Energy harvesting enhancement: A roadmap for systematically tuning controllers applied on synchronous generators of wind turbines by John Breno Santos Freitas, Felipe Augusto Silva Martins, Vinicius Foletto Montagner, Paulo Jefferson Dias de Oliveira Evald

“…Compared to the tenth algorithm in the rank, the ALO-based controller ensured a reduction of 96.78% and 90.27% of mean absolute error and root mean squared error, respectively. …”
Get full text

Optimization of the Backstepping Control Parameters of an Active Electrohydraulic Suspension to Improve Passenger Comfort and Road Handling by Rachid Fattah, Jean-Pierre Kenne, Khalid Benjelloun, Ahmed Chebak

“…The optimization process considers worst-case road disturbances, leading to a 79.5% reduction in tracking error, a 44.7% decrease in VDV, and a 51.2% improvement in Crest Factor, complying with ISO 2631 standards. …”
Get full text

Efficient Simulation of the Outage Probability of Multihop Systems by Chaouki Ben Issaid, Mohamed-Slim Alouini, Raul Tempone

“…The proposed estimator is endowed with the bounded relative error property. Simulation results show a significant reduction in terms of number of simulation runs compared to naive Monte Carlo.…”
Get full text

Predicting Ship Waiting Times Using Machine Learning for Enhanced Port Operations by Min-Hwa Choi, Woongchang Yoon

“…Shapley additive explanation (SHAP)-based feature selection is typically applied to enhance interpretability, and its effect is compared with principal component analysis-based dimensionality reduction and nonselection methods. The XGBoost Regressor (XGBR) is optimized using genetic-algorithm-based hyperparameter tuning, reducing mean squared error (RMSE) from 20.9531 to 19.6387, mean absolute error (MAE) from 13.6821 to 12.6753, and improving coefficient of determination (R2) from 0.2791 to 0.2949. …”
Get full text

Optimizing Methanol Injection Quantity for Gas Hydrate Inhibition Using Machine Learning Models by Mohammed Hilal Mukhsaf, Weiqin Li, Ghassan Husham Jani

“…R²), mean absolute error (MAE), and root mean square error (RMSE), were KNN < DT < RF < XGBoost. …”
Get full text

Numerical investigation of flow field characteristics over vertical drops with sudden contraction for different contraction ratios by Hossein Shahin, Afshin Eghbalzadeh, Mitra Javan

“…The computational model was validated against experimental data, yielding acceptable levels of accuracy based on average percentage error (APE) and root mean square error (RMSE) metrics. …”
Get full text

FBG‐driven simulation for virtual augmentation of fluoroscopic images during endovascular interventions by Valentina Scarponi, Juan Verde, Nazim Haouchine, Michel Duprez, Florent Nageotte, Stéphane Cotin

“…This system demonstrated accurate prediction with a mean 3D error of 2.4 ± 1.3 mm and a mean error of 1.1 ± 0.7 mm on the fluoroscopic image plane between the real catheter shape after guidewire withdrawal and the predicted shape. …”
Get full text

Medium-Term Hourly Electricity Tariff Forecasting Using Ensemble Models by Matrenin P.V., Arestova A.Yu., Antonenkov D.V.

“…The most significant results are the proof of the possibility of obtaining the month ahead electricity tariff rate forecast with the mean absolute percentage error 4 %. It could be used for electricity costs reduction by regulating the load curve. …”
Get full text

Adapted Speed Control of Two-Stroke Engine with Propeller for Small UAVs Based on Scavenging Measurement and Modeling by Yifang Feng, Tao Chen, Qinwang Liu, Heng Zhao

“…The results indicate an 89% reduction in average speed error under varying air pressure and an 83.7% decrease in average speed overshoot in continuous step speed target experiments.…”
Get full text

Research and validation of forest carbon sequestration measurement model based on biomass method-A case study of Guizhou Province. by Zhang Min, Wu Yang, Qiu Yan, Yan Jun, Li Chunling, Ran Wen Rui

“…Compared with the existing forestry carbon sequestration project evaluation, the results showed that the average relative error of the model was 6. 09%, and the absolute error range was 0. 348-4. 262/hm2, and the model effect was good. …”
Get full text

Red Fox Optimization-Based Estimation Algorithms for Splitting Tensile Strength of Basalt Fiber Reinforced Concrete by Xiao Wu, Daoyong Zhu, Qin Yan

