Industrial AI for Maintenance and Repair (2014-Present) 

Developing innovative algorithms for performance degradation detection, maintenance effectiveness estimation, failure prediction, remaining useful life estimation, and maintenance recommendation (more at Hitachi R&D)

Outcome: Two granted patents, ten pending patents and fourteen papers
Impact: Two patent awards, four achievement awards

Fast and Accurate Algorithms for Organizing Big Data (2013-2014) 

Developed MapReduce algorithms for big data summarization and mentoring a Master’s student in the development of MapReduce-efficient algorithms for big data clustering

Outcome: One journal paper in KAIS, Two conference papers in ICDM'13 and SDM'14, and two workshop papers in NIPS'13
Impact: Best Paper Award Runner-up in ICDM'13

Learning in Dynamic Environments (2013–2014)

Mentored a Ph.D. student in the development of innovative algorithms for domain adaptation and minimally supervised learning

Outcome: One conference paper in SDM'14, and two workshop papers in ICDM'13 and NIPS'13
Impact: Best Abstract Award in NIPS'13 Workshop on New Directions in Transfer and Multi-Task Learning

Minimally-supervised Query Understanding for Intelligent Personal Assistants  (2013)

Managed a team of two researchers to build an innovative solution for Vestec, Inc. to understand the semantics of transcribed queries 

Impact: More than 75% reduction in the required training data

Representative Selection for Unsupervised Data Analysis  (2009–2012)

Developed novel algorithms to select a few representative instances and features from data and enhance the efficiency and effectiveness of data clustering algorithms

Outcome: One journal paper in KAIS, two papers in ICDM'11 and AISTATS'11, one workshop paper in NIPS'10
Impact: Nomination for the Best Paper Award in ICDM'11

Fast and Accurate Recognition of Banknote Serial Numbers (2011-2012)

Managed a team of two researchers to develop a novel solution for NCR Canada, Ltd. to recognize banknote serial numbers at the speed of accepting/dispensing banknotes

Impact: Less than 2% error and half a millisecond recognition time per character using a few training data

Statistical Semantics for Enhancing Document Clustering  (2008–2010)

Developed novel measures of semantic similarity between documents to enhance different clustering algorithms

Outcome: One journal paper in KAIS and two papers in specialized workshops in ICDM'09 and SDM'10
Impact: Best Paper Award in ICDM'09 Workshop on Semantic Aspects in Data Mining 

High–Speed Number Recognition for Inline Print Inspection Systems (2008-2009)

Developed a novel solution for Erhardt+Leimer, Ltd. to inspect prints with changing numbers at the speed of the printing process 

Impact: Less than 0.01% error and half a millisecond recognition time per digit using a few training data

Detecting Anomalous Behaviour for Business Process Management (2005–2007)

Co-invented two IBM patents to detect and predict anomalous behaviour in business processes

Outcome: Two patents were filed based on this work
Impact: Selected as one of the Innovation that Matters for IBM