Conventional Back Propagation Neural Network Research Articles

An Improved Back Propagation Neural Network Based on Differential Evolution and Grey Wolf Optimizer and Its Application in the Height Prediction of Water-Conducting Fracture Zone

Given that the conventional back propagation neural network (BPNN) easily falls into the local optimal solutions, resulting in poor prediction accuracy, an improved BPNN based on the differential evolution and grey wolf optimizer (DEGWO) is proposed, the so-called DEGWO-BPNN. The prediction of the water-conducting fracture zone (WCFZ) height is significant for mine safety operations. A total of 104 sample data are trained and 25 sample data are tested to identify the optimal prediction model. Five evaluation indexes are selected to assess the prediction performance of the models quantitatively. Finally, the DEGWO-BPNN model is applied to a specific engineering case. The main conclusions are as follows: (1) Mining height, mining depth, coal seam dip, panel width, and ratio of hard rock as the main factors affecting the WCFZ height are selected. The topology structure of the model is defined as ‘5-12-1’; (2) the bias between the predicted value and the actual value of the training samples is smaller with an average error of 2.39. Test samples further validate the prediction precision through evaluation indexes. The values of MAE, RMSE, MAPE, and R2 are 2.3952, 3.4674, 5.3148%, and 0.99077, respectively. The prediction accuracy is 94.6852%; (3) ‘Mining Code’, MLR, BPNN, and GWO-BPNN models are treated as the comparison groups. The comparative analysis shows that the prediction performance of ‘Mining Code’ is the worst, while that of DEGWO-BPNN is the best, and it outperforms other algorithms and statistical approaches; (4) the prediction of WCFZ height in the 11601 panel is in line with the actual value. The prediction error of the DEGWO-BPNN model is lower than that of the comparison models. As such, the DEGWO-BPNN model can be well applied to the prediction of WCFZ height and is suitable for coal mines with different regional geological conditions. It can provide a valuable reference for mine safety operations.

Height Prediction of Water-Conducting Fracture Zone in Jurassic Coalfield of Ordos Basin Based on Improved Radial Movement Optimization Algorithm Back-Propagation Neural Network

The development height of the water-conducting fracture zone (WCFZ) is crucial for the safe production of coal mines. The back-propagation neural network (BP-NN) can be utilized to forecast the WCFZ height, aiding coal mines in water hazard prevention and control efforts. However, the stochastic generation of initial weights and thresholds in BP-NN usually leads to local optima, which might reduce the prediction accuracy. This study thus invokes the excellent global optimization capability of the Improved Radial Movement Optimization (IRMO) algorithm to optimize BP-NN. The influences of mining thickness, coal seam depth, working width, and hard rock lithology proportion coefficient on the height of WCFZ are investigated through 75 groups of in situ data of WCFZ heights measured in the Jurassic coalfield of the Ordos Basin. Consequently, an IRMO-BP-NN model for predicting WCFZ height in the Jurassic coalfield of the Ordos Basin was constructed. The proposed IRMO-BP-NN model was validated through monitoring data from the 4−2216 working faces of Jianbei Coal Mine, followed by a comparative analysis with empirical formulas and conventional BP-NN models. The relative error of the IRMO-BP-NN prediction model is 4.93%, outperforming both the BP-NN prediction model, the SVR prediction model, and empirical formulas. The results demonstrate that the IRMO-BP-NN model enhances the accuracy of predicting WCFZ height, providing an application foundation for predicting such heights in the Jurassic coalfield of the Ordos Basin and protecting the ecological environment of Ordos Basin mining areas.

