{"id":"W2772780151","doi":"10.1109/icdmw.2017.97","title":"Towards Automatic Feature Extraction for Activity Recognition from Wearable Sensors: A Deep Learning Approach","year":2017,"lang":"en","type":"article","venue":"","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Softmax function; Feature extraction; Classifier (UML); Activity recognition; Dimensionality reduction; Pattern recognition (psychology); Machine learning; Wearable computer; Generalization; Matrix decomposition; Deep learning","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006713353,0.0002471036,0.0003601334,0.0001235956,0.00100321,0.001430643,0.0006889304,0.0002368321,0.00006240538],"category_scores_gemma":[0.000576009,0.000237958,0.0001876789,0.0001139042,0.00004245804,0.003345635,0.0001857999,0.000393197,0.0001686896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000130212,"about_ca_system_score_gemma":0.00007406336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009333747,"about_ca_topic_score_gemma":0.0001374034,"domain_scores_codex":[0.9980897,0.0002357812,0.0002167309,0.0007270559,0.0003649002,0.0003658834],"domain_scores_gemma":[0.9978493,0.0003677239,0.0005089285,0.0008874352,0.0002582967,0.0001283426],"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":[0.00002427269,0.0001324411,0.0001690818,0.00005371757,0.00006293706,0.000003325459,0.0004500913,0.00002611915,0.004377395,0.00004523007,0.0003444686,0.9943109],"study_design_scores_gemma":[0.001227913,0.0001279894,0.01722671,0.0001442657,0.0000433856,0.00006916733,0.0002556771,0.9595376,0.01531424,0.002461891,0.003044351,0.0005467729],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1651186,0.00003441318,0.820522,0.000857394,0.0005825327,0.0006886733,0.00001263705,0.000612124,0.01157153],"genre_scores_gemma":[0.8996099,0.0000100663,0.09809199,0.00004824192,0.0002777611,0.0002170869,0.00002286445,0.00002291084,0.001699241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9937642,"threshold_uncertainty_score":0.999606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0569353017406226,"score_gpt":0.2971040498722523,"score_spread":0.2401687481316297,"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."}}