{"id":"W3162789749","doi":"10.1109/wcnc49053.2021.9417253","title":"Missing Data Inference for Crowdsourced Radio Map Construction: An Adversarial Auto-Encoder Method","year":2021,"lang":"en","type":"article","venue":"","topic":"Indoor and Outdoor Localization Technologies","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Inference; Missing data; Crowdsourcing; Scheme (mathematics); Data mining; Encoder; Deep learning; Artificial intelligence; Adversarial system; Machine learning; Quality (philosophy); Matrix completion","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":[0.0001643002,0.0001304793,0.0001746428,0.00006209948,0.000117937,0.0001098002,0.0003045172,0.0001580036,0.0003436617],"category_scores_gemma":[0.0002524275,0.0001313481,0.00003451885,0.0001726129,0.00005052451,0.0003722745,0.0000970964,0.0001163166,0.000009047639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003648618,"about_ca_system_score_gemma":0.00007416704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001068253,"about_ca_topic_score_gemma":0.00001926883,"domain_scores_codex":[0.99917,0.00002875964,0.000212021,0.0002792193,0.000100935,0.0002090883],"domain_scores_gemma":[0.9990656,0.0001222174,0.0000232891,0.0006420588,0.00009578638,0.00005102954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007540624,0.00009105463,0.001114536,0.0006482588,0.0004396842,0.00004975776,0.001402708,0.1459714,0.05387808,0.1449154,0.03096447,0.6204492],"study_design_scores_gemma":[0.0006122834,0.00001607215,0.00004002861,0.00001739623,0.00003551252,0.00003018881,0.0008572296,0.8556647,0.08568953,0.002884813,0.05390352,0.0002487023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004267238,0.0001167702,0.9950265,0.0002903026,0.0009114477,0.000111922,0.00004908045,0.00121398,0.001853282],"genre_scores_gemma":[0.0905496,0.00001901379,0.9083154,0.0001014304,0.0002442516,0.00001208153,0.0003479618,0.00003523102,0.0003750401],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7096933,"threshold_uncertainty_score":0.5356222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04066670652942805,"score_gpt":0.3122847258207017,"score_spread":0.2716180192912737,"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."}}