Support Vector Regression Model Research Articles

Soil moisture estimation using ground scatterometer and Sentinel-1 data

Soil moisture (SM) is a crucial criterion for agronomics and the management of water resources, particularly in areas where the socio-economic status and significant source of income depend upon agriculture and related sectors. This paper intends to estimate SM over the vegetative area using a generalized regression neural network (GRNN) and ground scatterometer and compare the results with SM retrieved using Sentinel-1 data. At the same time, random forest regression (RFR) and support vector regression (SVR) models are used for SM estimation. Correlation analysis results concluded that L-band HV-polarization at 300 incidence angle showed the highest correlation with the measured field parameters. This study investigated backscattering coefficients, VV/VH polarization ratio and polarization phase difference over wheat’s entire growth phase to estimate SM. The results indicate that the GRNN with backscattering coefficients and polarization ratio provided the highest accuracy compared to the random forest (RF) and SVR with the root mean square error of 0.093 over the Yavatmal District, Maharashtra, India.

Machine learning algorithm partially reconfigured on FPGA for an image edge detection system

Unmanned aerial vehicles (UAVs) have been used for many applications including military, construction, image and video mapping, medical, search and rescue, wireless communications, and aerial surveillance. One key research topic involving UAVs is pose estimation in autonomous navigation. A standard procedure for this process for UAVs is to combine inertial navigation system (INS) sensor information with the global navigation satellite system (GNSS) signal. However, some factors can interfere with the GNSS signal, such as natural phenomena (ionospheric scintillation) or malicious attacks (jamming or spoofing). One alternative method to avoid using the GNSS signal is to apply an image processing approach by matching UAV images with georeferenced images. But a high effort is required for image edge extraction. In this paper, a support vector regression (SVR) model is proposed to reduce the computational load and processing time for image edge detection. The dynamic partial reconfiguration (DPR) of part of the SVR datapath was implementated to accelerate the process, reduce the area, and analyze its granularity aspect by increasing the grain size of the reconfigurable region. Results show that the implementation in hardware is 68 times faster than that in software. This kind of architecure with DPR also facilitates the low power consumption of 4 mW, leading to a reduction of 57 % compared with that without DPR, which is also the lowest power consumption compared with other machine learning (ML) hardware implementations. Besides, the circuitry area is 41 times smaller. SVR with Gaussian kernel showed a success rate of 99.18 % and minimum square error of 0.0146 for testing with the planning trajectory. This system is useful for adaptive applications where the user/designer can modify/reconfigure the hardware layout during its application, thus contributing to lower power consumption, smaller hardware area, and shorter execution time.

Optimizing Accumulator Performance in Hydraulic Systems through Support Vector Regression and Rotational Factors

The piston-type accumulator is an energy storage device in hydraulic–pneumatic systems, playing a significant role in industries such as petrochemicals, heavy machinery, and steel metallurgy. The displacement parameters of the piston-type accumulator are vitally important for fault diagnosis and early warning in hydraulic systems. Traditional displacement measurement methods cannot meet the requirements of the internal testing environment of the accumulator. Therefore, this paper proposes an accumulator piston displacement signal compensation method based on rotational factors and support vector regression. Firstly, empirical mode decomposition is utilized to denoise the signal. Then, rotational factors are used to generate a delay compensation module to compensate for the signal attenuation and time delay caused by metallic reflection and scattering within the cylinder of the radar signal. The support vector regression model is improved based on a hash table to enhance its computational efficiency and achieve radar displacement signal compensation. Finally, a simulation experiment is designed to verify the effectiveness of the proposed method.

