{"id":"W2019577451","doi":"10.3390/ijgi2030854","title":"An Improved Neural Network Training Algorithm for Wi-Fi Fingerprinting Positioning","year":2013,"lang":"en","type":"article","venue":"ISPRS International Journal of Geo-Information","topic":"Indoor and Outdoor Localization Technologies","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"RSS; Computer science; Artificial neural network; Signal strength; Algorithm; Location-based service; Real-time computing; Mean squared error; Indoor positioning system; Data mining; Artificial intelligence; Computer network; Wireless sensor network; Accelerometer; Mathematics; Statistics","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":[0.0002939098,0.0001339736,0.0001589238,0.0002818181,0.0001301814,0.0003848659,0.0003713174,0.0001054149,0.00005326701],"category_scores_gemma":[0.0001061517,0.0001307221,0.0001078813,0.0001137801,0.0000251576,0.004578032,0.00002446558,0.0002157676,0.00001575988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001210167,"about_ca_system_score_gemma":0.00002920956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001304646,"about_ca_topic_score_gemma":0.000001306728,"domain_scores_codex":[0.9987356,0.00001210476,0.0006907863,0.00005176433,0.0002733641,0.0002363793],"domain_scores_gemma":[0.9986269,0.00006068251,0.0003309778,0.00008594058,0.0008363926,0.00005904089],"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":[0.00001358729,0.000007581986,0.0001171504,0.00001393867,0.00009198747,0.00000100984,0.001220241,0.2270959,0.0006266517,0.0006099108,0.001226747,0.7689753],"study_design_scores_gemma":[0.0006288241,0.00009503464,0.0008276644,0.00006217005,0.00001428682,0.00007419586,0.001254156,0.9907556,0.002001098,0.001262754,0.002866992,0.0001572544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04699749,0.0000387666,0.9495113,0.000268333,0.002315697,0.0002008059,0.00002034129,0.0002011205,0.0004460819],"genre_scores_gemma":[0.9271193,0.00002089532,0.071757,0.0003417709,0.0006245913,0.00002122006,0.00009468618,0.0000146872,0.000005900034],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8801218,"threshold_uncertainty_score":0.5330691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005624948004334438,"score_gpt":0.2227190325928814,"score_spread":0.217094084588547,"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."}}