{"id":"W3001393370","doi":"10.13140/rg.2.2.21591.21924","title":"NEAR REAL-TIME MAP BUILDING WITH MULTI-CLASS IMAGE SET LABELLING AND CLASSIFICATION OF ROAD CONDITIONS USING CONVOLUTIONAL NEURAL NETWORKS","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Convolutional neural network; Leverage (statistics); Computer science; Transfer of learning; Set (abstract data type); Artificial intelligence; Deep learning; Labelling; Data set; Class (philosophy); Construct (python library); Artificial neural network; Pattern recognition (psychology)","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":[0.00006933096,0.0002739221,0.0003157047,0.000105782,0.0001572824,0.00005368083,0.0001856539,0.0002152453,0.00001281145],"category_scores_gemma":[0.000008275234,0.0003156605,0.00007205913,0.0002012566,0.0002104934,0.0002002777,0.000164642,0.000518277,0.000002899428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001878482,"about_ca_system_score_gemma":0.00005500862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009860915,"about_ca_topic_score_gemma":0.000006755897,"domain_scores_codex":[0.9989935,0.0000391651,0.0002036426,0.0004289318,0.00006094241,0.0002738169],"domain_scores_gemma":[0.9992943,0.00004275984,0.0001626112,0.0002511137,0.0001400472,0.0001091139],"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":[0.00002841054,0.000006821727,0.001786287,0.0001558152,0.0001110746,0.00004491411,0.0001003685,0.9779122,0.01875298,0.001030519,0.00004523108,0.00002540903],"study_design_scores_gemma":[0.0004476215,0.00001765549,0.004586109,0.0002017529,0.000150118,0.000007088987,0.0001178244,0.9936047,0.0002818093,0.0002646662,0.00001936059,0.0003012468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7427595,0.00004569168,0.2564299,0.00001176065,0.0002541581,0.0001849477,0.00007851402,0.0001517589,0.00008374757],"genre_scores_gemma":[0.9915872,0.00007605802,0.008000103,0.000005781209,0.0001432455,8.968215e-7,0.0001128757,0.00004391135,0.000029989],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2488276,"threshold_uncertainty_score":0.9999295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04868556593797495,"score_gpt":0.2032667118289482,"score_spread":0.1545811458909733,"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."}}