{"id":"W4224292997","doi":"10.1145/3530908","title":"EdgeWise: Energy-efficient CNN Computation on Edge Devices under Stochastic Communication Delays","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Embedded Computing Systems","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Energy consumption; Edge device; Workload; Enhanced Data Rates for GSM Evolution; Efficient energy use; Edge computing; Computation; Energy (signal processing); Markov decision process; Real-time computing; Distributed computing; Computer engineering; Embedded system; Markov process; Algorithm; Cloud computing; Artificial intelligence","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":[0.0002480635,0.0006032035,0.0003463594,0.0001693239,0.0002519233,0.000576139,0.001241224,0.0004930968,0.002379332],"category_scores_gemma":[0.0007415893,0.0002214618,0.0002892764,0.000202544,0.0003198769,0.001050225,0.0008586204,0.0007180024,0.0002685706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00080651,"about_ca_system_score_gemma":0.001055914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005459769,"about_ca_topic_score_gemma":0.01071953,"domain_scores_codex":[0.9998611,0.00002012194,0.000005473153,0.00003306518,0.00004110769,0.00003904027],"domain_scores_gemma":[0.9998806,0.00004525113,0.00001166838,0.00002246724,0.00002712326,0.00001287817],"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":[0.0001923328,0.00005143993,0.0006181066,0.00006591778,0.00003140259,0.0001632153,0.00003994324,0.8968266,0.01084736,0.01694429,0.002959576,0.07125992],"study_design_scores_gemma":[0.000002731723,0.000008948905,0.0000348736,0.000001723214,0.000002055078,0.000006609191,0.000003191735,0.9968097,0.00145393,0.001331558,0.0003427507,0.000001787545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05843319,0.0003749059,0.93305,0.0002210835,0.00009681423,0.00004810162,0.0001264231,0.001490743,0.006158816],"genre_scores_gemma":[0.8223755,0.0002754784,0.1718331,0.0001660517,0.00003355336,0.00008349675,0.0002188797,0.000131,0.004882872],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005459769,"threshold_uncertainty_score":0.01085597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0263423239433636,"score_gpt":0.2648530679194582,"score_spread":0.2385107439760946,"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."}}