Search Results (112)

Flash flood events are some of the most life-threatening natural disasters, so it is important to predict extreme rainfall events effectively. This study introduces an LSTM model that utilizes a customized loss function to effectively predict extreme rainfall events. The proposed model incorporates dynamic environmental variables, such as rainfall, LST, and NDVI, and incorporates additional static variables such as soil type and proximity to infrastructure. Wavelet transformation decomposes the time series into low- and high-frequency components to isolate long-term trends and short-term events. Model performance was compared against Random Forest (RF), Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), and an LSTM-RF ensemble. The custom loss LSTM achieved the best performance (MAE = 0.022 mm/day, RMSE = 0.110 mm/day, R² = 0.807, SMAPE = 7.62%), with statistical validation via a Kruskal–Wallis ANOVA, confirming that the improvement is significant. Model uncertainty is quantified using a Bayesian MCMC framework, yielding posterior estimates and credible intervals that explicitly characterize predictive uncertainty under extreme rainfall conditions. The sensitivity analysis highlights rainfall and LST as the most influential predictors, while wavelet decomposition provides multi-scale insights into environmental dynamics. The study concludes that customized loss functions can be highly effective in extreme rainfall event prediction and thus useful in managing flash flood events. Full article

The wavelet transform (WT) is an integral transform primarily used for processing and analyzing nonstationary signals due to its multiresolution property. Multiresolution analysis is one method that finds applications in many fields because of the characteristics of the transform. Over the years, WT has become standard and is integrated into many coding protocols and applications without special mention. Decades of research in the field of wavelets have revealed several stages of development. In the initial stage, the focus was on wavelet families, with scientists deriving new families for emerging applications. The second stage addressed implementation issues, emphasizing more efficient implementation techniques. The next stage involved artificial neural networks (ANNs) that perform WT. This paper reviews the development of WT with examples from maritime applications. We also provide an overview of cutting-edge trends in wavelets and propose the aforementioned stages as a new taxonomy of WT development. Full article

This paper presents a novel pipeline leak diagnosis framework that combines Savitzky–Golay scalograms with a lightweight advanced deep learning architecture. Pipelines are critical for transporting fluids and gases, but leaks can lead to operational disruptions, environmental hazards, and financial losses. Leak events generate acoustic emissions (AE), captured as transient signals by AE sensors; however, these signals are often masked by noise and affected by the transported medium. To overcome this challenge, a fluid-independent detection approach is proposed that begins with acquiring AE data under various operational conditions, including multiple intensities of pinhole leaks and normal states. The transient signals are transformed into detailed scalograms using the Continuous Wavelet Transform (CWT), revealing subtle time–frequency patterns associated with leak events. To enhance these leak-specific features, a targeted Savitzky–Golay (SG) filter is applied, producing refined Savitzky–Golay scalograms (SG scalograms). These SG scalograms are then used to train a Convolutional Neural Network (CNN) and a newly developed lightweight Vision Transformer with streamlined self-attention (LViT-S), which autonomously learn both local and global features. The LViT-S achieves reduced embedding dimensions and fewer Transformer layers, significantly lowering computational cost while maintaining high performance. Extracted local and global features are merged into a unified feature vector, representing diverse visual characteristics learned by each network through their respective loss functions. This comprehensive feature representation is then passed to an Artificial Neural Network (ANN) for final classification, accurately identifying the presence, severity, and absence of leaks. The effectiveness of the proposed method is evaluated under two different pressure conditions, two fluid types (gas and water), and three distinct leak sizes, achieving a high classification accuracy of 98.6%. Additionally, a comparative evaluation against four state-of-the-art methods demonstrates that the proposed framework consistently delivers superior accuracy across diverse operational scenarios. Full article

