{"id":"W4206727444","doi":"10.1088/2634-4386/ac4c38","title":"Human activity recognition: suitability of a neuromorphic approach for on-edge AIoT applications","year":2022,"lang":"en","type":"article","venue":"Neuromorphic Computing and Engineering","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Waterloo","funders":"Horizon 2020 Framework Programme; Electronic Components and Systems for European Leadership; European Commission","keywords":"Neuromorphic engineering; Computer science; Activity recognition; Hyperparameter; Artificial intelligence; Edge computing; Enhanced Data Rates for GSM Evolution; Artificial neural network; Wearable computer; Machine learning; Classifier (UML); Edge device; Software deployment; Energy consumption; Human–computer interaction; Embedded system; Engineering; Software engineering","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"],"consensus_categories":[],"category_scores_codex":[0.0002757621,0.0002228368,0.0002970946,0.0001267387,0.0004041084,0.00001798649,0.0001688049,0.00003808245,0.000006528617],"category_scores_gemma":[0.00003527611,0.0002754375,0.00008672316,0.0003091832,0.00003313143,0.00005294627,0.0001303377,0.0005051551,4.528276e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004044083,"about_ca_system_score_gemma":0.000008213869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002127785,"about_ca_topic_score_gemma":1.496138e-7,"domain_scores_codex":[0.9988472,0.00004169053,0.0002809411,0.0003706608,0.0001526269,0.000306903],"domain_scores_gemma":[0.9992401,0.0003136032,0.00006616714,0.000261027,0.00003264269,0.00008646357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001573073,0.00009487303,0.00006783156,0.0005101339,0.00001910561,0.0000034794,0.00009527236,0.8872514,0.09839294,0.0001995656,0.00003140953,0.01331831],"study_design_scores_gemma":[0.0007394661,0.0003846547,0.002855419,0.00003441588,0.00003274437,0.0001123516,0.00003676554,0.9821051,0.01213028,0.0001572826,0.0009596027,0.0004518729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8901193,0.0000691384,0.1084207,0.00001819892,0.0002055157,0.0005094683,0.00005055917,0.0004528385,0.0001542925],"genre_scores_gemma":[0.997701,0.000003224668,0.001916145,0.0000275012,0.0001428941,0.0001210022,0.00002648595,0.00005485533,0.000006928015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1075816,"threshold_uncertainty_score":0.9999698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05506559468370577,"score_gpt":0.245333075403273,"score_spread":0.1902674807195673,"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."}}