Combined forecasting model of urban water consumption based on adaptive filtering and BP neural network

Combined forecasting model of urban water consumption based on adaptive filtering and BP neural network

Combined forecasting model of urban water consumption based on adaptive filtering and BP neural network

In order to solve the problem of improving the precision of urban short-term water consumption forecasting, the idea of combination forecasting is put forward. According to the water use data of a city, the time series prediction method and the explanatory prediction method are used to forecast the water use in the short-term. In order to combine the advantages of the two forecasting methods, this paper proposes a combination forecasting method based on weight coefficient optimisation theory. Compared with the single prediction model, the combined forecasting model has higher accuracy and stability.

An Improved Forecasting Method for Photovoltaic Power Based on Adaptive BP Neural Network with a Scrolling Time Window

Due to the large scale of grid-connected photovoltaic (PV) power generation installations, accurate PV power forecasting is critical to the safe and economic operation of the electric power system. In the paper, by analyzing the influence of external ambient factors and the changing characteristics of PV modules with time, it is found that PV power generation is a nonlinear and time-varying process. This suggests that a certain single forecasting model is inadequate for representing actual generation characteristics, and it is difficult to obtain an accurate forecasting result. An adaptive back propagation (BP) neural network model adopting scrolling time window is proposed to solve the problem. Via an update of the training data of BP neural network with the scrolling time window, the forecasting model adapts to time and a changing external environment with the required modeling precision. Meanwhile, through evaluation of the forecasting performance in different time windows, an optimized time window can be determined to guarantee accuracy. Finally, using the actual operation data of a PV plant in Beijing, the approach is validated as being applicable for PV power forecasting and is able to effectively respond to the dynamic change of the PV power generation process. This improves the forecasting accuracy and also reduces computation complexity as compared with the conventional BP neural network algorithm.