Results 131 to 140 of about 91,735 (266)

Predicting Postresection Colorectal Liver Metastases Recurrence Using Advanced Graph Neural Networks with Explainability and Causal Inference

Advanced Intelligent Systems, EarlyView.
This study introduces a framework that combines graph neural networks with causal inference to forecast recurrence and uncover the clinical and pathological factors driving it. It further provides interpretability, validates risk factors via counterfactual and interventional analyses, and offers evidence‐based insights for treatment planning ...
Jubair Ahmed, Md. Abdur Rahman, Mohaimenul Azam Khan Raiaan, Sami Azam   +3 more
wiley   +1 more source

Encapsulated Non‐Exchangeable Na+ Ions Determining the Upper Limit of Al Inclusion in FAU—A Multiscale Simulation

Angewandte Chemie, EarlyView.
DFT computation, AIMD simulations, machine learning, statistical analysis, and experimental characterization reveal that the upper limit of Al inclusion in FAU zeolite synthesized under hydrothermal conditions is determined by the encapsulated non‐exchangeable Na+ ions.
Qi Dong, Tao Zhang, Chuanhao Zhang, Tong Zhang, Yanze Du, Jinghong Ma, Ruifeng Li, Bo Qin, Haijun Jiao   +8 more
wiley   +2 more sources

Hybrid PSO-XGBoost Model for Accurate Flood Risk Assessment

Journal of Applied Informatics and Computing
Flood risk prediction is a crucial step in disaster mitigation. This study optimizes the Extreme Gradient Boosting (XGBoost) algorithm using the Particle Swarm Optimization (PSO) method to improve prediction accuracy.
Lailatun Nabilah, Lukman Hakim
doaj   +1 more source

RPSLearner: A Novel Approach Based on Random Projection and Deep Stacking Learning for Categorizing Non‐Small Cell Lung Cancer

Advanced Intelligent Systems, EarlyView.
Identifying non‐small cell lung cancer (NSCLC) subtypes is essential for precision cancer treatment. Conventional methods are laborious, or time‐consuming. To address these concerns, RPSLearner is proposed, which combines random projection and stacking ensemble learning for accurate NSCLC subtyping. RPSLearner outperforms state‐of‐the‐art approaches in
Xinchao Wu, Jieqiong Wang, Shibiao Wan
wiley   +1 more source

Multiclass Classification of Tomato Leaf Diseases Using GLCM, Color, and Shape Feature Extraction with Optimized XGBoost

Journal of Applied Informatics and Computing
Automatic classification of tomato leaf diseases is an essential component in advancing precision agriculture based on artificial intelligence. This study aims to develop a multiclass classification model for tomato leaf diseases by utilizing texture ...
Fransisko Andrade Laiskodat, Majid Rahardi   +1 more
doaj   +1 more source

SmartDetectAI: An AI‐Powered Web App for Real‐Time Colorimetric Detection of Heavy Metals in Water

Advanced Intelligent Systems, EarlyView.
SmartDetectAI integrates silver nanoparticle‐based colorimetric sensing with an AI‐powered web app for rapid, on‐site detection of toxic heavy metals in water. By combining aggregation‐driven optical changes with machine learning analysis of red ‐ green ‐ blue values, the platform achieves portable, low‐cost, and accurate monitoring of Hg‐ and Cd‐based
Nishat Tasnim, Mirza M. A. Tunur, Fahad Arefin, Shahad Saroar, Md. Wahadoszamen, Taslim Ur Rashid, Aminul I. Talukder, Md. Nurul Amin, Mahmudur Rahman, Ahsan Habib   +9 more
wiley   +1 more source

Three Synchronized, Miniaturized, Wireless Inertial Measurement Unit Sensors for Automated Gait and Balance Analysis System

Advanced Intelligent Systems, EarlyView.
This study presents a compact, three IMU wearable system that enables accurate motion capture and robust gait‐feature extraction, thereby supporting reliable machine learning‐based balance evaluation. Accurate assessment of balance is critical for fall prevention and targeted rehabilitation, particularly in older adults and individuals with ...
Seok‐Hoon Choi, Ki‐Hoon Kim, Heung Jin Park, Yuna Kim, Hyunjin Lee, Yu Bin Lee, Youn Joung Kang, Sungchul Huh, Min‐Ho Seo   +8 more
wiley   +1 more source

Predicting lung cancer risk based on artificial intelligence: Leveraging multifactorial inputs for early detection

Medicine Science
Lung cancer remains the leading cause of cancer-related mortality worldwide, largely because most cases are detected at advanced stages. This study develops and validates multifactorial machine-learning models that integrate demographic, behavioural ...
Emek Guldogan, Fatma Hilal Yagin, Erol Karaaslan   +2 more
doaj   +1 more source

Data‐Driven Design of Bimodal Networked Dielectric Elastomers for High‐Performance Artificial Muscles

Advanced Intelligent Systems, EarlyView.
A data‐efficient artificial intelligence‐assisted framework, which integrates experimental data with machine learning, is developed for the design of bimodal networked dielectric elastomers (DEs) as advanced artificial muscles. It adopts neural networks to predict DEs’ mechanical properties and support vector machines to classify electromechanical ...
Ofoq Normahmedov, Hanzhi Ma, Junbo Peng, Huifeng Dong, Jiangshan Zhuo, Mengke Shi, Lvting Wang, Shengchao Jiang, Ye Shi   +8 more
wiley   +1 more source

Improving algorithms for predicting electric vehicle energy consumption to accurately estimate power reserve based on real terrain parameters and current meteorological factors

Transportation and Information Technologies in Russia
Background. Accurate forecasting of the energy consumption of electric vehicles is a critically important task for improving the efficiency of vehicle operation and reducing drivers' anxiety about power reserve.
Vladislav V. Matviyuk
doaj   +1 more source