{"@type": "dcat:Dataset", "accessLevel": "public", "accrualPeriodicity": "irregular", "bureauCode": ["026:00"], "contactPoint": {"@type": "vcard:Contact", "fn": "Elizabeth Foughty", "hasEmail": "mailto:elizabeth.a.foughty@nasa.gov"}, "description": "PROBABILITY CALIBRATION BY THE MINIMUM AND MAXIMUM PROBABILITY\r\nSCORES IN ONE-CLASS BAYES LEARNING FOR ANOMALY DETECTION\r\n\r\nGUICHONG LI, NATHALIE JAPKOWICZ, IAN HOFFMAN, R. KURT UNGAR\r\n\r\nABSTRACT. One-class Bayes learning such as one-class Na\u00efve Bayes and one-class Bayesian\r\nNetwork employs Bayes learning to build a classifier on the positive class only for discriminating\r\nthe positive class and the negative class. It has been applied to anomaly detection for identifying\r\nabnormal behaviors that deviate from normal behaviors. Because one-class Bayes classifiers can\r\nproduce probability score, which can be used for defining anomaly score for anomaly detection,\r\nthey are preferable in many practical applications as compared with other one-class learning\r\ntechniques. However, previously proposed one-class Bayes classifiers might suffer from poor\r\nprobability estimation when the negative training examples are unavailable. In this paper, we\r\npropose a new method to improve the probability estimation. The improved one-class Bayes\r\nclassifiers can exhibits high performance as compared with previously proposed one-class Bayes\r\nclassifiers according to our empirical results.", "distribution": [{"@type": "dcat:Distribution", "description": "PROBABILITY CALIBRATION BY THE MINIMUM AND MAXIMUM PROBABILITY SCORES IN ONE-CLASS BAYES LEARNING FOR ANOMALY DETECTION", "downloadURL": "https://c3.nasa.gov/dashlink/static/media/publication/Paper_13_.pdf", "format": "PDF", "mediaType": "application/pdf", "title": "Paper 13 .pdf"}], "identifier": "DASHLINK_235", "issued": "2010-10-13", "keyword": ["ames", "dashlink", "nasa"], "landingPage": "https://c3.nasa.gov/dashlink/resources/235/", "modified": "2025-03-31", "programCode": ["026:029"], "publisher": {"@type": "org:Organization", "name": "Dashlink"}, "title": "PROBABILITY CALIBRATION BY THE MINIMUM AND MAXIMUM PROBABILITY SCORES IN ONE-CLASS BAYES LEARNING FOR ANOMALY DETECTION"}