{"id":"W4402473808","doi":"10.1109/ccece59415.2024.10667341","title":"On the Effectiveness of Training Objectives of Pretrained Models for Inertial Sensor Data*","year":2024,"lang":"en","type":"article","venue":"","topic":"Inertial Sensor and Navigation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Training (meteorology); Training set; Artificial intelligence; Inertial measurement unit; Machine learning","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":[0.005313405,0.002438304,0.0008003153,0.0005058668,0.0004430503,0.001130072,0.00131205,0.002186018,0.001567845],"category_scores_gemma":[0.02991927,0.0007079003,0.0005839084,0.0003215018,0.001161095,0.003680358,0.001731558,0.003526832,0.0005810792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113664,"about_ca_system_score_gemma":0.001423066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006426218,"about_ca_topic_score_gemma":0.00765286,"domain_scores_codex":[0.9981321,0.0009717509,0.0001144622,0.0004235671,0.0001989036,0.0001592851],"domain_scores_gemma":[0.9810494,0.01597024,0.0006587675,0.001149735,0.000889947,0.000281874],"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":[0.001153732,0.000579154,0.009250068,0.0003169502,0.000233119,0.0001120266,0.0002122376,0.7714109,0.007257872,0.003141916,0.002480046,0.2038519],"study_design_scores_gemma":[0.00001853052,0.0002875694,0.0007417492,0.00003176,0.00002084433,0.00002190639,0.00003140765,0.9942135,0.003151172,0.001298368,0.0001726658,0.00001055258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.598638,0.003421058,0.3869812,0.001982797,0.0002475264,0.0002051684,0.0004293921,0.002902174,0.005192603],"genre_scores_gemma":[0.9322683,0.0004152672,0.063819,0.0005512576,0.00005517072,0.0001120177,0.0007819107,0.0001578939,0.001839121],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006426218,"threshold_uncertainty_score":0.02810031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03981883087315456,"score_gpt":0.2699531530875223,"score_spread":0.2301343222143677,"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."}}