Gait-Based Hand Load Estimation via Deep Latent Variable Models with Auxiliary Information Article Swipe
Jingyi Gao
,
Sol Lim
,
Seokhyun Chung
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2507.05544
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2507.05544
Machine learning methods are increasingly applied to ergonomic risk assessment in manual material handling, particularly for estimating carried load from gait motion data collected from wearable sensors. However, existing approaches often rely on direct mappings from loaded gait to hand load, limiting generalization and predictive accuracy. In this study, we propose an enhanced load estimation framework that incorporates auxiliary information, including baseline gait patterns during unloaded walking and carrying style. While baseline gait can be automatically captured by wearable sensors and is thus readily available at inference time, carrying style typically requires manual labeling and is often unavailable during deployment. Our model integrates deep latent variable modeling with temporal convolutional networks and bi-directional cross-attention to capture gait dynamics and fuse loaded and unloaded gait patterns. Guided by domain knowledge, the model is designed to estimate load magnitude conditioned on carrying style, while eliminating the need for carrying style labels at inference time. Experiments using real-world data collected from inertial measurement units attached to participants demonstrate substantial accuracy gains from incorporating auxiliary information and highlight the importance of explicit fusion mechanisms over naive feature concatenation.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2507.05544
- https://arxiv.org/pdf/2507.05544
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4416060397
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4416060397Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2507.05544Digital Object Identifier
- Title
-
Gait-Based Hand Load Estimation via Deep Latent Variable Models with Auxiliary InformationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-07-08Full publication date if available
- Authors
-
Jingyi Gao, Sol Lim, Seokhyun ChungList of authors in order
- Landing page
-
https://arxiv.org/abs/2507.05544Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2507.05544Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2507.05544Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4416060397 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2507.05544 |
| ids.doi | https://doi.org/10.48550/arxiv.2507.05544 |
| ids.openalex | https://openalex.org/W4416060397 |
| fwci | |
| type | preprint |
| title | Gait-Based Hand Load Estimation via Deep Latent Variable Models with Auxiliary Information |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2507.05544 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2507.05544 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2507.05544 |
| locations[1].id | doi:10.48550/arxiv.2507.05544 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2507.05544 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100362392 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-5484-5541 |
| authorships[0].author.display_name | Jingyi Gao |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Gao, Jingyi |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5089829375 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5569-9312 |
| authorships[1].author.display_name | Sol Lim |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lim, Sol |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5045078106 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-5176-4180 |
| authorships[2].author.display_name | Seokhyun Chung |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Chung, Seokhyun |
| authorships[2].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2507.05544 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Gait-Based Hand Load Estimation via Deep Latent Variable Models with Auxiliary Information |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-28T10:27:00.752357 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2507.05544 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2507.05544 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2507.05544 |
| primary_location.id | pmh:oai:arXiv.org:2507.05544 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2507.05544 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2507.05544 |
| publication_date | 2025-07-08 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.In | 46 |
| abstract_inverted_index.an | 51 |
| abstract_inverted_index.at | 85, 149 |
| abstract_inverted_index.be | 74 |
| abstract_inverted_index.by | 77, 126 |
| abstract_inverted_index.in | 10 |
| abstract_inverted_index.is | 81, 95, 131 |
| abstract_inverted_index.of | 176 |
| abstract_inverted_index.on | 32, 138 |
| abstract_inverted_index.to | 6, 38, 114, 133, 162 |
| abstract_inverted_index.we | 49 |
| abstract_inverted_index.Our | 100 |
| abstract_inverted_index.and | 43, 67, 80, 94, 111, 118, 121, 172 |
| abstract_inverted_index.are | 3 |
| abstract_inverted_index.can | 73 |
| abstract_inverted_index.for | 15, 145 |
| abstract_inverted_index.the | 129, 143, 174 |
| abstract_inverted_index.data | 22, 155 |
| abstract_inverted_index.deep | 103 |
| abstract_inverted_index.from | 19, 24, 35, 157, 168 |
| abstract_inverted_index.fuse | 119 |
| abstract_inverted_index.gait | 20, 37, 62, 72, 116, 123 |
| abstract_inverted_index.hand | 39 |
| abstract_inverted_index.load | 18, 53, 135 |
| abstract_inverted_index.need | 144 |
| abstract_inverted_index.over | 180 |
| abstract_inverted_index.rely | 31 |
| abstract_inverted_index.risk | 8 |
| abstract_inverted_index.that | 56 |
| abstract_inverted_index.this | 47 |
| abstract_inverted_index.thus | 82 |
| abstract_inverted_index.with | 107 |
| abstract_inverted_index.While | 70 |
| abstract_inverted_index.gains | 167 |
| abstract_inverted_index.load, | 40 |
| abstract_inverted_index.model | 101, 130 |
| abstract_inverted_index.naive | 181 |
| abstract_inverted_index.often | 30, 96 |
| abstract_inverted_index.style | 89, 147 |
| abstract_inverted_index.time, | 87 |
| abstract_inverted_index.time. | 151 |
| abstract_inverted_index.units | 160 |
| abstract_inverted_index.using | 153 |
| abstract_inverted_index.while | 141 |
| abstract_inverted_index.Guided | 125 |
| abstract_inverted_index.direct | 33 |
| abstract_inverted_index.domain | 127 |
| abstract_inverted_index.during | 64, 98 |
| abstract_inverted_index.fusion | 178 |
| abstract_inverted_index.labels | 148 |
| abstract_inverted_index.latent | 104 |
| abstract_inverted_index.loaded | 36, 120 |
| abstract_inverted_index.manual | 11, 92 |
| abstract_inverted_index.motion | 21 |
| abstract_inverted_index.study, | 48 |
| abstract_inverted_index.style, | 140 |
| abstract_inverted_index.style. | 69 |
| abstract_inverted_index.Machine | 0 |
| abstract_inverted_index.applied | 5 |
| abstract_inverted_index.capture | 115 |
| abstract_inverted_index.carried | 17 |
| abstract_inverted_index.feature | 182 |
| abstract_inverted_index.methods | 2 |
| abstract_inverted_index.propose | 50 |
| abstract_inverted_index.readily | 83 |
| abstract_inverted_index.sensors | 79 |
| abstract_inverted_index.walking | 66 |
| abstract_inverted_index.However, | 27 |
| abstract_inverted_index.accuracy | 166 |
| abstract_inverted_index.attached | 161 |
| abstract_inverted_index.baseline | 61, 71 |
| abstract_inverted_index.captured | 76 |
| abstract_inverted_index.carrying | 68, 88, 139, 146 |
| abstract_inverted_index.designed | 132 |
| abstract_inverted_index.dynamics | 117 |
| abstract_inverted_index.enhanced | 52 |
| abstract_inverted_index.estimate | 134 |
| abstract_inverted_index.existing | 28 |
| abstract_inverted_index.explicit | 177 |
| abstract_inverted_index.inertial | 158 |
| abstract_inverted_index.labeling | 93 |
| abstract_inverted_index.learning | 1 |
| abstract_inverted_index.limiting | 41 |
| abstract_inverted_index.mappings | 34 |
| abstract_inverted_index.material | 12 |
| abstract_inverted_index.modeling | 106 |
| abstract_inverted_index.networks | 110 |
| abstract_inverted_index.patterns | 63 |
| abstract_inverted_index.requires | 91 |
| abstract_inverted_index.sensors. | 26 |
| abstract_inverted_index.temporal | 108 |
| abstract_inverted_index.unloaded | 65, 122 |
| abstract_inverted_index.variable | 105 |
| abstract_inverted_index.wearable | 25, 78 |
| abstract_inverted_index.accuracy. | 45 |
| abstract_inverted_index.auxiliary | 58, 170 |
| abstract_inverted_index.available | 84 |
| abstract_inverted_index.collected | 23, 156 |
| abstract_inverted_index.ergonomic | 7 |
| abstract_inverted_index.framework | 55 |
| abstract_inverted_index.handling, | 13 |
| abstract_inverted_index.highlight | 173 |
| abstract_inverted_index.including | 60 |
| abstract_inverted_index.inference | 86, 150 |
| abstract_inverted_index.magnitude | 136 |
| abstract_inverted_index.patterns. | 124 |
| abstract_inverted_index.typically | 90 |
| abstract_inverted_index.approaches | 29 |
| abstract_inverted_index.assessment | 9 |
| abstract_inverted_index.estimating | 16 |
| abstract_inverted_index.estimation | 54 |
| abstract_inverted_index.importance | 175 |
| abstract_inverted_index.integrates | 102 |
| abstract_inverted_index.knowledge, | 128 |
| abstract_inverted_index.mechanisms | 179 |
| abstract_inverted_index.predictive | 44 |
| abstract_inverted_index.real-world | 154 |
| abstract_inverted_index.Experiments | 152 |
| abstract_inverted_index.conditioned | 137 |
| abstract_inverted_index.demonstrate | 164 |
| abstract_inverted_index.deployment. | 99 |
| abstract_inverted_index.eliminating | 142 |
| abstract_inverted_index.information | 171 |
| abstract_inverted_index.measurement | 159 |
| abstract_inverted_index.substantial | 165 |
| abstract_inverted_index.unavailable | 97 |
| abstract_inverted_index.incorporates | 57 |
| abstract_inverted_index.increasingly | 4 |
| abstract_inverted_index.information, | 59 |
| abstract_inverted_index.participants | 163 |
| abstract_inverted_index.particularly | 14 |
| abstract_inverted_index.automatically | 75 |
| abstract_inverted_index.convolutional | 109 |
| abstract_inverted_index.incorporating | 169 |
| abstract_inverted_index.bi-directional | 112 |
| abstract_inverted_index.concatenation. | 183 |
| abstract_inverted_index.generalization | 42 |
| abstract_inverted_index.cross-attention | 113 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |