{"id":"W2913697492","doi":"10.1016/j.autcon.2019.01.017","title":"Sewer damage detection from imbalanced CCTV inspection data using deep convolutional neural networks with hierarchical classification","year":2019,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":175,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Deep learning; Process (computing); Offset (computer science); Pattern recognition (psychology); Contextual image classification; Machine learning; Artificial neural network; Image (mathematics)","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":[0.0002702415,0.0009078818,0.0006696316,0.00143079,0.0002528216,0.0004541568,0.0007129978,0.0006532553,0.001012029],"category_scores_gemma":[0.0007711242,0.0002997246,0.0006101229,0.001028131,0.0002054652,0.0005953912,0.0008365975,0.0008423846,0.0006559666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006176208,"about_ca_system_score_gemma":0.0007271002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02401417,"about_ca_topic_score_gemma":0.04115853,"domain_scores_codex":[0.9997097,0.00002263608,0.0000113567,0.00009035387,0.00006937039,0.00009666221],"domain_scores_gemma":[0.999668,0.00007345348,0.00005122494,0.00005745653,0.0001219189,0.00002796264],"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":[0.001030725,0.001130258,0.08231793,0.0002217762,0.00031036,0.0005809137,0.0001651373,0.226129,0.04121847,0.001193086,0.0240118,0.6216906],"study_design_scores_gemma":[0.000008904249,0.0000400505,0.01605536,0.00001259075,0.00002916007,0.00003329384,0.00003655278,0.978458,0.003976371,0.0006055082,0.0007339295,0.0000102422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8153595,0.00134673,0.1677591,0.0005909813,0.0002855288,0.0001018979,0.005563519,0.004449412,0.004543346],"genre_scores_gemma":[0.9721597,0.0001785073,0.01886128,0.00008368208,0.0000637483,0.00003646238,0.005709769,0.00005448284,0.002852271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02401417,"threshold_uncertainty_score":0.0477488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0116575526586173,"score_gpt":0.2227223710027695,"score_spread":0.2110648183441522,"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."}}