Calculation Method of Oil Saturation of Mixed Shale Based on Lithology Classification by CAO Zhifeng, LIN Jingqi, WANG Xianhu, LIU Jieli, WANG Xiaodan, LIU Dingwen

“…Applied to the calculation of effective thickness oil saturation of mixed shale oil, the average error between calculated oil saturation and core analysis oil saturation is 2.06%, which is higher than 5.00% of the reserve standard. …”
Get full text

Numerical Simulation of Low-Level Wind Shear Using CFD and LSTM Technology Based on the WRF Model by Zexin DONG, Shuoyan WU, Fang YE, Lijing CHEN, Yi LI, Chenbo SUN, Feng XU, Lei LIU

“…In an effort to elevate the precision of low-level wind shear forecasting， this paper amalgamates European Centre for Medium-Range Weather Forecasts （ECMWF） fifth-generation reanalysis data （ERA5） and National Centers for Environmental Prediction Final Operational Global Analysis （FNL） reanalysis data， high-resolution Advanced Spaceborne Thermal Emission and Reflection Radiometer Global Digital Elevation Model （ASTER GDEM） terrain data， and real-time observational data from Lanzhou Zhongchuan Airport.It employs the Weather Research and Forecasting Model （WRF）， WRF integrated with Computational Fluid Dynamics （CFD）， and Long Short-Term Memory （LSTM） neural network methods to simulate and analyze two wind shear events at Lanzhou Zhongchuan Airport on April 15-16， 2021.The findings reveal that： （1） within grids smaller than 1 kilometer utilizing Large Eddy Simulation （LES）， the WRF model demonstrates superior performance in wind speed simulation for individual stations， yet it falls short when compared to the WRF model combined with Computational Fluid Dynamics （CFD） models in simulating near-surface horizontal wind field wind speeds； （2） concerning the simulation of two low-level wind shears encountered during aircraft landing， both Weather Research and Forecasting Model - Large Eddy Simulation （WRF-LES） and Weather Research and Forecasting Model - Computational Fluid Dynamics （WRF-CFD） models are capable of simulating the first wind shear， however， the second appears to be influenced by the potentially lower wind speed data input into the models， with neither model achieving the threshold for wind speed difference， necessitating further validation in future work； （3） under low wind speed conditions （6 meters per second）， the LSTM-based single-variable wind speed prediction model maintains an average absolute error of approximately 0.59 meters per second， effectively capturing the nonlinear relationship of wind speed changes under various terrain and circulation background conditions.Despite being constrained by WRF errors and incomplete observational elements， multi-variable wind speed prediction can achieve wind speed forecasting with higher computational efficiency and generalization capabilities while ensuring that the average absolute percentage error is less than 6.60%.This paper not only verifies the differences between WRF-CFD and WRF-LES coupling schemes in wind field and low-level wind shear forecasting but also explores the feasibility and accuracy of LSTM-based wind speed prediction， aspiring to offer new perspectives and methods for enhancing wind field simulation accuracy and reducing the time required for detailed wind field simulation.…”
Get full text

Detection and Theoretical Numerical Simulation of the Failure Depth of the Bottom Plate in Belt Pressure Mining by Xipeng Cui, Shuancheng Gu, Jinhua Li, Jiahao Wen, Kailei Zhao, Xinlei Liu

“…Considering that the traditional pressure water test method has disadvantages such as easy collapse hole, long period, and large error in monitoring the failure rule of deep floor rock mass, the embedded stress monitoring and reverse analysis method and ultrasonic detection method are used to successfully collect and real-time monitor the data of rock floor before, during and after mining in the lower part of wide mining face of Xizhuo Coal Mine for the first time, and several effective data are obtained, which solves the three-part “spatial-time” all-round floor disturbance and failure law field measurement which cannot be realized by traditional testing technology. …”
Get full text

Advanced Applications of Artificial Intelligence in Pharmacovigilance: Current Trends and Future Perspectives by Yogesh S Ahire, Jayesh H Patil, Harshita N Chordiya, Rashmi A Deore, Vinod A Bairagi

“…Conventional approaches suffer from biases in human error, inefficiency, and scalability problems. A new era in pharmacovigilance is being ushered in by the introduction of artificial intelligence (AI), which holds the promise of vast data analysis, automated procedures, and enhanced safety signal detection. …”
Get full text

G-Pre: A Graph-Theory-Based Matrix Preconditioning Algorithm for Finite Element Simulation Solutions by Min Chen, Jingyan Li, Lijie Li, Kang Liang, Gai Wu, Wei Shen

“…However, the most commonly used preconditioning methods for incomplete LU factorization usually increase data access and computation due to data padding and forward/backward operations, as well as affect parallel computing design. …”
Get full text

A clustering-based federated deep learning approach for enhancing diabetes management with privacy-preserving edge artificial intelligence by Xinyi Yang, Juan Li

“…The results show that the Clu-FDL approach achieves high precision (0.93), recall (0.96), and F1 scores (0.95), along with low Root Mean Square Error (RMSE) values (11.08 ± 1.77 mg/dL). Additionally, for new patients with different data durations, analysis based on 0.25–3 days of data indicates that Clu-FDL models exhibit greater stability, with smaller RMSE and higher precision, recall, and F1 scores compared to non-clustering models. …”
Get full text

Investigating diverse photogrammetric techniques in the hazard assessment of historical sites of the Museum of the Coal Basin Area in Będzin, Poland by Świerczyńska Ewa, Karsznia Krzysztof, Książek Krzysztof, Odziemczyk Waldemar

“…Point clouds, TIN grids, and façade orthophotos were examined. Statistical analysis was used to determine the repeatability of the data. …”
Get full text

Convolutional neural network (CNN) based month’s name recognition in Gurumukhi script for Punjab state of India by Tajinder Pal Singh, Sheifali Gupta, Jamil Hussain, Sapna Juneja, Meenu Garg, Deepali Gupta, Majed Alsafyani

“…In the context of natural language recognition, the development of an automated system for data analysis and interpretation has tremendous demand. …”
Get full text

A novel quantile regression for fractiles based on unit logistic exponential distribution by Hanan Haj Ahmad, Kariema A. Elnagar

“…Continuous developments in unit interval distributions have shown effectiveness in modeling proportional data. However, challenges persist in diverse dispersion characteristics in real-world scenarios. …”
Get full text

Permeability Predictions for Tight Sandstone Reservoir Using Explainable Machine Learning and Particle Swarm Optimization by Jing-Jing Liu, Jian-Chao Liu

“…., the shale content, the AC slope, and the GR slope) as data sets. Based on the data preprocessing, global and local interpretations are performed according to the Shapley additive explanations (SHAP) analysis, and the redundant features in the data set are screened to identify the porosity, AC, CAL, and GR slope as the four most important features. …”
Get full text

A Study on Predicting Key Times in the Takeout System’s Order Fulfillment Process by Dongyi Hu, Wei Deng, Zilong Jiang, Yong Shi

“…Extensive experiments conducted on a real-world takeout food order dataset demonstrate that the Mean Squared Error of the prediction results of GRU-Transformer with time chain simulation is reduced by about 9.78% compared to the Transformer. …”
Get full text

Accuracy and Precision Evaluation of Image-Based Computer Assisted Surgical System for Total Ankle Arthroplasty by Matthew C. Rueff MSc, Zach Tupper, Matthew Hamilton PhD, Prudhvi Chinimilli, Scott Gulbransen, Laureline Prouvost, Edward T. Haupt MD, Laurent Angibaud, Dipl Ing.

“…One deviation to surgical technique was identified with video tracking: The talar fixator was not tightened on specimen five which leading to tracker movement during talus resection. Therefore, the data from specimen five was removed from the analysis since the operative technique for the TAA navigation system was not followed. …”
Get full text

Artificial neural network (ANN) approach in predicting the thermo-solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolant by Tawsif Mahmud, Jiaul Haque Saboj, Preetom Nag, Goutam Saha, Bijan K. Saha

“…The ANN model with 6-50-100-50-2 architecture showcases the best fit with the mean squared error of 0.8923 and an R² value of 99.96 % on testing data. …”
Get full text

ResTUnet: A Novel Neural Network Model for Nowcasting Using Radar Echo Sequences by Ground-Based Remote Sensing by Lei Zhang, Ruoyang Zhang, Yu Wu, Yadong Wang, Yanfeng Zhang, Lijuan Zheng, Chongbin Xu, Xin Zuo, Zeyu Wang

Get full text

ECG-based beat-to-beat assessment of AV node conduction properties during AF by Mattias Karlsson, Mattias Karlsson, Felix Plappert, Pyotr G. Platonov, Sten Östenson, Mikael Wallman, Frida Sandberg

Get full text

RESEARCH INTO SPEECH-TO-TEXT TRANFROMATION MODULE IN THE PROPOSED MODEL OF A SPEAKER’S AUTOMATIC SPEECH ANNOTATION by Olesia Barkovska

“…The goal of the work is to elimination of false or corrupt data in the process of converting the audio sequence into the relevant text for further semantic analysis. …”
Get full text

Mental and Emotional Experiences among Registered Nurses during SARS COV-2 Pandemic: A Meta-Synthesis by Manish Kumar Balai, V. A. Raghu, Dutt Avasthi Rishi, Ram Bishnoi Hanuman

“…The meta-synthesis reported data from 10 phenomenological studies with 198 nurses as informants of which 122 were female and 40 were male and the remaining 36 sample categories were not reported and their mean age was 29.62 years. …”
Get full text

Maximum Entropy Estimates of Hubble Constant from Planck Measurements by David P. Knobles, Mark F. Westling

“…Thus, the ME analysis does not appear to support the existence of the Hubble tension.…”
Get full text

Estimation of Time-Varying Passenger Demand for High Speed Rail System by Tangjian Wei, Feng Shi, Guangming Xu

“…Based on the precedence relationships of itineraries, two typical situations are proposed, in which the Single Booking Phase Reverse Assignment (SBPRA) algorithm and the Multiple Booking Phases Reverse Assignment (MBPRA) algorithm are proposed to estimate the time-varying demand respectively. Case analysis on OD pair Beijing-Shanghai are presented, and the validity analysis demonstrates that the error rates of SBPRA algorithm and MBPRA algorithm are 8.64% and 6.37%, respectively.…”
Get full text

Multi-agent maglev harmonic prediction algorithm based on integrated attention mechanism by WANG Zongyan, MAO Zhongya, HUANG Shize, GUO Qiyi

“…Theoretical analysis and simulations of Shanghai high-speed maglev traction system were conducted, with the grid-side current data collected for experiment and analysis using the proposed algorithm model. …”
Get full text