Narrow Results

Automatic test oracle generation is a bottleneck in realizing full automation of the entire software testing process. This study proposes a new method for automatically generating a test oracle for a new test input on the basis of several historical test cases by using a backpropagation neural network (BPNN) model. The new method is different from existing test oracle techniques. Specifically, our method has two steps. First, the values of variables are collected as training data when several historical test inputs are used to execute the program at different breakpoints. The test oracles (pass or fail) of these test cases are utilized to classify and label the training data. Second, a new test input is used to execute the program at different breakpoints, where the trained BPNN prediction model automatically generates its test oracle on the basis of the collected values of the variables involved. We conduct an experiment to validate our method. In the experiment, 113 faulty versions of seven types of programs are used as experimental objects. Results show that the average prediction accuracy rate of 74,651 test oracles is 95.8%. Although the failed test cases in the training data account for less than 5%, the overall average recall rate (prediction accuracy of test case execution failure) of all programs is 78.9%. Furthermore, the trained BPNN can reveal not only the impact of the values of variables but also the impact of the logical correspondence between variables in test oracle generation.

The purpose of this paper is to control and judge the big data of students’ learning and living conditions in college education. College students’ book-borrowing data are mined deeply from three aspects, the multi-source preprocessing of students’ borrowing data from university and college libraries, the quantification of students’ book borrowing, and academic performance prediction by learning and book borrowing. The data mining technology analyzes and processes students’ primary information, score information, and book-borrowing information. Students’ book borrowing is modeled and analyzed using the backpropagation neural network (BPNN) algorithm, and the constructed BPNN book-borrowing model’s loss function is optimized based on the partial differential equations. The library access control data and book-borrowing data are used for statistics of the learning behavior frequency. Data such as students’ stay duration in the learning area and attendance rate are input into the analysis model for experiments, and the average absolute error, the mean square error, and the determination coefficient evaluate the prediction results. The results show that as students’ booking borrowing frequency decreases, their scores decrease, and students who often borrow books have strong learning motivations. In Experiment 4, when $R^2$ reaches its maximum value, 0.594, the predicted scores by the students’ book-borrowing model have a high correlation with students’ actual scores, indicating that the BPNN algorithm has the best prediction results. The results show that the indicator of students’ book borrowing has significantly improved the model’s prediction performance, and the borrowed book number and book-borrowing frequency are significant in the prediction model construction.

The purpose of this paper is to improve the financial management efficiency of large enterprises and enhance the overall operation vitality of enterprises. First, the connotation and characteristics of enterprise resource planning (ERP) are analyzed, and the financial ERP system is established. Then, the relevant dynamic models of nonlinear systems are classified and their characteristics are analyzed. Moreover, the system model of enterprise financial risk management is constructed based on the key success factors of project implementation risk and control flow chart of project life cycle. Finally, based on MATLAB software, $Z$ large enterprise is taken as an example to evaluate the implementation effect of analytical hierarchy process (AHP) algorithm and back propagation neural network (BPNN) algorithm in ERP system. The results reveal that compared with 2019, the capital concentration in 2020 increases by 8%, the operating cost decreases by 23.6%, and the expense reimbursement process time decreases from 60–80 days to about 6 days. The expected output and assessment result of AHP are 6.912 and 6.823, respectively, and the error between them is 0.0196. The expected output and assessment result of BPNN are 6.798 and 6.675, respectively, and the error between them is 0.0121. The error value of BPNN in ERP implementation effect assessment is less than that of AHP, which indicates that the assessment effect of BPNN is better than that of AHP.

The purpose is to further explore the application effect of the neural network algorithm in defense audit and improve the user information security performance. Based on the relevant theoretical basis of neural network in machine learning, the back propagation neural network (BPNN) algorithm model is constructed and optimized. Moreover, by comparing with the classification and prediction effect of the decision tree method, the application effect of BPNN is further clarified. Through statistical analysis, a total of six risk users are screened out. The test data are classified into non-risk user group and risk user group to study the prediction of classification. The specific results are as follows. The prediction accuracy of non-risk group is 99% by using the BPNN algorithm and that is improved to 99.5% by using the optimized BPNN; for risk group, the prediction accuracy of BPNN is only 50% and that of optimized BPNN is 83.3%. Meanwhile, the prediction error rate of the BPNN algorithm is significantly lower than that of the decision tree algorithm, which further verifies the good application effect of the BPNN algorithm. This study can provide scientific and effective reference for the follow-up research of defense audit.

