Advanced Intelligent Systems, EarlyView.This review explores the transformative impact of artificial intelligence on multiscale modeling in materials research. It highlights advancements such as machine learning force fields and graph neural networks, which enhance predictive capabilities while reducing computational costs in various applications.
Artem Maevskiy +2 more
wiley +1 more source
An AI-driven multi-objective framework for optimizing window dimensions considering energy demand and thermal comfort. [PDF]
Sci RepNasab SMRA, Rabiei H.
europepmc +1 more source
Optimizing 3D Bin Packing of Heterogeneous Objects Using Continuous Transformations in SE(3)
Advanced Intelligent Systems, EarlyView.This article presents a method for solving the three‐dimensional bin packing problem for heterogeneous objects using continuous rigid‐body transformations in SE(3). A heuristic optimization framework combines signed‐distance functions, neural network approximations, point‐cloud bin modeling, and physics simulation to ensure feasibility and stability ...
Michele Angelini, Marco Carricato
wiley +1 more source
On machine learning based QSPR analysis of amphetamine derivatives using regression models. [PDF]
Sci RepHanif MF +3 more
europepmc +1 more source
MusicSwarm: Biologically Inspired Intelligence for Music Composition
Advanced Intelligent Systems, EarlyView.Biologically inspired swarms of frozen foundation models self‐organize to compose complex music without fine‐tuning. By coordinating through stigmergic signals, decentralized agents dynamically evolve specialized roles and adapt to solve complex tasks.
Markus J. Buehler
wiley +1 more source
A cost-optimized medical digital twin framework for secure and efficient patient data management in smart healthcare. [PDF]
Sci RepAlotaibi FM +5 more
europepmc +1 more source
Comparing the Latent Features of Universal Machine‐Learning Interatomic Potentials
Advanced Intelligent Systems, EarlyView.This study quantitatively assesses how universal machine‐learning interatomic potentials encode the chemical space into latent features, showing unique model‐specific representations with high cross‐model reconstruction errors. It explores how training datasets, protocols, and targets affect these encodings.
Sofiia Chorna +5 more
wiley +1 more source
Performance Analysis and Coefficient Generation Method of Parallel Hammerstein Model Under Underdetermined Condition. [PDF]
Sensors (Basel)Hu N, Xiang Y, Li M, Li X, Tian J.
europepmc +1 more source
SiOx‐Based Probabilistic Bits Enabling Invertible Logic Gate for Cryptographic Applications
Advanced Intelligent Systems, EarlyView.To enable lightweight hardware encryption and decryption, a Ti/SiOx/Ti threshold switching device is engineered to generate controllable stochastic oscillations. By tuning the input voltage, the device produces a programmable spike probability governed by intrinsic switching dynamics, enabling probabilistic bits that construct an invertible ...
Jihyun Kim, Hyeonsik Choi, Jiyong Woo
wiley +1 more source
Development of Quince Peel Extract Loaded Chitosan/PVA-Based Edible Films for Food Coating. [PDF]
J Food SciYağmur N, Karkar B, Şahin S.
europepmc +1 more source