{"id":"W2914434280","doi":"10.1109/tii.2019.2897001","title":"MASM: A Multiple-Algorithm Service Model for Energy-Delay Optimization in Edge Artificial Intelligence","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Beijing Municipal Commission of Education; National Natural Science Foundation of China","keywords":"Computer science; Mobile edge computing; Cloudlet; Edge computing; Computation; Workload; Optimization problem; Computation offloading; Enhanced Data Rates for GSM Evolution; Distributed computing; Cloud computing; Artificial intelligence; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0004023346,0.0002306818,0.0002606318,0.0003985859,0.0001862762,0.000222931,0.0006151831,0.0003093833,0.000005476851],"category_scores_gemma":[0.00001426579,0.0002404875,0.0001042594,0.000943065,0.00001940707,0.001094567,0.00001014069,0.0004080882,0.00004940598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001551006,"about_ca_system_score_gemma":0.000240057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006185282,"about_ca_topic_score_gemma":0.00002120465,"domain_scores_codex":[0.9981604,0.00003564375,0.0008816777,0.0002166319,0.0002826613,0.0004230448],"domain_scores_gemma":[0.9988115,0.0002881438,0.0002030008,0.0004154404,0.0001819815,0.00009991325],"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":[0.00003251157,0.00007828832,0.00000121368,0.0000145639,0.00001013364,3.165384e-7,0.001787923,0.814177,0.00000686541,0.0003462786,0.0001083245,0.1834366],"study_design_scores_gemma":[0.000560247,0.0001116922,1.588486e-7,0.00006595832,0.000009710901,0.000004914305,0.0001486262,0.9949696,0.002944113,0.000614818,0.0002956653,0.0002744877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001654053,0.000002018841,0.9893591,0.0002114843,0.007872703,0.0005355706,0.000009079957,0.000146295,0.0002096699],"genre_scores_gemma":[0.3456515,0.00001384364,0.6517696,0.001040192,0.001008328,0.000149255,0.0000283562,0.00004464207,0.0002942483],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3439974,"threshold_uncertainty_score":0.9806796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0757528923251239,"score_gpt":0.2636674138298111,"score_spread":0.1879145215046872,"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."}}