Wavelet Neural Network Research Articles

Research on islanding detection of solar distributed generation based on best wavelet packet and neural network

Research on islanding detection of solar distributed generation based on best wavelet packet and neural network

Predicting Corporate Financial Distress Using a Hybrid Model of Artificial Immune System and Wavelet Neural Network (Artificial Intelligence)

In today's financial landscape, the prediction of corporate financial distress plays a crucial role in risk management and economic stability. This study aims to develop a hybrid predictive model that combines the Artificial Immune System (AIS) with the Wavelet Neural Network (WNN) to forecast financial distress in companies. The hybrid model leverages the strengths of both algorithms to improve accuracy in identifying distressed firms based on financial data. Utilizing a dataset of Tehran Stock Exchange-listed companies, this research compares the performance of the hybrid model against traditional methods like logistic regression and standalone neural networks. Results demonstrate that the AIS-WNN hybrid model outperforms other techniques in terms of prediction accuracy, sensitivity, and overall robustness. The findings indicate that the proposed model provides a powerful tool for investors, auditors, and policymakers to anticipate financial distress and make informed decisions. This approach can be further expanded to other domains of financial forecasting, contributing to the advancement of predictive analytics in the field.

A Dynamic Weights-Based Wavelet Attention Neural Network for Defect Detection.

Automatic defect detection plays an important role in industrial production. Deep learning-based defect detection methods have achieved promising results. However, there are still two challenges in the current defect detection methods: 1) high-precision detection of weak defects is limited and 2) it is difficult for current defect detection methods to achieve satisfactory results dealing with strong background noise. This article proposes a dynamic weights-based wavelet attention neural network (DWWA-Net) to address these issues, which can enhance the feature representation of defects and simultaneously denoise the image, thereby improving the detection accuracy of weak defects and defects under strong background noise. First, wavelet neural networks and dynamic wavelet convolution networks (DWCNets) are presented, which can effectively filter background noise and improve model convergence. Second, a multiview attention module is designed, which can direct the network attention toward potential targets, thereby guaranteeing the accuracy for detecting weak defects. Finally, a feature feedback module is proposed, which can enhance the feature information of defects to further improve the weak defect detection accuracy. The DWWA-Net can be used for defect detection in multiple industrial fields. Experiment results illustrate that the proposed method outperforms the state-of-the-art methods (mean precision: GC10-DET: 6.0%; NEU: 4.3%). The code is made in https://github.com/781458112/DWWA.

Implementing advanced techniques for urban mountain torrent surveillance and early warning using rainfall predictive analysis

Urban flood forecasting and early warning play a pivotal role in ensuring efficient flood mitigation and management. The unpredictability in precipitation's intensity, temporal patterns, and spatial distribution introduces considerable variability into the basin's flow dynamics. This, in turn, escalates the uncertainty surrounding hydrological predictions, complicating the task of flood forecasting and early warning. To address these challenges, this research introduces a method that refines rainfall forecasts using a Wavelet Neural Network (WNN). By establishing a benchmark for area rainfall, we've developed a comprehensive disaster prevention and early warning system that synergizes real-time precipitation data, area rainfall, and flood peak predictions. Specifically tailored for urban terrains prone to mountain torrents, the WNN-based monitoring and pre-alarm model offers a sound and practical forecasting tool. Its relevance is accentuated by its potential to spearhead urban flood control initiatives. Our findings validate the model's adaptability and efficacy, particularly within urban mountainous watersheds, heralding a fresh paradigm in mountain flood disaster forecasting and early warnings.

