BP Neural Network Classifier Research Articles

Target Cell Extraction and Spectrum-Effect Relationship Coupled with BP Neural Network Classification for Screening Potential Bioactive Components in Ginseng Extract with a Protective Effect against Myocardial Damage.

Cardiovascular disease has become a common ailment that endangers human health, having garnered widespread attention due to its high prevalence, recurrence rate, and sudden death risk. Ginseng possesses functions such as invigorating vital energy, enhancing vein recovery, promoting body fluid and blood nourishment, calming the nerves, and improving cognitive function. It is widely utilized in the treatment of various heart conditions, including palpitations, chest pain, heart failure, and other ailments. Although numerous research reports have investigated the cardiovascular activity of single ginsenoside, there remains a lack of systematic research on the specific components group that predominantly contribute to cardiovascular efficacy in ginseng medicinal materials. In this research, the spectrum-effect relationship, target cell extraction, and BP neural network classification were used to establish a rapid screening system for potential active substances. The results show that red ginseng extract (RGE) can improve the decrease in cell viability and ATP content and inhibit the increase in ROS production and LDH release in OGD-induced H9c2 cells. A total of 70 ginsenosides were identified in RGE using HPLC-Q-TOF-MS/MS analysis. Chromatographic fingerprints were established for 12 batches of RGE by high-performance liquid chromatography (HPLC). A total of 36 common ingredients were found in 12 batches of RGE. The cell viability, ATP, ROS, and LDH of 12 batches RGE were tested to establish gray relationship analysis (GRA) and partial least squares discrimination analysis (PLS-DA). BP neural network classification and target cell extraction were used to narrow down the scope of Spectral efficiency analysis and screen the potential active components. According to the cell experiments, RGE can improve the cell viability and ATP content and reduce the oxidative damage. Then, seven active ingredients, namely, Ginsenoside Rg1, Rg2, Rg3, Rb1, Rd, Re, and Ro, were screened out, and their cardiovascular activity was confirmed in the OGD model. The seven ginsenosides were the main active substances of red ginseng in treating myocardial injury. This study offers a reference for quality control in red ginseng and preparations containing red ginseng for the management of cardiovascular diseases. It also provides ideas for screening active ingredients of the same type of multi-pharmacologically active traditional Chinese medicines.

Detection and metrology of micro-nano particles through the integration of image and laser modes

Micro-nano particles are an indispensable component in various industrial and scientific applications. Accurate granular information is critical for manufacturing products involving these particles. This study presents a novel detection method that merges image and laser modes to achieve precise size and shape determination of micro-nano particles. The proposed method integrates adaptive image analysis with laser particle size fitting to ensure accurate feature detection. Experimental results using ternary precursor samples demonstrate that the fusion mode outperforms both the laser and image modes in terms of size and shape accuracy. The errors of D10, D50, and D90 of the fusion mode are 4.89%, 1.88%, and 2.94%, respectively, which are significantly lower than those obtained using the laser or image mode alone. Additionally, the fusion mode retains the particle shape information from the image mode. The fusion model offers a promising approach for dual-mode detection of micro-nano particles, demonstrating enhanced robustness compared to single-mode methods. Furthermore, the study introduces an image processing method based on a BP neural network classification model that accurately classifies and detects agglomerated and non-agglomerated particles. The classification accuracy reaches 94.98%, and the particle size information remains within the acceptable range.

Prediction and simulation of wearable sensor devices for sports injury prevention based on BP neural network

In the research of sports injury prevention, the recognition of sports action plays an important role in the action recognition model and the prediction evaluation model. In view of the above problems, this paper constructs a new mathematical model through the idea of BP neural network. The model combines wearable technology and can improve the recognition accuracy of sports actions. The model uses the BP network classifier, which can be used in data. Processes such as feature extraction improve efficiency and reliability. In this paper, the algorithm simulation is carried out, and the experiments are carried out for three movements: running, running and static. The results show that for the recognition of running and running action, when the hidden layer node is 11, the BP neural network classifier shows the best recognition effect. For static motion, the recognition effect of each classifier is basically the same. This paper analyzes the wearable sports action recognition system, including perception layer, application layer and service layer, to realize the recognition and classification of sports actions, predict actions in advance and prevent sports injuries. Finally, this paper analyzes the causes of sports injury, puts forward specific measures to prevent sports injury, and further reduces sports injury events through wearable devices.