Background/Objectives: An ASD diagnosis from EEG is challenging due to non-stationary, low-SNR signals and small cohorts. We propose a compact, interpretable pipeline that pairs a shift-invariant Stationary Wavelet Transform (SWT) with Fisher’s Linear Discriminant (FLDA) as a supervised projection method, delivering band-level insight and subject-wise evaluation suitable for resource-constrained clinics. Methods: EEG from the KAU dataset (eight ASD, eight controls; 256 Hz) was decomposed with SWT (db4). We retained levels 3, 4, and 6 (γ/β/θ) as features. FLDA learned a low-dimensional discriminant subspace, followed by a linear decision rule. Evaluation was conducted using a subject-wise 70/30 split (no subject overlap) with accuracy, precision, recall, F1, and confusion matrices. Results: The β band (Level 4) achieved the best performance (accuracy/precision/recall/F1 = 0.95), followed by γ (0.92) and θ (0.85). Despite partial overlap in FLDA scores, the projection maximized between-class separation relative to within-class variance, yielding robust linear decisions. Conclusions: Unlike earlier FLDA-only pipelines and wavelet–entropy–ANN approaches, our study (1) employs SWT (undecimated, shift-invariant) rather than DWT to stabilize sub-band features on short resting segments, (2) uses FLDA as a supervised projection to mitigate small-sample covariance pathologies before classification, (3) provides band-specific discriminative insight (β > γ/θ) under a subject-wise protocol, and (4) targets low-compute deployment. These choices yield a reproducible baseline with competitive accuracy and clear clinical interpretability. Future work will benchmark kernel/regularized discriminants and lightweight deep models as cohort size and compute permit. Full article

Accurate nitrogen (N) content estimation in grassland vegetation is essential for ecosystem health and optimizing pasture quality, as N supports plant photosynthesis and water uptake. Traditional lab methods are slow and unsuitable for large-scale monitoring, while remote sensing models often face accuracy challenges due to hyperspectral data complexity. This study improves N content estimation in the typical steppe of Inner Mongolia by integrating hyperspectral remote sensing with advanced machine learning. Hyperspectral reflectance from Leymus chinensis and Cleistogenes squarrosa was measured using an ASD FieldSpec-4 spectrometer, and leaf N content was measured with an elemental analyzer. To address high-dimensional data, four spectral transformations—band combination, first-order derivative transformation (FDT), continuous wavelet transformation (CWT), and continuum removal transformation (CRT)—were applied, with Least Absolute Shrinkage and Selection Operator (LASSO) used for feature selection. Four machine learning models—Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Artificial Neural Network (ANN), and K-Nearest Neighbors (KNN)—were evaluated via five-fold cross-validation. Wavelet transformation provided the most informative parameters. The SVM model achieved the highest accuracy for L. chinensis (R² = 0.92), and the ANN model performed best for C. squarrosa (R² = 0.72). This study demonstrates that integrating wavelet transform with machine learning offers a reliable, scalable approach for grassland N monitoring and management. Full article

By weaving together cutting-edge AI robotics, resilient global supply chains, universal school enrollment, and dynamic public–private energy investments, this study unveils a powerful, integrated blueprint for driving environmental sustainability in the 21st century. In doing so, the study employed advanced machine-learning techniques—specifically, it introduced an ANN-enhanced wavelet quantile regression framework to uncover the multiscale determinants of China’s ecological footprint. Leveraging quarterly data from 2011/Q1 through 2024/Q4, it reveals dynamic, quantile-specific relationships that conventional approaches often miss. The result from the study demonstrates that robotics, supply-chain integration, public–private energy investments, gender-parity enrolment, and economic growth each exert a positive—and often escalating—upward pressure on the nation’s ecological footprint over short, medium, and long horizons, with the strongest effects in high ecological footprint contexts. The study proposes a significant, tailor-made policy based on these findings. Full article

