Related references
Note: Only part of the references are listed.
Article
Engineering, Mechanical
Zohreh Mousavi et al.
Summary: This study proposes a novel vibration-based method for damage detection of real systems using Dictionary Learning (DL) based on a FE model and real intact state under different uncertainties. The method is validated using real measurements from an experimental offshore jacket model, and the results show higher accuracy in the case of changing working load.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
JoonHo Lee et al.
Summary: Unsupervised domain adaptation (UDA) aims to improve prediction performance in the target domain by minimizing the divergence between the source and target domains. This paper proposes a novel UDA method, called Model Uncertainty-based UDA (MUDA), which learns domain-invariant features to minimize domain divergence. MUDA utilizes a Bayesian framework and Monte Carlo dropout sampling to evaluate model uncertainty. Experimental results on image recognition tasks demonstrate the superiority of MUDA over existing state-of-the-art methods. MUDA is also extended to multi-source domain adaptation problems.
Article
Mathematics
Konstantinos Poulinakis et al.
Summary: This study compares machine-learning methods and cubic splines on their ability to handle sparse and noisy training data. The results show that cubic splines provide more precise interpolation than deep neural networks and multivariate adaptive regression splines with very sparse data. However, machine-learning models show robustness to noise and can outperform splines after reaching a threshold of training data. The study aims to provide a general framework for interpolating one-dimensional signals, often obtained from complex scientific simulations or laboratory experiments.
Article
Computer Science, Artificial Intelligence
JoonHo Lee et al.
Summary: In this paper, a novel source-free unsupervised domain adaptation (UDA) method is proposed, which only uses a pre-trained source model and unlabeled target images for training. The method captures aleatoric uncertainty through data augmentation and trains the feature generator with two consistency objectives to improve the robustness of the adapted model to image perturbations. Experimental results on popular UDA benchmark datasets demonstrate that the proposed method is comparable or even superior to vanilla UDA methods.
Article
Chemistry, Multidisciplinary
Tamas Orosz et al.
Summary: In recent years, many machine learning-based document processing applications have been developed, which can reduce costs and reshape company structures. These applications can replace trainees, allowing experts to focus on higher-value tasks and foster innovation. However, the development cost of these methods is often high and not straightforward. This paper presents a survey that compares a machine learning-based legal text labeler with individuals possessing legal domain knowledge. The results show the effectiveness and accuracy of the machine learning system and highlight the potential for increased discoverability and value enrichment.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Electrical & Electronic
Congming Shi et al.
Summary: Clustering, a traditional machine learning method, often relies on a predetermined exact number of clusters which may not be practical in real-world scenarios where the number of clusters is unpredictable. A new elbow point discriminant method is proposed to estimate the optimal cluster number using statistical metrics. Experimental results demonstrate that this method outperforms the widely used Silhouette method in determining the optimal cluster number.
EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING
(2021)
Article
Chemistry, Analytical
Emmanuel Pintelas et al.
Summary: The study introduces a novel approach using a convolutional autoencoder topological model to address the issue of noise and redundant information affecting deep learning models, leading to a significant performance improvement by compressing and filtering initial high-dimensional input images.
Article
Biochemical Research Methods
Ziheng Zou et al.
Summary: HGC is a fast Hierarchical Graph-based Clustering tool that addresses the issues of fixed number of clusters and lack of hierarchical information in single-cell data clustering. Experiments demonstrate that HGC enables multiresolution exploration of biological hierarchy, achieves state-of-the-art accuracy on benchmark data, and is capable of scaling to large datasets.
Article
Physics, Multidisciplinary
Meshal Shutaywi et al.
Summary: Grouping objects based on similarities is crucial in machine learning, with k-means and kernel k-means being popular clustering methods. This study extends previous work by introducing a weighted majority voting method based on NMI, and proposing an unsupervised weighting function based on the Silhouette index to improve clustering without the need for a training set.
Article
Mathematics, Interdisciplinary Applications
Volodymyr Melnykov et al.
JOURNAL OF CLASSIFICATION
(2020)
Article
Computer Science, Artificial Intelligence
Alfredo Vellido
NEURAL COMPUTING & APPLICATIONS
(2020)
Review
Computer Science, Information Systems
Mohiuddin Ahmed et al.
Proceedings Paper
Computer Science, Hardware & Architecture
Maciej Besta et al.
2020 IEEE 34TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM IPDPS 2020
(2020)
Review
Mathematics, Interdisciplinary Applications
Michael Frank et al.
Article
Multidisciplinary Sciences
Dmitry Krotov et al.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2019)
Article
Biochemical Research Methods
Z. Mousavi et al.
JOURNAL OF NEUROSCIENCE METHODS
(2019)
Article
Computer Science, Artificial Intelligence
Pasi Franti et al.
PATTERN RECOGNITION
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Daniel Ting
KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING
(2018)
Review
Computer Science, Artificial Intelligence
Fionn Murtagh et al.
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY
(2012)
Article
Biochemical Research Methods
Eun-Youn Kim et al.
BMC BIOINFORMATICS
(2009)
Article
Computer Science, Software Engineering
S Har-Peled et al.
