K
Karthik Ganesan Pillai
Researcher at Montana State University
Publications - 19
Citations - 296
Karthik Ganesan Pillai is an academic researcher from Montana State University. The author has contributed to research in topics: Swarm intelligence & Swarm behaviour. The author has an hindex of 11, co-authored 19 publications receiving 283 citations. Previous affiliations of Karthik Ganesan Pillai include Georgia State University.
Papers
More filters
Proceedings ArticleDOI
A large-scale solar image dataset with labeled event regions
TL;DR: This paper introduces a new public benchmark dataset of solar image data from the Solar Dynamics Observatory (SDO) mission, which contains over 15,000 images and nearly 24,000 solar events spanning the first six months of 2012.
Proceedings ArticleDOI
A filter-and-refine approach to mine spatiotemporal co-occurrences
TL;DR: A novel and effective filter-and-refine algorithm to efficiently find prevalent STCOPs in massive spatiotemporal data repositories with polygon shapes that move and evolve over time is introduced.
Proceedings ArticleDOI
Spatio-temporal Co-occurrence Pattern Mining in Data Sets with Evolving Regions
TL;DR: This work proposes a set of measures to identify spatio-temporal co-occurring patterns and proposes an Apriori-based spatIO-tem temporal co- Occurrence mining algorithm to find prevalent spatio’s temporal representations for extended spatial representations that evolve over time.
Proceedings ArticleDOI
Spatiotemporal indexing techniques for efficiently mining spatiotemporal co-occurrence patterns
Berkay Aydin,Dustin J. Kempton,Vijay Akkineni,Shakthidhar Gopavaram,Karthik Ganesan Pillai,Rafal A. Angryk +5 more
TL;DR: This paper presents a new framework for mining spatiotemporal co-occurrence patterns that can use various indexing techniques for efficiently accessing data.
Proceedings ArticleDOI
Overlapping swarm intelligence for training artificial neural networks
TL;DR: An overlapping swarm intelligence technique to train multilayer feedforward networks is introduced and the results show that OSI method performs either on par with or better than the other methods tested.