Wavelet Neural Network Model Research Articles

Hybrid wavelet-neural network models for time series

The use of wavelet analysis contributes to better modeling for financial time series in the sense of both frequency and time. In this study, S&P500 and NASDAQ data are separated into several components utilizing multiresolution analysis (MRA). Subsequently, using an appropriate neural network structure, each component is modeled. In addition, wavelets are used as an activation function in long short-term memory (LSTM) networks to form a hybrid model. The hybrid model is merged with MRA as a proposed method in this paper. Four distinct strategies are employed: LSTM, LSTM+MRA, hybrid LSTM-Wavenet, and hybrid LSTM-Wavenet+MRA. Results show that the use of MRA and wavelets as an activation function together reduces the error the most.

A wavelet neural network informed by time-domain signal preprocessing for bearing remaining useful life prediction

Rolling bearings are important components in rotating machinery in various industries. Conducting intelligent prognostics for bearing remaining useful life (RUL) prediction plays an important role in the health management and reliability assessment of these machinery systems. While the bearing fault prognosis using measured system response through machine learning techniques has attracted significant attention and demonstrated promising potential, completely data-driven approaches face some challenges in understanding complex domains with data efficient learning. In this research, we develop an integral bearing fault prognosis framework informed by the well-designed time-domain signal preprocessing to conduct the bearing RUL prediction. This framework is built upon physical feature-oriented signal preprocessing and an associated wavelet neural network (WNN). Sequential procedures of time-domain analyses are proposed to extract the physical features of bearing degradation. Empirical mode decomposition (EMD) is specifically chosen owing to its capability of handling bearing fault signals that are nonstationary with underlying nonlinearities. The WNN is a new class of neural networks that combines the classic neural network and wavelet analysis. Here in this research a WNN model built upon B-spline mother wavelet to suit the preceding EMD-based signal preprocessing is constructed to process the bearing degradation features extracted and then identify their correlation with bearing RUL. The combination of EMD-based signal preprocessing and B-spline mother wavelet in WNN enables the network to learn the input-output correlation in a physical sense. Case studies formulated upon multiple bearing datasets and multiple benchmark methods are carried out to systematically validate the proposed framework. The results consistently demonstrate prediction accuracy and performance robustness.

Epicasting: An Ensemble Wavelet Neural Network for forecasting epidemics

Infectious diseases remain among the top contributors to human illness and death worldwide, among which many diseases produce epidemic waves of infection. The lack of specific drugs and ready-to-use vaccines to prevent most of these epidemics worsens the situation. These force public health officials and policymakers to rely on early warning systems generated by accurate and reliable epidemic forecasters. Accurate forecasts of epidemics can assist stakeholders in tailoring countermeasures, such as vaccination campaigns, staff scheduling, and resource allocation, to the situation at hand, which could translate to reductions in the impact of a disease. Unfortunately, most of these past epidemics exhibit nonlinear and non-stationary characteristics due to their spreading fluctuations based on seasonal-dependent variability and the nature of these epidemics. We analyze various epidemic time series datasets using a maximal overlap discrete wavelet transform (MODWT) based autoregressive neural network and call it Ensemble Wavelet Neural Network (EWNet) model. MODWT techniques effectively characterize non-stationary behavior and seasonal dependencies in the epidemic time series and improve the nonlinear forecasting scheme of the autoregressive neural network in the proposed ensemble wavelet network framework. From a nonlinear time series viewpoint, we explore the asymptotic stationarity of the proposed EWNet model to show the asymptotic behavior of the associated Markov Chain. We also theoretically investigate the effect of learning stability and the choice of hidden neurons in the proposal. From a practical perspective, we compare our proposed EWNet framework with twenty-two statistical, machine learning, and deep learning models for fifteen real-world epidemic datasets with three test horizons using four key performance indicators. Experimental results show that the proposed EWNet is highly competitive compared to the state-of-the-art epidemic forecasting methods.

