{"id":"W4320496975","doi":"10.3390/rs15040982","title":"Data Preparation Impact on Semantic Segmentation of 3D Mobile LiDAR Point Clouds Using Deep Neural Networks","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Université Laval; Nvidia","keywords":"Computer science; Point cloud; Segmentation; Artificial intelligence; Lidar; Deep learning; Margin (machine learning); Convolutional neural network; Artificial neural network; Kernel (algebra); Deep neural networks; Data mining; Pattern recognition (psychology); Machine learning; Remote sensing","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":[0.0002502064,0.0001399963,0.000203251,0.0001452956,0.00006951005,0.00004111321,0.0000806317,0.00006205896,0.000003558032],"category_scores_gemma":[0.00001931003,0.000134312,0.00006826742,0.0004425304,0.00001147695,0.0001385056,0.00004356551,0.0001165191,0.000008644456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007550677,"about_ca_system_score_gemma":0.00001016017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001086874,"about_ca_topic_score_gemma":0.00001791333,"domain_scores_codex":[0.9990949,0.00004530139,0.0002744963,0.000205942,0.0001620918,0.0002172819],"domain_scores_gemma":[0.9993786,0.00005484866,0.00006391501,0.0004238935,0.00003701236,0.00004173714],"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":[0.000008995311,0.000002560225,0.000009258566,0.00002589401,0.0000524487,0.000006210718,0.0002045984,0.9218448,0.01529198,8.013296e-8,0.00002554317,0.06252757],"study_design_scores_gemma":[0.0001043532,0.00003086339,0.00003599278,0.00008385592,0.00008303761,0.00001004623,0.000108581,0.9979205,0.001482586,0.00001561831,0.000001496413,0.0001230317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6232352,0.00007188656,0.3763029,0.000004160493,0.0001153074,0.00007007168,0.000005269116,0.0001605045,0.00003471752],"genre_scores_gemma":[0.9939009,0.00004225646,0.00562401,0.000009823668,0.0001547792,1.37977e-8,0.0002250995,0.00003682083,0.000006327247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3706789,"threshold_uncertainty_score":0.5477084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03198507911452166,"score_gpt":0.3080154422653779,"score_spread":0.2760303631508562,"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."}}