Accurate and real-time classification of low-latency Internet traffic is critical for applications such as video conferencing, online gaming, financial trading, and autonomous systems, where millisecond-level delays can degrade user experience. Existing methods for low-latency traffic classification, reliant on raw temporal features or static statistical analyses, fail to capture dynamic frequency patterns inherent to real-time applications. These limitations hinder accurate resource allocation in heterogeneous networks. This paper proposes a novel framework integrating wavelet transform (WT) and artificial neural networks (ANNs) to address this gap. Unlike prior works, we systematically apply WT to commonly used temporal features—such as throughput, slope, ratio, and moving averages—transforming them into frequency-domain representations. This approach reveals hidden multi-scale patterns in low-latency traffic, akin to structured noise in signal processing, which traditional time-domain analyses often overlook. These wavelet-enhanced features train a multilayer perceptron (MLP) ANN, enabling dual-domain (time–frequency) analysis. We evaluate our approach on a dataset comprising FTP, video streaming, and low-latency traffic, including mixed scenarios with up to four concurrent traffic types. Experiments demonstrate 99.56% accuracy in distinguishing low-latency traffic (e.g., video conferencing) from FTP and streaming, outperforming k-NN, CNNs, and LSTMs. Notably, our method eliminates reliance on deep packet inspection (DPI), offering ISPs a privacy-preserving and scalable solution for prioritizing time-sensitive traffic. In mixed-traffic scenarios, the model achieves 74.2–92.8% accuracy, offering ISPs a scalable solution for prioritizing time-sensitive traffic without deep packet inspection. By bridging signal processing and deep learning, this work advances efficient bandwidth allocation and enables Internet Service Providers to prioritize time-sensitive flows without deep packet inspection, improving quality of service in heterogeneous network environments. Full article

Temperature forecasting is critical for public safety, environmental risk management, and energy conservation. However, reliable forecasting becomes challenging in regions where governmental institutions lack adequate measurement infrastructure. To address this limitation, the present study aims to improve temperature forecasting by collecting temperature, pressure, and humidity data through IoT sensor networks. The study further seeks to identify the most effective method for the real-time processing of large-scale datasets generated by sensor measurements and to ensure data reliability. The collected data were pre-processed using Discrete Wavelet Transform (DWT) to extract essential features and reduce noise. Subsequently, three wavelet-processed deep-learning models were employed: Wavelet-processed Artificial Neural Networks (W-ANN), Wavelet-processed Long Short-Term Memory Networks (W-LSTM), and Wavelet-processed Bidirectional Long Short-Term Memory Networks (W-BiLSTM). Among these, the W-BiLSTM model yielded the highest performance, achieving a test accuracy of 97% and a Mean Absolute Percentage Error (MAPE) of 2%. It significantly outperformed the W-LSTM and W-ANN models in predictive accuracy. Forecasts were validated using data obtained from the Turkish State Meteorological Service (TSMS), yielding a 94% concordance, thereby confirming the robustness of the proposed approach. The findings demonstrate that the W-BiLSTM-based model enables reliable temperature forecasting, even in regions with insufficient governmental measurement infrastructure. Accordingly, this approach holds considerable potential for supporting data-driven decision-making in environmental risk management and energy conservation. Full article

To address the persistent challenge of low recognition accuracy in precious wood species classification, this study proposes a novel methodology for identifying Pterocarpus santalinus, Pterocarpus tinctorius (PTD), and Pterocarpus tinctorius (Zambia). This approach synergistically integrates artificial neural networks (ANNs) with advanced image feature extraction techniques, specifically Fast Fourier Transform, Gabor Transform, Wavelet Transform, and Gray-Level Co-occurrence Matrix. Features were extracted from both transverse and longitudinal wood sections. Fifteen distinct ANN models were subsequently developed: hybrid-section models combined features from different sections using a single algorithm, while multi-algorithm models aggregated features from the same section across all four algorithms. The dual-section hybrid wavelet model (LC4) demonstrated superior performance, achieving a perfect 100% recognition accuracy. High accuracies were also observed in the four-parameter combination models for longitudinal (L5) and transverse (C5) sections, yielding 97.62% and 91.67%, respectively. Notably, 92.31% of the LC4 model’s test samples exhibited an absolute error of ≤1%, highlighting its high reliability and precision. These findings confirm the efficacy of integrating image processing with neural networks for fine-grained wood identification and underscore the exceptional discriminative power of wavelet-based features in cross-sectional data fusion. Full article

