{"id":"W2920757090","doi":"10.1109/globalsip.2018.8646338","title":"DATA-DRIVEN PREDICTION OF CELLULAR NETWORKS COVERAGE: AN INTERPRETABLE MACHINE-LEARNING MODEL","year":2018,"lang":"en","type":"article","venue":"","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Communications Research Centre Canada","funders":"","keywords":"Computer science; Context (archaeology); Key (lock); Service provider; Cellular network; Wireless; Wireless network; Data modeling; Data mining; Machine learning; Fuse (electrical); Term (time); Interpolation (computer graphics); Quality of service; Mobile broadband; Distributed computing; Service (business); Artificial intelligence; Computer network; Telecommunications; Database; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003549907,0.00009741552,0.0002720703,0.0001188927,0.0000862364,0.00004567378,0.0004182872,0.00007566161,0.001535026],"category_scores_gemma":[0.00004092299,0.0001015035,0.00004960059,0.0001848799,0.00004458542,0.0006133984,0.0001918438,0.0001234623,0.0001206842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001707201,"about_ca_system_score_gemma":0.000007987698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002213896,"about_ca_topic_score_gemma":0.0003251217,"domain_scores_codex":[0.9989854,0.00001714035,0.0004335043,0.0003733408,0.00003061719,0.0001600218],"domain_scores_gemma":[0.9990189,0.00001627979,0.0002203674,0.0006479255,0.00003561949,0.00006087515],"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":[0.00009823673,0.0002552799,0.3039323,0.0000353978,0.0003949977,0.000002114406,0.0005884888,0.6509488,0.0004775664,0.03462432,0.003899194,0.004743265],"study_design_scores_gemma":[0.0001563619,0.00009853302,0.0007856283,0.000004657774,0.00002078281,4.156649e-7,0.0000124522,0.9925063,0.00004960373,0.001469011,0.004798646,0.00009756217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04418381,0.0002224868,0.9387998,0.00002187912,0.00016001,0.0000600511,0.00170714,0.00004168613,0.01480315],"genre_scores_gemma":[0.9938625,0.0001634214,0.002120916,0.00008320931,0.0001704788,0.000002314313,0.002372037,0.00001438282,0.001210736],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9496787,"threshold_uncertainty_score":0.9993777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05660998325965361,"score_gpt":0.2302554857556299,"score_spread":0.1736455024959763,"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."}}