Status Identification in Support of Fishing Effort Estimation for Tuna Longliners in Waters near the Marshall Islands Based on AIS Data

Visualising the fishing behaviour of vessels and quantifying the spatial distribution of fishing effort is the scientific basis for assessing and managing fisheries resources. The information on the dynamics of fishing vessel voyages provided by the automatic identification system (AIS) of vessels serves as high-precision fishery data and provides a means of quantifying fishing effort with high spatial and temporal resolution in the tuna longline fishery. Based on the AIS data of five tuna longliners operating in the waters near the Marshall Islands from 2020 to 2021, this study used three methods, namely the threshold screening method, the construction of a BP neural network and the support vector machine (SVM) to identify the fishing and non-fishing status of the tuna longliners, respectively. This study investigates the status identification and fishing effort estimation of the tuna longliner (VESSEL A) in 2021 based on the constructed optimal model, and spatial correlation analyses are performed between the fishing effort estimated in hours based on AIS data and in hooks based on fishing logbook data, by month. The results showed (1) the recognition accuracy of the threshold screening method is 89.9%, the recognition accuracy of the BP neural network classification model is 95.11%, the kappa coefficient is 0.51, the recognition accuracy of the SVM classification model is 95.74% and the kappa coefficient is 0.52; (2) in comparison, the SVM classification model performs better than the other two status identification methods for tuna longliners; and (3) the correlation coefficients between the two types of effort of VESSEL A were greater than 0.79 on all fishing months, indicating that there was no significant difference in the spatial and temporal distribution between the two types of effort. This study suggests that the SVM model can be used to identify the status and estimate the fishing effort of longliners.

A Empirical Research on AI-Powered Athletic Posture Detection in Sports Training

Abstract: The current investigation delineates the efficacy of AI-facilitated detection of athletic postures within the realm of sports training. Employing a synthesis of literature review and empirical methodologies, data were amassed and scrutinized, affirming the study’s validity. The salient outcomes are manifold: (1) The frame difference algorithm efficaciously discerns inter-frame variances, evidencing pronounced adaptability and robustness, thereby enabling the recognition of weightlifting postures. (2) Confronting the challenge of negligible inter-frame disparities inherent in the frame difference algorithm, the research introduces a novel detection technique predicated on the cumulative inter-frame differences, which precisely pinpoints regions of posture alteration in weightlifting athletes. (3) Leveraging the dynamic space model of optical flow, the study ascertains the directional channel predicated on optical flow trajectory analyses, facilitating the identification of three distinct weightlifting postures: squatting, descending, and standing. (4) In alignment with the distinctive postural attributes of weightlifting athletes, a human posture paradigm was formulated, and a BP neural network classifier was deployed for both training and evaluative purposes, culminating in the successful differentiation of athlete from non-athlete entities within the training milieu. (5) The application of AI in posture recognition was extended to the scrutiny of pivotal postures and motions in weightlifting athletes, with experimental findings revealing a 98.21% accuracy rate in the recognition of force-exertion postures via the inter-frame difference method, and a flawless 100% accuracy in the identification of the apex and squatting postures. The enumeration of detected postures—encompassing knee extension, knee flexion, force application, squatting, and standing—through the poselet keyframe extraction approach, corresponded with the video count. Prospectively, AI’s role in athletic posture detection promises to augment coaches’ and athletes’ comprehension of their proficiencies and deficiencies, thereby steering training refinement and bolstering both the efficacy of training and the athletes’ caliber.

