{"id":"W3121969052","doi":"10.1109/tsmc.2020.3048696","title":"Attention-Based Sequence-to-Sequence Learning for Online Structural Response Forecasting Under Seismic Excitation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Systems","topic":"Structural Health Monitoring Techniques","field":"Engineering","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Recurrent neural network; Computer science; Earthquake shaking table; Sequence (biology); Structural health monitoring; Autoencoder; Time series; Warning system; Artificial intelligence; Deep learning; Data mining; Machine learning; Artificial neural network; Engineering; Structural engineering; Telecommunications","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.0003401105,0.0002988329,0.0003510515,0.000242887,0.0003103334,0.0001879067,0.0001201841,0.0001897958,0.000002591598],"category_scores_gemma":[0.0000262228,0.0003176579,0.0000871968,0.0003175966,0.000039753,0.0001089644,0.0000017299,0.0003247779,0.000005105247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004220967,"about_ca_system_score_gemma":0.00007943769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002304243,"about_ca_topic_score_gemma":0.00003818518,"domain_scores_codex":[0.9980609,0.0002381941,0.0005955042,0.0003987603,0.0002974553,0.0004091594],"domain_scores_gemma":[0.9986805,0.0004774256,0.0001094395,0.0002776091,0.0002625767,0.000192492],"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":[0.00009177002,0.000008787326,0.00005896587,0.0008838006,0.00004152162,0.00001083599,0.0002580826,0.9760376,0.01723176,0.00007783368,0.00002989776,0.00526919],"study_design_scores_gemma":[0.0005355727,0.0002354485,0.001189992,0.001220298,0.00004150337,0.0001570215,0.001110404,0.9916164,0.002934645,0.00005812623,0.0005087091,0.0003918549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6421762,0.0002237812,0.3543634,0.00005846416,0.001967741,0.0006610195,0.00009526189,0.0004399923,0.00001415546],"genre_scores_gemma":[0.9960852,0.00002717211,0.002612069,0.00003297802,0.0001947786,0.0002813617,0.00003270564,0.00008385759,0.0006499079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.353909,"threshold_uncertainty_score":0.9999275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06599065153340139,"score_gpt":0.3057209166497791,"score_spread":0.2397302651163777,"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."}}