{"id":"W4307122032","doi":"10.3390/app122010664","title":"Designing a Deep Q-Learning Model with Edge-Level Training for Multi-Level Task Offloading in Edge Computing Networks","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Mobile device; Mobile edge computing; Edge device; Cloud computing; Server; Enhanced Data Rates for GSM Evolution; Edge computing; Latency (audio); Workload; Task (project management); Distributed computing; Computer network; Artificial intelligence; Operating system; Engineering","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":[0.003830123,0.0003376393,0.0004210579,0.0004446243,0.003322315,0.0004865452,0.00192895,0.00006932294,0.000001353299],"category_scores_gemma":[0.00006957086,0.0003261561,0.00008248159,0.002067574,0.0002107523,0.0004546083,0.001000953,0.0006982551,0.000002459926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001710097,"about_ca_system_score_gemma":0.0003406788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002177658,"about_ca_topic_score_gemma":0.00001472345,"domain_scores_codex":[0.9962469,0.0001257426,0.0005210824,0.001156085,0.0006258392,0.001324337],"domain_scores_gemma":[0.9985281,0.0006554835,0.0003266278,0.0002789915,0.00006323277,0.0001475229],"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":[0.00001577992,0.00004200943,0.0005715901,0.00001203863,0.000009819486,0.000006761744,0.01530059,0.8689435,0.001218248,0.003331159,0.00006541863,0.1104831],"study_design_scores_gemma":[0.0009111527,0.0001423719,0.0004367188,0.00005037512,0.000007172245,0.0000248096,0.00283135,0.9941093,0.0001993064,0.0006498724,0.0001404275,0.0004971046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03819824,0.0001213817,0.9585345,0.00008820609,0.001146325,0.0005132266,5.170139e-7,0.0002498763,0.001147668],"genre_scores_gemma":[0.5669146,7.685672e-7,0.4325107,0.0002048731,0.0002448645,0.00006876459,0.000002625952,0.00001813114,0.00003465682],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5287163,"threshold_uncertainty_score":0.9999191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1371676314632298,"score_gpt":0.2881964247820711,"score_spread":0.1510287933188413,"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."}}