Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Arunabha M. Roy et al.
Summary: In order to address the deficiencies of existing DL-based damage detection models in complex and noisy environments, the authors propose a real-time high-performance damage detection model called DenseSPH-YOLOv5. By integrating DenseNet blocks with the backbone and implementing convolutional block attention modules (CBAM), the model achieves superior deep spatial feature extraction in challenging environments. Additional feature fusion layers and a Swin-Transformer Prediction Head (SPH) are also added to improve the efficiency of multi-scale object detection and reduce computational complexity.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Biology
Sonain Jamil et al.
Summary: This study proposes a new high-performance valvular heart disease (VHD) detection framework based on deep learning, which is relatively simple in terms of network structures but can accurately detect multiple VHDs. Both 1D and 2D PCG signals are used, and nature/bio-inspired algorithms are utilized for feature selection. The results show that the ViT model achieves the best performance among all classifiers, surpassing current state-of-the-art VHD classification models.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Engineering, Biomedical
Najwa Kouka et al.
Summary: This study presents a channel selection method based on a new Binary Many-Objective Particle Swarm Optimization with Cooperative Agents (BMaOPSO-CA), which performs unsupervised feature learning from clean EEG signals to recognize human emotions. Extensive validation on three different public benchmarks was conducted, highlighting the optimal electrode locations related to emotions and analyzing the relationship between specific brain regions and emotions.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Review
Automation & Control Systems
Albino Lopes D'Almeida et al.
Summary: The use of digital and artificial intelligence technologies has positively impacted the oil industry, particularly in drilling and production operations. Digital transformation has provided solutions for stuck pipes and hydrate formation, utilizing computational and AI techniques to enhance control and prediction in oil wells.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Operations Research & Management Science
Arnaud Flori et al.
Summary: This paper proposes a new algorithm called QUAntum Particle Swarm Optimization (QUAPSO) based on quantum superposition and inspired by the Kangaroo Algorithm to simplify the settings and improve the local search efficiency of PSO. Experimental results demonstrate that QUAPSO outperforms six well-known algorithms on a set of 30 test functions.
COMPUTATIONAL OPTIMIZATION AND APPLICATIONS
(2022)
Article
Energy & Fuels
Farouk Said Boukredera et al.
Summary: This paper presents the torsional dynamics of the drill string using lumped parameter modeling and continuous measurement of drill pipe properties. The model considers mechanical properties as variables for each drilled stand and employs a rock bit interactions model. Field data is used to validate the model and confirm the existence of drill string vibrations.
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME
(2022)
Article
Automation & Control Systems
Chenhui Zhou et al.
Summary: This article extends the framework of iterative learning control in discrete linear time-invariant systems, aiming to minimize energy consumption while maintaining tracking accuracy. The multiobjective problem is divided into two subproblems and solved using an iterative algorithm. Model uncertainty and constrained systems are also considered. The effectiveness of the proposed algorithm is validated through experiments.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2022)
Article
Computer Science, Artificial Intelligence
Bo Jiang et al.
Summary: The problem of multiple graph learning involves learning consistent representation by exploiting the complementary information of multiple graphs. This paper proposes a novel learning framework, called Multiple Graph Learning Neural Networks (MGLNN), which aims to learn an optimal graph structure from multiple graph structures and integrate multiple graph learning and Graph Neural Networks' representation. Experimental results demonstrate that MGLNN outperforms other methods on semi-supervised classification tasks.
Article
Computer Science, Information Systems
Sundaram B. Pandya et al.
Summary: This study proposes a techno-economic investigation into single- and multi-objective optimal power flow problems, coordinating with renewable energy sources such as wind, PV, and small hydropower. Different probability density functions are used to predict the required power, and a recently reported equilibrium optimizer is considered for handling the problems. The results show that the suggested algorithm can find better optimal solutions with faster convergence and well distributed optimal Pareto front for multi-objective problems.
Article
Computer Science, Interdisciplinary Applications
Mohamed Riad Youcefi et al.
EARTH SCIENCE INFORMATICS
(2020)
Article
Energy & Fuels
Chiranth Hegde et al.
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
(2019)
Article
Energy & Fuels
Mohammed F. Al Dushaishi et al.
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME
(2018)
Article
Engineering, Geological
Yaneng Zhou et al.
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES
(2017)
Article
Computer Science, Interdisciplinary Applications
Juing-Shian Chiou et al.
SIMULATION MODELLING PRACTICE AND THEORY
(2012)
Article
Energy & Fuels
Ahmet S. Yigit et al.
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME
(2006)
Article
Energy & Fuels
JCR Plácido et al.
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME
(2002)
