Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
M4SFWD: A Multi-Faceted synthetic dataset for remote sensing forest wildfires detection
Expert Systems with Applications: An International Journal (EXWA), Volume 248, Issue CAug 2024https://doi.org/10.1016/j.eswa.2024.123489AbstractForest wildfires are one of the most catastrophic natural disasters, which poses a severe threat to both the ecosystem and human life. Therefore, it is imperative to implement technology to prevent and control forest wildfires. The combination of ...
- ArticleJuly 2024
Reduced Simulations for High-Energy Physics, a Middle Ground for Data-Driven Physics Research
AbstractSubatomic particle track reconstruction (tracking) is a vital task in High-Energy Physics experiments. Tracking is exceptionally computationally challenging and fielded solutions, relying on traditional algorithms, do not scale linearly. Machine ...
- research-articleJuly 2024
Fractal interpolation in the context of prediction accuracy optimization
Engineering Applications of Artificial Intelligence (EAAI), Volume 133, Issue PDJul 2024https://doi.org/10.1016/j.engappai.2024.108380AbstractThis paper focuses on the hypothesis of optimizing time series predictions using fractal interpolation techniques. In general, the accuracy of machine learning model predictions is closely related to the quality and quantitative aspects of the ...
- surveyJune 2024
Synthetic Data for Deep Learning in Computer Vision & Medical Imaging: A Means to Reduce Data Bias
ACM Computing Surveys (CSUR), Volume 56, Issue 11Article No.: 271, Pages 1–37https://doi.org/10.1145/3663759Deep-learning (DL) performs well in computer-vision and medical-imaging automated decision-making applications. A bottleneck of DL stems from the large amount of labelled data required to train accurate models that generalise well. Data scarcity and ...
- research-articleJuly 2024
Exploring unseen 3D scenarios of physics variables using machine learning-based synthetic data: An application to wave energy converters
Environmental Modelling & Software (ENMS), Volume 177, Issue CJun 2024https://doi.org/10.1016/j.envsoft.2024.106051AbstractThis work uses machine learning to produce synthetic data of wave energy converters from time-expensive 3D simulations based on computational fluid dynamics models. The simulations to analyse the response of these systems to incoming waves are ...
Highlights- We propose a surrogate model for Wave Energy Converters Computational Fluid Dynamics.
- Generative models are used to create unseen scenarios of velocity and dynamic viscosity responses.
- Two different generative models are employed ...
-
- ArticleMay 2024
Text-Driven Data Augmentation Tool for Synthetic Bird Behavioural Generation
Bioinspired Systems for Translational Applications: From Robotics to Social EngineeringMay 2024, Pages 75–84https://doi.org/10.1007/978-3-031-61137-7_8AbstractEnvironmental conservation and biodiversity monitoring efforts have been greatly enhanced by the use of deep learning and computer vision technologies, particularly in protected areas such as parks and wildlife reserves. However, the development ...
- research-articleMay 2024
A review of deep learning and Generative Adversarial Networks applications in medical image analysis
AbstractNowadays, computer-aided decision support systems (CADs) for the analysis of images have been a perennial technique in the medical imaging field. In CADs, deep learning algorithms are widely used to perform tasks like classification, ...
- research-articleMay 2024JUST ACCEPTED
Generating and Evaluating Data of Daily Activities with an Autonomous Agent in a Virtual Smart Home
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Just Accepted https://doi.org/10.1145/3665331Training machine learning models to identify human behavior is a difficult yet essential task to develop autonomous and adaptive systems such as smart homes. These models require large and diversified amounts of labeled data to be trained effectively. Due ...
- research-articleApril 2024JUST ACCEPTED
GANs in the Panorama of Synthetic Data Generation Methods: Application and Evaluation: Enhancing Fake News Detection with GAN-Generated Synthetic Data
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Just Accepted https://doi.org/10.1145/3657294This paper focuses on the creation and evaluation of synthetic data to address the challenges of imbalanced datasets in machine learning applications (ML), using fake news detection as a case study. We conducted a thorough literature review on generative ...
- research-articleJuly 2024
SYNDSURV: A simple framework for survival analysis with data distributed across multiple institutions
Computers in Biology and Medicine (CBIM), Volume 172, Issue CApr 2024https://doi.org/10.1016/j.compbiomed.2024.108288AbstractData sharing among different institutions represents one of the major challenges in developing distributed machine learning approaches, especially when data is sensitive, such as in medical applications. Federated learning is a possible solution, ...
Highlights- Survival analysis prediction with a distributed learning framework.
- Synthetic time-to-event data generation through generative Bayesian Network.
- Privacy-preserving distributed learning for patients’ clinical data.
- Alternative ...
- research-articleMarch 2024
Terrain traversability prediction through self-supervised learning and unsupervised domain adaptation on synthetic data
- Giuseppe Vecchio,
- Simone Palazzo,
- Dario C. Guastella,
- Daniela Giordano,
- Giovanni Muscato,
- Concetto Spampinato
AbstractTerrain traversability estimation is a fundamental task for supporting robot navigation on uneven surfaces. Recent learning-based approaches for predicting traversability from RGB images have shown promising results, but require manual annotation ...
- research-articleJuly 2024
Data-efficient 3D instance segmentation by transferring knowledge from synthetic scans
Pattern Recognition Letters (PTRL), Volume 179, Issue CMar 2024, Pages 151–157https://doi.org/10.1016/j.patrec.2024.02.001AbstractThe 3D comprehension ability of indoor environments is critical for robots. While deep learning-based methods have improved performance, they require significant amounts of annotated training data. Nevertheless, the cost of scanning and ...
Highlights- Three synthetic point cloud datasets are created, each 10x larger than real data.
- Learning from synthetic data reduces reliance on annotated real data.
- Domain discrepancies affect the transfer of knowledge from synthetic to real ...
- research-articleApril 2024
Generation of probabilistic synthetic data for serious games: A case study on cyberbullying
Knowledge-Based Systems (KNBS), Volume 286, Issue CFeb 2024https://doi.org/10.1016/j.knosys.2024.111440AbstractSynthetic data generation has been a growing area of research in recent years. However, its potential applications in serious games have yet to be thoroughly explored. Advances in this field could anticipate data modeling and analysis, as well as ...
Highlights- Simulator tailored for generating synthetic data in decision-based serious games.
- Modular architecture to easily fit other serious games and decision making scenarios.
- We use Bayesian networks to combine expert knowledge and data ...
- research-articleFebruary 2024
Same-clothes person re-identification with dual-stream network
AbstractPerson re-identification (Re-ID) has long been a pressing challenge in the field of computer vision, with researchers primarily focusing on issues such as occlusion, clothing changes, and cross-modality scenarios. However, there has been a lack of ...
- research-articleJuly 2024
NOVAction23: Addressing the data diversity gap by uniquely generated synthetic sequences for real-world human action recognition
Computers and Graphics (CGRS), Volume 118, Issue CFeb 2024, Pages 1–10https://doi.org/10.1016/j.cag.2023.10.011AbstractRecognition of human actions using machine learning requires extensive datasets to develop robust models. Nevertheless, obtaining real-world data presents challenges due to the costly and time-consuming process involved. Additionally, existing ...
Graphical abstractDisplay Omitted
Highlights- NOVAction engine automatically generates massively diverse human action data.
- NOVAction23, created by NOVAction, novel dataset of human action data.
- Features 25,415 unique synthetic human action sequences with poses and labels.
- research-articleFebruary 2024
Digital twin for autonomous collaborative robot by using synthetic data and reinforcement learning
Robotics and Computer-Integrated Manufacturing (RCIM), Volume 85, Issue CFeb 2024https://doi.org/10.1016/j.rcim.2023.102632AbstractTraining robots in real-world environments can be challenging due to time and cost constraints. To overcome these limitations, robots can be trained in virtual environments using Reinforcement Learning (RL). However, this approach ...
Highlights- The increasing usage of robots cause the increase of programming time to adapt the arbitrary shapes of new products.
- research-articleJanuary 2024
A review of adaptable conventional image processing pipelines and deep learning on limited datasets
Machine Vision and Applications (MVAA), Volume 35, Issue 2Mar 2024https://doi.org/10.1007/s00138-023-01501-3AbstractThe objective of this paper is to study the impact of limited datasets on deep learning techniques and conventional methods in semantic image segmentation and to conduct a comparative analysis in order to determine the optimal scenario for ...
- research-articleMarch 2024
ITF-GAN: Synthetic time series dataset generation and manipulation by interpretable features
Knowledge-Based Systems (KNBS), Volume 283, Issue CJan 2024https://doi.org/10.1016/j.knosys.2023.111131AbstractMachine Learning methods require a huge amount of data to train. Real world constraints and missing labels hinder the assimilation of large data sets and therefore limit these methods. A common applied solution is the generation of synthetic ...
Highlights- Novel conditional residual autoencoder method to extract functions and patterns.
- Synthetic time series data generation by manipulating latent features.
- Time series GAN method to generate interpretable features for synthetic data.
- research-articleJuly 2024
Gradient Boosting classifier performance evaluation using Generative Adversarial Networks
Procedia Computer Science (PROCS), Volume 235, Issue C2024, Pages 3016–3024https://doi.org/10.1016/j.procs.2024.04.285AbstractIncreasing amount of cyber-attacks in past few years have necessitated the development of automatic threat detection systems for ensuring network and data security. Such automated threat detection models for handling cyber threats are subjected to ...
- research-articleApril 2024
Improving mixed-integer temporal modeling by generating synthetic data using conditional generative adversarial networks: A case study of fluid overload prediction in the intensive care unit
Computers in Biology and Medicine (CBIM), Volume 168, Issue CJan 2024https://doi.org/10.1016/j.compbiomed.2023.107749Abstract ObjectiveThe challenge of mixed-integer temporal data, which is particularly prominent for medication use in the critically ill, limits the performance of predictive models. The purpose of this evaluation was to pilot test integrating synthetic ...
Graphical abstractDisplay Omitted
Highlights- Addresses gap in modeling mixed-integer temporal data for ICU medication.
- Novel application of synthetic data integration to ICU medication data.
- Uses synthetic data to enhance the model's performance of fluid overload prediction.