{"id":"W2743199055","doi":"10.2196/mhealth.7521","title":"Feature-Free Activity Classification of Inertial Sensor Data With Machine Vision Techniques: Method, Development, and Evaluation","year":2017,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Convolutional neural network; Support vector machine; Feature (linguistics); Field (mathematics); Digital signal processing; Feature extraction; Random forest","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00362666,0.0009016508,0.0007329803,0.001785797,0.0002768832,0.0009379341,0.001145501,0.001060321,0.001835725],"category_scores_gemma":[0.007240897,0.0002493889,0.0006998125,0.001685038,0.0004450238,0.001353259,0.0007907329,0.001065029,0.0009729207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007112883,"about_ca_system_score_gemma":0.0007909446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002928019,"about_ca_topic_score_gemma":0.002029547,"domain_scores_codex":[0.9981364,0.0003356466,0.0001221539,0.0002501949,0.001055893,0.00009963578],"domain_scores_gemma":[0.9961761,0.0012521,0.0002817771,0.000375774,0.001759795,0.0001544276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003241365,0.0005195047,0.008652502,0.0006192501,0.0002484435,0.00009036984,0.00005803649,0.0415668,0.01339906,0.001623489,0.007116081,0.9257823],"study_design_scores_gemma":[0.0000563304,0.0008172953,0.01450097,0.0001552681,0.0001126876,0.0003512583,0.00005693144,0.9423103,0.03227354,0.00168577,0.007610315,0.00006931442],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1357365,0.01078008,0.8407274,0.0008893697,0.0007761058,0.0008195419,0.001108804,0.004681729,0.004480532],"genre_scores_gemma":[0.5562376,0.004565536,0.4310236,0.0002191193,0.0003202031,0.0007811795,0.003584403,0.0002848203,0.002983493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00362666,"threshold_uncertainty_score":0.01917982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1770644495911918,"score_gpt":0.4574087671608749,"score_spread":0.2803443175696831,"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."}}