Research on the Design Method of Blueberry Automatic Harvesting Clamp Force Based on Neural Networks

Highlights The relationship between fruit size and gripping force was found by BP algorithm. The error between the optimized holding force and the optimal value is not more than 8%, that is, the fruit integrity rate is greater than 92%. The simplified two-parameter method is more suitable for efficient field operation. Abstract. The flourishing development of the blueberry industry has urgently demanded mechanized harvesting, and the rational design of the clamping force of mechanical claws is a challenging aspect for achieving automatic and flexible harvesting. This article proposes a method to predict fruit hardness based on blueberry shape parameters, enabling dynamic adjustment of clamping force. Fruit diameter, height, weight, and rupture pressure data were collected, and using the classical BP neural network algorithm, a mapping relationship between fruit hardness and shape parameters was established. Experimental verification was conducted using an orthogonal table, and the results indicate that the predicted blueberry fruit hardness using this method deviates by less than 8% from the actual values. Further simplification into a two-parameter method was performed to enhance practical field operation efficiency. Although the error slightly increased, it still met the requirements of actual field operations.

Classification method of surrounding rock of plateau tunnel based on BP neural network

Due to the unique high-altitude geological conditions of the railway in the cold region, the problem of high ground stress in the construction process is very prominent. In constructing high ground stress tunnels, accurately evaluating the surrounding rock grades is important in rock mass engineering. Based on this, based on a plateau tunnel under construction, this paper selects the classification index of the surrounding rock, which can accurately reflect the geological characteristics of high ground stress tunnel around the geological environment elements of the surrounding rock of high ground stress tunnel. Based on the rapid classification method of surrounding rock of the BP neural network, the classification method of the surrounding rock suitable for high ground stress tunnel is constructed, and the tunnel engineering data is introduced into the BP neural network classification method of surrounding rock for training and testing. It is found that the classification results of surrounding rock obtained by the classification method of surrounding rock of high ground stress tunnel are in good agreement with the actual situation, which provides an important guarantee for the accurate and rapid determination of the surrounding rock grade of high ground stress tunnel and the safe and efficient construction of the tunnel.

Quality analysis of machine learning methods applied to the geothermal potential assessment: a case study

ABSTRACT Accurately determining the favorable areas of geothermal resources and selecting the target positions of exploration wells are extremely important for exploration and efficient development. This study used the Pearson correlation coefficient and Gini gain to analyze five influencing factors related to the presence of economically viable geothermal potential. The evaluation model of the favorable areas was constructed by using different Machine Learning (ML) methods: Bayesian classifier (Bayes), Support Vector Machine, Bootstrap Aggregating (Bagging), BP neural network, Decision Tree and Logistic Regression classification. The quality of each model was verified by statistical evaluation indicators: Accuracy (ACC), F 1 score (F 1) and Receiver Operating Characteristic curve (ROC curve). The methodology was applied to the case study of Xinjiang Uygur Autonomous Region, China. Due to the results obtained, all ML models showed strong prediction and classification performance on the target area selection of geothermal exploration, as evidenced by each model’s metrics: the ACC was above 80%, the F 1 was above 0.8, and the Area Under the ROC Curve (AUC) was greater than 0.85. The metrics obtained by the Bagging method were the highest. Finally, the results of the six ML models were combined to classify the study area’s geothermal potential, which was consistent with the available information. This study provides a specific basis and technical support for applying the method in further surveys and campaigns.

LW-BPNN: A Novel Feature Extraction Method for Rolling Bearing Fault Diagnosis

Efficiently diagnosing bearing faults is of paramount importance to enhance safety and reduce maintenance costs for rotating machinery. This paper introduces a novel bearing fault diagnosis method (LW-BPNN), which combines the rich properties of Legendre multiwavelet bases with the robust learning capabilities of a BP neural network (BPNN). The proposed method not only addresses the limitations of traditional deep networks, which rely on manual feature extraction and expert experience but also eliminates the complexity associated with designing and training deep network architectures. To be specific, only two statistical parameters, root mean square (RMS) and standard deviation (SD), are calculated on different Legendre multiwavelet decomposition levels to thoroughly represent more salient and comprehensive fault characteristics by using several scale and wavelet bases with various regularities. Then, the mapping relation between the extracted features and the health conditions of the bearing is automatically learned by the simpler BPNN classifier rather than the complex deep network structure. Finally, a few experiments on a popular bearing dataset are implemented to verify the effectiveness and robustness of the presented method. The experimental findings illustrate that the proposed method exhibits a high degree of precision in diagnosing various fault patterns. It outperforms other methods in terms of diagnostic accuracy, making it a viable and promising solution for real-world industrial applications in the field of rotating machinery.