LEVERAGING DEEP LEARNING FOR ACCURATE RICE LEAF DISEASE RECOGNITION

: Imagine a Rice Field, seemingly healthy, yet harboring invisible foes. This paper delves into the world of crop disease detection for the Tan spot, Leaf blight, Sheath decay, Bacterial leaf rot, and False smut Dataset consists of 3546 images. The image segmentation is done by BIRCH clustering followed by GMM clustering; various texture features have been extracted through this. The classification is done using existing models such as VGG16, VGG19, RESNET50, and INCEPTION V3. After comparing various models and validation, the observation was made that VGG19 performs well compared to other models. The overall accuracy obtained for the VGG19 is 95.88.%. The achieved accuracy surpasses that of conventional backpropagation neural network models, indicating significant advancements in crop disease diagnosis. This study introduces a novel approach that opens avenues for future research in the field of deep learning for crop disease diagnosis.

Credit and Loan Approval Classification Using a Bio-Inspired Neural Network.

Numerous people are applying for bank loans as a result of the banking industry's expansion, but because banks only have a certain amount of assets to lend to, they can only do so to a certain number of applicants. Therefore, the banking industry is very interested in finding ways to reduce the risk factor involved in choosing the safe applicant in order to save lots of bank resources. These days, machine learning greatly reduces the amount of work needed to choose the safe applicant. Taking this into account, a novel weights and structure determination (WASD) neural network has been built to meet the aforementioned two challenges of credit approval and loan approval, as well as to handle the unique characteristics of each. Motivated by the observation that WASD neural networks outperform conventional back-propagation neural networks in terms of sluggish training speed and being stuck in local minima, we created a bio-inspired WASD algorithm for binary classification problems (BWASD) for best adapting to the credit or loan approval model by utilizing the metaheuristic beetle antennae search (BAS) algorithm to improve the learning procedure of the WASD algorithm. Theoretical and experimental study demonstrate superior performance and problem adaptability. Furthermore, we provide a complete MATLAB package to support our experiments together with full implementation and extensive installation instructions.

Kinematic Calibration for the 3-UPS/S Shipborne Stabilized Platform Based on Transfer Learning

The three-degrees-of-freedom (3-DOF) parallel robot is commonly employed as a shipborne stabilized platform for real-time compensation of ship disturbances. Pose accuracy is one of its most critical performance indicators. Currently, neural networks have been applied to the kinematic calibration of stabilized platforms to compensate for pose errors and enhance motion accuracy. However, collecting a large amount of measured configuration data for robots entails high costs and time, which restricts the widespread use of neural networks. In this study, a “transfer network” is established by combining fine-tuning with a Back Propagation (BP) neural network. This network takes the motion transmission characteristics inherent in the ideal kinematic model as prior knowledge and transfers them to a network trained based on the actual poses. Compared with the conventional BP neural network trained by actual poses alone, the transfer network shows significant performance advantages, effectively solving the problems of low prediction accuracy and weak generalization ability in the case of small-sample measured data. Considering this, the impact pattern of the sample number of the actual pose on the effectiveness of transfer learning is revealed through the construction of multiple transfer network models under varying sample numbers of the actual pose, providing valuable marine engineering guidance. Finally, simulated sea-service experiments were conducted on the 3-UPS/S shipborne stabilized platform to validate the correctness and superiority of the proposed method.

Particle Swarm Optimized Back Propagation Neural Network for State of Health Estimation of Lithium-ion Battery

The assessment and monitoring of battery health is very crucial for the maintenance and safety of battery-powered applications such as Electric vehicles (EVs). To conduct appropriate battery operation in EVs, the battery capacity should be estimated accurately. In this regard, the State of health (SOH) estimation is conducted for evaluating the battery aging status. This work proposes a hybrid backpropagation neural network (BPNN) and particle swarm optimization (PSO) technique for SOH estimation. A multi-feature input data framework is constructed with 31-dimensional features for the model training by using 4 battery datasets from NASA i.e. B5, B6, B7 and B18. The acquisition of the data samples has been performed with a systematic sampling technique. The presented work is conducted with a training testing ratio of 70:30 and validated with the MIT Stanford battery dataset. The experimental outcomes demonstrated high SOH estimation accuracy compared with the conventional BPNN model. In the case of battery B5, it was observed that RMSE, MSE and MAPE for the BPNN-PSO model are 0.6791, 0.0046, 0.3203 compared with the conventional BPNN model i.e. 0.8796, 0.0077, 0.4881 respectively. Furthermore, the significance of capacity regeneration in B7 and B18 results in high-performance metrics compared with other battery datasets. The research conducted would be beneficial to estimate the battery status regarding battery health i.e. SOH accurately in Battery System Management (BMS) based EV application.

