{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00113517,0.0004422932,0.0004527291,0.000666839,0.002996918,0.0004770578,0.002427079,0.0001140609,0.000008091055],"category_scores_gemma":[0.00002829041,0.0004871797,0.0002141839,0.001500922,0.00007018861,0.0002028289,0.0002438427,0.0007853641,0.00007720412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006515394,"about_ca_system_score_gemma":0.0001723463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001769002,"about_ca_topic_score_gemma":0.000003310313,"domain_scores_codex":[0.9956111,0.000925079,0.000848492,0.0009306241,0.0009972339,0.0006874517],"domain_scores_gemma":[0.995942,0.001389377,0.0004823835,0.001781033,0.0002221006,0.0001831087],"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":[0.00002727095,0.0003863518,0.000004375975,0.00002659126,0.00006189407,0.00000427671,0.001869566,0.9651145,0.00004410042,0.004421852,0.0009274787,0.02711173],"study_design_scores_gemma":[0.0007424593,0.0003982712,0.0001620068,0.0001719441,0.00003451519,0.00009662903,0.0007997056,0.9953714,0.00007118497,0.000657688,0.0009758076,0.0005183911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03548888,0.0003776751,0.9496612,0.0005115124,0.01177452,0.0004449634,0.00000342573,0.0008513695,0.0008864803],"genre_scores_gemma":[0.9909496,0.00000247825,0.007672618,0.0005975617,0.0004627024,0.00008367541,0.00003252089,0.00005389376,0.0001449824],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9554607,"threshold_uncertainty_score":0.999758,"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."}}