RESEARCH ON CHAOTIC CHARACTERISTICS AND SHORT-TERM PREDICTION OF EN-ROUTE TRAFFIC FLOW USING ADS-B DATA

The short-term traffic flow prediction can help to reduce flight delays and optimize resource allocation. Using chaos dynamics theory to analyze the chaotic characteristics of en-route traffic flow is the basis of short-term en-route traffic flow prediction and ensuring the orderly and smooth state of the en-route. This paper takes the time series of en-route traffic flow extracted from Automatic-Dependent Surveillance Broadcast (ADS-B) measured data as the research object, uses the improved C–C method to reconstruct the phase space, and uses the improved small data volume method to calculate the Lyapunov index to identify the chaos phenomenon of en-route traffic flow. In order to avoid the interference of chaos phenomenon on traffic prediction, the Wavelet Neural Network (WNN) model is established to predict the traffic flow at en-route points. The experimental shows that when the number of iterations is 10,000, the average accuracy of WNN prediction is 0.87173, and the average running time is 6.9335334[Formula: see text]s. According to the experimental results, it can be seen that the smaller number of iterations has more advantages in running time, which greatly reduces the overall running time. At the same time, it indicates that appropriately increasing or reducing the number of iterations in this experiment has little effect on the results.

Temperature compensation study of infrared Sf6 gas sensor combining GA and wavelet neural network

Temperature compensation study of infrared Sf6 gas sensor combining GA and wavelet neural network

A Learnable and Explainable Wavelet Neural Network for EEG Artifacts Detection and Classification.

Electroencephalography (EEG) artifacts are very common in clinical diagnosis and can heavily impact diagnosis. Manual screening of artifact events is labor-intensive with little benefit. Therefore, exploring algorithms for automatic detection and classification of EEG artifacts can significantly assist clinical diagnosis. In this paper, we propose a learnable and explainable wavelet neural network (WaveNet) for EEG artifact detection and classification. The model is powered by the wavelet decomposition block based on invertible neural network, which can extract signal features without information loss, and a tree generator for building wavelet tree structure automatically. They provide the model with good feature extraction capabilities and explainability. To evaluate the model's performance more fairly, we introduce the base point level matching score (BASE) and the Event-Aligned Compensation Scoring (EACS) at the event level as two metrics for model performance evaluation. On the challenging Temple University EEG Artifact (TUAR) dataset, our model outperforms other baselines in terms of F1-score for both artifact detection and classification tasks. The case study also validates the model's ability to offer explainability for predictions based on frequency band energy, suggesting potential applications in clinical diagnosis.

Wavelet Probabilistic Neural Networks.

In this article, a novel wavelet probabilistic neural network (WPNN), which is a generative-learning wavelet neural network that relies on the wavelet-based estimation of class probability densities, is proposed. In this new neural network approach, the number of basis functions employed is independent of the number of data inputs, and in that sense, it overcomes the well-known drawback of traditional probabilistic neural networks (PNNs). Since the parameters of the proposed network are updated at a low and constant computational cost, it is particularly aimed at data stream classification and anomaly detection in off-line settings and online environments where the length of data is assumed to be unconstrained. Both synthetic and real-world datasets are used to assess the proposed WPNN. Significant performance enhancements are attained compared to state-of-the-art algorithms.

Vibration vision measurement and wavelet neural network control of flexible hinged plate

Vibration vision measurement and wavelet neural network control of flexible hinged plate

Adaptive Energy Management for Fuel Cell Heavy Trucks Based on Wavelet Neural Network Speed Predictor and Real-Time Weight Distribution

Adaptive Energy Management for Fuel Cell Heavy Trucks Based on Wavelet Neural Network Speed Predictor and Real-Time Weight Distribution

Dynamic Analysis and Neural-Adaptive Prescribed-Time Control of the FO Memristive Magnetic-Field Electromechanical Transducer.

