{"id":"W4385381666","doi":"10.1007/s11265-023-01885-5","title":"The Good, the Bad and the Ugly: Practices and Perspectives on Hardware Acceleration for Embedded Image Processing","year":2023,"lang":"en","type":"article","venue":"Journal of Signal Processing Systems","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Hardware acceleration; Bespoke; Design space exploration; Acceleration; Image processing; Software deployment; Computer engineering; Process (computing); Partition (number theory); Application-specific integrated circuit; Computer hardware; Embedded system; Computer architecture; Artificial intelligence; Image (mathematics); Programming language; Software engineering; Field-programmable gate array","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004145177,0.0001204006,0.0001833585,0.00008403996,0.001338512,0.003075627,0.0004991752,0.00003943899,1.316336e-7],"category_scores_gemma":[0.0004543503,0.00005241144,0.00004781975,0.0003157241,0.000164302,0.001007882,0.0000776461,0.0002466587,4.303183e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002476428,"about_ca_system_score_gemma":0.000170275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004599794,"about_ca_topic_score_gemma":7.660337e-7,"domain_scores_codex":[0.9986009,0.0003186448,0.0003773695,0.0001827242,0.0003579406,0.0001623915],"domain_scores_gemma":[0.9967372,0.001145221,0.001348612,0.0001300395,0.0006023191,0.00003658767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001826945,0.0002776981,0.0004121526,0.001837532,0.0004559945,0.00004729656,0.2088046,0.05617033,0.00573991,0.1214618,0.01957714,0.5833886],"study_design_scores_gemma":[0.0007099077,0.000183551,0.0002032438,0.0004934664,0.00002734857,0.0001747726,0.009037959,0.9848112,0.0002765561,0.00224822,0.001720289,0.0001134292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006130461,0.009812795,0.9658086,0.01683474,0.0001662164,0.0005670534,8.776706e-7,0.0001431186,0.0005361123],"genre_scores_gemma":[0.991998,0.0003465578,0.007037104,0.0001274908,0.0002644803,0.00002823654,2.790064e-7,0.00001144759,0.0001864288],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9858675,"threshold_uncertainty_score":0.9999616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04221078103026647,"score_gpt":0.3194950669638841,"score_spread":0.2772842859336176,"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."}}