Convex Relaxations for Mixed-Integer Nonlinear Programs
ISBN:978-3-95404-474 ...
openaire +3 more sources
STELLAR‐CB: Synthetic Temporal LSTM for Livestock Activity Recognition—Cow Behaviour
This study introduces a novel framework combining LSTM networks with SMOTE to address class imbalance in precision livestock farming. It improves the detection of rare behaviours in livestock, achieving state‐of‐the‐art performance while reducing computational overhead, offering a practical, breed‐agnostic solution for enhancing automated behaviour ...
Ghufran Ahmed +9 more
wiley +1 more source
Abstract “L'eau c'est la vie” is a well‐known French expression for “water is life,” which reflects the fact that water is undoubtedly the most vital resource in the world. The main mission for water utility companies is to convey and distribute water that is of acceptable quality to satisfy the demand of the population at any time of the day.
Franklin Djeumou Fomeni +4 more
wiley +1 more source
Gas network value chain optimization considering compressor capacity constraints. [PDF]
Qiu J, Zhao L, Ning X, Yu D.
europepmc +1 more source
Diffusion–Model–Driven Discovery of Ferroelectrics for Photocurrent Applications
We developed a diffusion model–based generative AI and high‐throughput screening framework that accelerates the discovery of photovoltaic ferroelectrics. By coupling AI driven crystal generation with machine learning and DFT screening, we identified Ca3P2 and LiCdP as new ferroelectric materials exhibiting strong polarization, feasible switching ...
Byung Chul Yeo +3 more
wiley +1 more source
Data-driven acceleration of mixed-integer bilinear programs: a comparative study for robot motion planning. [PDF]
Lin X.
europepmc +1 more source
Optimal exact designs of experiments via Mixed Integer Nonlinear Programming
B. Duarte, J. Granjo, W. Wong
semanticscholar +1 more source
Graph‐based imitation and reinforcement learning for efficient Benders decomposition
Abstract This work introduces an end‐to‐end graph‐based agent for accelerating the computational efficiency of Benders Decomposition. The agent's policy is parameterized by a graph neural network, which takes as input a bipartite graph representation of the master problem and proposes a candidate solution.
Bernard T. Agyeman +3 more
wiley +1 more source
Identifying outstanding units in centralized systems: A DEA approach. [PDF]
Cheraghali Z, Rostamy-Malkhalifeh M.
europepmc +1 more source
Convexification and Global Optimization in Continuous and Mixed-Integer Nonlinear Programming
Mohit Tawarmalani, N. Sahinidis
semanticscholar +1 more source

