{"id":"W3013276295","doi":"10.1109/access.2020.2983003","title":"SMOTEFUNA: Synthetic Minority Over-Sampling Technique Based on Furthest Neighbour Algorithm","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"European Social Fund; Magyarország Kormánya","keywords":"Computer science; Algorithm; Sampling (signal processing); Detector; Telecommunications","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003137445,0.000265536,0.0002636491,0.0001569697,0.0001571888,0.0005280967,0.003162108,0.0001479568,0.00003950806],"category_scores_gemma":[0.0001617541,0.00026058,0.00009196206,0.0008004647,0.00006684001,0.001017146,0.000290461,0.0003637558,0.00007178071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000955764,"about_ca_system_score_gemma":0.0001101327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005735739,"about_ca_topic_score_gemma":0.000001799727,"domain_scores_codex":[0.9978701,0.0001086554,0.0003465611,0.0008246935,0.0004727915,0.0003771235],"domain_scores_gemma":[0.9979583,0.0002428773,0.000206771,0.001284817,0.0001103594,0.0001968588],"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":[0.00009089964,0.001012247,0.00378968,0.0004164056,0.00006680464,0.0001636704,0.0004569188,0.001456587,0.1149178,0.03135382,0.01835788,0.8279173],"study_design_scores_gemma":[0.0003924738,0.0002191874,0.004447513,0.0001060276,0.0000140408,0.00000884635,0.000004925857,0.4872396,0.4866076,0.003939664,0.01630081,0.0007192672],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005661537,0.00001378261,0.9927079,0.003116421,0.0002592558,0.0005055277,0.00005595794,0.001309923,0.001465084],"genre_scores_gemma":[0.6680821,0.00001019776,0.3266169,0.004803022,0.0002311005,0.0001959913,0.00001607025,0.0000269373,0.00001773866],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.827198,"threshold_uncertainty_score":0.9999846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06019594001374554,"score_gpt":0.3177182528903892,"score_spread":0.2575223128766436,"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."}}