Fuzzy wavelet neural network driven vehicle detection on remote sensing imagery

Remote sensing-based target detection process is applied to spot the targeted objects in remote sensing images (RSIs). However, it is challenging to detect small-sized vehicles in RSIs. The current study designs a Chicken Swarm Optimization with Transfer Learning-Driven Vehicle Detection and Classification on Remote Sensing Imagery (CSOTL-VDCRS) technique to resolve these issues. The presented CSOTL-VDCRS technique employs the mask-region based Convolutional Neural Network (Mask RCNN) technique for the detection of the vehicles. Once the vehicles in the RSIs are detected, the next step is to classify them using the Fuzzy Wavelet Neural Network (FWNN) model. To enhance the performance of the proposed model in terms of vehicle detection, the CSO technique is used as a hyperparameter optimizer for the Mask RCNN technique. The proposed CSOTL-VDCRS technique was experimentally validated using the benchmark dataset, and the outcomes demonstrate its superior performance over other existing models.

Predicting vertical ground reaction force in rearfoot running: A wavelet neural network model and factor loading

ABSTRACT This study proposed a simple method for selecting input variables by factor loading and inputting these variables into a wavelet neural network (WNN) model to predict vertical ground reaction force (vGRF). The kinematic data and vGRF of 9 rearfoot strikers at 12, 14, and 16 km/h were collected using a motion capture system and an instrumented treadmill. The input variables were screened by factor loading and utilized to predict vGRF with the WNN. Nine kinematic variables were selected, corresponding to nine principal components, mainly focusing on the knee and ankle joints. The prediction results of vGRF were effective and accurate at different speeds, namely, the coefficient of multiple correlation (CMC) > 0.98 (0.984–0.988), the normalized root means square error (NRMSE) < 15% (9.34–11.51%). The NRMSEs of impact force (8.18–10.01%), active force (4.92–7.42%), and peak time (7.16–12.52%) were less than 15%. There was a small number (peak, 4.12–6.18%; time, 4.71–6.76%) exceeding the 95% confidence interval (CI) using the Bland-Altman method. The knee joint was the optimal location for estimating vGRF, followed by the ankle. There were high accuracy and agreement for predicting vGRF with the peak and peak time at 12, 14, and 16 km/h. Therefore, factor loading could be a valid method to screen kinematic variables in artificial neural networks.

Multi-feature Extraction of Metal Cracks using Based on Wavelet Neural network

The traditional ultrasonic testing mostly uses a single feature, which induce the inaccuracy of the crack detection. This paper proposes a metal crack detection method based on multi-feature extraction. First, the characteristics of time-frequency information of the signal obtained by using wavelet packet transform is briefly introduced. Secondly, the designed wavelet neural network model consists of first layer with three neurons (wavelet packet transform of the ultrasonic echo signal, the peak and energy function), and the output layer with one neuron presenting recognition features to identify and analyze metal cracks. The experimental results show ultrasonic echo measurement with the improved method proposed model can effectively reduce the influence of white gaussian noise while significantly improving the recognition rate of metal cracks.

Internet-based centralized remote real-time long-span bridge health monitoring system

The safe operation of bridges is a major issue related to the national economy and people’s livelihood. With the rapid development of the water transport industry, the problems of ship yaw and bridge collision avoidance occur frequently, which cause serious harm to the bridge structure and safety. However, the current bridge health monitoring system is difficult to feed back the monitored information in time, and in the process of collecting information by wireless sensors, information errors or missing problems easily occur, which hinders the normal monitoring of bridge health. With the rapid development of the Internet and the gradual maturity of wireless sensor technology, how to achieve complete and effective collection and feedback of monitoring information has become a hot research topic and an urgent problem. Therefore, on the basis of Internet technology, this study perceives, collects and processes the ship information in the bridge monitoring area covered by the network through the wireless sensor network, uses the embedded wavelet neural network model to denoise the monitoring data, and finally transmits it to the data processing center, thus establishing a centralized remote real-time Long-span bridge health monitoring system based on the Internet. The experimental results show that the monitoring deformation displacement curve based on the Internet centralized remote real-time long-span bridge health monitoring system technology presents a stable fluctuation state. The cumulative shape variable fluctuates in the range of -5 mm to 5 mm, indicating that the deformation trend of the bridge has always existed.

