Efficiently Learning an Encoder That Classifies Token Replacements and Masked Permuted Network-Based BIGRU Attention Classifier for Enhancing Sentiment Classification of Scientific... by Muhammad Inaam Ul Haq, Khalid Mahmood, Qianmu Li, Ashok Kumar Das, Sachin Shetty, Majid Hussain

Get full text

Computational hybrid analysis of drug diffusion in three-dimensional domain with the aid of mass transfer and machine learning techniques by Mohammed Alqarni, Ali Alqarni

“…Additionally, $$\:\nu\:$$ -SVR exhibits the lowest RMSE and MAE, showing excellent predictive accuracy compared to KRR and MLR. Overall, our analysis demonstrates the effectiveness of employing tree-based ensemble models coupled with BFO for accurately predicting chemical concentrations in three-dimensional space, with $$\:\nu\:$$ -SVR emerging as the most promising model for this task. …”
Get full text

Explainable Artificial Intelligence (XAI) for Flood Susceptibility Assessment in Seoul: Leveraging Evolutionary and Bayesian AutoML Optimization by Kounghoon Nam, Youngkyu Lee, Sungsu Lee, Sungyoon Kim, Shuai Zhang

“…We first employed the Tree-based Pipeline Optimization Tool (TPOT), an evolutionary AutoML algorithm, to construct baseline ensemble models using Gradient Boosting (GB), Random Forest (RF), and XGBoost (XGB). …”
Get full text

Toward a conceptual model to improve the user experience of a sustainable and secure intelligent transport system by Abdullah Alsaleh

“…A novel search and management protocol, supported by a tailored algorithm, was developed to enhance resource allocation success rates for vehicles within a defined area of interest. …”
Get full text

Rapid and Nondestructive Identification of Origin and Index Component Contents of Tiegun Yam Based on Hyperspectral Imaging and Chemometric Method by Yue Zhang, Yuan Li, Cong Zhou, Junhui Zhou, Tiegui Nan, Jian Yang, Luqi Huang

“…The optimal residual predictive deviation (RPD) values of starch, polysaccharide, and protein prediction models selected in this study were 5.21, 3.21, and 2.94, respectively. …”
Get full text

The doctor and patient of tomorrow: exploring the intersection of artificial intelligence, preventive medicine, and ethical challenges in future healthcare by Paulo Santos, Paulo Santos, Isabel Nazaré, Isabel Nazaré

“…AI-driven technologies, including real-time health monitoring and predictive analytics, offer new personalized preventive care possibilities. …”
Get full text

Modelling Ergonomic Hazard Risks in Manual Handling: Insights from Ponorogo’s Traditional Industry by Dian Afif Arifah, Ratih Andhika Akbar Rahma, Triana Harmini, Dhiya Irsyad Hafidz

“…This study aims to develop a model to evaluate and predict ergonomic hazards using a neural network algorithm, focusing on the relationship between manual handling postures and musculoskeletal pain in 12 body regions. …”
Get full text

Modelling the future of cleaner energy: Explainable artificial intelligence model for green hydrogen production rate estimation by Okorie Ekwe Agwu, Saad Alatefi, Ahmad Alkouh

“…The connection weights algorithm applied to the model enhances its explainability by illustrating the relative contributions of each input variable and their impacts on hydrogen yield. …”
Get full text

Classifying detrital zircon U-Pb age distributions using automated machine learning by Jack W. Fekete, Glenn R. Sharman, Xiao Huang

“…Applied to the North American Cordillera dataset, AutoML achieves an ∼0.91 F1 score when predicting between foreland and forearc basin tectonic settings and an ∼0.71 F1 score when predicting subbasins within these settings, outperforming both RF and R2. …”
Get full text

Chlorophyll-a in the Chesapeake Bay Estimated by Extra-Trees Machine Learning Modeling by Nikolay P. Nezlin, SeungHyun Son, Salem I. Salem, Michael E. Ondrusek

“…Our approach leverages the Extra-Trees (ET) algorithm, a tree-based ensemble method that offers predictive accuracy comparable to that of other ensemble models, while significantly improving computational efficiency. …”
Get full text

Selective Cleaning Enhances Machine Learning Accuracy for Drug Repurposing: Multiscale Discovery of MDM2 Inhibitors by Mohammad Firdaus Akmal, Ming Wah Wong