Vertical ground reaction force (vGRF) plays an important role in the study of running-related injuries (RRIs). This study explores the synchronization method between inertial measurement unit (IMU) and vGRF data of running and develops ANN models to accurately predict vGRF. Fifteen runners participated in this study. Acceleration data and vGRF values of eight rearfoot strikers and seven forefoot strikers running at 12, 14, and 16 km/h were collected by a single IMU and an instrumented treadmill. The sliding time window synchronization (STWS) algorithm was developed to sync IMU data with vGRF data. The wavelet neural network model (WNN) and feed-forward neural network model (FFNN) were adapted to predict vGRF using three-axis or sagittal-axis acceleration data in the stance phase, respectively. One rearfoot striker and one forefoot striker were randomly selected as a test set, while the other participants formed training sets. After synchronization, mean absolute errors for stride time of the IMU and vGRF data were less than 11.2 ms. The coefficient of multiple correlations for vGRF measured curves and predicted curves was more than 0.97. The normalized root mean square errors (NRMSEs) between two curves were 4.6~9.2%, and R² was 0.93~0.99. For peak vGRF, the NRMSEs were 1.6~8.2%, except for rearfoot strike runners at 16 km/h using the FFNN model (10.7% and 11.1%). The Bland–Altman plots indicate that the errors for both the WNN and FFNN models are within acceptable limits. The STWS algorithm can effectively achieve the data synchronization between the IMU and the force plate during running. Both WNN and FFNN models demonstrated good accuracy and agreement in predicting vGRF. Using sagittal-axis acceleration data may be an ideal model with good prediction accuracy and less input data. This work provides direction for developing ANN models of personalized monitoring of lower limb load. Full article

Wind energy is a renewable energy resource that can be harnessed to generate electrical energy. In this paper, a novel Artificial Neural Network (ANN) approach using wavelet analysis for wind energy forecasting is proposed and tested with wind data from Kanyakumari, India, for different seasons. The wavelet decomposition is used to decom-pose the wind power time series data into different frequency components. The model simulates the complex mapping of historical wind power to allow the forecasting of wind power data for the next 3 h or the next 24 h. The predicted components are then reconstructed to obtain the overall predicted wind energy time series. The proposed models give more promising prediction results than the model without the use of wavelets. The regression coefficient and Mean Square Error (MSE) are computed and observed in order to assess the model’s performance. Full article

Surface air pollution affects ecosystems and people’s health. However, traditional models have low prediction accuracy. Therefore, a hybrid model for accurately predicting daily surface PM_2.5 concentrations was integrated with wavelet (W), convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM), and bidirectional gated recurrent unit (BiGRU). The data for meteorological factors and air pollutants in Guangzhou City from 2014 to 2020 were utilized as inputs to the models. The W-CNN-BiGRU-BiLSTM hybrid model demonstrated strong performance during the predicting phase, achieving an R (correlation coefficient) of 0.9952, a root mean square error (RMSE) of 1.4935 μg/m³, a mean absolute error (MAE) of 1.2091 μg/m³, and a mean absolute percentage error (MAPE) of 7.3782%. Correspondingly, the accurate prediction of surface PM_2.5 concentrations is beneficial for air pollution control and urban planning. Full article

The paper presents an approach for detecting anomalies in radon concentration in seismically active areas. It involves training multiple artificial neural networks (ANNs) to predict radon concentration during periods without seismic events. The trained ANNs model the typical radon variations under non-seismic conditions, and the predicted values for normal radon behavior are compared with actual radon concentrations around the time of recorded earthquakes. Significant deviations from the predicted values are interpreted as radon anomalies potentially associated with upcoming seismic events. The methodology includes wavelet transformation for noise removal, a multilayer ANN trained using the Levenberg–Marquardt algorithm, and a segmentation approach based on radial zones (annuli) for localized predictions. Large datasets from three radon measurement stations in Bulgaria—Yambol, Dimitrovgrad, and Krupnik—were used. Data from seismic periods were excluded during the training of the neural networks to ensure that the models learn only the natural radon variations under non-seismic conditions. Key results indicate that, in Yambol and Dimitrovgrad, the actual radon concentration exceeds the predicted normal levels during earthquakes, whereas in Krupnik, radon concentration is lower than expected during seismic events. Analysis of the pre-seismic period shows elevated radon levels 48 h before earthquakes at some stations, while expected anomalies were not observed at others. Through this study, we demonstrate the effectiveness of ANN models in modeling radon behavior under non-seismic conditions and identifying deviations that may be linked to seismic activity. We believe that the obtained results contribute to the ongoing discussion on radon concentration anomalies as potential earthquake precursors and suggest that local geological and environmental factors may further influence radon emissions in different ways. Full article

