An atmospheric refractivity inversion method based on deep learning

In order to verify the feasibility of atmospheric duct inversion method using automatic identification system signal in the actual sea area, a sea experiment was carried out. The signal acquisition system of portable high sensitivity civil automatic identification system is developed, and the receiving and processing process of automatic identification system signal is analysed. The sea experiment scheme and main experiment equipment are given, and the collected experiment data are processed and analysed. Finally, the method of atmospheric duct inversion using automatic identification system signal is verified by the measured data. Atmospheric duct inversion is an inverse problem, which requires the use of various optimisation algorithms to optimise the duct parameters in order to obtain the characteristic parameter information of the duct. In this paper, the Lévy flight quantum‐behaved particle swarm optimisation algorithm and the deep learning algorithm are respectively used to invert the atmospheric duct parameters. The results show that there is little difference between the inverted duct parameters and the true duct parameters, which verifies the feasibility of using the automatic identification system signal to invert the atmospheric duct.

This study demonstrates the application of deep learning approach specifically the deep learning for cyberfraud incidence classification and time series prediction in the South African financial institutions. Secondary data from the South African Banking Risk Information Centre (SABRIC) was employed and the data was trained under the deep learning paradigm using the Long Short-Term Memory (LSTM) model and adaptive moment estimation (ADAM) algorithm for fraud incidence classification and time series prediction of fraud incidences. Overall, there were 94.1% correct classifications as opposed to 5.9% incorrect classifications. Moreover, the accuracy, precision, recall and F1-score of the LSTM classification model were 71.668%, 87.5%, 99.1% and 78.78% respectively. This indicates that the developed LSTM model is suitable for classification purposes. In addition, the model’s performance improves as new datasets are fed in. This is evident as the root mean square error (RMSE) reduced from 253.5116 obtained initially to 150.9 after new data was fed in. This study contributes conceptually, theoretically and empirical to knowledge on cyberfraud mitigation. The results show that the LSTM model can be deployed for fraud classification and time series analysis of fraud incidences. The outcome of this study may promote cyber resilience and sustain the fight against the perpetration of cyber-related fraud in South Africa’s financial institutions. The use of the LSTM model for cyberfraud classification and time series prediction of cyberfraud incidences in the South African financial institutions demonstrated in this study is unique.

Hepatocellular carcinoma (HCC), the primary cancer of the liver, is life-threatening, with few or no symptoms, and detection in the early stage will help for successful treatment with surgery, and transplant for a better life quality. Here, we proposed two stacking classification models based on deep learning with differential hybrid feature selection for the early detection of HCC using novel non-invasive biomarker PIVKA-II. We showed how the variations in hybrid feature selection affect the performance of stacking classification and different supervised machine-learning algorithms on a metaclassifier. The base layers were support vector machine (SVM), gradient boosting (GB), and linear discriminant analysis (LDA). The meta classifier was a multilayer perceptron (MLP) with three different optimizers, stochastic gradient descent (SGD), adaptive moment estimation (ADAM), and Limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS). Our first model outperformed the second with their hybrid features by improving accuracy by 1.5% and F1_score by 1% in both SGD and ADAM optimization, while MLP-LBFGS had a 1.4% increase in accuracy. The precision had hiked by 1.9%, 3.5%, and 1.7% in SGD, ADAM, and LBFGS, respectively, in Model-1. Matthew’s correlation coefficient (MCC) for MLP-SGD increased from 0.82 to 0.85, MLP-ADAM from 0.81 to 0.85, and MLP-LBFGS from 0.75 to 78 for the first model.

Hydrate plugging and pipeline leak can impair the normal operation of natural gas pipeline and may lead to serious accidents. Since natural gas pipeline safety monitoring based on active acoustic excitation can detect and locate not only the two abnormal events but also normal components such as valves and pipeline elbows, recognition and classification of these events are of great importance to provide maintenance guidance for the pipeline operators and avoid false alarm. In this article, long short-term memory (LSTM) network is introduced and applied to classify detection signals of hydrate plugging, pipeline leak, and elbow. Adaptive moment estimation (Adam) algorithm is introduced and utilized to accelerate the long short-term memory network convergence in training. Experimental results demonstrate that the network with three layers and 64 units per cell performs the best. The cross-entropy loss in training is 0.0005, and classification accuracies are all 100% in training, validation, and testing which verify the validity of the long short-term memory network. Therefore, the method based on the long short-term memory network and adaptive moment estimation algorithm can work efficiently on pipeline events classification and has great guiding significance for safety assurance of natural gas transmission.

