Overlapping point cloud registration algorithm based on KNN and the channel attention mechanism

Tropical cyclones (TCs) are destructive meteorological phenomena, necessitating accurate predictions of TC track and intensity to reduce risks to human life. This study evaluates three Transformer-based models – vanilla Transformer (Transformer), inverted Transformer (iTransformer), and temporal-variate Transformer (TVFormer) – which are trained, validated, and tested on best track data from 1980 to 2021 from the China Meteorological Administration for TC prediction, integrating temporal, variate, and hybrid token embeddings to analyze temporal and variate correlations. Comparative analysis with four recurrent neural network (RNN) models demonstrates the superiority of the refined Transformer models over RNNs: iTransformer reduces mean absolute error (MAE) and root mean square error (RMSE) by 29.55% and 25.80% (latitude), 50.31% and 46.18% (longitude), 8.71% and 9.98% (pressure), and 8.68% and 9.45% (wind speed), while TVFormer achieves MAE and RMSE reductions of 13.98% and 13.84% (latitude), 39.11% and 38.02% (longitude), 13.69% and 14.02% (pressure), and 12.84% and 12.94% (wind speed) on average. Among Transformer variants, iTransformer excels in track prediction, outperforming Transformer with 21.74% lower MAE and 18.26% lower RMSE for latitude, and 32.73% lower MAE and 24.01% lower RMSE for longitude. TVFormer dominates intensity prediction, reducing pressure errors by 4.42% (MAE) and 3.92% (RMSE) and wind speed errors by 19.21% (MAE) and 14.79% (RMSE) compared to Transformer, while outperforming iTransformer with 4.59% lower MAE and 3.68% lower RMSE for pressure and 3.83% lower MAE and 3.18% lower RMSE for wind speed. Notably, TVFormer also enhances track prediction, with 7.10% reduction in MAE and 7.02% reduction in RMSE for latitude, and 22.84% reduction in MAE and 17.09% reduction in RMSE for longitude compared to Transformer. These results highlight the superiority of iTransformer in track prediction and the efficacy of TVFormer in intensity prediction, thanks to their ability to exploit temporal and variate dependencies, offering potential for TC disaster preparedness systems.

Prediction of melt pool morphology of Ti alloy based on deep learning method

Small ground anchors are widely used to fix securing tents in disaster relief efforts. Given the urgent nature of rescue operations, it is crucial to obtain prompt and accurate estimations of their pullout capacity. In this study, a stacking machine learning (ML) model is developed for the rapid estimation of pullout capacity offered by small ground anchors used for temporary tents, leveraging cone penetration data. The proposed stacking model incorporates three ML algorithms as the base regression models: K-nearest neighbors (KNN), support vector regression (SVR), and extreme gradient boosting (XGBoost). A dataset comprising 119 in-situ anchor pullout tests, where the cone penetration data were measured, is utilized to train and assess the stacking model performance. Three metrics, i.e., coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE), are employed to evaluate the predictive accuracy of the proposed model and compare its performance against four popular ML models and an empirical formula to highlight the advantages of the proposed stacking approach. The results affirm that the proposed stacking model outperforms other ML models and the empirical approach as achieving higher R2 and lower MAE and RMSE and more predicted data points falling within 20% error line. Thus, the proposed stacking model holds promising potential as a solution for efficiently predicting the pullout capacity of small ground anchors.

