Loading Events

« All Events

  • This event has passed.

{Seminar} @ CDS: 24th May : “Scalable Cluster Assessment and Clustering for Big Data (both Static and Streaming), and its application for large-scale trajectory prediction.”

24 May @ 3:00 PM -- 4:00 PM

Department of Computational and Data Sciences

Department Seminar


SPEAKER      :   Dr. Punit Rathore, Postdoctoral Researcher in Senseable City Lab at Massachusetts Institute of Technology (MIT), Cambridge, USA.

TITLE             :  “Scalable Cluster Assessment and Clustering for Big Data (both Static and Streaming), and its application for large-scale trajectory prediction”

Date & Time :   May 24, 2021, 03:00 PM.

Venue              :   Online

 

ABSTRACT

Everyday, an abundant amount of data is generated from various sources such as Internet of Things (IoT) networks, smartphones, and social network activities. Making sense of such an unprecedented amount of data is essential for many businesses, services and almost every smart city domain such as healthcare, transportation, environment, and energy sectors. The data generated from these domains are mostly unlabeled, anomalous, spatio-temporal, streaming, and/or high-dimensional, which makes their interpretation challenging to create useful knowledge. Cluster analysis is a useful unsupervised approach to discover the underlying groups and useful patterns in the data, and consists of three problems, (P1) cluster assessment, which asks “Do the data have clusters? If yes, how many?”; (P2) Clustering i.e., partitioning the data into clusters, and (P3) cluster validity, which asks “Are the clusters found useful?” Traditional cluster analysis algorithms are not suitable for big data owing to its volume, variety, and velocity property.

 

In this talk, Dr. Punit Rathore will discuss his efficient machine learning algorithms to manage and extract actionable information from big data from various domains. Specifically, he will present his novel cluster assessment and clustering algorithm for time-efficient tracking of cluster structures in static big data and high-velocity data streams, and its application for large-scale vehicle trajectory prediction.

 

BIOGRAPHY

Dr. Punit Rathore is currently a Postdoctoral Researcher in Senseable City Lab at Massachusetts Institute of Technology (MIT), Cambridge, USA, where he is working on urban intelligence and spatio-temporal data mining for Smart City applications. Previously, he was a Postdoctoral Researcher at the GRAB-NUS AI Lab at National University of Singapore, Singapore. Dr. Rathore completed his Masters (M. Tech) in Instrumentation Specialization from the Department of Electrical Engineering at IIT Kharagpur in 2011 and Doctor of Philosophy (PhD) from the Department of Electrical and Electronics Engineering at the University of Melbourne, Australia in Jan-2019. Prior to his PhD, Dr. Rathore also worked as a Researcher in Automation Division at Tata Steel Ltd. Jamshedpur for around three and half years where he designed and developed several automation systems based on Instrumentation, and computer vision and machine learning techniques. Dr. Punit Rathore has published more than 13 first-author papers in top IEEE/ACM journals and conferences in his field of research. His research work has also been internationally recognized with multiple best-paper awards at world-recognized IEEE conferences and Best PhD thesis prizes by IEEE System, Man, and Cybernetics Society (SMC) and Melbourne School of Engineering, the University of Melbourne, Australia.

 

Host Faculty: Prof. Sathish Vadhiyar

Details

Date:
24 May
Time:
3:00 PM -- 4:00 PM

Venue

Online