Explaining Human Activity Recognition with SHAP: Validating insights with perturbation and quantitative measures Article Swipe
Felix Tempel
,
Espen A. F. Ihlen
,
Lars Adde
,
Inga Strümke
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1016/j.compbiomed.2025.109838
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1016/j.compbiomed.2025.109838
In Human Activity Recognition (HAR), understanding the intricacy of body movements within high-risk applications is essential. This study uses SHapley Additive exPlanations (SHAP) to explain the decision-making process of Graph Convolution Networks (GCNs) when classifying activities with skeleton data. We employ SHAP to explain two real-world datasets: one for cerebral palsy (CP) classification and the widely used NTU RGB+D 60 action recognition dataset. To test the explanation, we introduce a novel perturbation approach that modifies the model's edge importance matrix, allowing us to evaluate the impact of specific body key points on prediction outcomes. To assess the fidelity of our explanations, we employ informed perturbation, targeting body key points identified as important by SHAP and comparing them against random perturbation as a control condition. This perturbation enables a judgment on whether the body key points are truly influential or non-influential based on the SHAP values. Results on both datasets show that body key points identified as important through SHAP have the largest influence on the accuracy, specificity, and sensitivity metrics. Our findings highlight that SHAP can provide granular insights into the input feature contribution to the prediction outcome of GCNs in HAR tasks. This demonstrates the potential for more interpretable and trustworthy models in high-stakes applications like healthcare or rehabilitation.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1016/j.compbiomed.2025.109838
- OA Status
- hybrid
- Cited By
- 11
- References
- 58
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4407858193
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4407858193Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1016/j.compbiomed.2025.109838Digital Object Identifier
- Title
-
Explaining Human Activity Recognition with SHAP: Validating insights with perturbation and quantitative measuresWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-02-22Full publication date if available
- Authors
-
Felix Tempel, Espen A. F. Ihlen, Lars Adde, Inga StrümkeList of authors in order
- Landing page
-
https://doi.org/10.1016/j.compbiomed.2025.109838Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1016/j.compbiomed.2025.109838Direct OA link when available
- Concepts
-
Computer scienceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
11Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 11Per-year citation counts (last 5 years)
- References (count)
-
58Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4407858193 |
|---|---|
| doi | https://doi.org/10.1016/j.compbiomed.2025.109838 |
| ids.doi | https://doi.org/10.1016/j.compbiomed.2025.109838 |
| ids.pmid | https://pubmed.ncbi.nlm.nih.gov/39987702 |
| ids.openalex | https://openalex.org/W4407858193 |
| fwci | 53.01719661 |
| mesh[0].qualifier_ui | |
| mesh[0].descriptor_ui | D006801 |
| mesh[0].is_major_topic | False |
| mesh[0].qualifier_name | |
| mesh[0].descriptor_name | Humans |
| mesh[1].qualifier_ui | Q000503 |
| mesh[1].descriptor_ui | D002547 |
| mesh[1].is_major_topic | True |
| mesh[1].qualifier_name | physiopathology |
| mesh[1].descriptor_name | Cerebral Palsy |
| mesh[2].qualifier_ui | |
| mesh[2].descriptor_ui | D006802 |
| mesh[2].is_major_topic | False |
| mesh[2].qualifier_name | |
| mesh[2].descriptor_name | Human Activities |
| mesh[3].qualifier_ui | |
| mesh[3].descriptor_ui | D016208 |
| mesh[3].is_major_topic | False |
| mesh[3].qualifier_name | |
| mesh[3].descriptor_name | Databases, Factual |
| mesh[4].qualifier_ui | |
| mesh[4].descriptor_ui | D016571 |
| mesh[4].is_major_topic | False |
| mesh[4].qualifier_name | |
| mesh[4].descriptor_name | Neural Networks, Computer |
| mesh[5].qualifier_ui | |
| mesh[5].descriptor_ui | D005260 |
| mesh[5].is_major_topic | False |
| mesh[5].qualifier_name | |
| mesh[5].descriptor_name | Female |
| mesh[6].qualifier_ui | |
| mesh[6].descriptor_ui | D006801 |
| mesh[6].is_major_topic | False |
| mesh[6].qualifier_name | |
| mesh[6].descriptor_name | Humans |
| mesh[7].qualifier_ui | Q000503 |
| mesh[7].descriptor_ui | D002547 |
| mesh[7].is_major_topic | True |
| mesh[7].qualifier_name | physiopathology |
| mesh[7].descriptor_name | Cerebral Palsy |
| mesh[8].qualifier_ui | |
| mesh[8].descriptor_ui | D006802 |
| mesh[8].is_major_topic | True |
| mesh[8].qualifier_name | |
| mesh[8].descriptor_name | Human Activities |