Medium-term forecast of daily passenger volume of high speed railway based on DLP-WNN

PurposeThis paper aims to propose a medium-term forecast model for the daily passenger volume of High Speed Railway (HSR) systems to predict the daily the Origin-Destination (OD) daily volume for multiple consecutive days (e.g. 120 days).Design/methodology/approachBy analyzing the characteristics of the historical data on daily passenger volume of HSR systems, the date and holiday labels were designed with determined value ranges. In accordance to the autoregressive characteristics of the daily passenger volume of HSR, the Double Layer Parallel Wavelet Neural Network (DLP-WNN) model suitable for the medium-term (about 120 d) forecast of the daily passenger volume of HSR was established. The DLP-WNN model obtains the daily forecast result by weighed summation of the daily output values of the two subnets. Subnet 1 reflects the overall trend of daily passenger volumes in the recent period, and subnet 2 the daily fluctuation of the daily passenger volume to ensure the accuracy of medium-term forecast.FindingsAccording to the example application, in which the DLP-WNN model was used for the medium-term forecast of the daily passenger volumes for 120 days for typical O-D pairs at 4 different distances, the average absolute percentage error is 7%-12%, obviously lower than the results measured by the Back Propagation (BP) neural network, the ELM (extreme learning machine), the ELMAN neural network, the GRNN (generalized regression neural network) and the VMD-GA-BP. The DLP-WNN model was verified to be suitable for the medium-term forecast of the daily passenger volume of HSR.Originality/valueThis study proposed a Double Layer Parallel structure forecast model for medium-term daily passenger volume (about 120 days) of HSR systems by using the date and holiday labels and Wavelet Neural Network. The predict results are important input data for supporting the line planning, scheduling and other decisions in operation and management in HSR systems.

Dynamic wavelet neural network model for damage features extraction and patterns recognition

Dynamic wavelet neural network model for damage features extraction and patterns recognition

Rainfall prediction using time-delay wavelet neural network (TDWNN) model for assessing agrometeorological risk

In an agriculturally dependent nation like India, accurate and effective rainfall forecasting methods are crucial for assessing agrometeorological risk. Forecasting rainfall is perhaps one amongst the most arduous tasks in this context due to the prevalence of a non-linear pattern. One of the most promising and frequently employed approaches for forecasting rainfall data is the Time-Delay Neural Network (TDNN) model. TDNN's non-parametric, data-driven, and self-adaptive characteristics make it increasingly attractive for modelling nonlinear dynamics and generating nonlinear forecasts. Nevertheless, since the conventional TDNN uses the sigmoid activation function, there is always a chance that the training process may converge to local minima. This study addresses the usage of a Time-delay wavelet neural network (TDWNN), which employs a TDNN architecture with a hidden layer activation function derived from the orthonormal wavelet family, in order to circumvent this issue. TDWNN has been empirically demonstrated using annual rainfall data from two districts in the Indian state of West Bengal. According to the findings of this study, the TDWNN model is superior than the conventional TDNN method to assess agrometeorological risk.

Classification of COVID-19 from CT chest images using Convolutional Wavelet Neural Network

&lt;p&gt;Analyzing X-rays and computed tomography-scan (CT scan) images using a convolutional neural network (CNN) method is a very interesting subject, especially after coronavirus disease 2019 (COVID-19) pandemic. In this paper, a study is made on 423 patients’ CT scan images from Al-Kadhimiya (Madenat Al Emammain Al Kadhmain) hospital in Baghdad, Iraq, to diagnose if they have COVID or not using CNN. The total data being tested has 15000 CT-scan images chosen in a specific way to give a correct diagnosis. The activation function used in this research is the wavelet function, which differs from CNN activation functions. The convolutional wavelet neural network (CWNN) model proposed in this paper is compared with regular convolutional neural network that uses other activation functions (exponential linear unit (ELU), rectified linear unit (ReLU), Swish, Leaky ReLU, Sigmoid), and the result is that utilizing CWNN gave better results for all performance metrics (accuracy, sensitivity, specificity, precision, and F1-score). The results obtained show that the prediction accuracies of CWNN were 99.97%, 99.9%, 99.97%, and 99.04% when using wavelet filters (rational function with quadratic poles (RASP1), (RASP2), and polynomials windowed (POLYWOG1), superposed logistic function (SLOG1)) as activation function, respectively. Using this algorithm can reduce the time required for the radiologist to detect whether a patient has COVID or not with very high accuracy.&lt;/p&gt;

Sailfish Optimizer with Deep Transfer Learning-Enabled Arabic Handwriting Character Recognition