A Transformer and LSTM-Based Approach for Blind Well Lithology Prediction

Petrographic prediction is crucial in identifying target areas and understanding reservoir lithology in oil and gas exploration. Traditional logging methods often rely on manual interpretation and experiential judgment, which can introduce subjectivity and constraints due to data quality and geological variability. To enhance the precision and efficacy of lithology prediction, this study employed a Savitzky–Golay filter with a symmetric window for anomaly data processing, coupled with a residual temporal convolutional network (ResTCN) model tasked with completing missing logging data segments. A comparative analysis against the support vector regression and random forest regression model revealed that the ResTCN achieves the smallest MAE, at 0.030, and the highest coefficient of determination, at 0.716, which are indicative of its proximity to the ground truth. These methodologies significantly enhance the quality of the training data. Subsequently, a Transformer–long short-term memory (T-LS) model was applied to identify and classify the lithology of unexplored wells. The input layer of the Transformer model follows an embedding-like principle for data preprocessing, while the encoding block encompasses multi-head attention, Add & Norm, and feedforward components, integrating the multi-head attention mechanism. The output layer interfaces with the LSTM layer through dropout. A performance evaluation of the T-LS model against established rocky prediction techniques such as logistic regression, k-nearest neighbor, and random forest demonstrated its superior identification and classification capabilities. Specifically, the T-LS model achieved a precision of 0.88 and a recall of 0.89 across nine distinct lithology features. A Shapley analysis of the T-LS model underscored the utility of amalgamating multiple logging data sources for lithology classification predictions. This advancement partially addresses the challenges associated with imprecise predictions and limited generalization abilities inherent in traditional machine learning and deep learning models applied to lithology identification, and it also helps to optimize oil and gas exploration and development strategies and improve the efficiency of resource extraction.

Predicting the hydraulic response of critical transport infrastructures during extreme flood events

Understanding the effects of extreme floods on critical infrastructures such as bridges is paramount for ensuring safety and resilient design in the face of climate change and extreme events. This study develops robust computational and predictive modeling tools for assessing the impacts of extreme floods on the hydraulic response and structural resilience of bridges. A computational fluid dynamic (CFD) model utilizing RANS equations and k-ω Shear Stress Transport (SST) for simulating supercritical flows is adopted to compute hydrodynamic pressures and the water levels on bridge piers of cylindrical and rectangular shapes during a flood event. The CFD model is validated based on the case study data obtained from the Haj Omran Bridge, built on the Khorramabad River in Iran. The numerical simulations consider hydrological conditions and exclude geotechnical parameters and abutment damages. The numerical results are evaluated based on well-established design guidelines. Machine learning techniques, including Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Regression (SVR), optimized with Grid Search Cross-Validation (GSCV), are adopted to enhance the accuracy of hydrodynamic pressure forecasting at bridge piers. The XGBoost model exhibits superior performance (R2 = 0.908, RMSE = 0.0279, and E = 3.41%) compared to the RF and SVR models. All the estimated pressure data by XGBoost falls within ±6 percent error lines, highlighting the model's robustness for out-of-range hydrodynamic pressure prediction. Additionally, an optimized Long Short-Term Memory (LSTM) model is adopted to effectively predict free surface flow profiles (i.e. flood depth) over the bridge (R2 = 0.937 and RMSE = 0.083), demonstrating its potential for practical applications of flood depth predictions over bridge infrastructures. The proposed methodological framework outlined in this study can facilitate modeling the impacts of extreme floods on bridges, enabling robust climate resilience assessment of critical infrastructures.

Enhancing a machine learning model for predicting agricultural drought through feature selection techniques

This study aims to determine the crucial variables for predicting agricultural drought in various climates of Iran by employing feature selection methods. To achieve this, two databases were used, one consisting of ground-based measurements and the other containing six reanalysis products for temperature (T), root zone soil moisture (SM), potential evapotranspiration (PET), and precipitation (P) variables during the 1987–2019 period. The accuracy of the global database data was assessed using statistical criteria in both single- and multi-product approaches for the aforementioned four variables. In addition, five different feature selection methods were employed to select the best single condition indices (SCIs) as input for the support vector regression (SVR) model. The superior multi-products based on time series (SMT) showed increased accuracy for P, T, PET, and SM variables, with an average 47%, 41%, 42%, and 52% reduction in mean absolute error compared to SSP. In hyperarid climate regions, PET condition index was found to have high relative importance with 40% and 36% contributions to SPEI-3 and SPEI-6, respectively. This suggests that PET plays a key role in agricultural drought in hyperarid regions because of very low precipitation. Additionally, the accuracy results of different feature selection methods show that ReliefF outperformed other feature selection methods in agricultural drought modeling. The characteristics of agricultural drought indicate the occurrence of drought in 2017 and 2018 in various climates in Iran, particularly arid and semi-arid climates, with five instances and an average duration of 12 months of drought in humid climates.

