On Scene Engineering and Domain Randomization: Synthetic Data for Industrial Item Picking

Weisenböhler, Moritz; Hein, Björn; Wurll, Christian

doi:10.1007/978-3-031-22216-0_43

Cited by 2 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By using a simulation model, researchers can generate large amounts of synthetic data that are representative of the real-world population, while also controlling for important variables such as age, gender, and disease state. Multimodality and multidimensionality are important characteristics of modern data [12,13]. Multimodality refers to the presence of multiple sources of information within a single dataset [14].…”

Section: Introductionmentioning

confidence: 99%

Synthetic Generation of Multidimensional Data to Improve Classification Model Validity

Al-Qerem

Ali

Attar

et al. 2023

J. Data and Information Quality

View full text Add to dashboard Cite

This paper aims to compare Generative Adversarial Network (GAN) models and feature selection methods for generating synthetic data in order to improve the validity of a classification model. The synthetic data generation technique involves generating new data samples from existing data to increase the diversity of the data and help the model generalize better. The multidimensional aspect of the data refers to the fact that it can have multiple features or variables that describe it. The GAN models have proven to be effective in preserving the statistical properties of the original data. However, the order of data augmentation and feature selection is crucial to build robust and accurate predictive models. By comparing the different GAN models with feature selection methods on multi-dimensional datasets, this paper aims to determine the best combination to support the validity of a classification model in multidimensional Data

show abstract

Section: Introductionmentioning

confidence: 99%