{"id":"W4205603079","doi":"10.1109/jsen.2021.3133488","title":"Multiple Binocular Cameras-Based Indoor Localization Technique Using Deep Learning and Multimodal Fusion","year":2021,"lang":"en","type":"article","venue":"IEEE Sensors Journal","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Computer vision; Feature extraction; Pattern recognition (psychology); Fuse (electrical); Image fusion; Deep learning; Feature (linguistics); Pooling; Image (mathematics); Engineering","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":[0.0003496986,0.0009896924,0.0008244382,0.0008925548,0.0002493335,0.0004364317,0.000922225,0.0006297754,0.001815358],"category_scores_gemma":[0.0006887268,0.0003146806,0.0006989025,0.000932393,0.000276268,0.001146926,0.001245218,0.0006626614,0.0006225268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004663366,"about_ca_system_score_gemma":0.0005902534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003059915,"about_ca_topic_score_gemma":0.004236837,"domain_scores_codex":[0.9995572,0.00005883741,0.00001841192,0.0001192283,0.0001710514,0.00007518984],"domain_scores_gemma":[0.99978,0.00003222824,0.00003811972,0.00004443503,0.00008703036,0.00001819169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003172267,0.0001078688,0.002106161,0.0002334543,0.0001464431,0.000330189,0.0001886923,0.08910117,0.08416664,0.004665899,0.003559146,0.8150771],"study_design_scores_gemma":[0.00002494869,0.0001845158,0.001713968,0.00002793028,0.00007624855,0.0004570002,0.00007456128,0.9514451,0.03909094,0.002757562,0.004106031,0.00004116648],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01243246,0.0003269401,0.9844417,0.00007376714,0.0000435383,0.00002290951,0.00005709095,0.0009579555,0.001643647],"genre_scores_gemma":[0.6202456,0.0005716801,0.373555,0.0002437594,0.00007995952,0.0000879013,0.0003570761,0.0001089851,0.004750001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003059915,"threshold_uncertainty_score":0.006084204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009190907211286304,"score_gpt":0.2270567793281961,"score_spread":0.2178658721169098,"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."}}