Privacy protection of quantum BP neural network based on game theory

How to ensure privacy security and improve computing efficiency is a research hotspot in the field of machine learning. Among them, how to balance the interests of users, cloud servers and attackers on the premise of ensuring user privacy is a difficult problem in the field of machine learning privacy protection. The development of quantum computing breaks through the computational bottleneck of classical machine learning and has derived the research direction of quantum machine learning. At present, hybrid quantum–classical machine learning in NISQ era has become a research hotspot, but researchers rarely pay attention to the privacy protection in quantum machine learning. Therefore, this paper is the first to apply game theory to the privacy protection in quantum machine learning and proposes the privacy game model of user - server - attacker in Hybrid Classical Quantum BP Neural Network (HCQBPNN). Different from previous studies, this paper sets game strategies based on users’ privacy requirements in practical applications, and aims to maximize the interests of attackers, cloud servers and users. The experiment proves that users can use the privacy game model proposed in this paper to get the optimal privacy combination strategy, and at the same time make the cloud server and the attacker can obtain positive income.

Empirical Test of Credit Risk Assessment of Microfinance Companies Based on BP Neural Network

In recent years, the chaos of internet finance has occurred frequently, especially P2P, with high risks. As a kind of financial innovation, small loan companies are challenging to avoid alone, and the issue of credit risk is also highly valued. This study selects the loan records of a small loan company (a daily loan record from September 1, 2016 to July 1, 2021 has seven indicators, each of which has 21299 data). It uses MATLAB programming to test the correctness of risk indicator selection and the accuracy of BP neural network classification and identification results. This study obtains the corresponding risk value. According to the corresponding risk value, the newly applied loans are classified, that is, rated, to verify the effectiveness and applicability of this method. Therefore, BP neural network has strong applicability, generalization ability, and portability and is an effective method for small loan companies to guide credit risk assessment.

Short-term PV Power Prediction Model Based on VMD-CNN-IBiLSTM

Because PV power’s generation is unpredictable, so timely and accurate prediction of PV power has great practical significance and research value for daily grid dispatch and power system security. The combined forecast model presented in our study is dependent on variational modal decomposition-convolutional neural network-improved bidirectional long short-term memory neural network (VMD-CNN-IBiLSTM) with PV power as the research object. The model uses VMD to decompose PV power sequences, thus reducing the non-smoothness of the sequences; CNN to extract the essential features of the information; BiLSTM with peephole connections to learn the forward and backward features of the temporal data; and genetic algorithm to enhance the model’s variables. For validation, actual data from the Australian DKASC testbed are used. According to the experimental findings, our study’s combined model is more precise than the classical BP neural network, SVM model, and LSTM model at making predictions.

Composition analysis and identification model of ancient glass products based on Spearman correlation coefficient and BP neural network

This paper analyzes the composition of glass products by statistical analysis of known data and then uses Spearman's correlation coefficient analysis model to analyze the composition of glass products, and uses BP neural network to build a prediction and classification model. We use BP neural network to build a prediction and classification model for the composition of glass products and classify the types. In this paper, a BP neural network classification model is constructed using C language. The number of neuron nodes in the input layer and the number of neuron nodes in the output layer are selected. The chemical composition content of the existing sample data is used as the input layer and the category is converted to the output layer after data pre-processing. Finally, a BP neural network classification model with very low classification error is obtained. The sensitivity of the classification results is obtained by sample carryover network calibration and Spearman correlation coefficient.

UAV LiDAR and Hyperspectral Data Synergy for Tree Species Classification in the Maoershan Forest Farm Region

The accurate classification of single tree species in forests is important for assessing species diversity and estimating forest productivity. However, few studies have explored the influence of canopy morphological characteristics on the classification of tree species. Therefore, based on UAV LiDAR and hyperspectral data, in this study, we designed various classification schemes for the main tree species in the study area, i.e., birch, Manchurian ash, larch, Ulmus, and mongolica, in order to explore the effects of different data sources, classifiers, and canopy morphological features on the classification of a single tree species. The results showed that the classification accuracy of a single tree species using multisource remote sensing data was greater than that based on a single data source. The classification results of three different classifiers were compared, and the random forest and support vector machine classifiers exhibited similar classification accuracies, with overall accuracies above 78%. The BP neural network classifier had the lowest classification accuracy of 75.8%. The classification accuracy of all three classifiers for tree species was slightly improved when UAV LiDAR-extracted canopy morphological features were added to the classifier, indicating that the addition of canopy morphological features has a certain relevance for the classification of single tree species.