| mesh[9].qualifier_ui | |
| mesh[9].descriptor_ui | D016208 |
| mesh[9].is_major_topic | False |
| mesh[9].qualifier_name | |
| mesh[9].descriptor_name | Databases, Factual |
| mesh[10].qualifier_ui | |
| mesh[10].descriptor_ui | D016571 |
| mesh[10].is_major_topic | True |
| mesh[10].qualifier_name | |
| mesh[10].descriptor_name | Neural Networks, Computer |
| mesh[11].qualifier_ui | |
| mesh[11].descriptor_ui | D008297 |
| mesh[11].is_major_topic | False |
| mesh[11].qualifier_name | |
| mesh[11].descriptor_name | Male |
| mesh[12].qualifier_ui | |
| mesh[12].descriptor_ui | D005260 |
| mesh[12].is_major_topic | False |
| mesh[12].qualifier_name | |
| mesh[12].descriptor_name | Female |
| mesh[13].qualifier_ui | Q000502 |
| mesh[13].descriptor_ui | D009068 |
| mesh[13].is_major_topic | False |
| mesh[13].qualifier_name | physiology |
| mesh[13].descriptor_name | Movement |
| type | article |
| title | Explaining Human Activity Recognition with SHAP: Validating insights with perturbation and quantitative measures |
| biblio.issue | |
| biblio.volume | 188 |
| biblio.last_page | 109838 |
| biblio.first_page | 109838 |
| topics[0].id | https://openalex.org/T12026 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9976999759674072 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Explainable Artificial Intelligence (XAI) |
| topics[1].id | https://openalex.org/T13702 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9925000071525574 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Machine Learning in Healthcare |
| topics[2].id | https://openalex.org/T10444 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9902999997138977 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Context-Aware Activity Recognition Systems |
| funders[0].id | https://openalex.org/F4320323299 |
| funders[0].ror | https://ror.org/00epmv149 |
| funders[0].display_name | Norges Forskningsråd |
| funders[1].id | https://openalex.org/F4320338453 |
| funders[1].ror | |
| funders[1].display_name | HORIZON EUROPE European Research Council |
| is_xpac | False |
| apc_list.value | 2610 |
| apc_list.currency | USD |
| apc_list.value_usd | 2610 |
| apc_paid.value | 2610 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 2610 |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.3645731806755066 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.3645731806755066 |
| keywords[0].display_name | Computer science |
| language | en |
| locations[0].id | doi:10.1016/j.compbiomed.2025.109838 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S44278595 |
| locations[0].source.issn | 0010-4825, 1879-0534 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 0010-4825 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Computers in Biology and Medicine |
| locations[0].source.host_organization | https://openalex.org/P4310320990 |
| locations[0].source.host_organization_name | Elsevier BV |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320990 |
| locations[0].source.host_organization_lineage_names | Elsevier BV |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Computers in Biology and Medicine |
| locations[0].landing_page_url | https://doi.org/10.1016/j.compbiomed.2025.109838 |
| locations[1].id | pmid:39987702 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306525036 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | PubMed |
| locations[1].source.host_organization | https://openalex.org/I1299303238 |
| locations[1].source.host_organization_name | National Institutes of Health |
| locations[1].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | publishedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | True |
| locations[1].is_published | True |
| locations[1].raw_source_name | Computers in biology and medicine |
| locations[1].landing_page_url | https://pubmed.ncbi.nlm.nih.gov/39987702 |
| indexed_in | crossref, pubmed |
| authorships[0].author.id | https://openalex.org/A5093876109 |
| authorships[0].author.orcid | https://orcid.org/0009-0005-6310-408X |
| authorships[0].author.display_name | Felix Tempel |
| authorships[0].countries | NO |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I204778367 |
| authorships[0].affiliations[0].raw_affiliation_string | Faculty of Informatics, Norwegian University of Science and Technology, Trondheim, Norway. Electronic address: [email protected]. |
| authorships[0].institutions[0].id | https://openalex.org/I204778367 |
| authorships[0].institutions[0].ror | https://ror.org/05xg72x27 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I204778367 |
| authorships[0].institutions[0].country_code | NO |
