{"id":"W3037900478","doi":"10.1109/jiot.2020.3004223","title":"Dynamic Computation Offloading in IoT Fog Systems With Imperfect Channel-State Information: A POMDP Approach","year":2020,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Partially observable Markov decision process; Energy consumption; Markov decision process; Computation offloading; Channel (broadcasting); Distributed computing; Mobile device; Computation; Wireless; Real-time computing; Computer network; Markov process; Internet of Things; Markov chain; Embedded system; Markov model; Edge computing; Telecommunications; Algorithm; Machine learning","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":[0.0006988092,0.0001855922,0.0003193489,0.0003023427,0.00007389826,0.0005553194,0.00077237,0.00005657265,5.187784e-7],"category_scores_gemma":[0.00003506862,0.0001544985,0.00007978921,0.0004524286,0.00003135717,0.001679638,0.0001341184,0.0005447047,0.00001286815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00013351,"about_ca_system_score_gemma":0.00009266092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000938527,"about_ca_topic_score_gemma":5.30027e-7,"domain_scores_codex":[0.9982665,0.00009638999,0.0006844298,0.000196337,0.0004338662,0.0003224331],"domain_scores_gemma":[0.9988826,0.00006259421,0.0006069815,0.0001134136,0.00019209,0.0001423025],"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":[0.0004488885,0.0002100162,0.002327326,0.00124846,0.0003862087,0.0002627967,0.282074,0.6409042,0.001940731,0.0003808716,0.008944181,0.06087235],"study_design_scores_gemma":[0.0006698241,0.0003123526,0.0002160486,0.0003728173,0.000005954361,0.0006866434,0.000196261,0.9967369,0.0003676863,0.0001275992,0.00012896,0.0001788837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2530571,0.0000734558,0.7434241,0.000299424,0.002451336,0.0001290476,1.529039e-7,0.0000581959,0.000507173],"genre_scores_gemma":[0.9824308,0.000004084444,0.01696529,0.0003069333,0.0002607544,0.000002481858,0.000001632454,0.00001092424,0.00001709646],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7293737,"threshold_uncertainty_score":0.6300267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01263711388045727,"score_gpt":0.2188937631320996,"score_spread":0.2062566492516423,"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."}}