{"id":"W4385337237","doi":"10.1016/j.inffus.2023.101953","title":"A multi-resolution fusion approach for human activity recognition from video data in tiny edge devices","year":2023,"lang":"en","type":"article","venue":"Information Fusion","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University","keywords":"Computer science; Edge device; Activity recognition; Artificial intelligence; Convolutional neural network; Deep learning; Inference; Edge computing; Wearable computer; Data stream mining; Real-time computing; Machine learning; Enhanced Data Rates for GSM Evolution; Embedded system; Cloud computing","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.001455309,0.000209383,0.0002573273,0.000647277,0.0003662688,0.0003701669,0.0009017782,0.0001992065,0.00001962521],"category_scores_gemma":[0.0003047152,0.0002160045,0.00006890045,0.001009491,0.0000245169,0.008471211,0.00088159,0.0001988514,0.0004780184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000147976,"about_ca_system_score_gemma":0.00007540908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001510245,"about_ca_topic_score_gemma":0.0008444039,"domain_scores_codex":[0.9979109,0.0001864993,0.0006209047,0.0004816949,0.0004659468,0.0003340776],"domain_scores_gemma":[0.9979863,0.0003110489,0.0004639792,0.000908222,0.0002437056,0.00008674388],"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":[0.00009980729,0.0002745776,0.001386887,0.0002189477,0.00002201868,0.000001657677,0.004145353,0.0002645914,0.01455797,0.00005781054,0.004463702,0.9745067],"study_design_scores_gemma":[0.001786184,0.00005486155,0.04103607,0.0001465505,0.000009034607,0.000004063944,0.0003448077,0.9461359,0.001161024,0.0002424204,0.008762379,0.0003167569],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2635612,0.00001252256,0.733218,0.0002929029,0.000422981,0.001111923,0.0003338851,0.0005177507,0.0005289125],"genre_scores_gemma":[0.9692921,0.00001510413,0.02382387,0.0001738332,0.0001251074,0.0002434679,0.006274763,0.00001212954,0.00003963594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9741899,"threshold_uncertainty_score":0.8808409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1433452693640636,"score_gpt":0.3218688183173329,"score_spread":0.1785235489532693,"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."}}