Customer churn classification through a weights and structure determination neural network

In today's corporate world, acquiring and keeping clients are the most important priorities. Every business’s market is expanding quickly, which is increasing the number of subscribers. Because neglect could result in a drop in profitability from a major standpoint, it has become imperative for service providers to limit churn rates. These days, identifying which customers are most likely to leave a business requires a lot less work thanks to machine learning. Taking this into account, a novel weights and structure determination (WASD) neural network has been built to meet the aforementioned challenge of customer churn classification, as well as to handle its unique characteristics. Motivated by the observation that WASD neural networks outperform conventional back-propagation neural networks in terms of slow training speed and trapping in a local minimum, we enhance the WASD algorithm's learning process with a new activation function for best adapting to the customer churn model. Superior performance and flexibility to problems are demonstrated in an experimental investigation using a dataset from a telecommunications provider.

Instability Risk Assessment for Deep Excavation of Soil–Rock Combinations Containing Groundwater

Dynamic risk assessment is a pivotal tool for enhancing construction safety and minimizing the potential for partial failure during deep and extensive excavation projects. To enhance the efficacy of dynamic risk assessment in deep excavation, this study introduces a novel risk assessment model designed to evaluate instability risk in extensive excavations. It comprises a risk factor selection model for identifying the most pertinent factors and an instability risk assessment model for gauging the extent of instability risk throughout the construction process. Then, the model was deployed in the construction of Anshan Road Station of the Qingdao Metro. To pinpoint the factors with the most pronounced impact on excavation instability, a risk factor selection model was employed, yielding a comprehensive risk evaluation index system. For real-time assessment of risk, the monitoring data were used as the primary source of evidence. A comprehensive comparative analysis involving actual data and predictions from conventional RBF and back propagation neural networks was performed. The outcome of this analysis underscored the superior accuracy and predictive capabilities of the assessment model. The instability risk assessment model offers the ability to dynamically evaluate the instability risk associated with extensive excavations featuring a combination of soil and rock. It can serve as a valuable methodological tool, furnishing essential support for the systematic prevention and mitigation of excavation instability disasters.

Development of a Displacement Prediction System for Deep Excavation Using AI Technology

This manuscript delineates an innovative artificial intelligence-based methodology for forecasting the displacement of retaining walls due to extensive deep excavation processes. In our selection of 17 training cases, we strategically chose a wall configuration that was not influenced by the corner effects. This careful selection was conducted with the intention of ensuring that each deep excavation instance included in our study was supported symmetrically, thereby streamlining the analysis in the ensuing phases. Our proposed multilayer functional-link network demonstrates superior performance over the traditional backpropagation neural network (BPNN), excelling in the precise prediction of displacements at predetermined observation points, peak wall displacements, and their respective locations. Notably, the predictive accuracy of our advanced model surpassed that of the conventional BPNN and RIDO assessment tools by a substantial 5%. The network process model formulated through this research offers a valuable reference for future implementations in diverse geographical settings. Furthermore, by utilizing local datasets for the training, testing, and validation phases, our system ensures the effective and accurate execution of displacement predictions.

