Can Earthquake Locations Be Improved for Real-time Monitoring? Revisiting the 1995 seismicity at Soufri`ere Hills Volcano, Montserrat by Jade Eyles, Jessica Johnson, Jenni Barclay, Paddy Smith, Victoria Miller

“…Analysis using new 'trusted' relocations focuses on four seismic clusters distal from Soufriere Hills in 1995. …”
Get full text

GENOMICON-Seq enables realistic simulation of amplicon and exome sequencing for low-frequency mutation detection by Milan S. Stosic, Jean-Marc Costanzi, Ole Herman Ambur, Trine B. Rounge

“…By tracking each mutation’s origin (true or error-derived), researchers can pinpoint detection limits and optimize variant-calling thresholds. …”
Get full text

A parameterized model for tower crane energy consumption was developed based on theoretical formulation and field data by Fan Zhang, Chunli Zhang, Yan Fu, Jun Liu, Jiarui Bu, Peng Duan, Si Chen

“…The best suitable version achieves a Mean Absolute Percentage Error of 25.55%, a Root Mean Square Error (RMSE) of 1036.19 kJ, and a Coefficient of Determination (R2) of 0.83, with just one independent variable. …”
Get full text

LSTM-H: A Hybrid Deep Learning Model for Accurate Livestock Movement Prediction in UAV-Based Monitoring Systems by Ayub Bokani, Elaheh Yadegaridehkordi, Salil S. Kanhere

“…Furthermore, LSTM-H exhibits robustness across noisy and dynamic conditions, with a 90% probability of errors below 13 m, as shown through cumulative error analysis. …”
Get full text

Improved FraSegNet-Based Rock Nodule Identification Method and Application by Yanbo Zhang, Guanghan Zhang, Qun Li, Xulong Yao, Hao Zhou

“…This small error proves the model works well. FraSegNet offers accurate segmentation and precise geometric parameter extraction, making it a valuable tool for advancing rock stability analysis and practical applications in rock mechanics.…”
Get full text

Research on the prediction model of gas emission based on grey system theory by Liyang Bai, Hui Geng, Guangming Yu

“…In order to improve the prediction accuracy of gas emission volume.A prediction model of gas emission based on grey system theory is proposed.11 indexes such as gas content, coal seam depth, coal seam thickness, coal seam dip angle and inclined length of working face are selected as the influencing factors of gas emission.The weight of each factor is determined by grey correlation analysis. The related factors with a grey correlation degree greater than 0.7, from largest to smallest, are: coal seam gas content X1 > coal seam thickness X3 > mining intensity X11 > coal seam depth X2 > adjacent gas content X8.Combined with the field measured data, three grey prediction models for predicting gas emission are determined.After a posterior difference test, the accuracy of GM (0,12) model is excellent.By comparing the predicted data of the model with the actual data, it shows that the GM (0,N) model has good forecasting results.At the same time, in order to prove the advantages of GM (0,N) model, the prediction results are compared with those of multiple linear regression model.The prediction results of GM (0,N) model and multiple linear regression model are compared.The prediction results show that the relative error of GM (0,12) model is 0.799%,the relative error of multiple linear regression model is 3.643%.It shows that GM (0,12) model can better predict gas emission.…”
Get full text

LoD2 Building Reconstruction from Stereo Satellite Imagery using Deep Learning and Model-Driven Approach by Rojgar Qarani Ismael, Haval Sadeq

“…Meanwhile, the computed root mean square error are shown to be within 0.9 m for the ridge and eave, which is essentially small. …”
Get full text

Enhancing Visitor Forecasting with Target-Concatenated Autoencoder and Ensemble Learning by Ray-I Chang, Chih-Yung Tsai, Yu-Wei Chang

“…The TCA method integrates the prediction target into the training process, ensuring that the learned feature representations are optimized for specific forecasting tasks. Extensive experiments conducted on the Taiwan and Hawaii datasets demonstrate that the proposed TCA method significantly outperforms traditional feature selection techniques and other advanced algorithms in terms of the mean absolute percentage error (MAPE), mean absolute error (MAE), and coefficient of determination (R²). …”
Get full text

Leveraging graph neural networks and gate recurrent units for accurate and transparent prediction of baseball pitching speed by Chen Yang, Pengfei Jin, Yan Chen

“…The prediction accuracy of the models was evaluated using mean absolute error (MAE), mean squared error (MSE), and R-squared (R2). …”
Get full text

A k-nearest text similarity-BiGRU approach for duration prediction of traffic accidents on expressways by Jiaona Chen, Jin Zhang, Peng Wang, Yinli Jin

“…In addition, the proposed approach is evaluated by the RMSE (root mean square error) and MAPE (mean absolute percent error) utilizing survey information gathered from expressways of Shaanxi Province in China. …”
Get full text

Reversible Adversarial Examples with Minimalist Evolution for Recognition Control in Computer Vision by Shilong Yang, Lu Leng, Ching-Chun Chang, Chin-Chen Chang

“…To achieve zero-bit error restoration, we utilize the differential evolution algorithm to optimize adversarial perturbations while minimizing distortion. …”
Get full text

A Computing Method to Determine the Performance of an Ionic Liquid Gel Soft Actuator by Bin He, Chenghong Zhang, Yanmin Zhou, Zhipeng Wang

“…The five-parameter and nine-parameter Mooney-Rivlin models of the ILG with a ZrO2 content of 3 wt% were obtained by uniaxial tensile testing, and the parameters are denoted as c10, c01, c20, c11, and c02 and c10, c01, c20, c11, c02, c30, c21, c12, and c03, respectively. Through the analysis and comparison of the uniaxial tensile stress between the calculated and experimental data, the error between the stress data calculated from the five-parameter Mooney-Rivlin model and the experimental data is less than 0.51%, and the error between the stress data calculated from the nine-parameter Mooney-Rivlin model and the experimental data is no more than 8.87%. …”
Get full text

Enterprise power emission reduction technology based on the LSTM–SVM model by Li Kun, Su Meng, Liu Qiang, Zhang Bin

“…The minimum relative prediction error was 0.20%, the maximum error fluctuation was 0.78%, the accuracy was 12.85% higher than the LSTM model, and the recall was 11.60% higher. …”
Get full text

A Novel Fractional Order Multivariate Partial Grey Model and Its Application in Natural Gas Production by Hui Li, Huiming Duan, Hongli Chen

“…Accurate prediction of natural gas production is of great significance for optimizing development strategies, simplifying production management, and promoting decision-making. …”
Get full text

Model Building for Regional Ecological Risk Prediction and Evaluation of Prediction Accuracy by Jia Shao, Bei-lan Li, Wei-jun Liu, Min Chen

“…The regional ecological risk model is built to predict the regional ecological risk level more accurately by using principal component analysis and optimizing standard BP neural network. …”
Get full text

Monitoring of Measurement Reliability in Power Systems on the basis of Statistical Decision Theory by V. A. Anishchenko

“…It is proposed to use a minimax criterion which makes it possible to solve the optimization problem under the conditions of initial uncertainty in the notions of gross error and unreliability of measurements. …”
Get full text

Modeling and Control of a 3DOF Robot Manipulator Using Artificial Fuzzy-Immune FOPID Controller by Worod Adris Shutnan, Nora Ahmed Mohammed, Faris Asaad Abdulmunem, Ali Hamzah Najim, Mustafa Yahya Hassan, Naglaa F. Soliman, Abeer D. Algarni

“…The controllers’ efficacy was verified through quantitative analysis that employed performance indices, including mean square error (MSE). …”
Get full text

Evaluating Leaf Water Potential of Maize Through Multi-Cultivar Dehydration Experiments and Segmentation Thresholding by Shuanghui Zhao, Yanqun Zhang, Pancen Feng, Xinlong Hu, Yan Mo, Hao Li, Jiusheng Li

“…The estimation of <i>Ψ_leaf</i> based on different regression analysis methods with hyperspectral vegetation indices (VIs) has been proven to be a simple and efficient technique. …”
Get full text

Adaptive drive-based integration technique for predicting rheological and mechanical properties of fresh gangue backfill slurry by Chaowei Dong, Jianfei Xu, Nan Zhou, Jixiong Zhang, Hao Yan, Zejun Li, Yuzhe Zhang

“…Analysis demonstrates that the particle swarm optimal (PSO) algorithm based on adaptive adjustment strategy can effectively optimize the hyperparameters of support vector regression (SVR), and the MC-PSO-SVR model exhibits better predictive capability (R2> 0.88) and lower error coefficients (MAE, RSE, and RMSE values approaching 0) and narrower widths of 95 % confidence intervals for yield stress, plastic viscosity, fluidity, and UCS. …”
Get full text

Experimental Characterization of Commercial Scroll Expander for Micro-Scale Solar Organic Rankine Cycle Application: Part 2 by Federico Fagioli, Maria Manieri, Gianmarco Agostini, Michele Salvestroni, Francesco Taddei, Filippo Cottone, Maurizio De Lucia

“…This paper also describes in detail the measurement methodology and the associated error analysis to ensure comparability between experimental and numerical data. …”
Get full text