Search

The cultivation of creativity is closely related to language learning. How to design the creativity promotion mechanism of English teaching in the public environment is the challenge faced by English teachers. With the advent of the era of big data, English teachers can apply the latest research results to classroom teaching. For example, the rational use of social media helps students to learn and communicate in the language, cultivate students' creativity in learning English, and improves the quality of teaching. Corporate social media has become the most important way for corporate employees to record their lives, express opinions, share and communicate, and it is also one of the reliable and real-time sources of big data that reflects the true state of English learners. Real, accurate, and timely enterprise social media big data samples contain an enormous educational value, providing more possibilities for educational research. From the perspective of value, through sentiment analysis, topic mining, social network analysis, etc. on social media big data, learner portraits can be realized, thereby providing decision-making reference and support for stakeholders. This paper first builds a learning interest classification model based on TCNN-GRU deep learning, collects experimental data sets from an online English learner's social media platform and performs learning interest classification and labeling, and then uses the TCNN-GRU model to determine the user's learning interest tendency. On this basis, the concept of learning interest index is further proposed, and a neural network-based corporate social platform English learner portrait model is established. The experimental results show that, compared with the traditional machine learning model, convolutional neural network model, and recurrent neural network model, the TCNN-GRU model can obtain better results in learning interest classification. [ABSTRACT FROM AUTHOR]

In order to solve the challenges brought by multi-source and cross-domain scenarios to online music education, this paper designs an online music education system based on advanced artificial intelligence technology, which can provide personalized learning course resource recommendations for music online learners. The system includes four layers, consisting of user interface layer, application module layer, function module layer and data storage layer. At the application module level, this paper proposes a music recommendation algorithm based on a personalized multimodal network model. The recommendation algorithm performs music information retrieval (MIR) based on the similarity judgment of the contour of music pitch and the overall change, and constructs a multimodal network model based on the user's preference for resources to achieve personalized music recommendation. This paper crawls more than one million music score data from a well-known music platform database in China to establish a dataset to evaluate the performance of this method. The comparison results with three existing works show that the method proposed in this paper has good performance and can provide users with suitable music recommendations. The artificial intelligence technology-driven online music education mechanism proposed in this paper has good prospects. [ABSTRACT FROM AUTHOR]

For the problem of class-imbalance in the operation monitoring data of wind turbine (WT) pitch connecting bolts, an improved Borderline-SMOTE oversampling method based on "two-step decision" with adaptive selection of synthetic instances (TSDAS-SMOTE) is proposed. Then, TSDAS-SMOTE is combined with XGBoost to construct a WT pitch connection bolt fault detection model. TSDAS-SMOTE generates new samples by "two-step decision making" to avoid the problem of class–class boundary blurring that Borderline-SMOTE tends to cause when oversampling. First, the nearest neighbor sample characteristics are perceived by the fault class samples in the first decision step. If the characteristics of this fault class sample are different from the characteristics of all its nearest neighbor samples, the fault class sample is identified as interference and filtered. Second, the faulty class samples in the boundary zone are extracted as synthetic instances to generate new samples adaptively. Finally, the normal class samples in the boundary zone are used to perceive the unqualified new generated samples in the boundary zone based on the minimum Euclidean distance characteristics, and these unqualified samples are eliminated. For the second step of decision making, since the first step decision removes some of the newly generated samples, the remaining fault class samples without interference samples and boundary zone samples are used as synthetic instances to continue adaptively generating new samples. Thus, a balanced data set with clear class–class boundary zone is obtained, which is then used to train a WT pitch connection bolt fault detection model based on the XGBoost algorithm. The experimental results show that compared with six popular oversampling methods such as Borderline-SMOTE, Cluster-SMOTE, K -means-SMOTE, etc., the fault detection model constructed by the proposed oversampling method is better than the compared fault detection models in terms of missed alarm rate (MAR) and false alarm rate (FAR). Therefore, it can well achieve the fault detection of large WT pitch connection bolts. [ABSTRACT FROM AUTHOR]

Abnormal detection of wind turbine converter (WT) is one of the key technologies to ensure long-term stable operation and safe power generation of WT. The number of normal samples in the SCADA data of WT converter operation is much larger than the number of abnormal samples. In order to solve the problem of low abnormal data and low recognition rate of WTs, we propose a sample enhancement method for WT abnormality detection based on an improved conditional Wasserstein generative adversarial network. Since the anomaly samples of WT converters are few and difficult to obtain, the CWGANGP oversampling method is constructed to increase the anomaly samples in the WT converter dataset. The method adds additional category labels to the inputs of the generative and discriminative models of the generative adversarial network, constrains the generative model to generate few types of anomalous samples, and enhances the generative model's ability to generate few types of anomalous samples, enabling data generation in a prescribed direction. The smooth continuous Wasserstein distance is used instead of JS divergence as a distance metric to measure the probability distribution of real and generated data in the conditional generative response network and reduce pattern collapse. The gradient constraint is added to the CWGANGP model to enhance the convergence of the WGAN model, so that the generative model can synthesize minority class anomalous samples more effectively and accurately under the condition of unbalanced sample data categories. The quality of anomalous sample generation is also improved. Finally, the anomaly detection is made on the actual operating variator dataset for the unbalanced dataset and the dataset after reaching Nash equilibrium. The experimental results show that the method used in this paper has lower MAR and FAR in WT converter anomaly detection compared with other oversampling data balance optimization methods such as SMOTE, RandomOverSampler, GAN, etc. The method can be well implemented for anomaly detection of large wind turbines and can be better applied in WT intelligent systems. [ABSTRACT FROM AUTHOR]