Marine Radar Oil Spill Extraction Based on Texture Features and BP Neural Network

Marine oil spills are one of the major threats to marine ecological safety, and the rapid identification of oil films is of great significance to the emergency response. Marine radar can provide data for marine oil spill detection; however, to date, it has not been commonly reported. Traditional marine radar oil spill research is mostly based on grayscale segmentation, and its accuracy depends entirely on the selection of the threshold. With the development of algorithm technology, marine radar oil spill extraction has gradually come to focus on artificial intelligence, and the study of oil spills based on machine learning has begun to develop. Based on X-band marine radar images collected from the Dalian 716 incident, this study used image texture features, the BP neural network classifier, and threshold segmentation for oil spill extraction. Firstly, the original image was pre-processed, to eliminate co-channel interference noise. Secondly, texture features were extracted and analyzed by the gray-level co-occurrence matrix (GLCM) and principal component analysis (PCA); then, the BP neural work was used to obtain the effective wave region. Finally, threshold segmentation was performed, to extract the marine oil slicks. The constructed BP neural network could achieve 93.75% classification accuracy, with the oil film remaining intact and the segmentation range being small; the extraction results were almost free of false positive targets, and the actual area of the oil film was calculated to be 42,629.12 m2. The method proposed in this paper can provide a reference for real-time monitoring of oil spill incidents.

Quantitative Analysis Model of Chinese Folk Painting Art Inheritance and Protection Based on Data Mining

Without powerful analytical tools, people will not be able to uncover the wealth of information hidden behind the data. In order to strip the information from the massive data, it is urgent to find a reasonable solution to deal with the challenge of information overload, and to develop an intelligent and automated alternative tool. Data mining technology transforms the original data into a form suitable for operation by integrating and learning data, extracting useful data for mining, and applying various strategies of data mining to generate useful patterns and rules. Based on this, people can make predictions on new sample data and obtain information. This paper analyzes and describes the problems faced by the inheritance of Chinese folk painting art, including the lack of knowledge of the inheritors, the single inheritance content, and the crisis of the inheritance method. In view of the problems faced by the inheritance of folk painting art, this paper proposes to inherit Chinese folk painting art from the aspects of value edification, rich content, and multiple forms. We analyze the different inheritance methods of contemporary national cultural inheritance and point out that different inheritance views have a certain influence on the formulation of cultural inheritance and the choice of inheritance methods. The preprocessing part of the original data is improved before the training on the data starts. By normalizing the order of magnitude of the original data, the values of the data are all in the same order of magnitude. Taking the least mean square algorithm and the BP neural network classification algorithm as the basic algorithm idea, using the rules of batch learning, and adding the momentum term factor, an improved batch learning BP algorithm is designed. The experimental results show that the improved batch learning BP algorithm can better solve the classification problem. Chinese folk painting art can satisfy people's spiritual and material needs, and also has a positive effect on promoting people's physical and mental development.

Evaluation of Women’s Entrepreneurship Education Based on BP Neural Network

Entrepreneurship education is the key to cultivating the entrepreneurial spirit of national talents. The goal of entrepreneurship education is to cultivate a large number of pioneering talents, and women’s entrepreneurship education is particularly important. The government, enterprises, schools, and all sectors of society start from multiple channels to let students strengthen their entrepreneurial awareness and improve their entrepreneurial ability. This paper uses the most advanced BP neural network algorithm to study and evaluate women’s entrepreneurship education. This paper briefly introduces the concept and model of the artificial neural network and establishes a BP neural network model while improving the classical BP neural network. Then, we list the application process of the BP neural network model in evaluating women’s entrepreneurship education. We select college students for empirical analysis, determine the number of neurons, and select 9 items as the evaluation index of women’s entrepreneurship education. Using valid assumptions, we further determine the model learning rate and momentum factor. Finally, the results show that the actual evaluation results based on the BP neural network are basically the same as the expected results, and the maximum relative error between the actual value and the expected value is approximately 1.64 %, and the comprehensive evaluation value is 92 points. The proposed algorithm can effectively avoid the problems of instability and slow convergence of the traditional model and can comprehensively improve the accuracy of the evaluation results of women’s entrepreneurship education.

