{"id":"W3172073922","doi":"10.5194/agile-giss-2-21-2021","title":"Using eigen decomposition and sequence-based representation to extract movement patterns from contextualized tracking data","year":2021,"lang":"en","type":"article","venue":"AGILE GIScience Series","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Categorical variable; Dimensionality reduction; Computer science; Principal component analysis; Set (abstract data type); Curse of dimensionality; Artificial intelligence; Representation (politics); Data mining; Biome; Data set; Sequence (biology); Pattern recognition (psychology); Geography; Ecology; Machine learning; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0002527934,0.00009660084,0.0001082365,0.00002250691,0.0003313304,0.0001246426,0.0002393016,0.00004160216,0.000808501],"category_scores_gemma":[0.0001267089,0.0000997352,0.00001836622,0.0002135825,0.0001712254,0.001433542,0.0002783325,0.00005720744,0.00002650266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008313403,"about_ca_system_score_gemma":0.00004622248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001997267,"about_ca_topic_score_gemma":0.002705892,"domain_scores_codex":[0.9987315,0.0001056205,0.0001958669,0.0005422604,0.0002350735,0.0001897002],"domain_scores_gemma":[0.9993253,0.00009079026,0.00007972212,0.0004044561,0.00002129843,0.00007843401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002823227,0.00004707013,0.7588591,0.000002940772,0.000006614362,0.00002780855,0.0006694059,0.002104384,0.229769,0.00006192234,0.000139025,0.008284509],"study_design_scores_gemma":[0.0002707723,0.00004153256,0.923781,0.00003723967,0.00002139631,0.000009399618,0.0009667798,0.01737397,0.0556495,0.001244397,0.0004170733,0.0001869266],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.977305,0.00002410493,0.02048048,0.001611903,0.0001443699,0.0001603999,0.00008581716,0.00002617088,0.0001617529],"genre_scores_gemma":[0.9840916,0.00001179817,0.01297619,0.002622803,0.00002738023,0.00001202007,0.0001893896,0.000005626139,0.00006319354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1741195,"threshold_uncertainty_score":0.8852519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1282803332838962,"score_gpt":0.3555813841266788,"score_spread":0.2273010508427825,"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."}}