Concrete Aggregate

Concrete aggregate research focuses on optimizing the properties and efficient use of the granular materials that comprise a significant portion of concrete. Current research employs machine learning techniques, including artificial neural networks and deep learning models with multi-scale feature extraction, to predict aggregate properties (e.g., size distribution, resistance to fragmentation) from images or ultrasonic data, streamlining quality control and potentially reducing material waste. These advancements aim to improve concrete production efficiency, reduce reliance on laboratory testing, and enhance the overall performance and sustainability of concrete structures. The development of novel semi-supervised learning methods further enhances the efficiency of these predictive models.

Papers

October 16, 2024

Explainable Artificial Intelligent (XAI) for Predicting Asphalt Concrete Stiffness and Rutting Resistance: Integrating Bailey's Aggregate Gradation Method
Warat Kongkitkul, Sompote Youwai, Siwipa Khamsoy, Manaswee Feungfung
Explainable Artificial Intelligence Resilience Measure Concrete Workability Asphalt Pavement Concrete Aggregate

October 2, 2023

Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learning
Debora Caldarola, Barbara Caputo, Marco Ciccone
Strong Generalization Heterogeneous Federated Learning Stable Learning Model Averaging Concrete Aggregate

May 18, 2023

Non-deterministic approximation operators: ultimate operators, semi-equilibrium semantics and aggregates (full version)
Jesse Heyninck, Bart Bogaerts
Feature Operator Logic Program Non Monotonic Stable Model Semantics Approximation Operator Concrete Aggregate Approximation Fixpoint Theory

February 12, 2023

Exploration of carbonate aggregates in road construction using ultrasonic and artificial intelligence approaches
Mohamed Abdelhedi, Rateb Jabbar, Chedly Abbes
Environment Exploration Artificial Intelligence Approach Road Infrastructure Material Domain Geotechnical Engineering Concrete Aggregate

April 10, 2022

ConsInstancy: Learning Instance Representations for Semi-Supervised Panoptic Segmentation of Concrete Aggregate Particles
Max Coenen, Tobias Schack, Dries Beyer, Christian Heipke, Michael Haist
Semantic Segmentation Deep Convolutional Neural Network Strong Consistency Panoptic Segmentation Consistency Regularization Semi Supervised Segmentation Instance Representation Concrete Aggregate Supervised Panoptic Segmentation

April 7, 2022

Learning to Sieve: Prediction of Grading Curves from Images of Concrete Aggregate
Max Coenen, Dries Beyer, Christian Heipke, Michael Haist
LeArning Abstract Human Prediction Concrete Workability Partial Credit Grading Bio Sieve Concrete Aggregate Particle Size

March 28, 2022

A Study of Reinforcement Learning Algorithms for Aggregates of Minimalistic Robots
Joshua Bloom, Apratim Mukherjee, Carlo Pinciroli
Deep Reinforcement Learning Non Humanoid Robot Robot Person Study Feature Coordinated Behavior Concrete Aggregate Minimalist Robot

Concrete Aggregate

Papers

Explainable Artificial Intelligent (XAI) for Predicting Asphalt Concrete Stiffness and Rutting Resistance: Integrating Bailey's Aggregate Gradation Method

Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learning

Non-deterministic approximation operators: ultimate operators, semi-equilibrium semantics and aggregates (full version)

Exploration of carbonate aggregates in road construction using ultrasonic and artificial intelligence approaches

ConsInstancy: Learning Instance Representations for Semi-Supervised Panoptic Segmentation of Concrete Aggregate Particles

Learning to Sieve: Prediction of Grading Curves from Images of Concrete Aggregate

A Study of Reinforcement Learning Algorithms for Aggregates of Minimalistic Robots