{"id":"W2770265759","doi":"10.1016/j.future.2017.11.029","title":"A robust human activity recognition system using smartphone sensors and deep learning","year":2017,"lang":"en","type":"article","venue":"Future Generation Computer Systems","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":653,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Deanship of Scientific Research, King Saud University","keywords":"Activity recognition; Computer science; Artificial intelligence; Inertial measurement unit; Support vector machine; Wearable computer; Machine learning; Pattern recognition (psychology); Linear discriminant analysis; Artificial neural network; Deep belief network; Autoregressive model; 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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009503808,0.0003899148,0.0005613245,0.0002482555,0.002574504,0.003466509,0.0006172391,0.0002662693,0.000003460519],"category_scores_gemma":[0.00002388538,0.0003996556,0.0001178899,0.0001621176,0.00005852925,0.002053504,0.0004020928,0.0003617423,0.00005127777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002399735,"about_ca_system_score_gemma":0.00005420146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005775954,"about_ca_topic_score_gemma":0.0001987856,"domain_scores_codex":[0.9967604,0.0008316246,0.0005321127,0.000971418,0.0005014303,0.0004030224],"domain_scores_gemma":[0.9972556,0.00007443553,0.000938056,0.001069269,0.0004537734,0.0002088303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006109587,0.0003825557,0.009770659,0.001919584,0.0007901993,0.0003815844,0.007778323,0.02783306,0.08081298,0.004144828,0.009499371,0.8566257],"study_design_scores_gemma":[0.0008437221,0.0001133035,0.003880677,0.0002693988,0.00002943269,0.0007496222,0.0001998524,0.9875911,0.001387997,0.000002305682,0.004353337,0.0005791875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3439979,0.0002263562,0.630538,0.0001279972,0.02408987,0.0004613544,0.000006100956,0.0003657716,0.0001866827],"genre_scores_gemma":[0.9524378,0.00000951221,0.009746864,0.00002923096,0.03753822,0.00005567426,0.00002799571,0.00003682275,0.0001178489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9597581,"threshold_uncertainty_score":0.9998455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09103652507543153,"score_gpt":0.2634169325374095,"score_spread":0.172380407461978,"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."}}