One-step vs horizon-step training strategies for multi-step traffic flow forecasting with direct particle swarm optimization grid search support vector regression and long short-term memory

In the increasingly complex urban transportation landscape, the necessity for accurate, multi-step forecasting has never been more apparent to help plan for long-term, strategic transportation initiatives like Intelligent Transportation Systems. This work focuses on resolving uncertainties around the proper training step size for machine learning models performing multi-step traffic flow forecasting. Two strategies are considered: one-step and horizon-step training sizes, which extend from the single-step forecasting method. This paper compares and evaluates two machine learning models: the Support Vector Regression and Long Short-Term Memory (LSTM). Data from two country road locations, including urban roads in Kuala Lumpur and the I5-North freeway in California, are employed to forecast traffic flow in 1-hour increments, projecting from 2 h up to 24 h ahead. The results reveal a significant difference in performance between the two training step sizes, with the one-step training size emerging as the more consistent and optimal strategy for both Direct and Multi-Input Multi-Output forecasting strategies. The proposed model, the Direct Particle Swarm Optimization Grid Search Support Vector Regression (Direct-PSOGS-SVR) model, exhibited comparable or slightly better performance than the LSTM model in both environments. In the I5-North freeway dataset, the Direct-PSOGS-SVR achieved similar Root Mean Squared Error values across most forecasting tasks compared to the LSTM, indicating its effectiveness in stable traffic flow patterns. Notably, in the more dynamic urban environment of Kuala Lumpur, the Direct-PSOGS-SVR model also demonstrated stability and resilience in forecasting accuracy, effectively handling the inherent noise and fluctuations in traffic patterns. These findings serve as a valuable guide for practitioners in selecting the most efficacious combination of training strategies for specific time series forecasting tasks utilizing machine learning models, particularly in traffic flow forecasting. Introducing the Direct-PSOGS-SVR model enriches the landscape of machine learning solutions for traffic forecasting, underscoring the paper’s contributions to the broader understanding of time series forecasting dynamics.

Deep neural network based distortion parameter estimation for blind quality measurement of stereoscopic images

Stereoscopic/3D image quality measurement (SIQM) has emerged as an active and important research branch in image processing/computer vision field. Existing methods for blind/no-reference SIQM often train machine-learning models on degraded stereoscopic images for which human subjective quality ratings have been obtained, and they are thus constrained by the fact that only a limited number of 3D image quality datasets currently exist. Although methods have been proposed to overcome this restriction by predicting distortion parameters rather than quality scores, the approach is still limited to the time-consuming, hand-crafted features extracted to train the corresponding classification/regression models as well as the rather complicated binocular fusion/rivalry models used to predict the cyclopean view. In this paper, we explore the use of deep learning to predict distortion parameters, giving rise to a more efficient opinion-unaware SIQM technique. Specifically, a deep fusion-and-excitation network which takes into account the multiple-distortion interactions is proposed to perform distortion parameter estimation, thus avoiding hand-crafted features by using convolution layers while simultaneously accelerating the algorithm by using the GPU. Moreover, we measure distortion parameter values of the cyclopean view by using support vector regression models which are trained on the data obtained from a newly-designed subjective test. In this way, the potential errors in computing the disparity map and cyclopean view can be prevented, leading to a more rapid and precise 3D-vision distortion parameter estimation. Experimental results tested on various 3D image quality datasets demonstrate that our proposed method, in most cases, offers improved predictive performance over existing state-of-the-art methods.

Application of machine learning methods for spent fuel characterization based on gamma spectrometry measurements

Machine learning models have been developed to predict properties of spent nuclear fuel assemblies from Paks NPP, such as burnup, cooling time, initial enrichment, and Pu-239 content. Measured gamma spectra are processed, and activity ratios of fission products are calculated to serve as input features for Support Vector Regression, Random Forest, and Multi-Layer Perceptron models. Data uncertainty is considered during inference to produce prediction intervals, and input features are ranked using the Gini importance of Random Forest models. A deep learning approach using Convolutional Neural Networks has also been developed to predict the spent fuel parameters from the measured spectra directly. The new models can predict spent fuel parameters with great precision, outperforming earlier approaches that rely on nonlinear regression using a single feature to predict burnup and cooling time and can estimate initial enrichment and Pu-239 content.

Analysis of machine learning prediction reliability based on sampling distance evaluation with feature decorrelation

Despite successful use in a wide variety of disciplines for data analysis and prediction, machine learning (ML) methods suffer from a lack of understanding of the reliability of predictions due to the lack of transparency and black-box nature of ML models. In materials science and other fields, typical ML model results include a significant number of low-quality predictions. This problem is known to be particularly acute for target systems which differ significantly from the data used for ML model training. However, to date, a general method for uncertainty quantification (UQ) of ML predictions has not been available. Focusing on the intuitive and computationally efficient similarity-based UQ, we show that a simple metric based on Euclidean feature space distance and sampling density together with the decorrelation of the features using Gram–Schmidt orthogonalization allows effective separation of the accurately predicted data points from data points with poor prediction accuracy. To demonstrate the generality of the method, we apply it to support vector regression models for various small data sets in materials science and other fields. We also show that this metric is a more effective UQ tool than the standard approach of using the average distance of k nearest neighbors (k = 1–10) in features space for similarity evaluation. Our method is computationally simple, can be used with any ML learning method and enables analysis of the sources of the ML prediction errors. Therefore, it is suitable for use as a standard technique for the estimation of ML prediction reliability for small data sets and as a tool for data set design.

Smart cost estimation: Empirical case for extra-high voltage transmission towers

Nowadays, electricity has become an integral part of human lives. Most of our daily appliances, tools, and personal belongings are inseparable from electricity. To ensure a proper electricity distribution with an efficient transfer capability, Extra-High Voltage (EHV) transmission towers are needed. To design such a structure, it is of utmost importance to account for the cost of said tower. However, the process to estimate the cost of EHV transmission towers is both time-consuming and strenuous on human labor since a lot of consideration have to be taken. To overcome this, an imperative requirement exists for a prompt, precise, and automated tool to replace the existing manual cost estimation method. This research endeavor aims to craft a tool using support vector regression (SVR) with the capacity to prognosticate construction expenses for projects involving EHV transmission towers. The exploration of pertinent literature has enabled us to amass historical data and delineate the attributes essential for estimating costs linked to EHV transmission tower construction. The investigation delves into a comprehensive dataset spanning the past decade in Taiwan. Within this timeframe, 317 EHV transmission towers were erected between 2009 and 2019. However, 79 of these instances are excluded due to incomplete information, thereby yielding 238 viable datasets (comprising 75% of the overall total) to underpin the development of the SVR model. By configuring the parameters to C=0.2 and γ=0.1, followed by 5-fold cross-validation, the resultant SVR model attains a remarkable prediction accuracy of 97.91%, on average. As a result, the proposed SVR-based model can effectively and accurately predict the cost of constructing an EHV transmission tower project and reduce the time spent on estimation, thus contributing to the enhancement of the resilience and robustness of the transmission network system.

