Search Results (33)

The conventional dynamic fracture simulation by using the explicit algorithm often involves a large number of iteration computation due to the extremely small time interval. Thus, the most time-consuming process is the integration of constitutive relation. To improve the efficiency of the dynamic fracture simulation, a physics-informed neural network integration (PINNI) model is developed to calculate the integration of constitutive relation. PINNI employs a shallow multilayer perceptron with integrable activations to approximate constitutive integrand. To train PINNI, a large number of strains in a reasonable range are generated at first, and then the corresponding stresses are calculated by the mechanical constitutive relation. With the generated strains as input data and the calculated stresses as output data, the PINNI can be trained to reach a very high precision, whose relative error is about $7.8\times {10}^{-5}$%. Next, the mechanical integration of constitutive relation is replaced by the well-trained PINNI to perform the dynamic fracture simulation. It is found that the simulation results by the mechanical and PINNI approach are almost the same. This suggests that it is feasible to use PINNI to replace the rigorous mechanical integration of constitutive relation. The computational efficiency is significantly enhanced, especially for the complicated constitutive relation. It provides a new AI-combined approach to dynamic fracture simulation. Full article

This study investigates the use of artificial neural networks (ANNs) and deep neural networks (DNNs) for estimating photovoltaic (PV) energy output, with a particular focus on hyperparameter tuning. Supervised regression for photovoltaic (PV) direct current power prediction was conducted using only sensor-based inputs (PanelTemp, Irradiance, AmbientTemp, Humidity), together with physically motivated-derived features (ΔT, IrradianceEff, IrradianceSq, Irradiance × ΔT). Samples acquired under very low irradiance (<50 W m⁻²) were excluded. Predictors were standardized with training-set statistics (z-score), and the target variable was modeled in log space to stabilize variance. A shallow artificial neural network (ANN; single hidden layer, widths {4–32}) was compared with deeper multilayer perceptrons (DNN; stacks {16 8}, {32 16}, {64 32}, {128 64}, {128 64 32}). Hyperparameters were selected with a grid search using validation mean squared error in log space with early stopping; Bayesian optimization was additionally applied to the ANN. Final models were retrained and evaluated on a held-out test set after inverse transformation to watts. Test performance was obtained as MSE, RMSE, MAE, R², and MAPE for the ANN and DNN. Hence, superiority in absolute/squared error and explained variance was exhibited by the ANN, whereas lower relative error was achieved by the DNN with a marginal MAE advantage. Ablation studies showed that moderate depth can be beneficial (e.g., two-layer variants), and a simple bootstrap ensemble improved robustness. In summary, the ANN demonstrated superior performance in terms of absolute-error accuracy, whereas the DNN exhibited better consistency with relative-error accuracy. Full article

In practical applications, intelligent diagnostic methods for actuator-integrated gearboxes in industrial driving systems encounter challenges such as the scarcity of fault samples and variable operating conditions, which undermine diagnostic accuracy. This paper introduces a multi-layer feature fusion meta-learning (MLFFML) approach to address fault diagnosis problems in cross-condition scenarios with class imbalance. First, meta-training is performed to develop a mature fault diagnosis model on the source domain, obtaining cross-domain meta-knowledge; subsequently, meta-testing is conducted on the target domain, extracting meta-features from limited fault samples and abundant healthy samples to rapidly adjust model parameters. For data augmentation, this paper proposes a frequency-domain weighted mixing (FWM) method that preserves the physical plausibility of signals while enhancing sample diversity. Regarding the feature extractor, this paper integrates shallow and deep features by replacing the first layer of the feature extraction module with a dual-stream wavelet convolution block (DWCB), which transforms actuator vibration or acoustic signals into the time-frequency space to flexibly capture fault characteristics and fuses information from both amplitude and phase aspects; following the convolutional network, an encoder layer of the Transformer network is incorporated, containing multi-head self-attention mechanisms and feedforward neural networks to comprehensively consider dependencies among different channel features, thereby achieving a larger receptive field compared to other methods for actuation system monitoring. Furthermore, this paper experimentally investigates cross-modal scenarios where vibration signals exist in the source domain while only acoustic signals are available in the target domain, specifically validating the approach on industrial actuator assemblies. Full article

