{"id":"W4381786635","doi":"10.1109/wf-iot54382.2022.10152039","title":"TinyHAR: Benchmarking Human Activity Recognition Systems in Resource Constrained Devices","year":2022,"lang":"en","type":"article","venue":"","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Edge device; Benchmarking; Convolutional neural network; Inference; Artificial intelligence; Activity recognition; Deep learning; Benchmark (surveying); Machine learning; Quantization (signal processing); Context (archaeology); Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007444421,0.001346586,0.0006416983,0.0008863672,0.0002833742,0.0007372402,0.001821323,0.0008256244,0.003093328],"category_scores_gemma":[0.002547314,0.000256533,0.0004708969,0.0009720594,0.0004695457,0.001107094,0.001037113,0.0007919061,0.001375139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006656598,"about_ca_system_score_gemma":0.0004792703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007837358,"about_ca_topic_score_gemma":0.01103456,"domain_scores_codex":[0.9991826,0.0001653682,0.00008591307,0.0003038462,0.0001765068,0.00008572189],"domain_scores_gemma":[0.9994068,0.0001955411,0.00004780676,0.0001595933,0.0001210422,0.00006917909],"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":[0.003442883,0.002268863,0.03455305,0.002552225,0.001086877,0.0009019489,0.0003302003,0.2964884,0.02409686,0.006281342,0.1579833,0.4700141],"study_design_scores_gemma":[0.0003245596,0.00148191,0.02876429,0.0001191732,0.0001127408,0.0006137756,0.0003326201,0.9024643,0.0354045,0.004966165,0.02530989,0.000106129],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7740932,0.003508181,0.1222854,0.001042322,0.001989196,0.0009608103,0.03732396,0.03733,0.02146711],"genre_scores_gemma":[0.8977885,0.0007606576,0.05545411,0.0004324594,0.00009928724,0.0004216303,0.03989928,0.0003809637,0.004763116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007837358,"threshold_uncertainty_score":0.01558346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04938194676671396,"score_gpt":0.2672890150702518,"score_spread":0.2179070683035378,"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."}}