BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks
<jats:title>Abstract</jats:title> <jats:p>In this paper, we present “BIKED,” a dataset comprised of 4500 individually designed bicycle models sourced from hundreds of designers. We expect BIKED to enable a variety of data-driven design applications for bicycles and...
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
ASME International
2023
|
Online Access: | https://hdl.handle.net/1721.1/150664 |
_version_ | 1811074220307775488 |
---|---|
author | Regenwetter, Lyle Curry, Brent Ahmed, Faez |
author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Regenwetter, Lyle Curry, Brent Ahmed, Faez |
author_sort | Regenwetter, Lyle |
collection | MIT |
description | <jats:title>Abstract</jats:title>
<jats:p>In this paper, we present “BIKED,” a dataset comprised of 4500 individually designed bicycle models sourced from hundreds of designers. We expect BIKED to enable a variety of data-driven design applications for bicycles and support the development of data-driven design methods. The dataset is comprised of a variety of design information including assembly images, component images, numerical design parameters, and class labels. In this paper, we first discuss the processing of the dataset, then highlight some prominent research questions that BIKED can help address. Of these questions, we further explore the following in detail: 1) How can we explore, understand, and visualize the current design space of bicycles and utilize this information? We apply unsupervised embedding methods to study the design space and identify key takeaways from this analysis. 2) When designing bikes using algorithms, under what conditions can machines understand the design of a given bike? We train a multitude of classifiers to understand designs, then examine the behavior of these classifiers through confusion matrices and permutation-based interpretability analysis. 3) Can machines learn to synthesize new bicycle designs by studying existing ones? We test Variational Autoencoders on random generation, interpolation, and extrapolation tasks after training on BIKED data. The dataset and code are available at http://decode.mit.edu/projects/biked/</jats:p> |
first_indexed | 2024-09-23T09:45:51Z |
format | Article |
id | mit-1721.1/150664 |
institution | Massachusetts Institute of Technology |
language | English |
last_indexed | 2024-09-23T09:45:51Z |
publishDate | 2023 |
publisher | ASME International |
record_format | dspace |
spelling | mit-1721.1/1506642023-05-12T03:43:14Z BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks Regenwetter, Lyle Curry, Brent Ahmed, Faez Massachusetts Institute of Technology. Department of Mechanical Engineering <jats:title>Abstract</jats:title> <jats:p>In this paper, we present “BIKED,” a dataset comprised of 4500 individually designed bicycle models sourced from hundreds of designers. We expect BIKED to enable a variety of data-driven design applications for bicycles and support the development of data-driven design methods. The dataset is comprised of a variety of design information including assembly images, component images, numerical design parameters, and class labels. In this paper, we first discuss the processing of the dataset, then highlight some prominent research questions that BIKED can help address. Of these questions, we further explore the following in detail: 1) How can we explore, understand, and visualize the current design space of bicycles and utilize this information? We apply unsupervised embedding methods to study the design space and identify key takeaways from this analysis. 2) When designing bikes using algorithms, under what conditions can machines understand the design of a given bike? We train a multitude of classifiers to understand designs, then examine the behavior of these classifiers through confusion matrices and permutation-based interpretability analysis. 3) Can machines learn to synthesize new bicycle designs by studying existing ones? We test Variational Autoencoders on random generation, interpolation, and extrapolation tasks after training on BIKED data. The dataset and code are available at http://decode.mit.edu/projects/biked/</jats:p> 2023-05-11T19:40:21Z 2023-05-11T19:40:21Z 2021 2023-05-11T19:37:40Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/150664 Regenwetter, Lyle, Curry, Brent and Ahmed, Faez. 2021. "BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks." Journal of Mechanical Design, 144 (3). en 10.1115/1.4052585 Journal of Mechanical Design Creative Commons Attribution-Noncommercial-Share Alike https://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf ASME International MIT web |
spellingShingle | Regenwetter, Lyle Curry, Brent Ahmed, Faez BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks |
title | BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks |
title_full | BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks |
title_fullStr | BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks |
title_full_unstemmed | BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks |
title_short | BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarks |
title_sort | biked a dataset for computational bicycle design with machine learning benchmarks |
url | https://hdl.handle.net/1721.1/150664 |
work_keys_str_mv | AT regenwetterlyle bikedadatasetforcomputationalbicycledesignwithmachinelearningbenchmarks AT currybrent bikedadatasetforcomputationalbicycledesignwithmachinelearningbenchmarks AT ahmedfaez bikedadatasetforcomputationalbicycledesignwithmachinelearningbenchmarks |