{"id":"W4312817501","doi":"10.1109/icjece.2022.3199227","title":"Deep Incremental Learning for Personalized Human Activity Recognition on Edge Devices","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Electrical and Computer Engineering","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Deep learning; Activity recognition; Machine learning; Artificial intelligence; Software deployment; Wearable computer; Enhanced Data Rates for GSM Evolution; Edge computing; Wearable technology; Human–computer interaction; Embedded system; Operating system","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003400334,0.0001149133,0.0002023033,0.0003897357,0.0003773369,0.0001534146,0.0002561146,0.00002894888,0.00001592191],"category_scores_gemma":[0.00003697407,0.000124016,0.00009444071,0.0002676169,0.00001010258,0.0002658365,0.00003947377,0.0003959127,9.376664e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002555636,"about_ca_system_score_gemma":0.0001387958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000238282,"about_ca_topic_score_gemma":0.0002179656,"domain_scores_codex":[0.9991059,0.00008858412,0.0001952933,0.000173511,0.0001732183,0.000263547],"domain_scores_gemma":[0.9991829,0.0002515768,0.0001295605,0.00006250551,0.00008690022,0.0002865818],"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":[0.00006277983,0.0001074384,0.002042715,0.00006972254,0.0002242002,0.0001796723,0.001329701,0.01049017,0.003347823,0.002984275,0.0006971387,0.9784644],"study_design_scores_gemma":[0.001539317,0.002252864,0.007591985,0.00007440589,0.00002589707,0.0009026634,0.00003588986,0.961743,0.0006938936,0.0002452257,0.02446103,0.0004337978],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.346137,0.0002000847,0.6529962,0.0001741332,0.0003204428,0.00011708,0.000002611448,0.00002412118,0.00002834976],"genre_scores_gemma":[0.9978355,0.000001541377,0.001731744,0.0001510731,0.0002337895,0.00001549588,0.000003214194,0.00001028144,0.00001737332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9780306,"threshold_uncertainty_score":0.5057225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02350932259401178,"score_gpt":0.2198667576536786,"score_spread":0.1963574350596668,"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."}}