This article is concerned with dynamic analysis and neural-adaptive prescribed-time control of the magnetic-field electromechanical transducer incorporating a memristor. First, a fractional-order (FO) mathematical model is developed, which comprehensively characterizes fractional properties of various dielectrics and establishes the relationship between magnetic flux and electric charge. The dynamical analysis explores internal evolution and complexity performance concerning a single factor or double factors among the FO, system parameter, and memristor configuration by the Bifurcation diagram, sample entropy, and C0 complexity from multiple perspectives. Subsequently, a neural-adaptive prescribed-time control scheme is proposed to transform detrimental chaotic oscillations into orderly motions, achieve the pregiven tracking precision and accommodating both actuator fault and system uncertainty. The controller design consists of three key steps: 1) a deferred constraint function is imposed on the tracking error starting from anywhere to get assignable tracking precision within a specified time, ensuring collision avoidance; 2) a type-2 fuzzy wavelet neural network (FWNN) is utilized effectively to handle parameter perturbations and system uncertainties; and 3) a second-order FO tracking differentiator (TD) is utilized to address the "explosion of complexity" of traditional backstepping under actuator fault model. It is shown that the proposed scheme is able to ensure the boundness of all signals of the closed-loop system. Finally, extensive simulation experiments are conducted to validate the effectiveness and robustness of the rendered scheme.

A modeling approach for the absorber of absorption heat pump systems

The study on the data-and-knowledge-driven modeling methods is very important for the digital twinning and the optimal control of absorption heat pump systems. For the purpose of obtaining an absorber model with high accuracy, low computational effort and less time-consuming for the absorption heat pump systems, a modeling method is proposed by combining the Simple Particle Swarm Optimization (SPSO) and the Wavelet Neural Network (WNN). The input-output structure of the model is presented by analyzing the operational principles of the absorber. In view of the complexity of the heat transfer and mass transfer processes inside the absorber, a single hidden layer WNN is employed as the internal structure of the model. The number of hidden layer nodes in the network model is determined by the trial-and-error method using the root mean square error and coefficient of determination. To overcome the drawback of WNN which can easily fall into the local optima during the error backpropagation process and improve the prediction accuracy of the model, the Morlet wavelet basis function and a SPSO algorithm are exploited respectively to replace the S-function of Neural Network and determine the optimal parameter values of the neural network (e.g. the weight, scaling factor, and translation factor, etc.). Experimental simulation results show the root mean square errors of the proposed model are 1.59 % and 2.21 % for the two outputs, respectively, which are smaller than the conventional WNN model. The proposed modeling approach effectively solves the problems of the BP neural network on easy falling into the local optimum and the slow convergence, which will be widely used in the process of the optimized operation control for heat pump systems.

Effect of the period of EEG signals on the decoding of motor information.

Decoding movement information from electroencephalogram to construct brain-computer interface has promising applications. The EEG data during the entire motor imagery (MI) period or movement execution (ME) period is generally decoded, and calculation of numerous information and massive dataset is time-consuming. In order to improve decoding efficiency, the joint topographic maps of the brain activation state of 15 subjects were studied during different periods. The results showed that the activation intensity of the preparation period in the motor imagery experiment was higher than during the exercise period, while during the exercise period, the activation intensity was higher than in the preparation period in the movement execution experiment. Hence, the wavelet neural network was used to decode the six-class movements including elbow flexion/extension, forearm pronation/supination and hand open/close in periods of MI/ME. The experimental results show that the accuracy obtained in the preparation period is the highest in the motor imagery experiment, which is 80.77%. On the other hand, the highest accuracy obtained in the exercise period of the movement execution experiment is 79.26%. It further proves that the optimized period is a key decoding factor to reduce the cost of calculation, and this new decoding method is effective to build a more intelligent brain-computer interface system.

A Method for Improving the Pronunciation Quality of Vocal Music Students Based on Big Data Technology

With the development of internet technology, big data has been used to evaluate the singing and pronunciation quality of vocal students. However, current methods have several problems such as poor information fusion efficiency, low algorithm robustness, and low recognition accuracy under low signal-to-noise ratio. To address these issues, this article proposes a new method for evaluating sound quality based on one-dimensional convolutional neural networks. It uses sound preprocessing, BP neural networks, wavelet neural networks, and one-dimensional CNNs to improve pronunciation quality. The proposed 1D CNN network is more suitable for one-dimensional sound signals and can effectively solve problems such as feature information fusion, pitch period detection, and network construction. It can evaluate singing art sound quality with minimum errors, good robustness, and strong portability. This method can be used for the evaluation and diagnosis of voice diseases, helping to improve students' professional abilities.

