Risk assessment and prevention in airport security assurance by integrating LSTM algorithm. by Yao Hu, Liguang Qiao, Feng Gu

“…The outcome indicates that the standard error of the LSTM algorithm model training is less than 0.18, and the decision coefficients were all greater than 0.9. …”
Get full text

Lithium-Ion Battery State of Health Estimation Based on CNN-LSTM-Attention-FVIM Algorithm and Fusion of Multiple Health Features by Guoju Liu, Zhihui Deng, Yonghong Xu, Lianfeng Lai, Guoqing Gong, Liang Tong, Hongguang Zhang, Yiyang Li, Minghui Gong, Mengxiang Yan, Zheng Ye

“…After the model is verified on a single NASA battery aging dataset, the model is compared with other models under the same relevant parameters and environmental settings to verify the high-precision prediction of the model. During the analysis and comparison process, CNN-LSTM-Attention-FVIM achieved a high fitting ability for battery SOH prediction estimation, with the mean absolute error (MAE) and root mean square error (RMSE) within 0.99% and 1.33%, respectively, reflecting the model’s high generalization ability and high prediction performance.…”
Get full text

Estimation of the Angles of a Robotic Arm with 7-Free Degrees Using an Improved Hybrid ESSA Algorithm by Inayet Hakki Cizmeci, Adem Alpaslan Altun

“…Moreover, ESSA has been tested in the optimization of a robotic arm, a technology that requires low-error rates in the medical field. …”
Get full text

The Importance of the Model Choice for Experimental Semivariogram Modeling and Its Consequence in Evaluation Process by Alessandro Mazzella, Antonio Mazzella

“…The purpose of this new science was to achieve an optimal evaluation of mining ore bodies. The interest in geostatistical tools has grown, and nowadays its techniques are applied in many branches of engineering where data analysis, interpolation, and evaluation are necessary. …”
Get full text

From Patterns to Predictions: Spatiotemporal Mobile Traffic Forecasting Using AutoML, TimeGPT and Traditional Models by Hassan Ayaz, Kashif Sultan, Muhammad Sheraz, Teong Chee Chuah

“…Model accuracy is assessed using standard evaluation metrics, including root mean square error (RMSE), mean absolute error (MAE) and the coefficient of determination (R²). …”
Get full text

A Novel Evolutionary Deep Learning Approach for PM_2.5 Prediction Using Remote Sensing and Spatial–Temporal Data: A Case Study of Tehran by Mehrdad Kaveh, Mohammad Saadi Mesgari, Masoud Kaveh

“…This paper employs a binary OA method for sensitivity analysis, optimizing feature selection by minimizing prediction error while retaining critical predictors through a penalty-based objective function. …”
Get full text

Impedance Characteristic-Based Frequency-Domain Parameter Identification Method for Photovoltaic Controllers by Yujia Tang, Xin Zhou, Yihua Zhu, Junzhen Peng, Chao Luo, Li Zhang, Jinling Qi

“…The maximum identification error of other intelligent algorithms was 5%, with a difference of less than 1% compared to the proposed method. …”
Get full text

Diabetes: Non-Invasive Blood Glucose Monitoring Using Federated Learning with Biosensor Signals by Narmatha Chellamani, Saleh Ali Albelwi, Manimurugan Shanmuganathan, Palanisamy Amirthalingam, Anand Paul

“…Clarke error grid analysis (CEGA) confirmed the model’s clinical reliability, with 99.31% of predictions falling within clinically acceptable limits. …”
Get full text

Sustainable strengthening of concrete deep beams with openings using ECC and Bamboo: An equation and data-driven approach through abaqus modeling and GEP by Fayiz Amin, Ijaz Ali, Ali Husnain, Muhammad Faisal Javed, Hisham Alabduljabbar, Asher Junaid

“…Gene expression programming (GEP) was used to develop predictive models for shear capacity, providing an interpretable framework for optimizing beam design. Although error analysis indicated areas for further calibration, the GEP models exhibited high predictive accuracy with R² > 0.85 in both training and validation datasets. …”
Get full text

A Comprehensive Framework for Transportation Infrastructure Digitalization: TJYRoad-Net for Enhanced Point Cloud Segmentation by Zhen Yang, Mingxuan Wang, Shikun Xie

“…These methods ensure accurate results with minimal memory overhead. The optimized 3D models have been successfully applied in driving simulation and traffic flow analysis, providing a practical and scalable solution for real-world infrastructure modeling and analysis. …”
Get full text

Short-Term Electric Load Forecasting for an Industrial Plant Using Machine Learning-Based Algorithms by Oğuzhan Timur, Halil Yaşar Üstünel

