{"id":"W2958371845","doi":"10.11575/prism/35761","title":"Real-time Pedestrian Classification System Using Deep Learning on a Raspberry Pi Cluster","year":2019,"lang":"en","type":"dissertation","venue":"PRISM (University of Calgary)","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs; University of Calgary","keywords":"Raspberry pi; Cluster (spacecraft); Artificial intelligence; Pedestrian; Deep learning; Computer science; Pedestrian detection; Cartography; Geography; Operating system; Embedded system; Internet of Things; Archaeology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003004264,0.0005132151,0.0004737658,0.0005478266,0.0002960601,0.0003917759,0.0009118253,0.0003374416,0.003246214],"category_scores_gemma":[0.0003562131,0.0002406114,0.0002443597,0.0003866936,0.0001244431,0.0005658045,0.0004368613,0.0003825099,0.001303802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009413384,"about_ca_system_score_gemma":0.0007233812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0093273,"about_ca_topic_score_gemma":0.009907156,"domain_scores_codex":[0.9997895,0.00001656031,0.000007997861,0.00007393212,0.00006872611,0.0000432663],"domain_scores_gemma":[0.9997813,0.00002084314,0.00001923261,0.00003146293,0.0001163633,0.00003089513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001760662,0.0006609303,0.01034457,0.000197015,0.0001252613,0.0006130926,0.0001729905,0.05974443,0.2276182,0.002207761,0.02917113,0.667384],"study_design_scores_gemma":[0.00004814478,0.0003112273,0.007254211,0.00001738846,0.00004632675,0.0001372052,0.00005694333,0.9108827,0.0755653,0.0005529315,0.005091116,0.00003653197],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4758825,0.0003026404,0.4829565,0.0003493137,0.0002832632,0.0003509402,0.0006825661,0.02791347,0.01127884],"genre_scores_gemma":[0.8501557,0.000145322,0.1391409,0.0001677716,0.00003034768,0.0001488979,0.0008648658,0.0001446817,0.009201526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0093273,"threshold_uncertainty_score":0.01854599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02218932565696793,"score_gpt":0.2509331122554019,"score_spread":0.2287437865984339,"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."}}