Results 171 to 180 of about 20,582 (244)

Comparative Analysis of Model‐Agnostic Explanation Methods in Materials Science

Advanced Intelligent Systems, EarlyView.
To address the critical lack of explainable artificial intelligence (XAI) benchmarks in materials science, we present a quantitative and qualitative analysis of six XAI methods applied to molecular fingerprints. Our results reveal significant discrepancies in feature importance rankings, demonstrating that the chosen explanation approach introduces ...
Anna Przybyłowska, Joanna Neubauer, Monika Sztuder, Witold Taisner, Agnieszka Hryniewicka, Julia Kolodziejczyk, Marta Eliza Plonska‐Brzezinska, Dariusz Brzezinski   +7 more
wiley   +1 more source

Explainable AI-based optimization framework for sustainable fly ash concrete design. [PDF]

Sci Rep
Khorshidi M, Nejatipour P, Teimortashlu A, Oliveto G, Afaridegan E.   +4 more
europepmc   +1 more source

Thermally Drawn Bioelectric Catheters: Enabling Proprioceptive Endovascular Navigation

Advanced Intelligent Systems, EarlyView.
This work introduces a novel bioelectric navigation system eliminates the need for harmful fluoroscopy during endovascular surgeries. A bespoke 16‐electrode catheter is fabricated using rapid thermal drawing and laser micro‐machining. Paired with a real‐time tracking algorithm fusing vascular geometry detection and distance estimation, this technology ...
Alex Ranne, Heiko Maier, Jinshi Zhao, Songli Moey, Ayhan Aktas, Manik Chana, Burak Temelkuran, Nassir Navab, Ferdinando Rodriguez y Baena   +8 more
wiley   +1 more source

A Benchmark Study of Machine-Learning Regressors and Semiempirical Quantum Methods for CO₂ Capture in Amine-Based Solvents. [PDF]

ACS Omega
Brum JB, Stoyanov SR, Carneiro JWM, Costa LM.   +3 more
europepmc   +1 more source

Exploiting Edge Semantics in Job Shop Scheduling Problem With Heterogeneous Graph Transformers

Advanced Intelligent Systems, EarlyView.
A heterogeneous graph transformer (HGT) is introduced for reinforcement learning‐based job shop scheduling by explicitly distinguishing precedence and machine‐contention relations through edge‐type‐specific attention. The proposed framework learns richer scheduling representations, improves decision quality over homogeneous graph models, and highlights
Bulent Soykan, Fatih Kasimoglu
wiley   +1 more source

Source signal sparsity enhancement based on local maximum synchronous extraction transform algorithm for mixed matrix estimation in UBSS. [PDF]

Sci Rep
Li X, Li Z, Yao R, Guo Y, Zhang X, Zhou G.   +5 more
europepmc   +1 more source

Uncovering renewable energy policy impact channels on land values, the local farm structure, and farmland heterogeneity

American Journal of Agricultural Economics, EarlyView.
Abstract Germany's Renewable Energy Sources Act (REA), enacted in 2000 and subsequently amended, subsidized national renewable energy production with fixed feed‐in tariffs for renewable energy sources (RE) from wind, solar, and biogas. Empirical studies suggest that the policy was creating windfall effects for landowners and attribute farmland use ...
Lars Isenhardt, Stefan Seifert, Saskia Wolff, Tobia Lakes, Marten Graubner, Axel Werwatz, Silke Hüttel   +6 more
wiley   +1 more source

GL-VSLAM: A General Lightweight Visual SLAM Approach for RGB-D and Stereo Cameras. [PDF]

Sensors (Basel)
Li X, Li T, Zhang Y, Li Z, Ban L, Ning Y.   +5 more
europepmc   +1 more source

Preferential trading in agriculture: New insights from a structural gravity analysis and machine learning

American Journal of Agricultural Economics, EarlyView.
Abstract Preferential trade agreements (PTAs) contain various non‐tariff provisions, yet identifying their trade effects remains challenging because these commitments are high‐dimensional and strongly correlated within agreements. We estimated a theory‐consistent structural gravity model with domestic flows for 26 agricultural subsectors over 1988–2017
Dongin Kim, Sandro Steinbach
wiley   +1 more source