Due to the rapid adoption of renewable energy sources and the increasing complexity of residential electricity consumption, there is a growing need for intelligent, scalable, and context-aware energy management systems in smart homes. This paper presents an artificial intelligence (AI)-based model that integrates high-resolution household power forecasting with dynamic demand response (DR) simulations to optimize energy consumption, enhance grid stability, and support sustainable energy transitions. Using the publicly available UCI Smart Home Energy dataset, a seven-step framework was implemented, including data preprocessing, exploratory data analysis (EDA), feature engineering, and the development of various predictive models—linear regression (LR), random forest regressor (RFR), support vector regression (SVR), k-nearest neighbors (k-NN), and long short-term memory (LSTM) neural networks. Each model was evaluated under seven DR strategies to capture temporal dependencies and nonlinear load behaviors: Peak Clipping, Valley Filling, Load Shifting, Load Leveling, Time-of-Use (ToU) Optimization, Price-Based Control, and Behavioral DR. Model performance was assessed using the mean absolute error (MAE), root mean squared error (RMSE), and the coefficient of determination ( R ²). Results revealed that the LSTM model achieved the highest accuracy, with the lowest MAE (18.95 Wh), lowest RMSE (24.83 Wh), and highest R ² (0.94) under the Price-Based DR strategy. Random forest emerged as the most effective traditional model, yielding an MAE of 25.13 Wh and R ² of 0.89, particularly for Behavioral and ToU-based DR strategies. The SVR and k-NN models provided moderate accuracy, while LR performed poorly, underscoring its limitation in modeling nonlinear and dynamic energy patterns. DR simulations indicated that Price-Based, Behavioral, and ToU Optimization strategies achieved the best alignment between household loads and grid requirements while maintaining user flexibility. Visualization tools such as heatmaps, grouped bar plots, and R ² comparisons further confirmed the superior temporal modeling capability of deep learning (DL) methods. Overall, the proposed framework offers a scalable and interpretable AI-driven platform that integrates load forecasting with DR evaluation, demonstrating that DL—particularly LSTM—can substantially enhance forecasting accuracy, enable smarter DR programs, and promote sustainable energy management in smart homes.

Globally, wind energy if properly harnessed, could serve as a source of energy generation in Africa. This study compared the performance of two Machine Learning (ML) algorithms (Linear regression and Random Forest) in predicting wind speed in five major cities in Africa (Yaoundé, Pretoria, Nairobi, Cairo and Abuja). Wind data were collected between January 1, 2000, and December 31, 2022, using the Solar Radiation Data Archive. The data preprocessing was carried out with 80% of the data used for training and 20% for validation. The performance of these ML algorithms was evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R2). The result shows that Nairobi (3.814795 m/s) closely followed by Cairo (3.606453 m/s) has the highest mean wind speed while Yaoundé (1.090512 m/s) has the lowest. Based on the performance metrics used, the two Machine Learning algorithms were competitive. Still, the Linear Regression (LR) algorithm outperformed the Random Forest Algorithm in predicting wind speed in all the selected major African cities. In Yaoundé (RMSE = 0.3892, MAE= 0.3001, MAPE =0.5030), Pretoria (RMSE=1.2339, MAE=0.9480, MAPE=0.7450) Nairobi (RMSE= 0.4223, MAE =0.6499, MAPE =0.1872), Nairobi (RMSE=0.6499, MAE=0.5171, MAPE =0.1872), Cairo (RMSE =1.0909, MAE =0.8544, MAPE =0.3541) and Abuja (RMSE = 0.70245, MAE =0.5441, MAPE= 0.4515) the Linear regression algorithms was found to outperformed Random Forest Regression. Therefore, the Linear regression algorithm is more reliable in predicting wind speed compared with the Random Forest regression.