Wind speed is a critical parameter for both energy applications and climate studies, particularly under changing climatic conditions and has attracted increasing research interest from the scientific comunity. This parameter is of interest to both researchers interested in climate change and researchers working on issues related to energy production. Based on this, in this study, prospective analyses were made with various machine learning algorithms, the long-short term memory (LSTM), the artificial neural network (ANN), and the support vector machine (SVM) algorithms, and one of the stochastic methods, the seasonal autoregressive integrated moving average (SARIMA), using the monthly wind data obtained from Bodo. In these analyses, five different models were created with the assistance of cross-correlation. The models obtained from the analyses were improved with the wavelet transformation (WT), and the results obtained were evaluated for the correlation coefficient (R), the Nash–Sutcliffe model efficiency (NSE), the Kling–Gupta efficiency (KGE), the performance index (PI), the root mean standard deviation ratio (RSR), and the root mean square error (RMSE). The results obtained from this study unveiled that LSTM emerged as the best performance metric in the M04 model among other models (R = 0.9532, NSE = 0.8938, KGE = 0.9463, PI = 0.0361, RSR = 0.0870, and RMSE = 0.3248). Another notable finding obtained from this study was that the best performance values in analyses without WT were obtained with SARIMA. The results of this study provide information on forward-looking modeling for institutions and decision-makers related to energy and climate change. Full article

To develop agricultural risk management strategies, the early identification of water deficits during the growing cycle is critical. This research proposes a deep learning hybrid approach for multi-step soil moisture forecasting in the Bundaberg region in Queensland, Australia, with predictions made for 1-day, 14-day, and 30-day, intervals. The model integrates Geospatial Interactive Online Visualization and Analysis Infrastructure (Giovanni) satellite data with ground observations. Due to the periodicity, transience, and trends in soil moisture of the top layer, time series datasets were complex. Hence, the Maximum Overlap Discrete Wavelet Transform (moDWT) method was adopted for data decomposition to identify the best correlated wavelet and scaling coefficients of the predictor variables with the target top layer moisture. The proposed 3-phase hybrid moDWT-Lasso-LSTM model used the Least Absolute Shrinkage and Selection Operator (Lasso) method for feature selection. Optimal hyperparameters were identified using the Hyperopt algorithm with deep learning LSTM method. This proposed model’s performances were compared with benchmarked machine learning (ML) models. In total, nine models were developed, including three standalone models (e.g., LSTM), three integrated feature selection models (e.g., Lasso-LSTM), and three hybrid models incorporating wavelet decomposition and feature selection (e.g., moDWT-Lasso-LSTM). Compared to alternative models, the hybrid deep moDWT-Lasso-LSTM produced the superior predictive model across statistical performance metrics. For example, at 1-day forecast, The moDWT-Lasso-LSTM model exhibits the highest accuracy with the highest $R^2\approx 0.92469$ and the lowest RMSE $\approx 0.97808$, MAE $\approx 0.76623$, and SMAPE $\approx 4.39700$%, outperforming other models. The moDWT-Lasso-DNN model follows closely, while the Lasso-ANN and Lasso-DNN models show lower accuracy with higher RMSE and MAE values. The ANN and DNN models have the lowest performance, with higher error metrics and lower R2 values compared to the deep learning models incorporating moDWT and Lasso techniques. This research emphasizes the utility of the advanced complementary ML model, such as the developed moDWT-Lasso-LSTM 3-phase hybrid model, as a robust data-driven tool for early forecasting of soil moisture. Full article