Hybrid time series models with exogenous variable for improved yield forecasting of major Rabi crops in India

Accurate and in-time prediction of crop yield plays a crucial role in the planning, management, and decision-making processes within the agricultural sector. In this investigation, utilizing area under irrigation (%) as an exogenous variable, we have made an exertion to assess the suitability of different hybrid models such as ARIMAX (Autoregressive Integrated Moving Average with eXogenous Regressor)–TDNN (Time-Delay Neural Network), ARIMAX–NLSVR (Non-Linear Support Vector Regression), ARIMAX–WNN (Wavelet Neural Network), ARIMAX–CNN (Convolutional Neural Network), ARIMAX–RNN (Recurrent Neural Network) and ARIMAX–LSTM (Long Short Term Memory) as compared to their individual counterparts for yield forecasting of major Rabi crops in India. The accuracy of the ARIMA model has also been considered as a benchmark. Empirical outcomes reveal that the ARIMAX–LSTM hybrid modeling combination outperforms all other time series models in terms of root mean square error (RMSE) and mean absolute percentage error (MAPE) values. For these models, an average improvement of RMSE and MAPE values has been observed to be 10.41% and 12.28%, respectively over all other competing models and 15.83% and 18.42%, respectively over the benchmark ARIMA model. The incorporation of the area under irrigation (%) as an exogenous variable in the ARIMAX framework and the inbuilt capability of the LSTM model to process complex non-linear patterns have been observed to significantly enhance the accuracy of forecasting. The performance supremacy of other hybrid models over their individual counterparts has also been evident. The results also suggest avoiding any performance generalization of individual models for their hybrid structures.

A New Method for Dynamical System Identification by Optimizing the Control Parameters of Legendre Multiwavelet Neural Network

Wavelet neural networks have been widely applied to dynamical system identification fields. The most difficult issue lies in selecting the optimal control parameters (the wavelet base type and corresponding resolution level) of the network structure. This paper utilizes the advantages of Legendre multiwavelet (LW) bases to construct a Legendre multiwavelet neural network (LWNN), whose simple structure consists of an input layer, hidden layer, and output layer. It is noted that the activation functions in the hidden layer are adopted as LW bases. This selection if based on the its rich properties of LW bases, such as piecewise polynomials, orthogonality, various regularities, and more. These properties contribute to making LWNNs more effective in approximating the complex characteristics exhibited by uncertainties, step, nonlinear, and ramp in the dynamical systems compared to traditional wavelet neural networks. Then, the number of selection LW bases and the corresponding resolution level are effectively optimized by the simple Genetic Algorithm, and the improved gradient descent algorithm is implemented to learn the weight coefficients of LWNN. Finally, four nonlinear dynamical system identification problems are applied to validate the efficiency and feasibility of the proposed LWNN-GA method. The experiment results indicate that the LWNN-GA method achieves better identification accuracy with a simpler network structure than other existing methods.

Comparison of hybrid RNA-based models to predict the degradation and mineralization of the microcontaminant hormone 17β-estradiol

New alternatives for effluent decontamination, such as electrochemical oxidation, are being developed to provide adequate removal of endocrine disruptors such as 17β-estradiol in wastewater. In this study, data-driven models of response surface methodology, artificial neural networks, wavelet neural networks, and adaptive neuro-fuzzy inference system will be used to predict the degradation and mineralization of the microcontaminant hormone 17β-estradiol through an electrochemical process to contribute to the treatment of effluent containing urine. With the use of different statistical criteria and graphical analysis of the correlation between observed and predicted data, it was possible to conduct a comparative analysis of the performances of the data-driven approaches. The results point to the superiority of the adaptive neuro-fuzzy inference system (correlation coefficient, R2, ranged from 0.99330 to 0.99682 for TOC removal and from 0.95330 to 0.99223 for the degradation of the hormone 17β-estradiol) techniques over the others. The remaining results obtained with the other metrics are consistent with this analysis.