Thermal Error Modeling of Numerical Control Machine Based on Beetle Antennae Search Back-propagation Neural Networks

Thermal errors are one key impact factor on the processing accuracy of numerical control machine. This study targeted at a certain vertical processing center presents a new algorithm for predictive modeling of thermal errors in numerical control machine. This algorithm is founded on back-propagation neural networks (BPNNs) and adopts beetle antennae search (BAS) to find the best weights and thresholds of BPNNs. It avoids the local minimization due to local extremums faced by traditional BPNNs. The intermingling rate and arithmetic computation efficiency of neural network algorithms are further improved. Then, a BAS-BP thermal error prediction model is built with the machine temperature changes and thermal errors as the input data. Compared with conventional BPNNs, the BPNN after particle swarm optimization suggests the convergence rate of BAS-BP is improved by 85%, the leftover mistakes between the genuine information and the anticipated information are under 1 um, and the overall prediction precision is above 90%. Thus, the new model has high precision, high anti-disturbance ability and strong robustness.

Online fusion estimation method for state of charge and state of health in lithium battery storage systems

To ensure the safe and reliable operation of Li-ion battery energy storage systems, it is important to diagnose the operational status and aging degree of the batteries. In this study, an online fusion estimation method based on back propagation neural network and genetic algorithm (BP-GA) is used for estimating the state of charge (SoC) and state of health (SoH) of Li-ion batteries. First, the effective features of SoC and SoH of Li-ion batteries during charging and discharging are analyzed, and the relevant features are extracted. Subsequently, a conventional back propagation neural network (BPNN) for SoC and SoH estimation is described. The extracted feature quantities are then used as inputs to the neural network for the estimation of the SoC and SoH of Li-ion batteries. A comparison of the SoC and SoH estimation results using, respectively, a single BPNN and a fusion algorithm using a genetic algorithm (GA) to optimize the BPNN shows that the accuracy and efficiency of the estimation results using BP-GA are significantly higher than that of the BPNN. The experimental component of this paper is a comparison experiment using the Panasonic 18650PF and the real-world data from NASA. The results show that the feature extraction operation is relatively easy to perform and combined with the neural network method used in this paper can have good accuracy, reduce the complexity of the algorithm, and improve the detection efficiency.

A novel method on the optimization problem of energy conservation in public buildings

ABSTRACT In recent years, the problem of energy consumption has received considerable attention. Among them, the proportion of energy consumption in public buildings accounts for a substantial part, and there is a large space for energy saving in this field. Practically, the major limiting factor for energy consumption optimization is indoor environment comfort degree. As such, a trade-off problem between energy conservation and indoor environment must be resolved. In this paper, an office in a public building is chosen as the experimental object, with 2520 real observations collected for two months, a series of intelligence based techniques are combined and applied to deal with this optimization problem. First, Partial Rank Correlation Coefficient (PRCC) was employed to perform correlation analysis for a set of candidate variables, such that the computational time of subsequent model training is reduced by 8.32 seconds as compared to the case where no PRCC is in use. Following this, Genetic Algorithm (GA)-based Levenberg-Marquardt algorithm (LM) are applied collectively to optimize the conventional Back Propagation (BP) neural network, and results suggest that there was a marked improvement in neural model performance, on one hand the epoch number for convergence drops from 72 to 13, on the other hand the mean squared error for test set is reduced by 7.46e-4 (from 9.93e-4 to 2.47e-4). Finally, pigeon-inspired Optimization (PIO) algorithm is employed to address the formulated optimization problem and the optimal value for Predicted Mean Vote (PMV) and Indoor Air Quality (IAQ) are −0.4775 and 0.007826, respectively. To verify the validity of our results that derived by the proposed approach, corresponding parameters are applied in a practical scenario. The experimental result indicates that the energy efficiency is improved by around 18.6% compared to that yielded before optimization is performed, which demonstrates the applicability and effectiveness of the proposed method.

