{"id":"W3184074903","doi":"10.22215/etd/2021-14478","title":"Investigation of Few-Shot Learning for Fall Detection","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Generalizability theory; Deep learning; Artificial intelligence; Computer science; Convolutional neural network; Wearable computer; Shot (pellet); Modalities; Machine learning; Embedded system; Psychology","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":[0.0001467479,0.0001345556,0.0001843801,0.0001576087,0.0001538602,0.00007017301,0.0002819604,0.0002186534,0.00001335591],"category_scores_gemma":[0.00004530913,0.000143601,0.0001401432,0.0004039783,0.00001223175,0.0001635062,0.0000268929,0.0001790091,0.000004166086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003637559,"about_ca_system_score_gemma":0.00009970053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000103708,"about_ca_topic_score_gemma":0.0003513198,"domain_scores_codex":[0.9990283,0.00003004477,0.0003161736,0.0003574672,0.0001528712,0.0001151876],"domain_scores_gemma":[0.998912,0.00006354838,0.0003224615,0.0002864322,0.000373785,0.00004172624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002940907,0.00005090327,0.0002542495,0.0007199453,0.00009777794,7.499281e-7,0.001864538,0.0001634611,0.4998799,0.09646697,0.001017105,0.399455],"study_design_scores_gemma":[0.0001064769,0.0001445033,0.001145034,0.00005959546,0.00002324576,0.000002713027,0.0003327053,0.01652568,0.9689441,0.006352793,0.006133636,0.0002294939],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03004355,0.00006812574,0.9637547,0.00005893017,0.0002263,0.0003997281,0.000001371379,0.0003166197,0.005130732],"genre_scores_gemma":[0.9061894,0.00006296007,0.06869934,0.00005601933,0.00008934105,0.0005686075,0.0003767976,0.00002775359,0.02392977],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8950553,"threshold_uncertainty_score":0.5855879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02816974352447025,"score_gpt":0.2790733379371244,"score_spread":0.2509035944126541,"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."}}