{"id":"W7115717146","doi":"10.3390/computers14120561","title":"Beyond the Norm: Unsupervised Anomaly Detection in Telecommunications with Mahalanobis Distance","year":2025,"lang":"en","type":"article","venue":"Computers","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Q & T Research","funders":"","keywords":"Mahalanobis distance; Anomaly detection; Dimensionality reduction; Troubleshooting; Key (lock); Overhead (engineering); Outlier; Reliability (semiconductor); Preprocessor; Performance indicator","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":[0.0001334782,0.000110183,0.0001047843,0.0001491395,0.0003120804,0.0001364768,0.001165447,0.00004159741,0.000002318245],"category_scores_gemma":[0.000004470872,0.00008217691,0.00004018974,0.001381091,0.00008383123,0.0002063729,0.0002180475,0.0001867415,0.000008360393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008408757,"about_ca_system_score_gemma":0.00005142433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001029673,"about_ca_topic_score_gemma":0.0004768058,"domain_scores_codex":[0.9992104,0.00005900967,0.0001923749,0.0002762307,0.00009148195,0.0001705135],"domain_scores_gemma":[0.9987396,0.0001133996,0.00005947112,0.001000686,0.00005744068,0.00002940618],"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":[0.00002981896,0.0003220652,0.01101539,0.00003529116,0.00006599004,0.000006592064,0.0009498151,0.002151471,0.001626546,0.3466016,0.003193229,0.6340021],"study_design_scores_gemma":[0.001462676,0.0003000852,0.242889,0.0001581211,0.0000311468,0.00005468857,0.0002152993,0.5854137,0.01850495,0.02708688,0.1230663,0.0008171175],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01759055,0.00009041366,0.9728897,0.004683007,0.00008999032,0.0003187117,0.000001174553,0.0002564195,0.00408007],"genre_scores_gemma":[0.9539405,0.00002912666,0.04472057,0.0008650934,0.00001259882,0.0001855323,0.000002164264,0.000005468686,0.0002389582],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9363499,"threshold_uncertainty_score":0.3351077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005782901952124114,"score_gpt":0.2232752974090357,"score_spread":0.2174923954569116,"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."}}