Artificial neural networks (ANNs) adjust to the underlying behavior in the dataset using a training rule or optimizer. The most popular first-and second-order optimizers, Adam (AD) and Levenberg–Marquardt (LM), were compared with the aim of predicting extreme flash floods of a runoff-dominated hydrological system. A fully connected multilayer perceptron with a shallow structure was used to reduce complexity and limit overfitting. The inputs of the ANN were determined by rainfall–water level cross-correlation analysis. For each optimizer, the hyperparameters of the ANN were selected using a grid search and the cross-validation score on a novel criterion (PERS PEAK) mixing the persistency (PERS) and the quality of flood-peak restitution (PEAK). For an extreme and unseen event used as a test set, LM outperformed AD by 25% on all performance criteria. The peak water level of this event, 66% greater than that of the training set, was predicted by 92% after more training iterations were done by the LM optimizer. This shows that the ANN can predict beyond the ranges of the training set, given the right optimizer. Nevertheless, the LM training time was up to five times longer than that of AD during grid search. Full article

Electroencephalogram (EEG) signals provide a direct and non-invasive means of interpreting brain activity and are increasingly becoming valuable in embedded emotion-aware systems, particularly for applications in healthcare, wearable electronics, and human–machine interactions. Among various EEG-based emotion recognition techniques, deep learning methods have demonstrated superior performance compared to traditional approaches. This advantage stems from their ability to extract complex features—such as spectral–spatial connectivity, temporal dynamics, and non-linear patterns—from raw EEG data, leading to a more accurate and robust representation of emotional states and better adaptation to diverse data characteristics. This study explores and compares deep and shallow neural networks for human emotion recognition from raw EEG data, with the goal of enabling real-time processing in embedded and edge-deployable systems. Deep learning models—specifically convolutional neural networks (CNNs) and recurrent neural networks (RNNs)—have been benchmarked against traditional approaches such as the multi-layer perceptron (MLP), support vector machine (SVM), and k-nearest neighbors (kNN) algorithms. This comparative study investigates the effectiveness of deep learning techniques in EEG-based emotion recognition by classifying emotions into four categories based on the valence–arousal plane: high arousal, positive valence (HAPV); low arousal, positive valence (LAPV); high arousal, negative valence (HANV); and low arousal, negative valence (LANV). Evaluations were conducted using the DEAP dataset. The results indicate that both the CNN and RNN-STM models have a high classification performance in EEG-based emotion recognition, with an average accuracy of 90.13% and 93.36%, respectively, significantly outperforming shallow algorithms (MLP, SVM, kNN). Full article

In estimating the global carbon cycle, the net ecosystem exchange (NEE) is crucial. The understanding of the mechanism of interaction between NEE and various environmental factors of ecosystems has been very limited, and the interactions between the factors are intricate and complex, which leads to difficulties in accurately estimating NEE. In this study, we propose the A-DMLP (attention-deep multilayer perceptron)-deep learning model for NEE simulation as well as an interpretability study using the SHapley Additive exPlanations (SHAP) model. The attention mechanism was introduced into the deep multilayer perceptual machine, and the important information in the original input data was extracted using the attention mechanism. Good results were obtained on nine eddy covariance sites in China. The model was also compared with the random forest, long short-term memory, deep neural network, and convolutional neural networks (1D) models to distinguish it from previous shallow machine learning models to estimate NEE, and the results show that deep learning models have great potential in NEE modeling. The SHAP method was used to investigate the relationship between the input features of the A-DMLP model and the simulated NEE, and to enhance the interpretability of the model. The results show that the normalized difference vegetation index, the enhanced vegetation index, and the leaf area index play a dominant role at most sites. This study provides new ideas and methods for analyzing the intricate relationship between NEE and environmental factors by introducing the SHAP interpretable model. These advancements are crucial in achieving carbon reduction targets. Full article