| authorships[0].institutions[0].display_name | Norwegian University of Science and Technology |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Felix Tempel |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Faculty of Informatics, Norwegian University of Science and Technology, Trondheim, Norway. Electronic address: [email protected]. |
| authorships[1].author.id | https://openalex.org/A5077369441 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-2469-1809 |
| authorships[1].author.display_name | Espen A. F. Ihlen |
| authorships[1].countries | NO |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I204778367 |
| authorships[1].affiliations[0].raw_affiliation_string | Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, Trondheim, Norway. Electronic address: [email protected]. |
| authorships[1].institutions[0].id | https://openalex.org/I204778367 |
| authorships[1].institutions[0].ror | https://ror.org/05xg72x27 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I204778367 |
| authorships[1].institutions[0].country_code | NO |
| authorships[1].institutions[0].display_name | Norwegian University of Science and Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Espen Alexander F Ihlen |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, Trondheim, Norway. Electronic address: [email protected]. |
| authorships[2].author.id | https://openalex.org/A5033077256 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-5532-0034 |
| authorships[2].author.display_name | Lars Adde |
| authorships[2].countries | NO |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I204778367 |
| authorships[2].affiliations[0].raw_affiliation_string | Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology, Clinic of Rehabilitation, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway. Electronic address: [email protected]. |
| authorships[2].institutions[0].id | https://openalex.org/I204778367 |
| authorships[2].institutions[0].ror | https://ror.org/05xg72x27 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I204778367 |
| authorships[2].institutions[0].country_code | NO |
| authorships[2].institutions[0].display_name | Norwegian University of Science and Technology |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Lars Adde |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology, Clinic of Rehabilitation, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway. Electronic address: [email protected]. |
| authorships[3].author.id | https://openalex.org/A5000311801 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-1820-6544 |
| authorships[3].author.display_name | Inga Strümke |
| authorships[3].countries | NO |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I204778367 |
| authorships[3].affiliations[0].raw_affiliation_string | Faculty of Informatics, Norwegian University of Science and Technology, Trondheim, Norway. Electronic address: [email protected]. |
| authorships[3].institutions[0].id | https://openalex.org/I204778367 |
| authorships[3].institutions[0].ror | https://ror.org/05xg72x27 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I204778367 |
| authorships[3].institutions[0].country_code | NO |
| authorships[3].institutions[0].display_name | Norwegian University of Science and Technology |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Inga Strümke |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Faculty of Informatics, Norwegian University of Science and Technology, Trondheim, Norway. Electronic address: [email protected]. |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1016/j.compbiomed.2025.109838 |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Explaining Human Activity Recognition with SHAP: Validating insights with perturbation and quantitative measures |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T12026 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9976999759674072 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Explainable Artificial Intelligence (XAI) |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 11 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 11 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1016/j.compbiomed.2025.109838 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S44278595 |
| best_oa_location.source.issn | 0010-4825, 1879-0534 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 0010-4825 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Computers in Biology and Medicine |
| best_oa_location.source.host_organization | https://openalex.org/P4310320990 |
| best_oa_location.source.host_organization_name | Elsevier BV |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320990 |
| best_oa_location.source.host_organization_lineage_names | Elsevier BV |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Computers in Biology and Medicine |
| best_oa_location.landing_page_url | https://doi.org/10.1016/j.compbiomed.2025.109838 |
