Daniel Nikovski

MERL Research / Technical Staff
Team Leader, Analytics
Ph.D., Carnegie Mellon University, 2002

Phone: (617) 621 7510
Email:



Daniel Nikovski's research is focused on algorithms for reasoning, planning, and learning with probabilistic models. His current work is on the application of such algorithms to hard industrial problems such as equipment condition monitoring and diagnosis, optimal HVAC control, group elevator scheduling, and car navigation. In addition, he is responsible for technical management of projects in enterprise information technology, such as business process management, customer relationship management, and service oriented architectures for enterprise integration. Recent results include an efficient algorithm for memory-based abrupt change detection in sensor data streams, a fast algorithm for accurate estimation of the peak power consumed by an elevator bank, and a polynomial algorithm for mining business process models with implicit concurrency.

Recent Projects:

Business Process Management Software
Equipment Condition Monitoring
SOA Integration Technology

Recent Publications:

Nikovski, D.; Jain, A., "Memory-Based Algorithms for Abrupt Change Detection in Sensor Data Streams", IEEE International Conference on Industrial Informatics, ISSN: 1935-4576, Vol. 1, pp. 547-552, June 2007 (IEEE Xplore)

Radhakrishnan, rR; Nikovski, D.; Peker, K.A.; Divakaran, A., "A Comparison between Polynomial and Locally Weighted Regression for Fault Detection and Diagnosis of HVAC Equipment", Conference on IEEE Industrial Electronics (IECON), ISSN: 1553-572X, pp. 3668-3673, November 2006 (IEEE Xplore, TR2006-094)

Nikovski, D.; Kulev, V., "Induction of Compact Decision Trees for Personalized Recommendation", ACM Symposium on Applied Computing (SAC), April 2006 (SAC 2006, TR2006-036)

Nikovski, D.; Nishiuma, N.; Goto, Y.; Kumazawa, H., "Univariate Short-Term Prediction of Road Travel Times", International IEEE Conference on Intelligent Transportation Systems (ITSC), pp. 1074-1079, September 2005 (IEEE Xplore, TR2005-086)

Recent Technical Reports:

TR2008-034 Workflow Trees for Representation and Mining of Implicitly Concurrent Business Processes
TR2007-072 Workflow Trees for Representation and Mining of Implicitly Concurrent Business Processes