Air pollution causes millions of premature deaths per year due to its strong association with several diseases and respiratory afflictions. Consequently, air quality monitoring and forecasting systems have been deployed in large urban areas. However, those systems forecast outdoor air quality while people living in relatively large cities spend most of their time indoors. Hence, this work proposes an indoor air quality forecasting system, which was trained with data from Mexico City, and that is supported by deep learning architectures. The novelty of our work is that we forecast an indoor air quality index, taking into account seasonal data for multiple horizons in terms of minutes; whereas related work mostly focuses on forecasting concentration levels of pollutants for a single and relatively large forecasting horizon, using data from a short period of time. To find the best forecasting model, we conducted extensive experimentation involving 133 deep learning models. The deep learning architectures explored were multilayer perceptrons, long short-term memory neural networks, 1-dimension convolutional neural networks, and hybrid architectures, from which LSTM rose as the best-performing architecture. The models were trained using (i) outdoor air pollution data, (ii) publicly available weather data, and (iii) data collected from an indoor air quality sensor that was installed in a house located in a central neighborhood of Mexico City for 17 months. Our empirical results show that deep learning models can forecast an indoor air quality index based on outdoor concentration levels of pollutants in conjunction with indoor and outdoor meteorological variables. In addition, our findings show that the proposed method performs with a mean squared error of 0.0179 and a mean absolute error of 0.1038. We also noticed that 5 months of historical data are enough for accurate training of the forecast models, and that shallow models with around 50,000 parameters have enough predicting power for this task. Full article

A common cause of deterioration in historic manuscripts is ink transparency or bleeding from the opposite page. Philologists and paleographers can significantly benefit from minimizing these interferences when attempting to decipher the original text. Additionally, computer-aided text analysis can also gain from such text enhancement. In previous work, we proposed the use of neural networks (NNs) in combination with a data model that characterizes the damage when both sides of a page have been digitized. This approach offers the distinct advantage of allowing the creation of an artificial training set that teaches the NN to differentiate between clean and damaged pixels. We tested this concept using a shallow NN, which proved effective in categorizing texts with varying levels of deterioration. In this study, we adapt the NN design to tackling remaining classification uncertainties caused by areas of text overlap, inhomogeneity, and peaks of degradation. Specifically, we introduce a new output class for pixels within overlapping text areas and incorporate additional features related to the pixel context information to promote the same classification for pixels adjacent to each other. Our experiments demonstrate that these enhancements significantly improve the classification accuracy. This improvement is evident in the quality of both binarization, which aids in text analysis, and virtual restoration, aimed at recovering the manuscript’s original appearance. Tests conducted on a public dataset, using standard quality indices, reveal that the proposed method outperforms both our previous proposals and other notable methods found in the literature. Full article