A Hybrid Model for Predicting Low Oxygen in the Return Air Corner of Shallow Coal Seams Using Random Forests and Genetic Algorithm

In order to better solve the phenomenon of low oxygen in the corner of return airway caused by abnormal gas emission in goaf during shallow coal seam mining, by analyzing the source and reason of low oxygen phenomenon, a prediction model of oxygen concentration in the corner of return airway based on genetic algorithm (GA) and random forest (RF) technology was proposed. The training sample set was established by using the field data obtained from actual monitoring, including the oxygen concentration in the return airway corner, the periodic pressure step distance of the roof, the surface temperature and atmospheric pressure. GA was used to optimize the parameters in the RF model, including trees and leaves in the forest. The results showed that the model prediction error was minimum when the number of trees was 398 and the number of leaves was 1. In addition, GA was used to optimize the number of hidden neurons and the initial weight threshold of the back-propagation neural network (BPNN). In order to verify the superiority of the model, the GA optimized RF and BPNN model are compared with the conventional RF and BPNN model. Analyze the average absolute percentage error (MAPE), root mean square error (RMSE), and average absolute error (MAE) of the prediction data of each model. The results show that the optimized RF prediction model is better than other models in terms of prediction accuracy.

Regional/Single Station Zenith Tropospheric Delay Combination Prediction Model Based on Radial Basis Function Neural Network and Improved Long Short-Term Memory

Atmospheric water vapor is an essential source of information that predicts global climate change, rainfall, and disaster-natured weather. It is also a vital source of error for Earth observation systems, such as the global navigation satellite system (GNSS). The Zenith Tropospheric Delay (ZTD) plays a crucial role in applications, such as atmospheric water vapor inversion and GNSS precision positioning. ZTD has specific temporal and spatial variation characteristics. Real-time ZTD modeling is widely used in modern society. The conventional back propagation (BP) neural network model has issues, such as local, optimal, and long short-term memory (LSTM) model needs, which help by relying on long historical data. A regional/single station ZTD combination prediction model with high precision, efficiency, and suitability for online modeling was proposed. The model, called K-RBF, is based on the machine learning algorithms of radial basis function (RBF) neural network, assisted by the K-means cluster algorithm (K-RBF) and LSTM of real-time parameter updating (R-LSTM). An online updating mechanism is adopted to improve the modeling efficiency of the traditional LSTM. Taking the ZTD data (5 min sampling interval) of 13 international GNSS service stations in southern California in the United States for 90 consecutive days, K-RBF, R-LSTM, and K-RBF were used for regions, single stations, and a combination of ZTD prediction models regarding research, respectively. Real-time/near real-time prediction results show that the root-mean-square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), and training time consumption (TTC) of the K-RBF model with 13 station data are 8.35 mm, 6.89 mm, 0.61, and 4.78 s, respectively. The accuracy and efficiency of the K-RBF model are improved compared with those of the conventional BP model. The RMSE, MAE, R2, and TTC of the R-LSTM model with WHC1 station data are 6.74 mm, 5.92 mm, 0.98, and 0.18 s, which improved by 67.43%, 66.42%, 63.33%, and 97.70% compared with those of the LSTM model. The comparison experiments of different historical observation data in 24 groups show that the real-time update model has strong applicability and accuracy for the time prediction of small sample data. The RMSE and MAE of K-RBF with 13 station data are 4.37 mm and 3.64 mm, which improved by 47.70% and 47.20% compared to K-RBF and by 28.48% and 31.29% compared to R-LSTM, respectively. The changes in the temporospatial features of ZTD are considered, as well, in the combination model.

