{"id":"W2939355860","doi":"10.1109/tim.2019.2909940","title":"DM-RIS: Deep Multimodel Rail Inspection System With Improved MRF-GMM and CNN","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University; University of Windsor","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; Education Department of Hunan Province","keywords":"Markov random field; Artificial intelligence; Mixture model; Computer science; Computer vision; Segmentation; Pixel; Expectation–maximization algorithm; Pattern recognition (psychology); Dirt; Frame (networking); Image segmentation; Engineering; Mathematics; Maximum likelihood","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":[0.000111202,0.0001776376,0.0001413346,0.0001201726,0.0001435388,0.00005452496,0.00003202301,0.00006090531,0.000009034792],"category_scores_gemma":[5.710181e-7,0.000155403,0.00002604842,0.00009000008,0.00002351415,0.0002258478,5.818497e-7,0.0001537098,0.000009008993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002974895,"about_ca_system_score_gemma":0.00001600023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006544138,"about_ca_topic_score_gemma":0.0001162098,"domain_scores_codex":[0.9991649,0.00001542319,0.0001879295,0.0002059387,0.0002459408,0.0001798657],"domain_scores_gemma":[0.9996842,0.000006191848,0.00003620577,0.0001210456,0.00007658893,0.00007573672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005919012,0.0001244407,0.001466511,0.001260474,0.0006407473,0.000004494585,0.005628547,0.3222392,0.3560758,0.0002707955,0.00007286652,0.3116241],"study_design_scores_gemma":[0.007024019,0.0006447952,0.005396363,0.0005759515,0.0001851619,0.00006945006,0.009358942,0.6738404,0.3017339,0.00001290654,0.0004149012,0.0007432624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4945379,0.00004878565,0.5027693,0.0000216881,0.001112463,0.0004459357,0.000004449642,0.0003532474,0.0007062864],"genre_scores_gemma":[0.9982829,0.0000691585,0.001444355,0.00002814615,0.00003957068,0.00008013734,0.000001710093,0.00002651661,0.0000275222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.503745,"threshold_uncertainty_score":0.633715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007656902211170655,"score_gpt":0.1798531891088934,"score_spread":0.1721962868977228,"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."}}