Results 71 to 80 of about 23,683 (254)

Shapley Additive Explanation for Local Class Differentiation: Local Explainability for Class Differentiation in Classification Models

Advanced Intelligent Systems, EarlyView.
An instance‐level, model‐agnostic explanation of class differentiation is introduced through SHAP‐LCD, linking probability shifts to feature‐wise Shapley contributions. The method operates on tabular and image data and is released in a fully reproducible implementation, offering a transparent way to examine, at each instance, why predictive models ...
Roxana M. Romero Luna, Hugo A. Ordoñez Erazo, Carlos A. Cobos Lozada   +2 more
wiley   +1 more source

Talk to Your Data: An Agentic Artificial Intelligence‐Driven Decision‐Support Framework for Prosumer Energy Optimization and Recommendations

Advanced Intelligent Systems, EarlyView.
An agentic AI‐driven decision‐support framework for prosumers is proposed, integrating PV generation, load profiling, and multihorizon optimization within a four‐agent architecture. The approach significantly reduces grid dependence, enhances self‐sufficiency and prevents system oversizing.
Adela BÂRA, Simona‐Vasilica OPREA
wiley   +1 more source

Application of Data Smoothing Method in Signal Processing for Vortex Flow Meters

ITM Web of Conferences, 2017
Vortex flow meter is typical flow measure equipment. Its measurement output signals can easily be impaired by environmental conditions. In order to obtain an improved estimate of the time-averaged velocity from the vortex flow meter, a signal filter ...
Zhang Jun, Zou Tian, Tian Chun-Lai
doaj   +1 more source

Idiopathic Intracranial Hypertension Is Characterized by a Distinct Proteomic Profile

Annals of Neurology, EarlyView.
Objectives The pathophysiology of idiopathic intracranial hypertension (IIH) is poorly understood and disease‐specific biomarkers are lacking. We aimed to shed light on IIH pathophysiology and identify disease‐specific biomarkers. Methods This prospective cross‐sectional cohort study included patients with new‐onset IIH and age‐, body mass index‐, and ...
Santosh D. Bhosale, Arkadiusz Nawrocki, Johanne J. Korsbæk, Nadja S. Hansen, Fabian Foettinger, Nik Krajnc, Mathias J. Norvig, Niclas L. Eriksen, Stefan Macher, Berthold Pemp, Connar S.J. Westgate, Christian B. Pedersen, Frantz R. Poulsen, Sune Munthe, Gabriel Bsteh, Martin R. Larsen, Rigmor H. Jensen, Dagmar Beier   +17 more
wiley   +1 more source

The state of NumPy

, 2014
The release of NumPy 1.9 a few days ago was a bit of a revelation for me. For the first time in the combined history of NumPy and its predecessor Numeric, a new release broke my own code so severely thatI don't see any obvious way to fix it, given the limited means I can dedicate to software maintenance.
openaire   +1 more source

Historical birth records from 1896 to 1944 from the Basel maternity hospital, Switzerland, reveal significant obstetric selection pressures

The Anatomical Record, EarlyView.
Abstract Maternal and neonatal morbidity and mortality have declined dramatically during the last century. Historical data are therefore important sources to study the evolutionary selection pressures related to childbirth and how they have fluctuated over time.
Mirella Woodert, Guillermo Bravo Morante, Viktoria A. Krenn, Cédric Cordey, Nicole Torres‐Tamayo, Kaspar Staub, Nicole M. Webb, Martin Haeusler   +7 more
wiley   +1 more source

Leveraging Big Multitemporal Multisource Satellite Data and Artificial Intelligence for the Detection of Complex and Invisible Features: The Case of Extensive Irrigation Mapping

Archaeological Prospection, EarlyView.
ABSTRACT The detection of buried or obscured archaeological features remains a central challenge in landscape archaeology, particularly in the irrigated floodplains of Mesopotamia where levees and canals formed the basis of complex agrarian systems. This study presents a deep learning–based approach for the large‐scale, automated detection of ancient ...
Nazarij Buławka, Hector A. Orengo, Felipe Lumbreras Ruiz, Iban Berganzo‐Besga, Ekta Gupta   +4 more
wiley   +1 more source

StarPSO: A Unified Framework for Particle Swarm Optimization Across Multiple Problem Types

Journal of Open Research Software
StarPSO is an open source, object-oriented, Python library designed to implement various particle swarm optimization (PSO) algorithms, including: (i) StandardPSO, (ii) BinaryPSO, (iii) IntegerPSO, (iv) QuantumPSO, (v) CategoricalPSO, (vi) BareBonesPSO ...
Michail D. Vrettas, Stefano Silvestri
doaj   +1 more source

Potassium hydroxide activation of microalgal biochar for improved adsorption efficiency

Biofuels, Bioproducts and Biorefining, EarlyView.
Abstract Activated carbon was prepared from Chlorella by carbonization and potassium hydroxide activation, and its structural properties and methylene blue (MB) adsorption performance were evaluated. Raw Chlorella exhibited an adsorption capacity of 287.2 mg g−1, which decreased to 214.8 mg g−1 after carbonization.
Keito Kubota, Numan Luthfi, Takashi Fukushima, Kenji Takisawa   +3 more
wiley   +1 more source

PySTRA: Python structural reliability analysis

SoftwareX
Structural reliability methods enable probabilistic analysis and design of structures. Furthermore, these methods are essential for the calibration of structural design codes.
Colin Caprani, Mohammad Shihabuddin Khan, Jürgen Hackl   +2 more
doaj   +1 more source