A guidance approach with obstacle avoidance is proposed for maneuvering target interception. Firstly, by decomposing the constrained optimal guidance problem into two associated subproblems, the overall scheme of guidance is presented. Secondly, to improve the guidance accuracy against the maneuvering target, an MPC controller with disturbance estimation is designed, which transforms the global optimization problem into a finite-horizon optimal control problem. An auxiliary controller is also developed to ensure the system’s stability. Then, to achieve obstacle avoidance without affecting the guidance accuracy, a unified function is built to assess the threats from obstacles of different shapes, based on which the optimal guidance-obstacle avoidance model is established. Finally, to solve the above optimization problems, a hybrid solver is developed based on the adaptive moment estimation (Adam) algorithm, whose output will serve as the real-time guidance command. The numerical simulation results show that the guidance approach presented in this paper can achieve precise guidance and obstacle avoidance in various scenarios, and the Monte Carlo experiment further demonstrates the robustness and computation efficiency of the approach.

Corrosion can affect the reliability of materials, which has attracted the attention of the industry. Corrosion detection and quantitative analysis are particularly important for scientific management and decision-making. In this paper, the imaging method based ultrasonic guided wave (UGW) detection technology and fully connected neural network (FCNN) is proposed to realize real-time imaging of corrosion damages. The imaging method contains offline training and online testing. Offline training aims to establish the relationship between detection signals and velocity maps and it is accelerated by adaptive moment estimation (Adam) algorithm. In the process of online testing, the trained model can be called directly to realize real-time imaging, that is, the detection signals are fed into the model and the network will predict the velocity maps. Finally, the velocity maps are converted to thickness maps according to the dispersion curves. Numerical experimental results show that the mean square errors (mses) are respectively 9.08 × 10−4, 2.47 × 10−3 and 2.59 × 10−3 in training, validation and testing. Compared with irregular corrosion damages, the imaging method has better imaging quality for circular corrosion damages.

According to the accuracy of BP (Back Propagation) neural network in leveling fitting, an improved BP neural network model is proposed. In order to overcome the defect of the low convergence rate and local minimal in leveling fitting. The BP neural network is improved by using Relu (Rectified Linear Units) function as network activation function and Adam (Adaptive Moment Estimation) algorithm as network optimization function. The experimental results show that the improved BP neural network can effectively improve the accuracy.

Building energy consumption prediction plays an important role in realizing building energy conservation control. Limited by some external factors such as temperature, there are some problems in practical applications, such as complex operation and low prediction accuracy. Aiming at the problem of low prediction accuracy caused by poor timing of existing building energy consumption prediction methods, a building energy consumption prediction and analysis method based on the deep learning network is proposed in this paper. Before establishing the energy consumption prediction model, the building energy consumption data source is preprocessed and analyzed. Then, based on the Keras deep learning framework, an improved long short-term memory (ILSTM) prediction model is built to support the accurate analysis of the whole cycle of the prediction network. At the same time, the adaptive moment (Adam) estimation algorithm is used to update and optimize the weight parameters of the model to realize the adaptive and rapid update and matching of network parameters. The simulation experiment is based on the actual dataset collected by a university in Southwest China. The experimental results show that the evaluation indexes MAE and RMSE of the proposed method are 0.015 and 0.109, respectively, which are better than the comparison method. The simulation experiment proves that the proposed method is feasible.