Prediction of Criminal Suspect Characteristics with Application of Wavelet Neural Networks

Abstract Crime incidents grow at a certain rate every year and become more complicated day by day, but at this stage, the development of the field of crime analysis and prediction is still lagging, so this paper applies a wavelet neural network to predict the characteristics of criminal suspects. Analyze the applicability of the WNN model, explore the principle of criminal suspect feature prediction, and study the basis of wavelet neural network analysis. Establish the face feature recognition framework, use the Morlet function and Mexican Hat function pair to optimize and improve the wavelet neural network, and construct the model evaluation index for evaluating the model prediction effect. Preprocessing the suspect feature point data by using the grayscale reflection in Haar features. Simulation experiments are used to analyze the performance of different algorithms and the prediction effect of criminal suspect features on wavelet neural networks. The proposed algorithm in this study is superior and has a lesser number of parameters than ResNet. From the loss curves of different algorithms, the algorithm proposed in this study has a faster-descending loss curve and a smaller loss rate in the epoch value of [100, 200] interval. The overall range of the evaluation indexes of the algorithms proposed in this study is above 88%, and the highest accuracy rate can reach 94.234%, which is a good performance of the algorithms and accurate prediction.

Bearing characteristics of prestressed full-length anchoring rockbolt based on Wavelet Neural Network

In order to improve bearing capacity of rockbolts in deep-buried coal mine roadways, orthogonal tests were conducted to study influencing factors of rockbolt anchoring effect. Wavelet neural network model was introduced to predict the pull-out force of rockbolt. The activation and output functions of the wavelet neural network were improved, and the scaling and translation parameters were also modified by using the gradient descent method. These improvements enhanced the approximation rate of the wavelet neural network model, and solve the problem that the wavelet transform method is monotonous and difficult to adapt to the complex and variable engineering conditions. Research results illustrated that The value of the ultimate pull-out force is positively correlated with the strength of the specimen and pre-tension value of the specimen. According to the test results, the coal mine roadway support scheme was optimized, and the high prestress full-length anchoring rockbolt support technology was proposed. The effectiveness of research was verified through the engineering applications and in-situ monitoring results.

Modeling of intelligent hyperparameter tuned deep learning based copy move image forgery detection technique

Due to the drastic increase in the generation of high-quality fake images in social networking, it is essential to design effective recognition approaches. Image/video manipulation defines any set of actions which can be carried out on digital content by the use of software editing approaches or artificial intelligence. A major kind of image and video editing comprises replicating the regions of the image, named as copy-move technique. Conventional image processing methods physically search for the pattern relevant to the replicated contents, restricting the utilization in massive classification of data. Contrastingly, the recently developed deep learning (DL) models have exhibited promising performance over the traditional models. In this aspect, this paper presents a novel intelligent deep learning based copy move image forgery detection (IDL-CMIFD) technique. The proposed IDL-CMIFD technique intends to design a DL model to classify the candidate images into two classes: original and forged/tampered and then localized the copy moved regions. In addition, the proposed IDL-CMIFD technique involves the Adam optimizer with Efficient Net based feature extractor to derive a useful set of feature vectors. Moreover, chaotic monarch butterfly optimization (CMBO) with deep wavelet neural network (DWNN) model is applied for classification purposes. The CMBO algorithm is utilized to optimally tune the parameters involved in the DWNN model in such a way that the classification performance gets improved. The performance validation of the proposed model takes place on benchmark MICC-F220, MICC-F2000, MICC-F600 datasets. A wide range of comparative analyses is performed and the results ensured the better performance of the IDL-CMIFD technique in terms of different evaluation parameters.