{"id":"W4388520051","doi":"10.1109/ojvt.2023.3331185","title":"Machine Learning-Based Self-Interference Cancellation for Full-Duplex Radio: Approaches, Open Challenges, and Future Research Directions","year":2023,"lang":"en","type":"article","venue":"IEEE Open Journal of Vehicular Technology","topic":"Full-Duplex Wireless Communications","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); Memorial University of Newfoundland","funders":"","keywords":"Computer science; Single antenna interference cancellation; Wireless; Interference (communication); Computer engineering; Electronic engineering; Key (lock); Spectral efficiency; Overhead (engineering); Duplex (building); Open research; Computational complexity theory; Telecommunications; Engineering; Algorithm; Channel (broadcasting)","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":[0.001663886,0.0001835758,0.0004116533,0.0007917318,0.0003786752,0.0001656918,0.001894923,0.0002999721,0.0000149339],"category_scores_gemma":[0.000129427,0.0001775159,0.00006337342,0.0009604173,0.0001242873,0.000283677,0.0003546554,0.001203648,0.00001061541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001941153,"about_ca_system_score_gemma":0.0001299199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003605164,"about_ca_topic_score_gemma":0.0004457236,"domain_scores_codex":[0.998533,0.0002049113,0.0004421512,0.0002496188,0.0002012763,0.0003691017],"domain_scores_gemma":[0.998581,0.0002598527,0.0001675411,0.0005511779,0.0003435815,0.00009683198],"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":[0.0002082425,0.0002498624,0.0002403051,0.0003167151,0.000583549,0.00005187155,0.001183825,0.7576758,0.01540601,0.00596352,0.002757348,0.2153629],"study_design_scores_gemma":[0.001289817,0.0004513065,0.0002649709,0.0001240142,0.00004178613,0.0001559429,0.0008431207,0.7294031,0.0025805,0.0001770427,0.2644508,0.0002176168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7737564,0.138742,0.008284462,0.06812947,0.001792224,0.005830089,0.0001018993,0.00169402,0.001669447],"genre_scores_gemma":[0.951603,0.03567801,0.01196099,0.000009191263,0.0001741705,0.0003153473,0.00003311296,0.00008018529,0.0001460198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2616934,"threshold_uncertainty_score":0.7238887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1183643174914587,"score_gpt":0.3278546221854314,"score_spread":0.2094903046939727,"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."}}