As the basic guarantee for people’s production and life, the safe operation of the power system has an important impact on the development and operation of society. To ensure the safe and stable operation of the power grid, predicting potential faults and taking reasonable preventive measures can effectively avoid the occurrence of power accidents. However, due to the difficulty in ensuring the prediction accuracy of traditional methods, there are issues of protection misoperation and rejection. Therefore, in order to achieve accurate prediction of power grid faults and avoid protection misoperation and rejection issues, a distribution network fault classification prediction model using a combination of three-layer data mining model (TLDM) and adaptive moment estimation (Adam) algorithm/random gradient descent algorithm improved backpropagation neural network (BPNN) is proposed. The implementation results showed that the classification accuracy of artificial fish school $a$priori, $k$-means clustering convolutional neural network model and TLDM for single-phase grounding faults was 93.2%, 91.5% and 96.6%, respectively. The classification accuracy for two-phase faults was 92.8%, 92.4% and 95.7%, respectively. The classification accuracy for two-phase grounding faults was 93.7%, 91.2% and 96.9%, respectively. The classification accuracy for three-phase faults was 93.3%, 92.1% and 97.1%, respectively. The TLDM had the highest classification accuracy. The average accuracy, average accuracy and average recall of the BPNN improved by the combination of the ADAM algorithm and random gradient descent algorithm were 94.1%, 90.9% and 88%, respectively, which were higher than the BPNN improved by the combination of ADAM algorithm and random gradient descent algorithm. The above results indicate that the proposed distribution network fault classification and prediction model has good performance and can achieve accurate prediction of distribution network faults.

Aiming at the low success rate of incubation investment of China’s technology-based start-ups, how to scientifically evaluate technology-based start-ups has become an important issue that needs to be faced. Considering the expert consultation characteristics of the Delphi method is extremely suitable for decision-making problems in the field of uncertainty, as well as the strong nonlinear mapping ability and learning ability of the backpropagation neural network (BPNN). According to the characteristics of the evaluation object and following the principle of index selection, the study uses the Delphi method to determine the evaluation index system suitable for technology-based entrepreneurial enterprises in the current environment and obtain the scores of each index. Based on the established evaluation index system, the BPNN evaluation model is further constructed, and its parameters are optimised to improve its performance. Aiming at the problem that it is easy to fall into a local optimal, a genetic algorithm (GA) is used to optimise it, and a GA-BPNN model is constructed. The comprehensive capability of GA-BPNN is evaluated by using the excellent nonlinear characteristic analysis ability of GA-BPNN to provide a reference for important decisions such as investment. Using BPNN simulation, it was concluded that the correct rate of evaluation of qualified enterprises was between 23.32% and 89.99%, with an average correct rate of 58.32%. The average correct rate was 80.99%. The evaluation accuracy rate was unstable and the average accuracy rate was low. The optimised GA-BPNN model had an average evaluation accuracy rate of 80.32% for qualified enterprises and 93.66% for unqualified enterprises, and the average evaluation accuracy rate increased by 21.99% and 12.66%, respectively. The effectiveness of the model and algorithm was verified. It shows that the GA-BPNN model can be used as an effective tool for the evaluation and screening of technology-based entrepreneurial enterprises. The evaluation system of technology-based entrepreneurial enterprises established by research is scientific and can be applied in practice.

Electron beam butt welding of stainless steel (SS 304) and electrolytically tough pitched (ETP) copper plates was carried out according to central composite design of experiments. Three input parameters, namely accelerating voltage, beam current and weld speed were considered in the butt welding experiments of dissimilar metals. The weld-bead parameters, such as bead width and depth of penetration, and weld strength in terms of yield strength and ultimate tensile strength were measured as the responses of the process. Input-output relationships were established in the forward direction using regression analysis, back-propagation neural network (BPNN), genetic algorithm-tuned neural network (GANN) and particle swarm optimization algorithm-tuned neural network (PSONN). Reverse mapping of this process was also conducted using the BPNN, GANN and PSONN approaches, although the same could not be done from the obtained regression equations. Neural networks were found to tackle the problems of both forward and reverse mappings efficiently. However, neural networks tuned by the genetic algorithm and particle swarm optimization algorithm were seen to perform better than the BPNN in most of the cases but not all.