BackgroundThe World Health Organization predicts that by 2030, chronic obstructive pulmonary disease (COPD) will be the third leading cause of death and the seventh leading cause of morbidity worldwide. Pulmonary function tests (PFT) are the gold standard for COPD diagnosis. Since COPD is an incurable disease that takes a considerable amount of time to diagnose, even by an experienced specialist, it becomes important to provide an analysis of abnormalities in a simple manner. Although many deep learning (DL) methods based on computed tomography (CT) have been developed to identify COPD, the pathological changes of COPD based on CT are multi-dimensional and highly spatially heterogeneous, and their predictive performance still needs to be improved.ObjectiveThe purpose of this study was to develop a DL-based multimodal feature fusion model to accurately estimate PFT parameters from chest CT images and verify its performance.Materials and methodsIn this retrospective study, participants underwent chest CT examination and PFT at the Fourth Clinical Medical College of Xinjiang Medical University between January 2018 and July 2024. In this study, the 1-s forced expiratory volume (FEV1), forced vital capacity (FVC), 1-s forced expiratory volume ratio forced vital capacity (FEV1/FVC), 1-s forced expiratory volume to predicted value (FEV1%), and forced vital capacity to predicted value (FVC%) of PFT parameters were used as predictors and the corresponding chest CT of 3108 participants. The data were randomly assigned to the training group and the validation group at a ratio of 9:1, and the model was cross-validated using 10-fold cross-validation. Each parameter was trained and evaluated separately on the DL network. The mean absolute error (MAE), mean squared error (MSE), and Pearson correlation coefficient (r) were used as evaluation indices, and the consistency between the predicted and actual values was analyzed using the Bland-Altman plot. The interpretability of the model’s prediction process was analyzed using the Grad-CAM visualization technique.ResultsA total of 2408 subjects were included (average age 66 ± 12 years; 1479 males). Among these, 822 cases were used for encoder training to extract image features, and 1,586 cases were used for the development and validation of a multimodal feature fusion model based on a multilayer perceptron (MLP). The MAE, MSE, and r predicted between PFT and model estimates for FEV1 were 0.34, 0.20, and 0.84, respectively. For FVC, the MAE, MSE, and r were 0.42, 0.31, and 0.81, respectively. For FEV1/FVC, the MAE, MSE, and r were 6.64, 0.73, and 0.77, respectively. For FEV1%, the MAE, MSE, and r were 13.42, 3.01, and 0.73, respectively. For FVC%, the MAE, MSE, and r were 13.33, 2.97, and 0.61, respectively. It was observed that there was a strong correlation between the measured and predicted indices of FEV1, FVC, FEV1/FVC, and FEV1%. The Bland-Altman plot analysis showed good consistency between the estimated values and the measured values of all PFT parameters.ConclusionsThe preliminary research results indicate that the MLP-based multimodal feature fusion model has the potential to predict PFT parameters in COPD patients in real time. However, it is worth noting that the study used indicators before the use of bronchodilators, which may affect the interpretation of the results. Future studies should use measurements taken after bronchodilator administration to better align with clinical standards.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12890-025-03957-7.

Since the height of sea detection radar antenna and ship targets is relatively low, it is generally believed that its over-the-horizon detection is mainly caused by the evaporation duct at sea. To fully understand the influence of atmospheric ducts on radar over-the-horizon detection, a shore-based navigation radar was used to carry out over-the-horizon detection experiments; radiosondes were used to measure the atmospheric profile and evaporation duct monitoring equipment was used to measure the evaporation duct. Based on experimental data and model simulation, a comparative analysis of a navigation radar’s over-the-horizon detection, the evaporation duct, and the lower atmospheric duct is presented in this study. The results show that the atmospheric duct can affect the signal propagation of the navigation radar, thus resulting in over-the-horizon detection. The long-range over-the-horizon detection of the navigation radar is caused by the strong lower atmospheric duct, while the evaporation duct can generally only form weak over-the-horizon detection, which is different from the general cognition.

Wind speed forecasting is important for wind energy forecasting. In the modern era, the increase in energy demand can be managed effectively by forecasting the wind speed accurately. The main objective of this research is to improve the performance of wind speed forecasting by handling uncertainty, the curse of dimensionality, overfitting and non-linearity issues. The curse of dimensionality and overfitting issues are handled by using Boruta feature selection. The uncertainty and the non-linearity issues are addressed by using the deep learning based Bi-directional Long Short Term Memory (Bi-LSTM). In this paper, Bi-LSTM with Boruta feature selection named BFS-Bi-LSTM is proposed to improve the performance of wind speed forecasting. The model identifies relevant features for wind speed forecasting from the meteorological features using Boruta wrapper feature selection (BFS). Followed by Bi-LSTM predicts the wind speed by considering the wind speed from the past and future time steps. The proposed BFS-Bi-LSTM model is compared against Multilayer perceptron (MLP), MLP with Boruta (BFS-MLP), Long Short Term Memory (LSTM), LSTM with Boruta (BFS-LSTM) and Bi-LSTM in terms of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE) and R2. The BFS-Bi-LSTM surpassed other models by producing RMSE of 0.784, MAE of 0.530, MSE of 0.615 and R2 of 0.8766. The experimental result shows that the BFS-Bi-LSTM produced better forecasting results compared to others.