CHANGE DETECTION OF BUILDINGS WITH THE UTILIZATION OF A DEEP BELIEF NETWORK AND HIGH-RESOLUTION REMOTE SENSING IMAGES

To enhance the accuracy results of the change detection of buildings utilizing high-resolution remote sensing (HRRS) images, a novel method was proposed by combining both tensor and deep belief network (DBN). To optimize the description of the essential characteristics for changes in buildings, a tensor-based structure covering time-space-spectrum-shadow features integrated into the model (TSSS-Cube) is proposed. The changes occurring as a combination of shadow and spectral features and spatio-temporal autocorrelation at each pixel are represented by a third-order tensor to maintain the structural information and the constraint integrity between them. Then, a restricted Boltzmann machine (TC-RBM) that can be directly used to process TSSS-Cube data is designed, and the support tensor machine (STM) is used to replace the conventional backpropagation neural network at the top of the DBN to construct a multi-tensor deep belief network (MTR-DBN) composing of multi-layer TC-RBMs and an STM classifier. Finally, the multi-layer TC-RBMs in MTR-DBN are trained layer by layer, and the global parameters of the MTR-DBN are optimized by combining a limited number of labeled data and fine-tuning the STM classifier. The implementation of both supervised and unsupervised learning methods comprehensively provides advantages to increase the accuracy result of the MTR-DBN network to detect changes. Three representative different sub-regions are selected from the whole original experimental area respectively for building change detection experiments, and a dataset composed of double-temporal HRRS images in 2012 and 2016 is used as the related experimental dataset. The experimental results show that both a change detection accuracy result with a higher average and better detection efficiency is attained by the proposed method called the MTR-DBN when compared with other similar methods.

Discrimination of geographical indication of Chinese green teas using an electronic nose combined with quantum neural networks: A portable strategy

Sensory attributes of teas are related to their geographical origin and directly affect consumer preference and thus the value of products. In this paper, we propose a portable strategy of identifying five famous green teas with official geographical indications of China using a lab-made electronic nose combined with a quantum neural network (QNN). QNN can be regarded as a modified version of back propagation neural network (BPNN), in which transfer functions are superposed by several sigmoids forming multilevel intervals and can be adjusted during training. Firstly, principal component analysis and linear discriminant analysis are used for low-dimensional visualization. Then different QNNs with 2–6 quantum intervals are trained and tested compared with BPNN, support vector machine (SVM) and k-nearest neighbor (k-NN). The results show that averaged classification accuracies of QNNs are higher than that of BPNN, SVM and k-NN, and they raise with increasing of initial quantum intervals but vary a little when quantum intervals exceed 3, and reach highest to 99.38 %, indicating 3 quantum intervals is adequate for this application considering the trade-off between calculating cost and classification accuracy. The results demonstrate that QNN is a promising pattern recognition method for portable electronic noses due to its better generalization ability but simple implementation as a conventional BPNN.

Harris hawks optimization algorithm and BP neural network for ultra-wideband indoor positioning.

Traditional back propagation neural networks (BPNNs) for ultrawideband (UWB) indoor localization can effectively improve localization accuracy, although there is high likelihood of becoming trapped in nearby minima. To solve this problem, the random weights and thresholds of the BPNN are optimized using the Harris Hawks optimization algorithm (HHO) to obtain the optimal global solution to enhance the UWB indoor positioning accuracy and NLOS resistance. The results show that the predicted trajectory of the HHO and BPNN hybrid algorithm (HHO-BP) matches the actual position in the two-dimensional localization scenario with four base stations; the optimized average positioning error is effectively reduced in both indoor LOS and NLOS environments. In the LOS environment, the total mean error of the traditional BPNN algorithm is 6.52 cm, which is 26.99% better than the UWB measurement error; in the NLOS environment, the total mean error of the conventional BPNN is 14.82 cm, which is 50.08% better than the UWB measurement error. The HHO-BP algorithm is further optimized on this basis, and the total mean error in the LOS environment is 4.50 cm, which is 22.57% better than the conventional BPNN algorithm; in the NLOS environment, the total mean error is 9.56 cm, which is 17.54% better than the conventional BPNN algorithm. The experimental findings suggest that the approach has greater calibration accuracy and stability than BPNN, making it a viable choice for scenarios requiring high positional precision.