Using multiple linear regression and BP neural network to predict critical meteorological conditions of expressway bridge pavement icing.

Icy bridge deck in winter has tremendous consequences for expressway traffic safety, which is closely related to the bridge pavement temperature. In this paper, the critical meteorological conditions of icy bridge deck were predicted by multiple linear regression and BP neural network respectively. Firstly, the main parameters affecting the bridge pavement temperature were determined by Pearson partial correlation analysis based on the three-year winter meteorological data of the traffic meteorological monitoring station on the bridge in Shandong province. Secondly, the bridge pavement temperature is selected as the dependent variable, while air temperature, wind speed, relative humidity, dew point temperature, wet bulb temperature and wind cold temperature were selected as independent variables, and the bridge pavement temperature prediction models of linear regression and 5-layer hidden layer classical BP neural network regression were established respectively based on whether the variables are linear or not. Finally, the prediction accuracy of the above models was compared by using the measured data. The results show that the linear regression model could be established only with air temperature, relative humidity and wind speed, owing to collinearity problem. Compared with multiple linear regression model, the predicted value of the BP neural network has a higher degree of fitting with the measured data, and the coefficient of determination reaches 0.7929. Using multiple linear regression and BP neural network, the critical meteorological conditions of bridge deck icing in winter can be effectively predicted even when the sample size is insufficient.

Online signature verification based on dynamic features from gene expression programming

Gene Expression Programming (GEP) is a powerful evolutionary algorithm with simple, linear and compact chromosomes, which has been applied in many fields to solve a large variety of complex problems such as logistic regression, function finding and time series prediction. Since online signature data are composed of discrete points, it is difficult to represent by functional forms, resulting in a limited amount of information used in calculating feature values. Hausdorff distance is utilized as a similarity measure to compute the maximum distance between two point sets, which reduces computational complexity compared with other distance measures. The main contributions of this work are: (1) In preprocessing stage, GEP is used to make signature curve continuous and control each parameter to obtain a fitting curve. Curve fitting is to find a suitable function that is the best fitting for a given set of data; (2) In feature extraction stage, curvature and torsion are utilized to construct eight feature sets for characterizing each user’s signatures, and then Hausdorff distance is proposed to calculate the distances between feature sets of two signatures to form an eight-dimensional feature vector; (3) In verification stage, combined with Feed-Forward BP Neural Network classifier, distance matrices consisting of feature vectors are trained and tested many times. The best performances can be provided with false rejection rate, false acceptance rate, average error rate and standard deviation. The experimental results implemented on three available online signature databases MCYT-100, SVC2004 and SUSIG indicate the effectiveness and robustness of our proposed method.

Trust Prediction Based on Extreme Learning Machine and Asymmetric Tri-Training

Currently, more and more people communicate and trade through online social networks, so it is necessary to predict the trust between users. In order to predict the trust between users through a social network requires some other factors, such as user similarity, topic relevance, and the number of common neighbors should be considered. Some scholars use BP neural network based on the asymmetric tri-training model to train one social network and use transfer learning to predict the social relationship of another social network. However, this method has high computational complexity and slow operation speed. To solve the problem, the three classifiers are expanded into four classifiers on the basis of asymmetric tri-training, and the extreme learning machine classifier is used to replace the BP neural network classifier. The specific steps are: we first obtain the common features between different networks, use source data samples to train the first three classifiers, save the model, and train target samples to generate pseudo labels; then we use standard pseudo label samples to train the fourth classifier and use it to predict the social relations of the target network. Finally, compare with the existing evaluation methods, we proposed an algorithm on six online social networks. The experimental results show that the model in this paper is superior to other evaluation methods in recall and stability.