Spectroscopic analysis and prediction of membrane fouling potential of NOM in the continuous membrane filtration-submersed (CMF[sbnd]S) reactor

The long-term running continuous microfiltration-submersed (CMFS) reactor was built and spectral indicators, organic matter, and fouling potential were monitored. The specific filtration volume decline rates (V0.5 and V0.25) and unified membrane fouling index (UMFI) were characterized as pore blocking, gel layer, and cake layer fouling potential, respectively. Spectral analysis results showed the parameters of both S275–295 (slope of log-transformed absorption coefficient with the range of 275–295 nm) and SR (the ratio of S275–295 and S350–400) were significant correlations with V0.5, V0.25, and UMFI. The humification index (HIX) had stronger correlations with UMFI, proving the humic acids (HA) had more significant impacts on the cake layer. The V0.5 and V0.25 had correlations with the ratio of peak T to peak C (fT/C) because the aromatic proteins (PN) were more involved in the pore blocking. Statistical analysis results showed that V0.5 and V0.25 were mainly contributed by the polysaccharide (PS) and the interactions of PS × PN × HA, while UMFI was mainly contributed by the HA and PS × PN × HA interactions. The multivariate linear regression (MLR), backpropagation neural network (BPNN), and support vector regression (SVR) models were successfully employed to achieve multiple signals fusion and prediction potential, with the SVR model having better accuracy, especially for UMFI.

Prediction of gas–solid erosion wear of bionic surfaces based on machine learning and unimodal intelligent optimization algorithm

Solid particle erosion wear is an inevitable phenomenon in industrial production, with erosion removal quality serving as a crucial metric for assessing the wear rate per unit area on the impacted surface. Developing predictive models to estimate the degree of mass removal is crucial for effectively controlling, evaluating, and preventing severe damage resulting from solid particle erosion wear. In this study, we constructed a comprehensive dataset comprising smooth and bionic surfaces, encompassing inner, outer, and planar surfaces. The dataset was used in a multifactorial erosion experiment, considering adjustable erosion angles, solid particle apparent gas velocities, and solid particle diameter sizes. Through visualization and analysis of the obtained dataset, we identified optimal scenarios for bionic surface erosion resistance, offering insights for structural design against bionic erosion resistance. Furthermore, we compared machine learning algorithms to address the prediction problem, resulting in the selection of the best-performing regression algorithm, SVR (Support Vector Regression). Additionally, we compared the performance of other advanced intelligent optimization algorithms using unimodal benchmark functions, finding that HHO (Harris Hawks Optimization) emerged as the optimal choice for unimodal optimization. Building on HHO, we developed the IHHO (Improved Harris Hawks Optimization)-SVR model, using experimental data from erosion tests as the training dataset. This model can predict gas–solid two-phase flow erosion patterns, encompassing various wall types, solid particle sizes, solid apparent gas velocities, and impact angles. Due to its robustness and rapid prediction capabilities, the model is expected to serve as a cost-effective tool for predicting erosion removal quality in gas–solid two-phase flow scenarios.

Predicting corrosion behaviour of steel reinforcement in eco-friendly coral aggregate concrete based on hybrid machine learning methods

ABSTRACT This study proposes a machine learning-assisted method for assessing steel reinforcement corrosion, utilising data on chloride ion concentration (CIC) and chloride ion concentration threshold (CCT) from eco-friendly coral aggregate concrete (EFCAC). A total of 2185 data points were collected to establish the EFCAC-CIC database. A multi-objective slime mould optimised support vector regression (MOSMA-SVR) model for EFCAC-CIC was developed. The significance of each feature to EFCAC-CIC was analysed. Subsequently, a graphical user interface (GUI) was developed based on the MOSMA-SVR model. Finally, the GUI and EFCAC-CCT were used to assess the corrosion behaviour of reinforcement. Results indicate that the MOSMA-SVR model provides predictions that are closer to the actual values, with smaller mean errors and standard deviations. The performance indicators, including coefficient of determination, mean absolute error, mean absolute percentage error, mean square error, root mean square error, and a20-index, of the MOSMA-SVR model are 0.987, 0.0124, 0.0332, 2.91e − 4, 0.0171 and 0.9991, respectively, and they are superior to those of the other tested models. The water type and the water–binder ratio are identified as the two most critical factors. Furthermore, by integrating the GUI and feature importance analysis results, chloride salt-resistant EFCAC can be designed. When this is combined with the GUI and EFCAC-CCT, the corrosion of rebar in EFCAC can be assessed in real time.

Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods

Monitoring tools are needed to maximise living systems' ability to mitigate emissions and adapt to changing environmental conditions. Therefore, it is important to be able to predict the fundamental fluxes in crops, in this case vineyards, such as sensible heat flux (H), latent heat flux (LE) and carbon dioxide flux (CO2), in order to know their capacity to adapt to the environmental effects of climate change. In this study, Linear Regression (LR), Elastic Net (EN) regression, K-Nearest Neighbours (KNN), Gaussian-Process (GP), Decision Tree (TREE) Regression, Random Forest (RF) Regression, XGBoost (XGB) Regression, Support Vector Regression (SVR) and Multi-layer Perceptron (MLP) models have been applied to predict fundamental fluxes of an eddy-covariance station from conventional meteorological parameters. These models reproduced well the estimations of three output parameters from the eddy-covariance station. The performance of each predictive model was evaluated using Root-Mean-Squared Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Scaled Error (MASE) and the coefficient of determination (R2). The findings indicate that for the variable H, the GP model outperformed the SVR and all other models, achieving an R2 value of 0.99. Conversely, the SVR demonstrated superior performance for the variables LE and CO2, with R2 values of 0.96 for both. In summary, these findings suggest that the three models proposed show a robust performance in the prediction of the studied fluxes, underlining their versatility and adaptability to the various environmental conditions of the vineyard.

A Novel State-of-Health Prediction and Assessment Strategies for High-Capacity Mining Lithium-Ion Batteries Based on Multi-Indicator

Accurately assessing battery state of health (SOH) is crucial for ensuring the safety of lithium-ion batteries. However, current SOH evaluation methods suffer from inconsistent criteria and limited accuracy in prediction models. This paper introduces a novel SOH prediction and assessment strategy that relies on multiple indicators to address these challenges. First, multifaceted health factors are extracted based on charge cycle data, including battery charging time, incremental capacity, and d V /d t curve. Subsequently, a support vector regression model optimized by the sparrow search algorithm is proposed to predict SOH. The results show that MAE, RMSE, and MAPE are less than 0.037%, 0.047%, and 0.04%, respectively. Meanwhile, the Kalman filtering method is used to identify the second-order RC model online, and the relative SOH curves are obtained by defining the SOH through the internal resistance. Finally, by analyzing the effects of capacity and internal resistance changes on SOH, a new strategy for SOH assessment is proposed, which considers various factors and selects an appropriate judgment mechanism according to the characteristics exhibited by the battery at different life stages. The strategy is more conservative and reliable, providing a solid guarantee for the safe operation of mining equipment.

Data-driven battery health state estimation based on charging and switching cabinets

Accurate evaluation of the battery’s state of health (SOH) in the charging and switching cabinet is crucial to ensure the battery operates safely and reliably, while also reducing maintenance costs for the battery system. A support vector regression technique, utilising the sparrow algorithm optimisation, is suggested to improve the precision of assessing the battery’s state of health in the charging and switching cabinet. This algorithm tackles the task of identifying parameters in the conventional model. Analysing the ageing dataset of lithium batteries is the initial stage to determine the health parameters that signal the battery’s health state. The support vector machine regression algorithm is employed to select the kernel function and penalty factor, which are fine-tuned using the sparrow optimisation technique. The data is utilised to create the SSA-SVR model. The battery health status of the charging and switching cabinet is assessed. The study shows that the enhanced support vector regression model can effectively monitor the status of lithium-ion batteries and achieve superior estimation results for different types of batteries.

