{"id":"W4389076731","doi":"10.1109/jiot.2023.3336600","title":"Adaptive Device-Edge Collaboration on DNN Inference in AIoT: A Digital-Twin-Assisted Approach","year":2023,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Carleton University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Inference; Artificial intelligence; Task (project management); Overhead (engineering); Enhanced Data Rates for GSM Evolution; Edge device; Artificial neural network; Machine learning; Workload; Upload; Cloud computing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001673227,0.001228013,0.00121189,0.0005812442,0.0008431334,0.001319659,0.002570702,0.001439398,0.0020784],"category_scores_gemma":[0.004743039,0.0005975572,0.0005992416,0.0006658495,0.0008653583,0.003368064,0.002530582,0.001849026,0.0003385122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001050966,"about_ca_system_score_gemma":0.002001466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006812544,"about_ca_topic_score_gemma":0.01270209,"domain_scores_codex":[0.998915,0.0002335498,0.00006869901,0.0003383364,0.0002541135,0.0001903667],"domain_scores_gemma":[0.9982547,0.0007665004,0.0001443063,0.0002539209,0.0004011564,0.0001793677],"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":[0.0005115117,0.0002728661,0.003004113,0.0001281113,0.00009918934,0.0003701193,0.0002695596,0.7487934,0.009678205,0.01235083,0.002269266,0.2222527],"study_design_scores_gemma":[0.000006461172,0.0000246316,0.00009958557,0.000003573286,0.00001193029,0.00002305559,0.00001684361,0.9938844,0.001543534,0.004059365,0.0003205627,0.000006192671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02866472,0.0002657264,0.9679671,0.0002048803,0.00006966953,0.00005812708,0.00005525997,0.0006135039,0.002100951],"genre_scores_gemma":[0.8203796,0.0001774311,0.1759657,0.0003015448,0.00007740088,0.00008533395,0.0001814289,0.0001106642,0.002721012],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006812544,"threshold_uncertainty_score":0.01354575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04508313692275029,"score_gpt":0.289127198594528,"score_spread":0.2440440616717777,"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."}}