In today's sophisticated global marketplace, supply chains are complex nonlinear systems in the presence of different types of uncertainties, including supply-demand and delivery uncertainties. Though up to now, some features of these systems are studied, there are still many aspects of these systems which need more attention. This necessitates more research studies on these systems. Hence, in this study, we propose a variable-order fractional supply chain network. The dynamic of the system is investigated using the Lyapunov exponent and bifurcation diagram. It is demonstrated that a minor change in the system's fractional-derivative may dramatically affect its behavior. Then, distributed consensus tracking of the multi-agent network is studied. To this end, a control technique based on the sliding concept and Chebyshev neural network estimator is offered. The system's stability is demonstrated using the Lyapunov stability theorem and Barbalat's lemma. Finally, through numerical results, the proposed controller's excellent performance for distributed consensus tracking of multi-agent supply chain network is demonstrated. [ABSTRACT FROM AUTHOR]

In this study, a novel heuristic computing technique is presented to solve bioinformatics problem for the corneal shape model of eye surgery using Morlet wavelet artificial neural network optimized by the global search schemes, i.e. genetic algorithm (GA), local search technique, i.e. sequential quadratic programming (SQP) and the hybrid of GA-SQP. To measure the performance of the design network configuration, different cases based on nonlinear second-order differential equations governing the corneal model have been solved effectively. The numerical procedure of Adams method is implemented for the comparison purpose of the presented outcomes of the stochastic solver, which shows the worth of the present scheme based on accuracy and convergence with negligible values of absolute error in the range 10 − 7 to 10 − 8 . Furthermore, statistical measures are presented based on "mean absolute error", "root mean square error" and "coefficient of Theil's inequality" which additionally endorsed consistently accurate performance of integrated intelligent computing framework for solving the corneal shape model. [ABSTRACT FROM AUTHOR]

The aim of this study is to present the numerical solutions of the Liénard nonlinear model by designing the structure of the computational Gudermannian neural networks (GNNs) along with the global/local search efficiencies of genetic algorithms (GAs) and interior-point algorithm (IPA), i.e. GNNs–GAs–IPA. A merit function in terms of differential system and its boundary conditions is designed and optimization is performed by using the proposed computational procedures of GAs–IPA to solve the Liénard nonlinear differential system. Three different highly nonlinear examples based on the Liénard differential system have been tested to check the competence, exactness and proficiency of the proposed computational paradigm of GNNs–GAs–IPA. The statistical performances in terms of different operators have been provided to check the reliability, consistency and stability of the computational GNNs–GAs–IPA. The plots of the absolute error, performance measures, results comparison, convergence analysis based on different operators, histograms and boxplots are also illustrated. Moreover, statistical gauges using minimum, mean, maximum, semi-interquartile range, standard deviation and median are also provided to authenticate the optimal performance of the GNNs–GAs–IPA. [ABSTRACT FROM AUTHOR]

The identification of nonlinear system is studied to establish an accurate model of coordination system. The original dynamic fuzzy neural network (DFNN) is first used to identify the nonlinear system for finding the existing problems. Aiming at the problems found, two improvements are made. For the problem of too many pre-set parameters in the original algorithm, the fuzzy completeness − is introduced to allocate the parameters, and the width of the membership function is modified. The simulation results reveal that the fuzzy neural network (FNN) model not improved produces seven fuzzy rules, and the root mean square error (RMSE) of training is 0.0261, while the improved FNN model produces six fuzzy rules, and the RMSE of training is 0.0161. The improved network has more advantages in performance. The model proposed provides some references for the application of FNN in dynamic nonlinear systems. [ABSTRACT FROM AUTHOR]

This paper introduces a fractional-order financial risk system for the first time. Employing well-known tools and analyses such as bifurcations diagrams and spectral entropy, the dynamical behaviors of the system associated with fractional derivative are investigated. The impacts of the fractional derivative on the system's behavior and its dynamical feature are shown. Then, tracking control and stabilization of the systems are studied. As it is obvious, the existence of faults and failures in the process of control of financial and economic systems is undeniable — this issue necessitates applying proper control techniques for the systems. So as to achieve appropriate results in the control of fractional financial risk system, two finite-time fault-tolerant controllers are proposed, namely, finite-time active fault-tolerant control and finite-time passive fault-tolerant control. Not only do these techniques force the system to reach desired values in finite time, but also, the proposed techniques are robust against uncertainties, faults, and failures in actuators. Through finite-time observers, the effects of all uncertainties are taken to account in the active controller. Finally, numerical simulations of tracking control and stabilization are presented. For numerical simulations, the fractional financial risk system is considered to be in the presence of unknown disturbance as well as faults and failures in actuators. It is assumed that the system is in the presence of various types of actuator faults. Numerical results affirm the ability of the offered control techniques for pushing the states of the fractional-order risk system to the desired value in a short period of time. [ABSTRACT FROM AUTHOR]