{"id":"W4414538951","doi":"10.1109/icc52391.2025.11161738","title":"Hardware Partitioning for Vision Analytics-based Systems: Performance and Trade-offs","year":2025,"lang":"en","type":"article","venue":"","topic":"CCD and CMOS Imaging Sensors","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Workflow; Cloud computing; Latency (audio); Enhanced Data Rates for GSM Evolution; Edge computing; Edge device; Artificial neural network; Analytics; Wireless; Resource (disambiguation)","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":[0.0007524833,0.000677001,0.0004972594,0.0003856847,0.000642102,0.00149813,0.001296473,0.0006255661,0.003112633],"category_scores_gemma":[0.004215672,0.0003398377,0.0003249878,0.0005181111,0.0005534464,0.002123762,0.0008931771,0.0007662483,0.0004823619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001896592,"about_ca_system_score_gemma":0.001273246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005642133,"about_ca_topic_score_gemma":0.00795462,"domain_scores_codex":[0.9993901,0.0001478429,0.00002800954,0.0001114625,0.000172172,0.0001504288],"domain_scores_gemma":[0.9985671,0.0007508124,0.0001254024,0.000238227,0.0002195263,0.00009894637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002634871,0.0001357489,0.002420446,0.0002000097,0.00005744513,0.0001593891,0.0001858609,0.8486829,0.02001937,0.03083413,0.003133082,0.09390809],"study_design_scores_gemma":[0.000006538886,0.00007375973,0.0003506392,0.00001381913,0.0000114116,0.0000549329,0.00007471323,0.9866174,0.003944303,0.007565479,0.001278527,0.000008406464],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1853496,0.002780649,0.7965163,0.001115127,0.0001690814,0.0001447419,0.0001434792,0.001219332,0.01256176],"genre_scores_gemma":[0.9334631,0.0005159777,0.06412404,0.00008584943,0.00002920562,0.00004917789,0.00006494113,0.0001128631,0.001554846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005642133,"threshold_uncertainty_score":0.01376081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00832269013602908,"score_gpt":0.2305275469807322,"score_spread":0.2222048568447032,"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."}}