The recognition of the Arabic characters is a crucial task in computer vision and Natural Language Processing fields. Some major complications in recognizing handwritten texts include distortion and pattern variabilities. So, the feature extraction process is a significant task in NLP models. If the features are automatically selected, it might result in the unavailability of adequate data for accurately forecasting the character classes. But, many features usually create difficulties due to high dimensionality issues. Against this background, the current study develops a Sailfish Optimizer with Deep Transfer Learning-Enabled Arabic Handwriting Character Recognition (SFODTL-AHCR) model. The projected SFODTL-AHCR model primarily focuses on identifying the handwritten Arabic characters in the input image. The proposed SFODTL-AHCR model pre-processes the input image by following the Histogram Equalization approach to attain this objective. The Inception with ResNet-v2 model examines the pre-processed image to produce the feature vectors. The Deep Wavelet Neural Network (DWNN) model is utilized to recognize the handwritten Arabic characters. At last, the SFO algorithm is utilized for fine-tuning the parameters involved in the DWNN model to attain better performance. The performance of the proposed SFODTL-AHCR model was validated using a series of images. Extensive comparative analyses were conducted. The proposed method achieved a maximum accuracy of 99.73%. The outcomes inferred the supremacy of the proposed SFODTL-AHCR model over other approaches.

Short- and long-term streamflow forecasting using wavelet neural networks for complex watersheds: A case study in the Mahanadi River, India

Water plans and operations (e.g., flood control, drought mitigation measures, water allocation, and engineering design) depend on reliable streamflow information. Thus, this study presents a methodology that improves streamflow forecasting using wavelet neural networks (WNN) for the short- (daily) and long-term (weekly, fortnightly, and monthly) in the Mahanadi River basin, India. The WNN model employs multilayer artificial neural networks (NN) to relate streamflows with wavelet-based approximations of previous streamflows and rainfalls. The methodology was validated using data from ten stations and three performance indices: Pearson correlation coefficient (R), percentage of trends (PBIAS), and Nash-Sutcliffe efficiency (NSE). These indices confirmed that adding rainfall data as input provided better estimations than the sole use of streamflows. The WNN approach was superior to all other applications (NSE ranging from 0.299 to 0.987 for all time horizons and stations), especially for long-term forecasts in the Mahanadi River basin, and could be a viable alternative to other catchments.

Special issue on International Conference on Computing and Communication Networks

Special issue on International Conference on Computing and Communication Networks

A Self-Adaption Recognition Method for English Speech on Cloud Platform Based on Wavelet Neural Network

Although there are various recognition methods for digital English speech (DES) on cloud platform network, the accuracy of them is low and the average time consumption is too long. Due to above shortages, this study put forward a self-adaption recognition method based on wavelet neural network (WNN). At first, the study used zero-crossing rate as feature of voiceless and voiced sound of the DES and used WNN to carry out conversion for the English speech information. Then, the study obtained wavelet-scaling function and parameterized wavelet function via zero-pole model. The parameterized wavelet function was used as the feature vector of the recognition. Wavelet function base of DES feature was generated via stretching and translating transformation. The transformed wavelet function was used to build WNN model. Moreover, error entropy function of the recognition was calculated by introducing momentum factor and partial derivative of the error entropy function to adjust parameter of the built WNN model. Thus, the study achieved the self-adaption recognition of DES. Simulation results show that the proposed method has high recognition accuracy and short recognition time.

Intelligent metaheuristics with optimal machine learning approach for malware detection on IoT‐enabled maritime transportation systems

AbstractThe latest advancements in Internet of Things (IoT) have revolutionized the productivity of global shipping industry in the recent years. It also led to the emergence of IoT‐enabled Maritime Transportation Systems (MTS). These approaches detect the malware in network before the execution process. Various machine learning (ML) models have been proposed and designed in literature for effective malware detection. However, the existence of numerous features in the data bring dimensionality problem which can be only resolved by the use of feature selection approaches. Therefore, the current research work presents Intelligent Metaheuristics‐based Feature Selection model with Optimal ML approach for Malware Detection (IMFSOML‐MD) on IoT‐enabled MTS. Primarily, IMFSOML‐MD technique involves the design of Quantum Invasive Weed Optimization Algorithm‐based Feature Selection technique to optimally choose a subset of features. Moreover, an Optimal Wavelet Neural Network (OWNN) model is employed to perform classification process. The initial parameters of WNN model are optimally tuned with the help of Colliding Bodies Optimization algorithm thereby improving the detection performance. The proposed IMFSOML‐MD technique was experimentally validated using publicly‐available CICMalDroid2020 dataset. The results from extensive comparative analysis demonstrated the superiority of the proposed IMFSOML‐MD technique over other compared methods in terms of detection performance with maximum accuracy of 98.96%.