Background:Syphilis remains a major public health concern in China. We aimed to construct an optimum model to forecast syphilis epidemic trends and provide effective precautionary measures for prevention and control.Methods:Data on the incidence of syphilis between 1982 and 2020 were obtained from the China Health Statistics Yearbook. An exponential smoothing model (ES model) and a BP neural network model were constructed, and on this basis, the ES-BP combination model was created. The prediction performance was assessed to compare the MAE (Mean Absolute Error), MSE (Mean Squared Error), MAPE (Mean Absolute Percentage Error), and RMSE (Root Mean Square Error).Results:The optimum ES model was Brown’s linear trend model, which had the lowest MAE and MAPE values, and its residual was a white noise sequence (P=0.359). The optimum BP neural network model had three layers with the number of nodes in the input, hidden, and output layers set to 5, 11, and 1, and the mean values of MAE, MSE, and RMSE by five-fold cross-validation were 1.519, 6.894, and 1.969, respectively. The ES-BP combination model had three layers, with model nodes 1, 4, and 1. The lowest mean values of MAE, MSE, and RMSE obtained by five-fold cross-validation were 1.265, 5.739, and 2.105, respectively.Conclusion:The ES, BP neural network, and ES-BP combination models can be used to predict syphilis incidence, but the prediction performance of the ES-BP combination model is better than that of a basic ES model and a basic BP neural network model.

Long-term average solar radiation prediction via seasonal Global Horizontal Irradiance (GHI) forecasting is increasingly leveraging Machine Learning (ML) to uncover complex relationships in historical GHI and climatic parameters surpassing traditional methods. This study investigates seasonal GHI forecasting across four climatically distinct Indian locations namely Chennai, Jaisalmer, Leh and Mawsynram using data from the National Solar Radiation Database. Following rigorous data quality assessment and feature selection based on Spearman's correlation and Mutual Information, eight key features are identified for training three ML models: Efficient Linear Regression (ELR), Regression Trees (RT) and Gaussian Process Regression (GPR). The GPR model demonstrates superior accuracy in seasonal GHI prediction across diverse Indian climatic conditions making it ideal for reliable and cost-efficient Stand-Alone Photovoltaic (SAPV) systems. It is observed that the GPR model achieves the lowest Root Mean Square Error (RMSE) of 0.0030, Mean Absolute Error (MAE) of 0.0022 and Coefficient of Determination (R²) of 0.9999 achieving a reduction of 189.1% in RMSE, 190.09% in MAE and 20.56% improvement in R² compared to ELR. Furthermore, the GPR model surpasses the RT model with a reduction of 124.05% in RMSE and 111.1% in MAE, together with an improvement of 0.2604% in R². While RT provides reasonably accurate forecasts, ELR shows the least reliability. These results confirm GPR's exceptional precision and ability to capture nearly all dataset variability.

Improved GAN-based deep learning approach for strain field prediction and failure analysis of precast bridge slab joints

Volatility forecasting of financial market returns is vital for risk management and portfolio optimization. In the quest for accurate volatility modeling, this article introduces an Artificial Neural Network -Generalized Autoregressive Conditional Heteroscedasticity model (ANN-GARCH) that fuses the strengths of neural networks with the well-known GARCH framework to deliver superior volatility predictions. The approach integrates volatility captured by conventional GARCH models into a neural network framework, combining return and realized volatility series. Then, the ANN architecture is designed to learn and process patterns, ultimately generating enhanced volatility predictions. The proposed model consistently outperforms traditional volatility forecasting methods when applied to Dow Jones Index returns during the COVID-19 period and its aftermath. Across various error distributions, the ANN-GARCH model demonstrates superior forecasting accuracy, evidenced by significantly lower root mean square error (RMSE) and mean absolute error (MAE) compared to competing models. This underscores the model's reliability and effectiveness in volatility forecasting. This innovative model will help academics and finance practitioners make informed decisions when the market conditions are stressed.

This study presents a novel hybrid model that combines two different algorithms to increase the accuracy of short-term berry yield prediction using only previous yield data. The model integrates both autoregressive integrated moving average (ARIMA) with Kalman filter refinement and neural network techniques, specifically support vector regression (SVR), and nonlinear autoregressive (NAR) neural networks, to improve prediction accuracy by correcting the errors generated by the system. In order to enhance the prediction performance of the ARIMA model, an innovative method is introduced that reduces randomness and incorporates only observed variables and system errors into the state-space system. The results indicate that the proposed hybrid models exhibit greater accuracy in predicting weekly production, with a goodness-of-fit value above 0.95 and lower root mean square error (RMSE) and mean absolute error (MAE) values compared with non-hybrid models. The study highlights several implications, including the potential for small growers to use digital strategies that offer crop forecasts to increase sales and promote loyalty in relationships with large food retail chains. Additionally, accurate yield forecasting can help berry growers plan their production schedules and optimize resource use, leading to increased efficiency and profitability. The proposed model may serve as a valuable information source for European food retailers, enabling growers to form strategic alliances with their customers.