The Analysis of Differential High-Quality Development of Economy by Deep Neural Network and Internet of Things

This study solves the problems of insufficient objectivity and a large amount of calculation in traditional regional economic development level evaluation methods. The conventional Back Propagation (BP) neural network can easily fall into local extremes and slow convergence speed. Firstly, an improved BP algorithm is proposed. The LM (Levenberg-Marquardt) algorithm optimizes the BP neural network. Secondly, the evaluation model of Henan County’s economic development level is constructed based on the improved BP algorithm. Finally, Matlab software is used to design simulation experiments. The BP model is used to evaluate the comprehensive economic development level of 107 counties in Henan Province. The results show that the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Square Error (MSE) of the output of the proposed BP model are 0.9, 1.72, and 3, respectively. This is far lower than other popular algorithms and is more suitable for estimating the comprehensive development level of the region. The overall economic development level of counties in Henan Province is relatively balanced but partially uneven. The polarization of development is more serious. The middle-level and middle- and low-level development counties account for a relatively large area, and the overall distribution characteristics are “convex”. This study aims to provide necessary technical support for a more accurate analysis of Henan counties’ comprehensive economic development level distribution and then to promote the coordinated development of counties in the province.

Application of the Backpropagation Neural Network Image Segmentation Method with Genetic Algorithm Optimization in Micropores of Intersalt Shale Reservoirs.

The pore types of intersalt shale reservoirs are diverse, and the pore structures are relatively complex. The size of the pores ranges from a few nanometers to a few microns, showing obvious heterogeneity and multiscale. Image segmentation is an important link in the study of micropore structures of intersalt shale using digital core technology. It can identify characteristics such as pore category, shape, size, spatial distribution, and connectivity characteristics. Therefore, how to improve the accuracy of image segmentation becomes very important. In this study, the research object is the 10 rhythmic layers of the Qian 34 oil group in the Wangping 1 well area of oil field A. First, focused ion beam scanning electron microscopy was used to obtain core imaging data. Then, in order to realize efficient processing of two-dimensional image information and compensate for the shortcomings of conventional segmentation methods such as long iteration period, slow convergence speed, and low accuracy, the backpropagation (BP) neural network segmentation method with a genetic algorithm (GA) was adopted. Also, the segmentation results before and after the improvement were compared. The results show the following: (1) Among the selected intersalt shale core samples, 90% of the pore radius is less than 150 nm and more than 90% of the throats are less than 100 nm. (2) Compared with the conventional BP neural network, the number of convergence steps is reduced to 10, the speed is 10 times faster, and the porosity prediction accuracy is increased by 4.03% on average, which is closer to the gas-measured porosity value. It shows that the BP neural network image segmentation method with a GA has the advantages of small calibration error, fast convergence speed, high efficiency, and high precision.

Network intrusion detection based on IE-DBN model

Existing network intrusion detection models suffer such problems as low detection accuracy and high false alarm rates in face of massive data traffic. Deep-learning models provide a solution as they can reduce the dimensionality of massive data, extract data features, and identify intrusions. However, the network structure and the number of hidden layer neurons of deep-learning models are determined by empirical or trial-and-error methods, which will affect the generalization ability and learning efficiency of the model. In the present work, a deep belief network model based on information entropy (IE-DBN model) is proposed for network intrusion detection. The model uses information gain (IG) to reduce the dimensionality of high-dimensional data features and remove redundant features. The information entropy is used to determine the number of hidden neurons in the DBN network and the network depth. The synthetic minority oversampling technique (SMOTE) algorithm is used to address the problem of data imbalance. Tests on the KDD CUP 99 intrusion detection data set have shown that the proposed IE-DBN model improved the convergence speed of the model and reduced the likelihood of overfitting. Compared with the conventional back propagation (BP) neural network and DBN network model, the IE-DBN model obtained a higher detection accuracy and a lower false alarm rate. Verification tests on other intrusion detection data sets showed that the proposed IE-DBN model had good generalization capacity.