“…A key innovation of this work is the development and application of a selective cleaning algorithm that systematically filters assay data to mitigate noise and inconsistencies inherent in large-scale bioactivity datasets. …”
Get full text

Smart estimation of protective antioxidant enzymes’ activity in savory (Satureja rechingeri L.) under drought stress and soil amendments by Amin Taheri-Garavand, Mojgan Beiranvandi, Abdolreza Ahmadi, Nikolaos Nikoloudakis

“…On the other hand, POX had a lower predictive correlation (R = 0.8737), indicating a lower capacity of the ANN system in forecasting this parameter. …”
Get full text

The impact of environmental variables on reed stands of the intermittent Lake Cerknica, Slovenia: 40 years of change by Nik Ojdanič, Alenka Gaberščik, Igor Zelnik, Aleksandra Golob

“…Decision tree-based data mining using the M5P algorithm effectively identified significant changes in MSAVI2. …”
Get full text

Magnetic resonance imaging (MRI) radiomics in paediatric neuro-oncology: A systematic review of clinical applications, feature interpretation, and biological insights in the ch... by Teesta Mukherjee, Omid Pournik, Theodoros N Arvanitis

“…SVM was the most used classification algorithm ( n  = 9), with an AUC range of 0.858–0.977. …”
Get full text

Quantitative structure-properties relationship, molecular dynamic simulations and designs of some novel lubricant additives by Usman Abdulfatai, Adamu Uzairu, Sani Uba, Gideon Adamu Shallangwa

“…Quantitative structure-properties relationship (QSPR) method was used to design some novel antioxidant lubricant additives, while molecular dynamics simulations were used to calculate their dynamic binding energies on steel and to hydrogen-containing DLC (a-C: H) crystal surfaces. 29 synthesized antioxidant lubricant additives were collected from literature and geometrically optimized by Spartan’14 version 1.1.2 software while Genetic Function Algorithm (GFA) method of the material studio version 8.0 software was used to build the predictive QSPR model. …”
Get full text

Early Warning for Stepwise Landslides Based on Traffic Light System: A Case Study in China by Shuangshuang Wu, Zhigang Tao, Li Zhang, Song Chen

“…Furthermore, leveraging the C5.0 machine learning algorithm, a comparison between the predictive capabilities of the TLS model and a pure rate threshold model reveals that the TLS model achieves a 93% accuracy rate, outperforming the latter by 7 percentage points. …”
Get full text

Identification of priority conservation areas and potential corridors for jaguars in the Caatinga biome, Brazil. by Ronaldo Gonçalves Morato, Katia Maria Paschoaletto Micchi de Barros Ferraz, Rogério Cunha de Paula, Cláudia Bueno de Campos

“…A total of 62 points records of jaguar occurrence and 10 potential predictors were analyzed in a GIS environment. A predictive distributional map was obtained using Species Distribution Modeling (SDM) as performed by the Maximum Entropy (Maxent) algorithm. …”
Get full text

Revealing High‐Temporal‐Resolution Flood Evolution With Low Latency Using GRACE Follow‐On Ranging Data by Hao‐si Li, Shuang Yi, Zi‐ren Luo, Peng Xu

“…To address this problem, this study develops an improved algorithm accounting for peripheral signal sources and temporal correlations in mass variation. …”
Get full text

Application of artificial intelligence and red-tailed hawk optimization for boosting biohydrogen production from microalgae by Hegazy Rezk, Ali Alahmer, Abdul Ghani Olabi, Enas Taha Sayed

“…Subsequently, the red-tailed hawk algorithm (RTH) is used to determine the optimal values for the process parameters, corresponding to maximum hydrogen yield. …”
Get full text

A Wind Power Density Forecasting Model Based on RF-DBO-VMD Feature Selection and BiGRU Optimized by the Attention Mechanism by Bixiong Luo, Peng Zuo, Lijun Zhu, Wei Hua

“…First, critical physical features relevant to WPD are identified using random forest (RF), effectively eliminating data redundancy and enhancing prediction efficiency. Second, the variational mode decomposition (VMD) parameters are optimized via the dung beetle optimizer (DBO) algorithm to extract independent intrinsic mode functions (IMFs), which, alongside the original data, serve as temporal feature inputs. …”
Get full text