Dr. Levente Klein is a Research Staff Member in the Artificial Intelligence department at the IBM T.J. Watson Research Center, Yorktown Heights, NY. His research is focused on developing models and tools to analyze big data and integrate them in physics based models in the Internet of Thing framework. Applications of these research are ranging from cognitive end devices, development of wireless communication networks, and global environmental monitoring. Current research focus on Internet of Thing devices and analytics solutions that can dynamically sample and extract information at the sensing point without sending all the data to the cloud. Implementing "intelligence at edge" can significantly reduce data transmission rate and enable analytics to be carried out on data streams.
Levente organize a focused workshop called “Big Data Analytics and Internet of Thing” part of the IEEE Big Data conference on December 11, 2017 that discussed the current challenges in wide adoption of the IoT technologies in industrial environments:
Previous work encompass the development of a large scale sensor networks for automation and integration of satellite imagery in daily operation of vineyards. The basis of this work was variable rate irrigation management where Landsat data and weather data is combined to provide an irrigation advice 10 days in advance at 30 m spatial resolution. Digitization of the irrigation system allowed to relate a single Landsat pixel to the corresponding irrigation zone in the vineyard. Analytics was developed to forecast the water requirement and integrated into an automatic control system that dispense water at 30 m by 30 m spatial resolution cross a drip irrigated vineyard.
An irrigation system prototype was developed in collaboration with EJ Gallo winery on a 10 acre area in Lodi, CA and run for t3 years. The results demonstrated 20 % increase in grape yield and 10% improvement in water use by grapes. The work was awarded the 2015 Vintage Report Award for innovation in water use and adoption of technology in grape growing operations.
The work in precision agriculture was awarded an IBM Outstanding Technical Achievement Award in 2016.
The variable rate irrigation work triggered the development of a big data geospatial platform that provide curated and spatially aligned data sets. The platform called Physical Analytics Integrated Repository and Services (PAIRS) can accelerate geospatial analytics by a factor of ten relying on curated data sets compared with cases when original and raw datasets are used. The PAIRS technology enable geo spatial analytics for data scientists without extensive geographical and cartography background. The PAIRS technology was awarded an IBM Outstanding Technical Achievement Award in 2017.
In the past, his work focused on developing wireless sensing technologies for data centers energy efficiency operation. Sensor networks and analytics were developed to enable air side economizer in data centers that can reduce energy consumption by 10% by using outside air when the environmental conditions are suitable for cooling. The air quality sensing solution based on sensing air corrosion was integrated in IBM's high end Z and P servers as part of environmental monitoring and quality assurance. The air quality work was awarded an IBM Outstanding Technical Achievement Award in 2015.
His doctoral work focused on developing measurement methods for high sensitivity electrical characterization of insulating surfaces. Levente contributed to implement a spin based quantum computer using single electron quantum dots fabricated in SiGe hetero-structures. Since joining IBM Research in 2006 he developed technologies to enable energy efficient cooling in data centers. Current research interests focus on geo spatial data processing, advanced analytics for precision agriculture, and distributed sensing data modeling and analytics.
Levente is a member of the American Physical Society (APS), American Vacuum Society (AVS) and the NY Academy of Sciences.