{"id":"W4205576441","doi":"10.1109/smc52423.2021.9659265","title":"Collision Detection: An Improved Deep Learning Approach Using SENet and ResNext","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Collision; Computer science; Deep learning; Artificial intelligence; Machine learning; Field (mathematics); Overhead (engineering); Baseline (sea); Population; Computer security; Mathematics; Medicine","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":[0.0005020844,0.001225208,0.000880389,0.001031656,0.0003751996,0.000618614,0.002785676,0.0009408497,0.0039021],"category_scores_gemma":[0.0009944845,0.0005526077,0.0008818317,0.0008396152,0.000370619,0.001313099,0.001234817,0.001331142,0.001128291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008045064,"about_ca_system_score_gemma":0.001407512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01508342,"about_ca_topic_score_gemma":0.02304208,"domain_scores_codex":[0.999738,0.00002566624,0.00001213935,0.00008767215,0.00007314308,0.00006324871],"domain_scores_gemma":[0.9997471,0.0000452599,0.00002539906,0.00003516759,0.0001198733,0.00002723357],"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":[0.0006871175,0.0005498648,0.005819548,0.0001323713,0.0002402499,0.0002726696,0.00005300214,0.564948,0.005865532,0.003788664,0.01495932,0.4026837],"study_design_scores_gemma":[0.00001224514,0.00007461553,0.0002708822,0.000005723511,0.00001650231,0.00003798426,0.000006005784,0.9962644,0.00157245,0.0007506869,0.0009805516,0.000007933912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1612575,0.001765985,0.8156998,0.000820422,0.0005636294,0.0002375566,0.001324083,0.009647672,0.008683317],"genre_scores_gemma":[0.8397822,0.0005575468,0.1407216,0.000587289,0.0001117046,0.0001895636,0.003102569,0.0002708785,0.01467668],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01508342,"threshold_uncertainty_score":0.02999127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06065582340973732,"score_gpt":0.3013403357631358,"score_spread":0.2406845123533985,"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."}}