{"id":"W2337546824","doi":"10.1109/percomw.2016.7457169","title":"From smart to deep: Robust activity recognition on smartwatches using deep learning","year":2016,"lang":"en","type":"article","venue":"","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":175,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Smartwatch; Activity recognition; Computer science; Wearable computer; Deep learning; Artificial intelligence; Machine learning; Context (archaeology); Wearable technology; Pipeline (software); Human–computer interaction; Embedded system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007224774,0.00009489619,0.0001367319,0.00009306015,0.0006997376,0.00008137342,0.0001210565,0.00009301827,0.004054934],"category_scores_gemma":[0.0007521308,0.00007341892,0.00008481099,0.0002796914,0.00009937783,0.0002346751,0.0000213009,0.00009489191,0.0006699673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002491651,"about_ca_system_score_gemma":0.00007002141,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04720342,"about_ca_topic_score_gemma":0.1264699,"domain_scores_codex":[0.9985931,0.0004215311,0.0001354328,0.0003195812,0.0002861882,0.0002441937],"domain_scores_gemma":[0.9989107,0.0006134198,0.00006043099,0.000154066,0.0001106117,0.0001507321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006102029,0.0001532222,0.01641827,0.000003798291,0.00005411799,0.000001515575,0.01033226,0.002306185,0.005227677,0.0001782872,0.00008486996,0.9651788],"study_design_scores_gemma":[0.006418287,0.001848827,0.3414921,0.001915872,0.001705486,0.000001566605,0.1862726,0.1170813,0.1230387,0.06912245,0.1428024,0.008300476],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8629852,0.000004314717,0.1276759,0.002087762,0.00008699952,0.0001160747,0.000003103294,0.0001010672,0.006939593],"genre_scores_gemma":[0.9968415,0.000009668025,0.001215484,0.0002296155,0.0003416809,0.00001122551,0.000006570034,0.000008287249,0.001335995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9568783,"threshold_uncertainty_score":0.9968555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07025401121407453,"score_gpt":0.306682747891044,"score_spread":0.2364287366769695,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}