Results 181 to 190 of about 65,893 (254)

Comparing convolutional neural network and random forest for benthic habitat mapping in Apollo Marine Park

Remote Sensing in Ecology and Conservation, EarlyView.
A comparison of Convolutional Neural Network (CNN) and Random Forest (RF) model predictions of benthic habitats within Apollo Marine Park. The CNN (left) and RF (right) classification maps show the spatial distribution of three habitat types: high energy circalittoral rock with seabed‐covering sponges, low complexity circalittoral rock with non‐crowded
Henry Simmons, Dang Nguyen, Benjamin Misiuk, Daniel Ierodiaconou, Sunil Gupta, Oli Dalby, Mary Young   +6 more
wiley   +1 more source

From Prediction to Prevention: An Explainable GeoAI Framework for Flood Susceptibility and Urban Exposure Assessment Using Machine and Deep Learning Models

Sustainable Development, EarlyView.
ABSTRACT Rapid urbanisation and intensifying rainfall have increased cities' vulnerability to flooding, posing major challenges to sustainable development. Although machine learning models have improved flood prediction accuracy, most remain limited by their black‐box nature and lack of actionable insights.
Abdulwaheed Tella, Izni Zahidi, Chow Ming Fai, Chukwuma Okolie, Quoc Bao Pham   +4 more
wiley   +1 more source

Age-Related Differences in Speech Production and Resting State Functional Network Dynamics. [PDF]

Neurobiol Lang (Camb)
Zhang H, Lei K, Yu H, Nakamura M, Diaz M.   +4 more
europepmc   +1 more source

Urban Heat and Spatial Statistics, Toward Sustainable Cities and Society: A PRISMA‐Based Systematic Review and Empirical Assessment (2020–2025)

Sustainable Development, EarlyView.
ABSTRACT Over the past few decades, the intensification of global warming has brought increased attention to urban thermal dynamics, particularly regarding Land Surface Temperature (LST) and the Urban Surface Heat Island (SUHI) effect. This study conducts a systematic literature review alongside a bibliometric analysis of 123 peer‐reviewed articles ...
David Hidalgo‐García, Hamed Rezapouraghdam, Antonio Jesús Aguilar‐Aguilera, María Luísa de la Hoz‐Torres, Rubén López‐Cantero   +4 more
wiley   +1 more source

A high-resolution database of historical and future climate for Africa developed with deep neural networks. [PDF]

Sci Data
Namiiro SA, Hamann A, Wang T, Castellanos-Acuña D, Mahony CR.   +4 more
europepmc   +1 more source

High Sensitivity Cardiac Troponin I Detection via MP‐Locked Aptamer and Multimeric DNAzyme‐Coupled Hyperbranched Hybridization Chain Reaction

Small, EarlyView.
We report a magnetic particle anchored locked aptamer platform integrated with hyperbranched HCR and DNAzyme amplification for enzyme‐free, ultrasensitive detection of cardiac troponin I. The assay achieves a 0.25 ng/L detection limit within 25 minutes and enables cross‐species MI detection, with machine learning classification reaching 90% accuracy ...
Sayantan Tripathy, Sahil Sharma, Ng Ka Wai, Siddhant Jaitpal, Anthony Dongchau, Saugat Bhattacharyya, Sonya R. Wesselowski, Ashley B. Saunders, Gerard L. Coté, Samuel B. Mabbott   +9 more
wiley   +1 more source

A physics-informed neural network approach for estimating population-level pharmacokinetic parameters from aggregated concentration data. [PDF]

J Pharmacokinet Pharmacodyn
Tsiros P, Minadakis V, Sarimveis H.
europepmc   +1 more source

Finding Minimum‐Cost Explanations for Predictions Made by Tree Ensembles

Software: Practice and Experience, EarlyView.
ABSTRACT The ability to reliably explain why a machine learning model arrives at a particular prediction is crucial when used as decision support by human operators of critical systems. The provided explanations must be provably correct, and preferably without redundant information, called minimal explanations.
John Törnblom, Emil Karlsson, Simin Nadjm‐Tehrani   +2 more
wiley   +1 more source

Generative Adversarial Networks for High-Dimensional Item Factor Analysis: A Deep Adversarial Learning Algorithm. [PDF]

Psychometrika
Luo N, Ji F.
europepmc   +1 more source