“…The integration of calendar, meteorological, and lagging electrical variables, along with machine learning-based algorithms, is employed to boost forecasting accuracy and optimize energy utilization. The ultimate objective of the present study is to conduct a thoroughgoing and detailed analysis of the statistical performance of the models and associated error metrics. …”
Get full text

Calibration and establishment for the discrete element simulation parameters of pepper stem during harvest period by Jiaxuan Yang, Jin Lei, Xinyan Qin, Zhi Wang, Jianglong Zhang, Lijian Lu

“…The results showed that the relative errors between simulated and actual values for the two models under optimal conditions were 0.86% and 1.02%, respectively. …”
Get full text

A Deep-Learning Workflow for CORONA-Based Historical Land Use Classifications by Wei Liu, Shuai Li, Di Fan, Yixin Wen, Austin Madson, Jessica Mitchell, Yaqian He, Di Yang

“…Results show that georeferencing achieved satisfactory accuracy with a mean absolute error of 5.99 m. The classification approach that uniquely incorporated terrain variation analysis achieved 89.36% overall accuracy (OA) in categorizing different land use types. …”
Get full text

Movie Box Office Prediction Based on IFOA-GRNN by Wei Lu, Xiaoqiao Zhang, Xinchen Zhan

“…This study improves the fruit fly algorithm to optimize the generalized regression neural network (IFOA-GRNN) model to predict whether a movie can become a high-grossing movie. …”
Get full text

Effects of Strain Node on the Actuation Performance of Multilayer Cantilevered Piezoactuator with Segmented Electrodes by Quan Bai, Xuejun Zheng

“…At the second mode, the maximum error between the theoretical calculation value of the tip deflection and the simulation result is 6.8%. …”
Get full text

Automatic Detection and Classification of Natural Weld Defects Using Alternating Magneto-Optical Imaging and ResNet50 by Yanfeng Li, Pengyu Gao, Yongbiao Luo, Xianghan Luo, Chunmei Xu, Jiecheng Chen, Yanxi Zhang, Genxiang Lin, Wei Xu

“…The effectiveness of these filtering methods is evaluated using metrics such as peak signal–noise ratio (PSNR) and mean squared error. Principal component analysis (PCA) is employed to extract column vector features from the downsampled defect MO images, which then serve as the input layer for the error backpropagation (BP) neural network model and the support vector machine (SVM) model. …”
Get full text

Bias in Discontinuous Elevational Transects for Tracking Species Range Shifts by Shixuan Li, Jiannan Yao, Yang Lin, Siyu Wu, Zhongjie Yang, Chao Jin, Yuhan Zhang, Zhen Wang, Jinliang Liu, Guochun Shen, Mingjian Yu

“…The results were striking: the widely used settings for discontinuous transects failed to detect 7.2% of species, inaccurately estimated shift distances for 78% of species, and produced an overall error rate of 86%. Wider quadrat spacing increased these error rates, while longer survey intervals generally reduced them. …”
Get full text

Autoencoder Extreme Learning Machine for Fingerprint-Based Positioning: A Good Weight Initialization is Decisive by Darwin P. Quezada Gaibor, Lucie Klus, Roman Klus, Elena Simona Lohan, Jari Nurmi, Mikko Valkama, Joaquin Huerta, Joaquin Torres-Sospedra

“…This research work includes a comparative analysis with several traditional ways to initialize the input weights in AE-ELM, showing that FID provide a significantly better reconstruction error. …”
Get full text

Ecofriendly Extraction of Polyphenols from <i>Ampelopsis grossedentata</i> Leaves Coupled with Response Surface Methodology and Artificial Neural Network–Genetic Algorithm by Xubo Huang, Chen Li, Yanbin Wang, Jinrong Jiang, Weizhi Wu, Shifeng Wang, Ming Lin, Liang He

“…Under those conditions, the actual AGPL yield was 15.32% ± 0.12%. The statistical analysis showed that both models could predict AGPL yield well and GA-ANN had relatively higher accuracy in the prediction of AGPL output, supported by the coefficient of determination (R² = 0.9809) in GA-based ANN compared to R² = 0.9145 in RSM, as well as lower values for mean squared error (MSE = 0.0279), root mean squared error (RMSE = 0.1669) and absolute average deviation (AAD = 0.1336) in the GA-ANN model. …”
Get full text

A Capillary-Based Micro Gas Flow Measurement Method Utilizing Laminar Flow Regime by Yuheng Zheng, Dailiang Xie, Zhengcheng Qin, Zhengwei Huang, Ya Xu, Da Wang, Hong Zheng

“…Through structural optimization with precise control of the capillary length–diameter ratios and theoretical error correction based on computational analysis, nonlinear errors were effectively reduced while improving the measurement accuracy in the field of micro gas flow. …”
Get full text