Search Results (1,211)

Intelligent Speech Technology (IST) is revolutionizing healthcare by enhancing transcription accuracy, disease diagnosis, and medical equipment control in smart hospital environments. This study introduces an innovative approach employing federated learning with Multi-Layer Perceptron (MLP) and Gated Recurrent Unit (GRU) neural networks to improve IST performance. Leveraging the “Medical Speech, Transcription, and Intent” dataset from Kaggle, comprising a variety of speech recordings and corresponding medical symptom labels, noise reduction was applied using a Wiener filter to improve audio quality. Feature extraction through MLP and sequence classification with GRU highlighted the model’s robustness and capacity for detailed medical understanding. The federated learning framework enabled collaborative model training across multiple hospital sites, preserving patient privacy by avoiding raw data exchange. This distributed approach allowed the model to learn from diverse, real-world data while ensuring compliance with strict data protection standards. Through rigorous five-fold cross-validation, the proposed Fed MLP-GRU model demonstrated an accuracy of 98.6%, with consistently high sensitivity and specificity, highlighting its reliable generalization across multiple test conditions. In real-time applications, the model effectively performed medical transcription, provided symptom-based diagnostic insights, and facilitated hands-free control of healthcare equipment, reducing contamination risks and enhancing workflow efficiency. These findings indicate that IST, powered by federated neural networks, can significantly improve healthcare delivery, accuracy in patient diagnosis, and operational efficiency in clinical settings. This research underscores the transformative potential of federated learning and advanced neural networks for addressing pressing challenges in modern healthcare and setting the stage for future innovations in intelligent medical technology. Full article

This paper analyzes the rounD dataset to advance motion forecasting algorithms for autonomous vehicles navigating complex roundabout environments. We develop a trajectory prediction framework inspired by Gated Recurrent Unit (GRU) networks and graph-based modules to effectively model vehicle interactions. Our primary objective is to evaluate the generalizability of the proposed model across diverse training and testing datasets. Through extensive experiments, we investigate how varying data distributions—such as different road configurations and recording times—impact the model’s prediction accuracy and robustness. This study provides key insights into the challenges of domain generalization in autonomous vehicle trajectory prediction. Full article

In this work, a novel model for hourly PM2.5 time series imputation is proposed for the estimation of missing values in different gap sizes, including 1, 3, 6, 12, and 24 h. The proposed model is based on statistical techniques such as moving averages, linear interpolation smoothing, and linear interpolation. For the experimentation stage, two datasets were selected in Ilo City in southern Peru. Also, five benchmark models were implemented to compare the proposed model results; the benchmark models include exponential weighted moving average (EWMA), autoregressive integrated moving average (ARIMA), long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional GRU (BiGRU). The results show that, in terms of average MAPEs, the proposed model outperforms the best deep learning model (GRU) between 26.61% and 90.69%, and the best statistical model (ARIMA) between 2.33% and 6.67%. So, the proposed model is a good alternative for the estimation of missing values in PM2.5 time series. Full article

Existing risk measurement methods often fail to fully consider the impact of climatic conditions on stock market risk, making it difficult to capture dynamic patterns and long-term dependencies. To address these issues, we propose the TS-GRU method: this approach utilizes a temporal convolutional network (TCN) to extract underlying features from historical data, capturing key characteristics of time series data. Subsequently, a gated recurrent unit (GRU) model is employed to capture dynamic patterns and long-term dependencies within the stock market. Finally, the TS-GRU model is optimized using the Sparrow algorithm based on collective behavior, iteratively evaluating and refining model parameters to obtain improved solutions. Experimental results demonstrate the effectiveness of the TS-GRU method in providing accurate risk assessment and forecasting. This comprehensive approach takes into account carbon finance, climate change, and environmental factors, offering valuable insights to investors to help them to understand and manage investment risks in the ever-changing stock market. Full article

The accurate prediction of mine water inflow is very important for mine design and safe production. The existing forecasting methods based on single factors are often less accurate and stable. Multi-factor data-driven models play a key role in predicting water inflow without taking physical changes into account. Therefore, a multi-factor prediction method based on an improved SSA-RG-MHA model is introduced in this study. The model uses two sets of data related to water inflow as the input to improve prediction accuracy and stability. The model first applies a residual network (ResNet) to mitigate the problems of disappearing gradients and explosions. Gated Recurrent Units (GRUs) are then used to learn the characteristics of long-term sequence data. The model combines ResNet and GRU into a new network architecture and incorporates a multiple attention (MHA) mechanism to focus on information at different time scales. Finally, the optimized sparrow search algorithm (SSA) is used to optimize the network parameters to improve the global search ability and avoid local optimization. The mine water inflow is affected by many factors, among which the water level and microseismic energy data are particularly important. Therefore, these data types are selected as the key variables of mine water inflow prediction. The experimental results show that the improved SSA-RG-MHA model significantly reduces the prediction error: the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) were reduced to 4.42 m³/h, 7.17 m³/h, and 5%, respectively. The multi-factor water inflow prediction method is more stable and reliable than single-factor models as it comprehensively considers the factors affecting the water inflow of the working face. Compared with other multi-factor models, this model exhibits higher prediction accuracy and robustness, providing a basis for mine water hazard monitoring and early warning. Full article

In a multi-carrier (MC) system, the transmitted data are split across several sub-carriers as a crucial approach for achieving high data rates, reliability, and spectral efficiency. Deep learning (DL) enhances MC systems by improving signal representation, leading to more efficient data transmission and reduced bit error rates. In this paper, we propose an MC system supported by DL for operation on fading channels. Deep neural networks are utilized to model the modulation block, while a gated recurrent unit (GRU) network is used to model the demodulation blocks, acting as the encoder and decoder within an autoencoder (AE) architecture. The proposed scheme, known as MC-AE, differs from existing AE-based systems by directly processing channel state information and the received signal in a fully data-driven way, unlike traditional methods that rely on channel equalizers. This approach enables MC-AE to improve diversity and coding gains in fading channels by simultaneously optimizing the encoder and decoder. In this experiment, we evaluated the performance of the proposed model under both perfect and imperfect channel conditions and compared it with other models. Additionally, we assessed the performance of the MC-AE system against index modulation-based MC systems. The results demonstrate that the GRU-based MC-AE system outperforms the others. Full article

This study addresses the usage of data from industrial plate mills to calculate the mean flow stress of different steel grades. Accurate flow stress values may optimize rolling technology, but the existing literature often provides coefficients like those in the Hensel–Spittel equation for a limited number of steel grades, whereas in modern production, the chemical composition may vary by thickness, customer requirements, and economic factors, making it necessary to conduct costly and labor-intensive laboratory studies. This research demonstrates that leveraging data from industrial rolling mills and employing machine learning (ML) methods can predict material rheological behavior without extensive laboratory research. Two modeling approaches are employed: Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) architectures. The model comprising one GRU layer and two fully connected layers, each containing 32 neurons, yields the best performance, achieving a Root Mean Squared Error (RMSE) of 7.5 MPa for the predicted flow stress of three steel grades in the validation set. Full article

Predicting streamflow is essential for managing water resources, especially in basins and watersheds where snowmelt plays a major role in river discharge. This study evaluates the advanced deep learning models for accurate monthly and peak streamflow forecasting in the Gilgit River Basin. The models utilized were LSTM, BiLSTM, GRU, CNN, and their hybrid combinations (CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU). Our research measured the model’s accuracy through root mean square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe efficiency (NSE), and the coefficient of determination (R²). The findings indicated that the hybrid models, especially CNN-BiGRU and CNN-BiLSTM, achieved much better performance than traditional models like LSTM and GRU. For instance, CNN-BiGRU achieved the lowest RMSE (71.6 in training and 95.7 in testing) and the highest R² (0.962 in training and 0.929 in testing). A novel aspect of this research was the integration of MODIS-derived snow-covered area (SCA) data, which enhanced model accuracy substantially. When SCA data were included, the CNN-BiLSTM model’s RMSE improved from 83.6 to 71.6 during training and from 108.6 to 95.7 during testing. In peak streamflow prediction, CNN-BiGRU outperformed other models with the lowest absolute error (108.4), followed by CNN-BiLSTM (144.1). This study’s results reinforce the notion that combining CNN’s spatial feature extraction capabilities with the temporal dependencies captured by LSTM or GRU significantly enhances model accuracy. The demonstrated improvements in prediction accuracy, especially for extreme events, highlight the potential for these models to support more informed decision-making in flood risk management and water allocation. Full article