A Hybrid ARFIMA Wavelet Artificial Neural Network Model for DJIA Index Forecasting

This paper proposes a hybrid modelling approach for forecasting returns and volatilities of the stock market. The model, called ARFIMA-WLLWNN model, integrates the advantages of the ARFIMA model, the wavelet decomposition technique (namely, the discrete MODWT with Daubechies least asymmetric wavelet filter) and artificial neural network (namely, the LLWNN neural network). The model develops through a two-phase approach. In phase one, a wavelet decomposition improves the forecasting accuracy of the LLWNN neural network, resulting in the Wavelet Local Linear Wavelet Neural Network (WLLWNN) model. The Back Propagation and Particle Swarm Optimization (PSO) learning algorithms optimize the WLLWNN structure. In phase two, the residuals of an ARFIMA model of the conditional mean become the input to the WLLWNN model. The hybrid ARFIMA-WLLWNN model is evaluated using daily returns of the Dow Jones Industrial Average index over 01/05/2010 to 02/11/2020. The experimental results indicate that the PSO-optimized version of the hybrid ARFIMA-WLLWNN outperforms the LLWNN, WLLWNN, ARFIMA-LLWNN, and the ARFIMA-HYAPARCH models and provides more accurate out-of-sample forecasts over validation horizons of one, five and twenty-two days.

Algorithm Design for Asset Trading Under Multiple Factors

For the strategy of investing in gold and Bitcoin, first collect the historical prices of two types of investment products in the market, and use the wavelet neural network model and WT-LSTM model to model and analyze to predict the future price trends of gold and Bitcoin. Second, considering the difference in price fluctuations between gold and Bitcoin, based on the GARCH-EVT model to increase the risk uncertainty of financial assets, proposes how to achieve the best trading strategy under risk characteristics. Finally, considering the influence of transaction rate on income, we use particle swarm algorithm and genetic algorithm to study what kind of transaction rate can achieve maximum income. The study found that although traders can predict future trends based on daily price changes, due to the different risk factors of gold and Bitcoin, and the different sensitivity of the two financial assets to transaction costs, trading strategies will be very different.

Prediction and Risk Assessment of Extreme Weather Events Based on Gumbel Copula Function

Damage caused by climate catastrophes is severe, especially for the 1-in-100-year events. This study is aimed at assessing the frequency and spatiotemporal regularity of extreme weather events. Based on the selected Gumbel copula function, a joint trivariate distribution of weather events is established. In this study, different univariate return periods and return periods of the joint trivariate distribution are calculated separately. Second, the Moran index is used to determine whether there is a spatial correlation between weather events. In this paper, the spatial and temporal patterns of weather events are determined based on a geographically weighted regression model. The suggestion of adding Bayesian information to the model measurements to improve the model accuracy is presented. Finally, a wavelet neural network model is constructed to predict the probability of extreme weather events throughout the Americas.

Early Detection of Network Fault Using Improved Gray Wolf Optimization and Wavelet Neural Network

To address the problem of diagnostic accuracy and stability degradation caused by random selection of the initial parameters for the wavelet neural network (WNN) fault diagnosis model, this paper proposes a network troubleshooting model based on the improved gray wolf algorithm (IGWO) and the wavelet neural network. First, the convergence factor and policy for the weight update are redesigned in the IGWO algorithm. This study uses a nonlinear convergence factor to balance the global and local search capabilities of the algorithm and dynamically adjusts the weights according to the adaptability of the head wolf α to strengthen its leadership position. Thereafter, the initial weights and biases of the WNN are optimized using the IGWO algorithm. During the backpropagation of the WNN error, momentum factors are introduced to prevent the model from falling into local optimization. Experimental results show that the IGWO algorithm is far better than GWO in terms of convergence speed and convergence accuracy. Furthermore, the average diagnostic accuracy of the IGWO-WNN model on the KDD-CUP99 dataset reaches 99.22%, which is 1.15% higher than that of the WNN model, and the stability of the diagnostic results is significantly improved.