{"id":"W3157038070","doi":"10.1109/jiot.2021.3077897","title":"Privacy Preserving and Efficient Data Collection Scheme for AMI Networks Using Deep Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"King Abdulaziz University","keywords":"Computer science; Scheme (mathematics); Computer network; Information privacy; Data collection; Deep learning; Artificial intelligence; Computer security","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":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001461312,0.0001743559,0.0002751854,0.0001906158,0.0002564617,0.0006344225,0.01453721,0.0001425997,0.00001006243],"category_scores_gemma":[0.01585685,0.0001729888,0.00006856758,0.0004137334,0.00008181657,0.001438041,0.04740413,0.0007876743,5.619291e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001157992,"about_ca_system_score_gemma":0.0001042465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005037815,"about_ca_topic_score_gemma":0.000002855749,"domain_scores_codex":[0.9980586,0.0001259219,0.0005113102,0.0005518466,0.0003610597,0.0003912796],"domain_scores_gemma":[0.9957097,0.0003438203,0.0005452202,0.002964747,0.0003468984,0.00008967712],"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":[0.0006344537,0.001261694,0.02981068,0.0009565839,0.002068904,0.0007121234,0.008808861,0.09854954,0.1687735,0.002008577,0.3087115,0.3777036],"study_design_scores_gemma":[0.0004905169,0.00008691812,0.000131009,0.0003054773,0.00001453785,0.0007337275,0.00006065933,0.9794908,0.01328979,0.004098562,0.001131825,0.0001662443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1967149,0.001348198,0.7994604,0.001245731,0.0009588532,0.0001107771,0.000001304532,0.0001167049,0.00004316372],"genre_scores_gemma":[0.3726292,0.0002218236,0.6268974,0.0000668932,0.0001035278,0.00000236647,0.000005511858,0.00001756145,0.00005577314],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8809412,"threshold_uncertainty_score":0.992433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05688638608537772,"score_gpt":0.3072392591663899,"score_spread":0.2503528730810122,"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."}}