This paper aims to: (1) develop models based on adaptive neuro-fuzzy inference system (ANFIS) able to predict five-day biochemical oxygen demand (BOD5) in Ouizert reservoir; (2) demonstrate the capability of the ANFIS in the practical issues of water quality management; (3) choose the optimal combination of input variables to improve the model performance; (4) compare two ANFIS partition methods, namely subtractive clustering called ANFIS-SC and grid partitioning, called ANFIS-GP. The models were developed using experimental data which were gathered during a ten-year period, at a mean monthly time step (scale). The input data used are total inorganic nitrogen, chemical oxygen demand (COD), total dissolved solid, dissolved oxygen and phosphate; the output is five-day biochemical oxygen demand (BOD5). Results reveal that ANFIS-SC models gave a higher correlation coefficient, a lower root mean square errors (RMSE) and mean absolute errors than the corresponding ANFIS-GP models. We can conclude that ANFIS-SC has supremacy over ANFIS-GP in terms of performance criteria and prediction accuracy for BOD5 estimation. The results showed that COD is the more effective variable for BOD5 estimating than other parameters, hence COD is the major driving factor for BOD5 modelling through ANFIS.

Mapping soil organic carbon and total nitrogen in croplands of the Corn Belt of Northeast China based on geographically weighted regression kriging model

The electromagnetic induction (EMI) and frequency domain reflectometry (FDR) sensors, which measure the soil apparent electrical conductivity (ECa) in situ, have emerged as efficient and rapid tools for the indirect assessment of soil salinity, conventionally determined by the electrical conductivity of the saturated soil paste extract (ECe). However, the limitations of applying a single soil sensor and the ECa dependence on multiple soil properties, such as soil moisture and texture, can hinder the interpretation of ECe, whereas selecting the most appropriate set of sensors is challenging. To address these issues, this study explored the prediction ability of a noninvasive EM38-MK2 (EMI) and a capacitance dielectric WET-2 probe (FDR) in assessing topsoil salinity and texture within 0–30 cm depth across diverse soil and land-use conditions in Laconia, Greece. To this aim, multiple linear regression models of laboratory-estimated ECe and soil texture were constructed by the in situ measurements of EM38-MK2 and WET-2, and their performances were individually evaluated using statistical metrics. As was shown, in heterogeneous soils with sufficient wetness and high salinity levels, both sensors produced models with high adjusted coefficients of determination (adj. R2 > 0.82) and low root mean square error (RMSE) and mean absolute error (MAE), indicating strong model fit and reliable estimations of topsoil salinity. For the EM38-MK2, model accuracy improved when clay was included in the regression, while for the WET-2, the soil pore water electrical conductivity (ECp) was the most accurate predictor. The drying soil surface was the greatest constraint to both sensors’ predictive performances, whereas in non-saline soils, the silt and sand were moderately assessed by the EM38-MK2 readings (0.49 < adj. R2 < 0.51). The results revealed that a complementary use of the contemporary EM38-MK2 and the low-cost WET-2 could provide an enhanced interpretation of the soil properties in the topsoil without the need for additional data acquisition, although more dense soil measurements are recommended.

Background:Systemic lupus erythematosus (SLE) is a chronic autoimmune disease that affects multiple organs and systems. However, in addition to physical damage, patients with SLE have an increased risk of mental...

Assessing forecast performance of daily reference evapotranspiration: A comparison of equations, machine and deep learning using weather forecasts