| primary_location.id | doi:10.1016/j.compbiomed.2025.109838 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S44278595 |
| primary_location.source.issn | 0010-4825, 1879-0534 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 0010-4825 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Computers in Biology and Medicine |
| primary_location.source.host_organization | https://openalex.org/P4310320990 |
| primary_location.source.host_organization_name | Elsevier BV |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320990 |
| primary_location.source.host_organization_lineage_names | Elsevier BV |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Computers in Biology and Medicine |
| primary_location.landing_page_url | https://doi.org/10.1016/j.compbiomed.2025.109838 |
| publication_date | 2025-02-22 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W2944006115, https://openalex.org/W4365440898, https://openalex.org/W4313648826, https://openalex.org/W4366262984, https://openalex.org/W4321350922, https://openalex.org/W2958089299, https://openalex.org/W3211639647, https://openalex.org/W6810837344, https://openalex.org/W6799127779, https://openalex.org/W4392912728, https://openalex.org/W2963095307, https://openalex.org/W4321786089, https://openalex.org/W6766846328, https://openalex.org/W3186197713, https://openalex.org/W4381929541, https://openalex.org/W4399433746, https://openalex.org/W2616247523, https://openalex.org/W6750391026, https://openalex.org/W6809351582, https://openalex.org/W6754669440, https://openalex.org/W6851136652, https://openalex.org/W6777015728, https://openalex.org/W4361762496, https://openalex.org/W6697443983, https://openalex.org/W6769161880, https://openalex.org/W4389740321, https://openalex.org/W6802620897, https://openalex.org/W4391591573, https://openalex.org/W6747795875, https://openalex.org/W2135673656, https://openalex.org/W4285037000, https://openalex.org/W4249502209, https://openalex.org/W2962862931, https://openalex.org/W4234842379, https://openalex.org/W2962851944, https://openalex.org/W2990138404, https://openalex.org/W3094509718, https://openalex.org/W4255556797, https://openalex.org/W4317438067, https://openalex.org/W2619947201, https://openalex.org/W4205616158, https://openalex.org/W3102564565, https://openalex.org/W4300235091, https://openalex.org/W4283396845, https://openalex.org/W2964134613, https://openalex.org/W4367331653, https://openalex.org/W4403814952, https://openalex.org/W4392745521, https://openalex.org/W3185273257, https://openalex.org/W2963076818, https://openalex.org/W2969476445, https://openalex.org/W4295312788, https://openalex.org/W4405715654, https://openalex.org/W4225984735, https://openalex.org/W4390784191, https://openalex.org/W4327919044, https://openalex.org/W2516809705, https://openalex.org/W2594475271 |
| referenced_works_count | 58 |
| abstract_inverted_index.a | 69, 121, 127 |
| abstract_inverted_index.60 | 59 |
| abstract_inverted_index.In | 0 |
| abstract_inverted_index.To | 63, 94 |
| abstract_inverted_index.We | 39 |
| abstract_inverted_index.as | 110, 120, 155 |
| abstract_inverted_index.by | 112 |
| abstract_inverted_index.in | 190, 203 |
| abstract_inverted_index.is | 14 |
| abstract_inverted_index.of | 8, 28, 86, 98, 188 |
| abstract_inverted_index.on | 91, 129, 141, 146, 163 |
| abstract_inverted_index.or | 138, 208 |
| abstract_inverted_index.to | 23, 42, 82, 184 |
| abstract_inverted_index.us | 81 |
| abstract_inverted_index.we | 67, 101 |
| abstract_inverted_index.HAR | 191 |
| abstract_inverted_index.NTU | 57 |
| abstract_inverted_index.Our | 170 |
| abstract_inverted_index.and | 53, 114, 167, 200 |
| abstract_inverted_index.are | 135 |
| abstract_inverted_index.can | 175 |
| abstract_inverted_index.for | 48, 197 |
| abstract_inverted_index.key | 89, 107, 133, 152 |
| abstract_inverted_index.one | 47 |
| abstract_inverted_index.our | 99 |
| abstract_inverted_index.the | 6, 25, 54, 65, 75, 84, 96, 131, 142, 160, 164, 180, 185, 195 |
| abstract_inverted_index.two | 44 |
| abstract_inverted_index.(CP) | 51 |
| abstract_inverted_index.GCNs | 189 |
| abstract_inverted_index.SHAP | 41, 113, 143, 158, 174 |
| abstract_inverted_index.This | 16, 124, 193 |
| abstract_inverted_index.body | 9, 88, 106, 132, 151 |
| abstract_inverted_index.both | 147 |
| abstract_inverted_index.edge | 77 |
| abstract_inverted_index.have | 159 |
| abstract_inverted_index.into | 179 |
| abstract_inverted_index.like | 206 |
| abstract_inverted_index.more | 198 |
| abstract_inverted_index.show | 149 |
| abstract_inverted_index.test | 64 |
| abstract_inverted_index.that | 73, 150, 173 |
| abstract_inverted_index.them | 116 |
| abstract_inverted_index.used | 56 |
| abstract_inverted_index.uses | 18 |
| abstract_inverted_index.when | 33 |
| abstract_inverted_index.with | 36 |
