Shreya Ghosh

Shreya Ghosh

Postdoctoral Researcher (2021-2023)

The Pennsylvania State University

Biography

Shreya Ghosh (শ্রেয়া ঘোষ) has joined as an Assistant Professor in School of Electrical Sciences (Computer Science and Enggineering) at IIT Bhubaneswar, India in Dec 2023. Prior joining at IIT, She was a postdoctoral scholar at Pennsylvania State University, USA since Dec 2021. Her research interests are in the areas of misinformation detection on social media using linguistic cues and network structure, and spatio- temporal data analytics (night-time light data and trajectory transfer learning). Additionally, she is passionate about applying artificial intelligence to analyze and understand wildlife mobility and human-wildlife conflict. Shreya completed her PhD from IIT Kharagpur in 2021 on semantic analysis of human movement and understanding human movement behaviours. More generally, she is interested in applied data science and application-oriented research projects with a focus on NLP and spatial informatics. Her scholarly work has been published in top-tier conferences and journals such as WWW, ICWSM, ECML PKDD, IEEE Transactions on Services Computing etc.

Interests
  • Machine Learning
  • Spatial Data Science
  • Computational Linguistics
  • Social Informatics
Education
  • PhD in Machine Learning/ Data Science, 2021

    Indian Institute of Technology (IIT) Kharagpur

  • MS (by research) in Artificial Intelligence, 2016

    Indian Institute of Technology (IIT) Kharagpur

  • BTech in Computer Science and Engineering, 2015

    Indian Institute of Engineering Science and Technology, Shibpur

Recent Publications

Quickly discover relevant content by filtering publications.
(2023). FEEL: FEderated LEarning Framework for ELderly Healthcare using Edge-IoMT. Journal of Source Themes, 1(1).

PDF Cite Code Slides

(2023). Lumos in the Night Sky: AI-enabled Visual Tool for Exploring Night-Time Light Patterns. ECML PKDD 2023 (Demo).

PDF

(2023). MCG: Mobility-aware Computation Offloading in Edge using Weighted Majority Game. IEEE Transactions on Network Science and Engineering.

PDF

Projects

*
Misinformation detection from social media
Existing methods to detect and to grade misinformation, however, are met with significant challenges and limitations: (I) Static Evaluation: Existing models predominantly use static scoring systems, which prove inadequate due to their failure to adapt to the dynamic nature of social networks.
Misinformation detection from social media
Mobility data analytics
Both analyzing mobility traces and understanding a user’s movement semantics from mobile sensor data are challenging issues in ubiquitous computing systems. With the pervasiveness of sensor technologies, wireless networks and GPS-equipped devices, a huge volume of location information is being accumulated.
Mobility data analytics
Night-time light data analytics
Night-time light (NTL) data has emerged as a valuable source of information for analyzing human activity patterns from the sky. NTL helps in understanding urbanization patterns, economic development, impact of disasters and finding hotspots of excessive night-light utilization.
Night-time light data analytics

Experience

 
 
 
 
 
The Pennsylvania State University
Postdoctoral scholar
December 2021 – Present Pennsylvania, USA

Responsibilities include:

  • Research (Misinformation detection): Understanding misinformation propagation in social network and proposing mitigation techniques
  • Research (Wildlife informatics): Predicting human wildlife conflicts and mitigating strategies
  • Research (Night time data analytics)
  • Research (Exploring generative language model for cross-domain applications such as trajectory trace analysis)
  • Student Mentoring and assisting in their research
 
 
 
 
 
Indian Institute of Technology Kharagpur (IIT Kharagpur)
Senior research associate
January 2021 – November 2021 Kharagpur, India
Led research project on COVID-19 and mentored undergraduate and postgraduate students. • Analysis of mobility and other context and predicting COVID-19 hotspots and assisting in zone-based lockdown strategy. • Socio-economical impacts of COVID-19 at India
 
 
 
 
 
Indian Institute of Technology Kharagpur (IIT Kharagpur)
PhD research scholar
August 2016 – December 2020 Kharagpur, India

Research projects include:

  • Analysis of large scale GPS traces to explore human movement behaviours and Transferring mobility knowledge from source to target region to annotate trajectory trips and POI-classification

  • Temporal fingerprinting of individuals by modelling and analysing their activity patterns

  • Cloud-fog-edge-IoT based collaborative framework to facilitate applications related to improved health-care, transportation and urban planning in less delay along with less energy consumption

  • Developed Activity-aware Internet of Health Things (IoHT), and Mobility-aware Internet of Spatial Things (Mobi-IoST)

 
 
 
 
 
Indian Institute of Technology Kharagpur (IIT Kharagpur)
MS research scholar
August 2015 – December 2016 Kharagpur, India

Research projects include:

  • Decision Support System for transportation of hazardous materials

  • Designed a SDI (Spatial Data Infrastructure) to assist in routing decisions regarding transportation of hazardous materials

 
 
 
 
 
Indian Institute of Engineering Science and Technology, Shibpur (IIEST)
Undergraduate research project
August 2014 – December 2015 Shibpur, India

Research projects include:

  • Efficient data analysis and classification in Chemoinformatics

  • Developed chemical graph mining algorithm which extends Ugi’s scheme and capable to classify a wide variety of chemical reactions

Recent News!

GeoWildLife 2023!
In collaboration with ACM SIGSPATIAL, we are pleased to announce the call for papers for GeoWildLife 2023, a workshop dedicated to bridging the gap between AI-enabled spatio-temporal data analytics and wildlife conservation.
GeoSocial 2023!
In collaboration with ACM SIGSPATIAL, we are pleased to announce the call for papers for GeoSocial 2023. The workshop aims to bring together a diverse community of researchers, practitioners, and students from various disciplines to exchange ideas, share knowledge, and foster collaboration in the burgeoning field of geocomputational and socio-economic data analysis.
InfoWild 2023!
In collaboration with CIKM 2023, we are pleased to announce the call for papers for InfoWild 2023, a workshop dedicated to explore and enhance AI’s role in big data analysis for wildlife conservation, in brief, Nature Through the Lens of AI . It seeks to address crucial challenges related to data heterogeneity, scale integration, data privacy, mitigating biases, and decision-making under uncertainty. This workshop is centred around leveraging AI’s prowess in deciphering complex spatio-temporal data patterns for wildlife conservation, thereby contributing significantly to the broader canvas of AI for social good.

Skills

Mobility analysis
Natural lanuage processing
Social media data analytics
Cloud computing
Data mining
Python, R, C, PostGreSQL, QGIS, TensorFlow

Contact