“…Also, the models’ results indicate that RFORF outperforms another model, with −34% lower values in symmetric mean absolute percentage error (SMAPE) and a significant −80% reduction in mean squared logarithmic error (MSLE). …”
Get full text

Construction of a NOx Emission Prediction Model for Hybrid Electric Buses Based on Two-Layer Stacking Ensemble Learning by Jiangyan Qi, Xionghui Zou, Ren He

“…The evaluation metrics of the proposed model—mean absolute error, root mean square error, and coefficient of determination—are 0.0068, 0.0283, and 0.9559, respectively, demonstrating a significant advantage compared to other benchmark models.…”
Get full text

Estimation of Ambient Air PM2.5 Concentration Using MLP and RBF by Ali Mohammadi Bardshahi, Nematollah Jaafarzadeh, Tayebeh Tayebeh, Fazel Amiri

“…The dataset was divided into three subsets: 70% for training, 15% for testing, and 15% for validation.Results: The results showed that the average concentration of PM2.5 was 26.5 μg/m3. The root mean square error (RMSE) was estimated as 6.49 μg/m3. Increasing the input data resulted in a slight reduction in network error, with the RBF model, utilizing 1450 inputs and an RMSE of 6.47, achieving the same accuracy as the MLP model with 10 inputs.Conclusion: Given that the PM2.5 concentration estimates from the RBF and MLP models deviated by less than 23 and 25%, respectively, compared to the observed concentrations, both MLP and RBF can be regarded as reliable tools for predicting PM2.5 levels.…”
Get full text

GDSMOTE: A Novel Synthetic Oversampling Method for High-Dimensional Imbalanced Financial Data by Libin Hu, Yunfeng Zhang

“…The failure of distance measurement in high-dimensional space, error accumulation caused by noise samples, and the reduction of recognition accuracy of majority samples caused by the distribution of synthetic samples are the main reasons that limit the performance of current methods. …”
Get full text

Silent speech recognition using visual cascading fusion of tongue-lip movements based on pre-trained and fine-tuned model by Chongchong Yu, Xuening Wang, Zhaopeng Qian

“…Experimental results show that the average word error rate (WER) of proposed model can achieve to 23.34%, representing a 1.75% reduction compared to the baseline model. …”
Get full text

Residual learning based convolution neural network for improved channel estimation for VehA channel by Sunita Khichar, Yahui Meng, Abhishek Sharma, Muhammad Saadi, Amir Parniarifard, Sushank Chaudhary

“…Traditional channel estimation techniques, such as least squares (LS) and linear minimum mean square error (LMMSE), face limitations in terms of estimation accuracy and computational complexity. …”
Get full text

An Improvement of the Load Transfer Method for Energy Piles Under Thermo-Mechanical Loads by Haofan Yang, Haowen Pan, Chenfeng Zong, Ziyi Wang, Gang Jiang

“…The calculated results at the pile head show an 18% reduction in error compared to previous studies. The average error compared with field test results is within 20%, with consistent trend patterns, confirming the feasibility of the proposed method. …”
Get full text

Smooth Guided Adversarial Fully Test-Time Adaptation by Dong Li, Panfei Yang

“…Experimentally, SAFTTA demonstrates state-of-the-art results, improving error rate by 0.7% on the CIFAR-10-C benchmark and achieving a 1.1% reduction in error rate on the ImageNet-C benchmark compared to existing methods. …”
Get full text

Prediction of the discharge coefficient of steeply crested inclined weirs using different neural network techniques by Adnan A. Ismael, Abdulnaser A. Ahmed, Raid Rafi Omar Al-Nima, Mohammed Khaire Hussain

“…CFNN achieved a significant reduction in mean square errors (MSE), with values of 9.4363×10-12 and 1.6336×10-05, respectively, in the training and testing phases. …”
Get full text

Comparison of nonlinear Kalman filtering schemes for sensorless control of permanent magnet-assisted synchronous reluctance machines by M.A. González-Cagigal, Cristina Martín, Mario Bermúdez, Pedro Cruz-Romero

“…Performance, computational effort, and sensitivity to measurement errors and model parameters are evaluated and compared through simulation to clarify which filtering algorithm is more suitable for the system under study.…”
Get full text