Prediction of subthalamic stimulation efficacy on isolated dystonia via support vector regression

IntroductionDeep brain stimulation (DBS) of subthalamic nucleus (STN) has been well-established and increasingly applied in patients with isolated dystonia. Nevertheless, the surgical efficacy varies among patients. This study aims to explore the factors affecting clinical outcomes of STN-DBS on isolated dystonia and establish a well-performed prediction model. MethodsIn this prospective study, thirty-two dystonia patients were recruited and received bilateral STN-DBS at our center. Their baseline characteristics and up to one-year follow-up outcomes were assessed. Implanted electrodes of each subject were reconstructed with their contact coordinates and activated volumes calculated. We explored correlations between distinct clinical characteristics and surgical efficacy. Those features were then trained for the model in outcome prediction via support vector regression (SVR) algorithm and testified through cross-validation. ResultsPatients demonstrated an average clinical improvement of 56 ± 25 % after STN-DBS, significantly affected by distinct symptom forms and activated volumes. The optimal targets and activated volumes were concentratedly located at the dorsal posterior region to STN. Most patients had a rapid response to STN-DBS, and their motor score improvement within one week was highly associated with long-term outcomes. The trained SVR model, contributed by distinct weights of features, could reach a maximum prediction accuracy with mean errors of 11 ± 7 %. ConclusionSTN-DBS demonstrated significant and rapid therapeutic effects in patients with isolated dystonia, by possibly affecting the pallidofugal fibers. Early improvement highly indicates the ultimate outcomes. SVR proves valid in outcome prediction. Patients with predominant phasic and generalized symptoms, shorter disease duration, and younger onset age may be more favorable to STN-DBS in the long run.

Nonparametric Modelling of Ship Dynamics Using Puma Optimizer Algorithm-Optimized Twin Support Vector Regression

Ship dynamic models serve as the foundation for designing ship controllers, trajectory planning, and obstacle avoidance. Support vector regression (SVR) is a commonly used nonparametric modelling method for ship dynamics. Achieving high accuracy SVR models requires a substantial amount of training samples. Additionally, as the number of training samples increases, the computational efficiency for solving the quadratic programming problem (QPP) of SVR decreases. Ship controllers demand dynamic models with both high accuracy and computational efficiency. Therefore, to enhance the prediction accuracy and computational efficiency of SVR, this paper proposes a nonparametric modelling method based on twin SVR (TSVR). TSVR replaces a large QPP with a set of smaller QPPs, significantly enhancing generalizability and computational efficiency. To further improve the predictive accuracy of TSVR, the puma optimizer algorithm is employed to determine the optimal hyperparameters. The performance of the proposed method is validated using a Mariner class vessel. Gaussian white noise is introduced into the modelling data to simulate measurement error. The TSVR model accurately predicts various zigzag and turning circle manoeuvring motions under disturbance conditions, demonstrating its robustness and generalizability. Compared to the SVR model, the TSVR model achieves lower root mean square error and computational time, confirming its superior predictive accuracy and computational efficiency.

Prediction of Ground Vibration Velocity Induced by Long Hole Blasting Using a Particle Swarm Optimization Algorithm

Obtaining accurate basic parameters for long hole blasting is challenging, and the resulting vibration damage significantly impacts key surface facilities. Predicting ground vibration velocity accurately and mitigating the harmful effects of blasting are crucial aspects of controlled blasting technology. This study focuses on the prediction of ground vibration velocity induced by underground long hole blasting tests. Utilizing the fitting equation based on the US Bureau of Mines (USBM) formula as a baseline for predicting peak particle velocity, two machine learning models suitable for small sample data, Support Vector Regression (SVR) machine and Random Forest (RF), were employed. The models were optimized using the particle swarm optimization algorithm (PSO) to predict peak particle velocity with multiple parameters specific to long hole blasting. Mean absolute error (MAE), mean Squared error (MSE), and coefficient of determination (R2) were used to assess the model predictions. Compared with the fitting equation based on the USBM model, both the Support Vector Regression (SVR) and Random Forest (RF) models accurately and effectively predict peak particle velocity, enhancing prediction accuracy and efficiency. The SVR model exhibited slightly superior predictive performance compared to the RF model.