Potatoes are an important crop in the world; they are the main source of food for a large number of people globally and also provide an income for many people. The true forecasting of potato yields is a determining factor for the rational use and maximization of agricultural practices, responsible management of the resources, and wider regions’ food security. The latest discoveries in machine learning and deep learning provide new directions to yield prediction models more accurately and sparingly. From the study, we evaluated different types of predictive models, including K-nearest neighbors (KNN), gradient boosting, XGBoost, and multilayer perceptron that use machine learning, as well as graph neural networks (GNNs), gated recurrent units (GRUs), and long short-term memory networks (LSTM), which are popular in deep learning models. These models are evaluated on the basis of some performance measures like mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) to know how much they accurately predict the potato yields. The terminal results show that although gradient boosting and XGBoost algorithms are good at potato yield prediction, GNNs and LSTMs not only have the advantage of high accuracy but also capture the complex spatial and temporal patterns in the data. Gradient boosting resulted in an MSE of 0.03438 and an R2 of 0.49168, while XGBoost had an MSE of 0.03583 and an R2 of 0.35106. Out of all deep learning models, GNNs displayed an MSE of 0.02363 and an R2 of 0.51719, excelling in the overall performance. LSTMs and GRUs were reported to be very promising as well, with LSTMs comprehending an MSE of 0.03177 and GRUs grabbing an MSE of 0.03150. These findings underscore the potential of advanced predictive models to support sustainable agricultural practices and informed decision-making in the context of potato farming.

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. Among the research challenges on a global scale, the investigation of deep transfer learning (DTL) in the field of electricity load forecasting represents a fundamental effort that can inform artificial intelligence applications in general. In this paper, a comprehensive study is reported regarding day-ahead electricity load forecasting. For this purpose, three sequence-to-sequence (Seq2seq) deep learning (DL) models are used, namely the multilayer perceptron (MLP), the convolutional neural network (CNN) and the ensemble learning model (ELM), which consists of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL, emphasizing the way the datasets are trained and fine-tuned for higher forecasting accuracy. In order to implement the forecasting strategies using deep learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1–24 h) for each month of the year for the Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. Four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only the Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for the Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) involves the training of the DL models using the Lesvos dataset, and the testing period is performed directly on the Chios dataset without fine-tuning. The fourth strategy is a multi-task deep learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. The results obtained demonstrate that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, DTL Case 1 and 2 outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it is concluded that the MLP model presents the best monthly forecasts with MAPE values of 6.24% and 6.01% for the first two cases, the CNN model presents the best monthly forecasts with MAPE values of 5.57% and 5.60%, respectively, and the ELM model achieves the best monthly forecasts with MAPE values of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

A deep learning method based on partition modeling for reconstructing temperature field

The three-dimension (3D) inversion of magnetic data is an effective method of recovering underground magnetic susceptibility distributions using magnetic anomaly data. The conventional regularization inversion method has good data fitting; however, its inversion model has the problem of a poor model-fitting ability due to a low depth resolution. The 3D inversion method based on deep learning can effectively improve the model-fitting accuracy, but it is difficult to guarantee the data-fitting accuracy of the inversion results. The loss function of traditional deep learning 3D inversion methods usually adopts the metric of the absolute mean squared error (MSE). In order to improve the accuracy of the data fitting, we added a forward-fitting constraint term (FFit) on the basis of the MSE. Meanwhile, in order to further improve the accuracy of the model fitting, we added the Dice coefficient to the loss function. Finally, we proposed a multi-constraint deep learning 3D inversion method based on UNet++. Compared with the traditional single-constraint deep learning method, the multi-constraint deep learning method has better data-fitting and model-fitting effects. Then, we designed corresponding test models and evaluation metrics to test the effectiveness and feasibility of the method, and applied it to the actual aeromagnetic data of a test area in Suqian City, Jiangsu Province.