{"id":"https://openalex.org/W4281786927","doi":"https://doi.org/10.48550/arxiv.2205.13607","title":"Self-supervised Pretraining and Transfer Learning Enable Flu and COVID-19 Predictions in Small Mobile Sensing Datasets","display_name":"Self-supervised Pretraining and Transfer Learning Enable Flu and COVID-19 Predictions in Small Mobile Sensing Datasets","publication_year":2022,"publication_date":"2022-05-26","ids":{"openalex":"https://openalex.org/W4281786927","doi":"https://doi.org/10.48550/arxiv.2205.13607"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2205.13607","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.13607","pdf_url":"https://arxiv.org/pdf/2205.13607","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.13607","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009772512","display_name":"Mike A. Merrill","orcid":"https://orcid.org/0000-0003-2994-0058","observed_orcids":["https://orcid.org/0000-0003-2994-0058"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Merrill, Mike A.","raw_affiliation_strings":["University of Washington Seattle , Washington , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington Seattle , Washington , USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033639139","display_name":"Tim Althoff","orcid":"https://orcid.org/0000-0003-4793-2289","observed_orcids":["https://orcid.org/0000-0003-4793-2289"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Althoff, Tim","raw_affiliation_strings":["University of Washington Seattle , Washington , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington Seattle , Washington , USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.8618000149726868,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.8618000149726868,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.03060000017285347,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.021700000390410423,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mobile-sensing","display_name":"mobile sensing","score":0.699999988079071},{"id":"https://openalex.org/keywords/self-supervised-pretraining","display_name":"self-supervised pre-training","score":0.843999981880188},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/multivariate-time-series-classification","display_name":"multivariate time series classification","score":0.8859999775886536},{"id":"https://openalex.org/keywords/covid-19-prediction","display_name":"COVID-19 prediction","score":0.9980000257492065},{"id":"https://openalex.org/keywords/wearable-sensors","display_name":"wearable sensors","score":0.4519999921321869},{"id":"https://openalex.org/keywords/activity-trackers","display_name":"wearable activity trackers","score":0.6019999980926514},{"id":"https://openalex.org/keywords/long-term-dependencies","display_name":"long-range dependencies","score":0.8159999847412109},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.8009999990463257},{"id":"https://openalex.org/keywords/small-datasets","display_name":"small datasets","score":0.7210000157356262},{"id":"https://openalex.org/keywords/zero-shot-prediction","display_name":"zero-shot prediction","score":0.7379999756813049},{"id":"https://openalex.org/keywords/medical-surveillance","display_name":"medical surveillance","score":0.7250000238418579},{"id":"https://openalex.org/keywords/transformer-self-attention","display_name":"transformer self-attention","score":0.7429999709129333},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.7649999856948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765140175819397},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7096027731895447},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6815001368522644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6548811197280884},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5946691632270813},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5055687427520752},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.49021512269973755},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.4264557361602783}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2205.13607","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.13607","pdf_url":"https://arxiv.org/pdf/2205.13607","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2205.13607","doi":"https://doi.org/10.48550/arxiv.2205.13607","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2205.13607","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.13607","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.13607","pdf_url":"https://arxiv.org/pdf/2205.13607","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8560000061988831,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281786927.pdf","grobid_xml":"https://content.openalex.org/works/W4281786927.