| abstract_inverted_index.Graph | 29 |
| abstract_inverted_index.Human | 1 |
| abstract_inverted_index.RGB+D | 58 |
| abstract_inverted_index.based | 140 |
| abstract_inverted_index.data. | 38 |
| abstract_inverted_index.input | 181 |
| abstract_inverted_index.novel | 70 |
| abstract_inverted_index.palsy | 50 |
| abstract_inverted_index.study | 17 |
| abstract_inverted_index.truly | 136 |
| abstract_inverted_index.(GCNs) | 32 |
| abstract_inverted_index.(HAR), | 4 |
| abstract_inverted_index.(SHAP) | 22 |
| abstract_inverted_index.action | 60 |
| abstract_inverted_index.assess | 95 |
| abstract_inverted_index.employ | 40, 102 |
| abstract_inverted_index.impact | 85 |
| abstract_inverted_index.models | 202 |
| abstract_inverted_index.points | 90, 108, 134, 153 |
| abstract_inverted_index.random | 118 |
| abstract_inverted_index.tasks. | 192 |
| abstract_inverted_index.widely | 55 |
| abstract_inverted_index.within | 11 |
| abstract_inverted_index.Results | 145 |
| abstract_inverted_index.SHapley | 19 |
| abstract_inverted_index.against | 117 |
| abstract_inverted_index.control | 122 |
| abstract_inverted_index.enables | 126 |
| abstract_inverted_index.explain | 24, 43 |
| abstract_inverted_index.feature | 182 |
| abstract_inverted_index.largest | 161 |
| abstract_inverted_index.matrix, | 79 |
| abstract_inverted_index.model's | 76 |
| abstract_inverted_index.outcome | 187 |
| abstract_inverted_index.process | 27 |
| abstract_inverted_index.provide | 176 |
| abstract_inverted_index.through | 157 |
| abstract_inverted_index.values. | 144 |
| abstract_inverted_index.whether | 130 |
| abstract_inverted_index.Activity | 2 |
| abstract_inverted_index.Additive | 20 |
| abstract_inverted_index.Networks | 31 |
| abstract_inverted_index.allowing | 80 |
| abstract_inverted_index.approach | 72 |
| abstract_inverted_index.cerebral | 49 |
| abstract_inverted_index.dataset. | 62 |
| abstract_inverted_index.datasets | 148 |
| abstract_inverted_index.evaluate | 83 |
| abstract_inverted_index.fidelity | 97 |
| abstract_inverted_index.findings | 171 |
| abstract_inverted_index.granular | 177 |
| abstract_inverted_index.informed | 103 |
| abstract_inverted_index.insights | 178 |
| abstract_inverted_index.judgment | 128 |
| abstract_inverted_index.metrics. | 169 |
| abstract_inverted_index.modifies | 74 |
| abstract_inverted_index.skeleton | 37 |
| abstract_inverted_index.specific | 87 |
| abstract_inverted_index.accuracy, | 165 |
| abstract_inverted_index.comparing | 115 |
| abstract_inverted_index.datasets: | 46 |
| abstract_inverted_index.high-risk | 12 |
| abstract_inverted_index.highlight | 172 |
| abstract_inverted_index.important | 111, 156 |
| abstract_inverted_index.influence | 162 |
| abstract_inverted_index.intricacy | 7 |
| abstract_inverted_index.introduce | 68 |
| abstract_inverted_index.movements | 10 |
| abstract_inverted_index.outcomes. | 93 |
| abstract_inverted_index.potential | 196 |
| abstract_inverted_index.targeting | 105 |
| abstract_inverted_index.activities | 35 |
| abstract_inverted_index.condition. | 123 |
| abstract_inverted_index.essential. | 15 |
| abstract_inverted_index.healthcare | 207 |
| abstract_inverted_index.identified | 109, 154 |
| abstract_inverted_index.importance | 78 |
| abstract_inverted_index.prediction | 92, 186 |
| abstract_inverted_index.real-world | 45 |
| abstract_inverted_index.Convolution | 30 |
| abstract_inverted_index.Recognition | 3 |
| abstract_inverted_index.classifying | 34 |
| abstract_inverted_index.high-stakes | 204 |
| abstract_inverted_index.influential | 137 |
| abstract_inverted_index.recognition | 61 |
| abstract_inverted_index.sensitivity | 168 |
| abstract_inverted_index.trustworthy | 201 |
| abstract_inverted_index.applications | 13, 205 |
| abstract_inverted_index.contribution | 183 |
| abstract_inverted_index.demonstrates | 194 |
| abstract_inverted_index.exPlanations | 21 |
| abstract_inverted_index.explanation, | 66 |
| abstract_inverted_index.perturbation | 71, 119, 125 |
| abstract_inverted_index.specificity, | 166 |
| abstract_inverted_index.explanations, | 100 |
| abstract_inverted_index.interpretable | 199 |
| abstract_inverted_index.perturbation, | 104 |
| abstract_inverted_index.understanding | 5 |
| abstract_inverted_index.classification | 52 |
| abstract_inverted_index.decision-making | 26 |
| abstract_inverted_index.non-influential | 139 |
| abstract_inverted_index.rehabilitation. | 209 |
| cited_by_percentile_year.max | 99 |
| cited_by_percentile_year.min | 98 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/13 |
| sustainable_development_goals[0].score | 0.46000000834465027 |
| sustainable_development_goals[0].display_name | Climate action |
| citation_normalized_percentile.value | 0.99779447 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |