Results 161 to 170 of about 172,371 (266)

Uncertainty Calibration in Molecular Machine Learning: Comparing Evidential and Ensemble Approaches

Chemistry – A European Journal, EarlyView.
ABSTRACT Machine learning (ML) models are increasingly used in quantum chemistry, but their reliability hinges on uncertainty quantification (UQ). In this study, we compare two prominent UQ paradigms—deep evidential regression (DER) and deep ensembles—on the QM9 and WS22 datasets, with a specific emphasis on the role of post hoc calibration.
Bidhan Chandra Garain, Max Pinheiro Jr., Matheus de Oliveira Bispo, Mario Barbatti   +3 more
wiley   +1 more source

Optimization of Communication Signal Adversarial Examples by Selectively Preserving Low-Frequency Components of Perturbations. [PDF]

Sensors (Basel)
Zhang Y, Wang L, Wang X, Shi D, Bai J.
europepmc   +1 more source

Practice Insight: Adapting Peacebuilding Dialogue Methodologies to City‐Resident Relations and Inclusive Policymaking in Calgary, Canada

Conflict Resolution Quarterly, EarlyView.
ABSTRACT This case study presents a project in which peacebuilding dialogue methodologies were adapted for use in municipal‐level dialogue sessions that took place in Calgary, Canada in late 2022 and early 2023. The authors found that using this approach built trust among cross‐sectoral participants and facilitators, resulted in greater diversity ...
Aleem Bharwani, Josh Nadeau
wiley   +1 more source

Translational symmetry in convolutions with localized kernels causes an implicit bias toward high frequency adversarial examples. [PDF]

Front Comput Neurosci
Caro JO, Ju Y, Pyle R, Dey S, Brendel W, Anselmi F, Patel AB.   +6 more
europepmc   +1 more source

Real‐time monitoring of tunnel structures using digital twin and artificial intelligence: A short overview

Deep Underground Science and Engineering, EarlyView.
How artificial intelligence (AI) and digital twin (DT) technologies are revolutionizing tunnel surveillance, offering proactive maintenance strategies and enhanced safety protocols. It explores AI's analytical power and DT's virtual replicas of infrastructure, emphasizing their role in optimizing maintenance and safety in tunnel management.
Mohammad Afrazi, Danial Jahed Armaghani, Hossein Afrazi, Hadi Fattahi, Pijush Samui   +4 more
wiley   +1 more source

Sustainable Live Sound Monitoring and Classification System Enabled by a Triboelectric Nanogenerator and Machine Learning Techniques

ENERGY &ENVIRONMENTAL MATERIALS, EarlyView.
A high‐performance Triboelectric Nanogenerator (TENG) acoustic sensor using polyimine/graphite polypropylene (PI/GP) was developed for real‐time, sustainable sound monitoring and classification. The self‐powered device delivers 25.67 μW output power, 92.7% accuracy with MobileNet V1, and powers a wireless transmission circuit, demonstrating dual ...
Majid Haji Bagheri, Araz Rajabi‐Abhari, Owen Gibbs, Pengcheng Xi, Asif Abdullah Khan, Fangzheng Huang, Md Soyaeb Hassan, Ning Yan, Dayan Ban   +8 more
wiley   +1 more source

Power Relations in the Preparation of the Nondiscrimination Act: The Controversial Issue of Supervising Discrimination in Working Life

European Policy Analysis, EarlyView.
ABSTRACT In the context of Europeanisation and neo‐corporatism, we examine the lengthy process of revising the Nondiscrimination Act in Finland, spanning from 2007 to 2023. The focus is on the mandate of the Nondiscrimination Ombudsman in the workplace and on explaining the sudden policy change of strengthening it after a prolonged standstill.
Laura Jauhola, Kati Rantala
wiley   +1 more source

On the Applicability of the Advocacy Coalition Framework for Analyzing EU Policy Processes

European Policy Analysis, EarlyView.
ABSTRACT Initially developed for the US context, the Advocacy Coalition Framework (ACF) is increasingly used to analyze policy processes in the EU. But policymaking in EU differs from the US context, why the applicability of ACF in the EU context should be scrutinized.
Fredrik von Malmborg
wiley   +1 more source

AI‐based localization of the epileptogenic zone using intracranial EEG

Epilepsia Open, EarlyView.
Abstract Artificial intelligence (AI) is rapidly transforming our lives. Machine learning (ML) enables computers to learn from data and make decisions without explicit instructions. Deep learning (DL), a subset of ML, uses multiple layers of neural networks to recognize complex patterns in large datasets through end‐to‐end learning.
Atsuro Daida, Yipeng Zhang, Sotaro Kanai, Richard Staba, Vwani Roychowdhury, Hiroki Nariai   +5 more
wiley   +1 more source

Neural Network Models for Solar Irradiance Forecasting in Polluted Areas: A Comparative Study

Energy Science &Engineering, EarlyView.
Pollution‐aware hybrid ensemble model is proposed to forecast solar irradiance across eight diverse cities. The model integrates MLP, RNN, and NARX to handle varying atmospheric pollution levels. The model outperforms state‐of‐the‐art methods with enhanced accuracy and interpretability on standard solar irradiance data set.
Mujtaba Ali, Muhammad Yaqoob Javed, Aamer Bilal Asghar, Khurram Hashmi, Abbas Javed, Basem Alamri, Krzysztof Ejsmont   +6 more
wiley   +1 more source