The Community for Technology Leaders
Green Image
Issue No. 10 - Oct. (2016 vol. 28)
ISSN: 1041-4347
pp: 2582-2595
Yen-Cheng Lu , Computer Science Department, Virginia Tech, Falls Church, VA
Feng Chen , Computer Science Department, University at Albany, Albany, NY
Yating Wang , Computer Science Department, Virginia Tech, Falls Church, VA
Chang-Tien Lu , Computer Science Department, Virginia Tech, Falls Church, VA
Anomaly detection in mixed-type data is an important problem that has not been well addressed in the machine learning field. Existing approaches focus on computational efficiency and their correlation modeling between mixed-type attributes is heuristically driven, lacking a statistical foundation. In this paper, we propose MIxed-Type Robust dEtection (MITRE), a robust error buffering approach for anomaly detection in mixed-type datasets. Because of its non-Gaussian design, the problem is analytically intractable. Two novel Bayesian inference approaches are utilized to solve the intractable inferences: Integrated-nested Laplace Approximation (INLA), and Expectation Propagation (EP) with Variational Expectation-Maximization (EM). A set of algorithmic optimizations is implemented to improve the computational efficiency. A comprehensive suite of experiments was conducted on both synthetic and real world data to test the effectiveness and efficiency of MITRE.
Robustness, Numerical models, Correlation, Data models, Bayes methods, Computational modeling, Estimation

Y. Lu, F. Chen, Y. Wang and C. Lu, "Discovering Anomalies on Mixed-Type Data Using a Generalized Student- $t$ Based Approach," in IEEE Transactions on Knowledge & Data Engineering, vol. 28, no. 10, pp. 2582-2595, 2016.
182 ms
(Ver 3.3 (11022016))