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2892035503","https://openalex.org/W2965373594","https://openalex.org/W2975059944","https://openalex.org/W3015468748","https://openalex.org/W3048152463","https://openalex.org/W3125949103","https://openalex.org/W3128981305","https://openalex.org/W4226099029"],"related_works":["https://openalex.org/W3177990722","https://openalex.org/W6906718991","https://openalex.org/W4226099029","https://openalex.org/W4318464905","https://openalex.org/W7163815345","https://openalex.org/W4392202379","https://openalex.org/W4385651932","https://openalex.org/W7164829406","https://openalex.org/W4283370926","https://openalex.org/W3137981739"],"abstract_inverted_index":{"Detailed":[0],"mobile":[1],"sensing":[2],"data":[3,155,218,243],"from":[4],"phones,":[5],"watches,":[6],"and":[7,16,29,40,60,69,115,150,157,220],"fitness":[8],"trackers":[9],"offer":[10],"an":[11,176,232,241],"unparalleled":[12],"opportunity":[13],"to":[14,25,32,48,80,86,132,153,199],"quantify":[15],"act":[17],"upon":[18],"previously":[19],"unmeasurable":[20],"behavioral":[21,91,140],"changes":[22],"in":[23,36,53,89,185,216,227,240],"order":[24],"improve":[26],"individual":[27],"health":[28,92],"accelerate":[30],"responses":[31],"emerging":[33],"diseases.":[34],"Unlike":[35],"natural":[37],"language":[38],"processing":[39],"computer":[41],"vision,":[42],"deep":[43],"representation":[44,141],"learning":[45,142,152,226],"has":[46],"yet":[47],"broadly":[49],"impact":[50],"this":[51],"domain,":[52,93],"which":[54,100],"the":[55,90,222],"vast":[56],"majority":[57],"of":[58,106,197,212,224,236],"research":[59],"clinical":[61],"applications":[62],"still":[63],"rely":[64],"on":[65],"manually":[66],"defined":[67],"features":[68],"boosted":[70],"tree":[71],"models":[72],"or":[73],"even":[74],"forgo":[75],"predictive":[76],"modeling":[77],"altogether":[78],"due":[79,85],"insufficient":[81],"accuracy.":[82],"This":[83],"is":[84],"unique":[87,135],"challenges":[88],"including":[94],"very":[95],"small":[96,217],"datasets":[97],"(~10^1":[98],"participants),":[99],"frequently":[101],"contain":[102],"missing":[103],"data,":[104],"consist":[105],"long":[107],"time":[108,128,163],"series":[109,129,164],"with":[110],"critical":[111],"long-range":[112,159],"dependencies":[113,160],"(length>10^4),":[114],"extreme":[116],"class":[117],"imbalances":[118],"(>10^3:1).":[119],"Here,":[120],"we":[121,190,246],"introduce":[122],"a":[123],"neural":[124,170],"architecture":[125],"for":[126,147,250],"multivariate":[127],"classification":[130],"designed":[131],"address":[133,154],"these":[134],"domain":[136],"challenges.":[137],"Our":[138],"proposed":[139],"approach":[143],"combines":[144],"novel":[145,228],"tasks":[146],"self-supervised":[148],"pretraining":[149],"transfer":[151,208,225],"scarcity,":[156],"captures":[158],"across":[161,203],"long-history":[162],"through":[165,231],"transformer":[166],"self-attention":[167],"following":[168],"convolutional":[169],"network-based":[171],"dimensionality":[172],"reduction.":[173],"We":[174],"propose":[175],"evaluation":[177],"framework":[178],"aimed":[179],"at":[180],"reflecting":[181],"expected":[182],"real-world":[183],"performance":[184,193,210],"plausible":[186],"deployment":[187],"scenarios.":[188],"Concretely,":[189],"demonstrate":[191],"(1)":[192],"improvements":[194,211],"over":[195],"baselines":[196],"up":[198],"0.15":[200],"ROC":[201],"AUC":[202,215],"five":[204],"prediction":[205,239],"tasks,":[206],"(2)":[207],"learning-induced":[209],"16%":[213],"PR":[214],"scenarios,":[219],"(3)":[221],"potential":[223,248],"disease":[229],"scenarios":[230],"exploratory":[233],"case":[234],"study":[235],"zero-shot":[237],"COVID-19":[238],"independent":[242],"set.":[244],"Finally,":[245],"discuss":[247],"implications":[249],"medical":[251],"surveillance":[252],"testing.":[253]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-06-13T00:00:00"}