In nature, objects that use camouflage have features like colors and textures that closely resemble their background. This creates visual illusions that help them hide and protect themselves from predators. This similarity also makes the task of detecting camouflaged objects very challenging. Methods for camouflaged object detection (COD), which rely on deep neural networks, are increasingly gaining attention. These methods focus on improving model performance and computational efficiency by extracting edge information and using multi-layer feature fusion. Our improvement is based on researching ways to enhance efficiency in the encode–decode process. We have developed a variant model that combines Swin Transformer (Swin-T) and EfficientNet-B7. This model integrates the strengths of both Swin-T and EfficientNet-B7, and it employs an attention-guided tracking module to efficiently extract edge information and identify objects in camouflaged environments. Additionally, we have incorporated dense skip links to enhance the aggregation of deep-level feature information. A boundary-aware attention module has been incorporated into the final layer of the initial shallow information recognition phase. This module utilizes the Fourier transform to quickly relay specific edge information from the initially obtained shallow semantics to subsequent stages, thereby more effectively achieving feature recognition and edge extraction. In the latter phase, which is focused on deep semantic extraction, we employ a dense skip joint attention module to enhance the decoder’s performance and efficiency, ensuring accurate capture of deep-level information, feature recognition, and edge extraction. In the later stage of deep semantic extraction, we use a dense skip joint attention module to improve the decoder’s performance and efficiency in capturing precise deep information. This module efficiently identifies the specifics and edge information of undetected camouflaged objects across channels and spaces. Differing from previous methods, we introduce an adaptive pixel strength loss function for handling key captured information. Our proposed method shows strong competitive performance on three current benchmark datasets (CHAMELEON, CAMO, COD10K). Compared to 26 previously proposed methods using 4 measurement metrics, our approach exhibits favorable competitiveness. Full article

This study uses a neural network to propose a methodology for creating digital bathymetric models for shallow water areas that are partially covered by a mix of hydroacoustic and photogrammetric data. A key challenge of this approach is the preparation of the training dataset from such data. Focusing on cases in which the training dataset covers only part of the measured depths, the approach employs generalized linear regression for data optimization followed by multilayer perceptron neural networks for bathymetric model creation. The research assessed the impact of data reduction, outlier elimination, and regression surface-based filtering on neural network learning. The average values of the root mean square (RMS) error were successively obtained for the studied nearshore, middle, and deep water areas, which were 0.12 m, 0.03 m, and 0.06 m, respectively; moreover, the values of the mean absolute error (MAE) were 0.11 m, 0.02 m, and 0.04 m, respectively. Following detailed quantitative and qualitative error analyses, the results indicate variable accuracy across different study areas. Nonetheless, the methodology demonstrated effectiveness in depth calculations for water bodies, although it faces challenges with respect to accuracy, especially in preserving nearshore values in shallow areas. Full article

In the algorithm selection problem, where the task is to identify the most suitable solving technique for a particular situation, most methods used as performance mapping mechanisms have been relatively simple models such as logistic regression or neural networks. In the latter case, most implementations tend to have a shallow and straightforward architecture and, thus, exhibit a limited ability to extract relevant patterns. This research explores the use of attention-based neural networks as meta-learners to improve the performance mapping mechanism in the algorithm selection problem and fully take advantage of the model’s capabilities for pattern extraction. We compare the proposed use of an attention-based meta-learner method as a performance mapping mechanism against five models from the literature: multi-layer perceptron, k-nearest neighbors, softmax regression, support vector machines, and decision trees. We used a meta-data dataset obtained by solving the vehicle routing problem with time window (VRPTW) instances contained in the Solomon benchmark with three different configurations of the simulated annealing meta-heuristic for testing purposes. Overall, the attention-based meta-learner model yields better results when compared to the other benchmark methods in consistently selecting the algorithm that best solves a given VRPTW instance. Moreover, by significantly outperforming the multi-layer perceptron, our findings suggest promising potential in exploring more recent and novel advancements in neural network architectures. Full article

Water availability is a key factor in territorial sustainable development. Moreover, groundwater constitutes the survival element of human life and ecosystems in arid oasis areas. Therefore, groundwater potential (GWP) identification represents a crucial step for its management and sustainable development. This study aimed to map the GWP using ten algorithms, i.e., shallow models comprising: multilayer perceptron, k-nearest neighbor, decision tree, and support vector machine algorithms; hybrid models comprising: voting, random forest, adaptive boosting, gradient boosting (GraB), and extreme gradient boosting; and the deep learning neural network. The GWP inventory map was prepared using 884 binary data, with “1” indicating a high GWP and “0” indicating an extremely low GWP. Twenty-three GWP-influencing factors have been classified into numerical data using the frequency ration method. Afterwards, they were selected based on their importance and multi-collinearity tests. The predicted GWP maps show that, on average, only 11% of the total area was predicted as a very high GWP zone and 17% and 51% were estimated as low and very low GWP zones, respectively. The performance analyses demonstrate that the applied algorithms have satisfied the validation standards for both training and validation tests with an average area under curve of 0.89 for the receiver operating characteristic. Furthermore, the models’ prioritization has selected the GraB model as the outperforming algorithm for GWP mapping. This study provides decision support tools for sustainable development in an oasis area. Full article

This paper presents the application of shallow neural networks (SNNs): multi-layer perceptron (MLP) and self-organizing Kohonen maps (SOMs) to the early detection and classification of the stator and rotor faults in permanent magnet synchronous motors (PMSMs). The neural networks were trained based on the vector coming from measurements on a real object. The elements of the input vector of SNNs constituted the selected amplitudes of the diagnostic signal spectrum. The stator current and axial flux were used as diagnostic signals. The test object was a 2.5 kW PMSM motor supplied by a frequency converter operating in a closed-loop control structure. The experimental verification of the proposed diagnostic system was carried out for variable load conditions and values of the supply voltage frequency. The obtained results were compared with an approach based on a deep neural network (DNN). The research presented in the article confirm the possibility of detection and assessing the individual damage of stator winding and permanent magnets as well as the simultaneous faults of the PMSM stator and rotor using SNNs with simple signal preprocessing. Full article

Multi-kernel learning methods are essential kernel learning methods. Still, the base kernel functions in most multi-kernel learning methods only with select kernel functions with shallow structures, which are weak for large-scale uneven data. We propose two types of acceleration models from a multidimensional perspective of the data: the neural tangent kernel (NTK)-based multi-kernel learning method is proposed, where the NTK kernel regressor is shown to be equivalent to an infinitely wide neural network predictor, and the NTK with deep structure is used as the base kernel function to enhance the learning ability of multi-kernel models; and a parallel computing kernel model based on data partitioning techniques. An RBF, POLY-based multi-kernel model is also proposed. All models use historical memory-based PSO (HMPSO) for efficient search of parameters within the model. Since NTK has a multi-layer structure and thus has a significant computational complexity, the use of a Monotone Disjunctive Kernel (MDK) to store and train Boolean features in binary achieves a 15–60% training time compression of NTK models in different datasets while obtaining a 1–25% accuracy improvement. Full article

Accurate bathymetric data is crucial for marine and coastal ecosystems. A lot of studies have been carried out for nearshore bathymetry using satellite data. The approach adopted extensively in shallow water depths estimation has recently been one of empirical models. However, the linear empirical model is simple and only takes limited band information at each bathymetric point into consideration. It may be not suitable for complex environments. In this paper, a deep learning framework was proposed for nearshore bathymetry (DL-NB) from ICESat-2 LiDAR and Sentinel-2 Imagery datasets. The bathymetric points from the spaceborne ICESat-2 LiDAR were extracted instead of in situ measurements. By virtue of the two-dimensional convolutional neural network (2D CNN), DL-NB can make full use of the initial multi-spectral information of Sentinel-2 at each bathymetric point and its adjacent areas during the training. Based on the trained model, the bathymetric maps of several study areas were produced including the Appalachian Bay (AB), Virgin Islands (VI), and Cat Island (CI) of the United States. The performance of DL-NB was evaluated by empirical method, machine learning method and multilayer perceptron (MLP). The results indicate that the accuracy of the DL-NB is better than comparative methods can in nearshore bathymetry. After quantitative analysis, the RMSE of DL-NB could achieve 1.01 m, 1.80 m and 0.28 m in AB, VI and CI respectively. Given the same data conditions, the proposed method can be applied for high precise global scale and multitemporal nearshore bathymetric maps generation, which are beneficial to marine environmental change assessment and conservation. Full article