This paper addresses the challenge of degradation prediction in proton-exchange membrane fuel cells (PEMFCs). Traditional methods often struggle to balance accuracy and complexity, particularly under dynamic operational conditions. To overcome these limitations, this study proposes a data-driven approach based on the gated recurrent unit (GRU) neural network, optimized by the grey wolf optimizer (GWO). The integration of the GWO automates the hyperparameter tuning process, enhancing the predictive performance of the GRU network. The proposed GWO-GRU method was validated utilizing actual PEMFC data under dynamic load conditions. The results demonstrate that the GWO-GRU method achieves superior accuracy compared to other standard methods. The method offers a practical solution for online PEMFC degradation prediction, providing stable and accurate forecasting for PEMFC systems in dynamic environments. Full article

To improve the forecasting accuracy of traffic flow, this paper proposes a traffic flow forecasting algorithm based on Principal Component Analysis (PCA) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) for data processing. The Grey Wolf Optimizer (GWO) algorithm is used to optimize the weights of a combined model called the GWO-PC-CGLX model, which consists of the Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Extreme Gradient Boosting (XGBoost). Initially, PCA and CEEMDAN are used to reduce the dimensionality and noise in the air quality index (AQI) data and traffic flow data. The smoothed data are then input into the CNN, GRU, LSTM, and XGboost models for forecasting. To improve the forecasting accuracy, the GWO algorithm is used to find the optimal weight combination of the four single models. Taking the data from Jiayuguan and Lanzhou in Gansu Province as an example, compared with the actual data, the values of the evaluation indicator R² (Coefficient of Determination) reached 0.9452 and 0.9769, respectively, which are superior to those of the comparison models. The research results not only improve the accuracy of traffic flow forecasting but also provide effective support for the construction of intelligent transportation systems and sustainable traffic management. Full article

With the rapid development of renewable energy, accurately forecasting wind power is crucial for the stable operation of power systems and effective energy management. This paper proposes a short-term wind power forecasting method based on the Orthogonalized Maximal Information Coefficient (OMNIC) combined with an Adaptive fractional Generalized Pareto motion (fGPm) model. The method quantifies the influence of meteorological factors on wind power prediction and identifies the optimal set and number of influencing factors. The model accounts for long-range dependence (LRD) in time series data and constructs an uncertainty model using the properties and parameters of the fractional generalized Pareto distribution (GPD), significantly improving prediction accuracy under nonlinear conditions. The proposed approach was validated using a real dataset from a wind farm in northwest China and compared with other models such as Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) and Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU). Results show that the adaptive fGPm model reduces RMSE by 0.448 MW and 0.466 MW, MAPE by 6.936% and 9.702%, and achieves an average R² of 0.9826 compared to CNN-GRU and CNN-LSTM. The improvement is due to the dynamic adjustment to data trends and effective use of LRD features. This method provides practical value in improving wind power prediction accuracy and addressing grid integration and regulation challenges. Full article

As the world shifts towards a low-carbon economy, the strategic deployment of renewable energy sources (RESs) is critical for maximizing energy output and ensuring sustainability. This study introduces GREENIA, a novel artificial intelligence (AI)-powered framework for optimizing RES placement that holistically integrates machine learning (gated recurrent unit neural networks with swish activation functions and attention layers), evolutionary optimization algorithms (Jaya), and Shapley additive explanations (SHAPs). A key innovation of GREENIA is its ability to provide natural language explanations (NLEs), enabling transparent and interpretable insights for both technical and non-technical stakeholders. Applied in Greece, the framework addresses the challenges posed by the interplay of meteorological factors from 10 different meteorological stations across the country. Validation against real-world data demonstrates improved prediction accuracy using metrics like root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). SHAP analysis enhances transparency by identifying key meteorological influences, such as temperature and humidity, while NLE translates these insights into actionable recommendations in natural language, improving accessibility for energy planners and policymakers. The resulting strategic plan offers precise, intelligent, and interpretable recommendations for deploying RES technologies, ensuring maximum efficiency and sustainability. This approach not only advances renewable energy optimization but also equips stakeholders with practical tools for guiding the strategic deployment of RES across diverse regions, contributing to sustainable energy management. Full article

The Industrial Internet of Things (IIoT) revolutionizes both industrial and residential operations by integrating AI (artificial intelligence)-driven analytics with real-time monitoring, optimizing energy usage, and significantly enhancing energy efficiency. This study proposes a secure IIoT framework that simultaneously predicts both active and reactive loads while also incorporating anomaly detection. The system is optimized for real-time deployment on an edge server, such as a single-board computer (SBC), as well as on a cloud or centralized server. It ensures secure and reliable industrial operations by integrating smart data acquisition systems with real-time monitoring, control, and protective measures. We propose a Temporal Convolutional Networks-Gated Recurrent Unit-Attention (TCN-GRU-Attention) model to predict both active and reactive loads, which demonstrates superior performance compared to other conventional models. The performance metrics for active load forecasting are 0.0183 Mean Squared Error (MSE), 0.1022 Mean Absolute Error (MAE), and 0.1354 Root Mean Squared Error (RMSE), while for reactive load forecasting, the metrics are 0.0202 (MSE), 0.1077 (MAE), and 0.1422 (RMSE). Furthermore, we introduce an optimized Isolation Forest model for anomaly detection that considers the transient conditions of appliances when identifying irregular behavior. The model demonstrates very promising performance, with the average performance metrics for all appliances using this Isolation Forest model being 95% for Precision, 98% for Recall, 96% for F1 Score, and nearly 100% for Accuracy. To secure the entire system, Transport Layer Security (TLS) and Secure Sockets Layer (SSL) security protocols are employed, along with hash-encoded encrypted credentials for enhanced protection. Full article

Automatic modulation recognition (AMR) has wide applications in the fields of wireless communications, radar systems, and intelligent sensor networks. The existing deep learning-based modulation recognition models often focus on temporal features while overlooking the interrelations and spatio-temporal relationships among different types of signals. To overcome these limitations, a hybrid neural network based on a multimodal parallel structure, called the multimodal parallel hybrid neural network (MPHNN), is proposed to improve the recognition accuracy. The algorithm first preprocesses the data by parallelly processing the multimodal forms of the modulated signals before inputting them into the network. Subsequently, by combining Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU) models, the CNN is used to extract spatial features of the received signals, while the Bi-GRU transmits previous state information of the time series to the current state to capture temporal features. Finally, the Convolutional Block Attention Module (CBAM) and Multi-Head Self-Attention (MHSA) are introduced as two attention mechanisms to handle the temporal and spatial correlations of the signals through an attention fusion mechanism, achieving the calibration of the signal feature maps. The effectiveness of this method is validated using various datasets, with the experimental results demonstrating that the proposed approach can fully utilize the information of multimodal signals. The experimental results show that the recognition accuracy of MPHNN on multiple datasets reaches 93.1%, and it has lower computational complexity and fewer parameters than other models. Full article

Physics-guided machine learning (PGML) methods are emerging as valuable tools for modelling the constitutive relations of solids due to their ability to integrate both data and physical knowledge. While various PGML approaches have successfully modeled time-independent elasticity and plasticity, viscoelasticity remains less addressed due to its dependence on both time and loading paths. Moreover, many existing methods require large datasets from experiments or physics-based simulations to effectively predict constitutive relations, and they may struggle to model viscoelasticity accurately when experimental data are scarce. This paper aims to develop a physics-guided recurrent neural network (RNN) model to predict the viscoelastic behavior of solids at large deformations with limited experimental data. The proposed model, based on a combination of gated recurrent units (GRU) and feedforward neural networks (FNN), utilizes both time and stretch (or strain) sequences as inputs, allowing it to predict stress dependent on time and loading paths. Additionally, the paper introduces a physics-guided initialization approach for GRU–FNN parameters, using numerical stress–stretch data from the generalized Maxwell model for viscoelastic VHB polymers. This initialization is performed prior to training with experimental data, helping to overcome challenges associated with data scarcity. Full article