I have moved to Microsoft (Azure) as Principal Data Scientist.
This Page is not Updated regularly.
Previous Appointment:
Assistant Professor · Computer Science · Georgia Southern University
Director - Mobile Systems and Solutions (MOSYS) Lab
Pradipta De is an Assistant Professor at the Department of Computer Science at Georgia Southern University. His professional career spans over 10 years in academia and industry research. He had been a founding faculty member of SUNY Korea, a remote campus of StonyBrook University in Songdo, South Korea. He also worked as a Research Staff Member at IBM Research from 2005 to 2012. Pradipta received his Ph.D. from StonyBrook University (SUNY) in 2007. He did his undergraduate in Computer Science and Engineering from Jadavpur University, Kolkata.
Pradipta's current research focuses on Mobile Computing, and Affective Computing. It encompasses applying Machine Learning, and Networking principles in designing and implementing networked systems, related to Cyber-physical systems, Internet-of-Things, Edge Computing, He has published extensively in international journals and conferences with over 100 publications and 1500 citations of his work. He is co-inventor in 15 patents. He is also a Senior Member of the IEEE. He is involved as Technical Program Committee Member for several IEEE conferences, and serves as external reviewer for international journals.
Advances in Machine Learning techniques have shown the promise to
take up challenging problems in different domains. With our prior
expertise in mobile and network computing, we have applied Machine
Learning techniques on some of the problems in these areas.
Detection of human affect, or emotion, based on behavior patterns
is a challenging problem. We predict user emotion based on her
smartphone interactions, specifically the way she types. In
another inter-disciplinary project, based on a student’s eye
movement on the computer screen during a class lecture we are able
to predict the attention level of the student during the lecture.
We developed our custom data collection software, all along
learning nuances of collecting ground truth labels from users for
such human-centric experiment. We also developed prediction models
using feature engineering, as well as, learning feature
representations from the data.
Analysis and prediction of network traffic based on volumes of
traffic data, that is often encrypted, is difficult. In this
project, we applied Machine Learning techniques to (i) detect
signatures in traffic that indicate whether traffic is originating
from video applications, and (ii) we could do the detection even
on encrypted traffic. The solutions have applications in enforcing
network security.
The Mobile Computing research is focused on resource optimized
application design for resource constrained devices, such as
smartphones, smartwatches, or other emerging smart devices for
Internet-of-Things. We approach this theme by (a) considering
novel application design to solve a problem, and (b) architecting
the infrastructure that supports such applications.
To solve the problem of finding location on a smartphone, we
introduced the idea of finding matching patterns in images
captured using the smartphone camera. To reduce the resource cost,
we partitioned the application execution between the device, and
remote servers. In another project, we improved mobile video
playback performance by finding tradeoff between video quality,
which affects network traffic and battery usage, and time to
finish the playback.
Since mobile platforms are inherently resource limited, we play
with the idea of offloading parts of the applications on remote
servers. Enabling offloading requires delicate balance among
energy usage, computation capacity, network bandwidth, and
time-to-finish an application. Mobile Cloud/Edge Computing
paradigm encompasses some of the solutions we are working on.
Data Comm and Networking: Introduction to Computer Networks with hands-on exercises.
Computer Architecture: Basics of Computer Hardware Design along with Assembly Programming.
Wireless and Mobile Systems: Introduction to Android Programming.
Data Structures: Introduction to Data Structures.
Introduction to Programming: Introduction to Java.
Parallel Algorithm Design: Introduction to building blocks of parallel algorithms.
Operating System: Advanced OS design features and implementation.
Compiler Design: Basics of designing and implementing a compiler.
Distributed Systems: Introduction to fundamental concepts in distributed systems theory.
Towards Improving Emotion Self-report
Collection using Self-reflection
Surjya Ghosh, Bivas Mitra, Pradipta De
In ACM Computer Human Interactions (CHI) Late Breaking Work, Apr
2020.
Profiling Instructor Activities Using
Smartwatch Sensors in a Classroom
Zayed Uddin Chowdhury, Pradipta De, Andrew Allen
In ACM SouthEast Conference, Apr 2020.
Non-intrusive Identification of
Student Attentiveness and Finding Their Correlation with
Detectable Facial Emotions
Tasnia Tabassum, Andrew Allen, Pradipta De
In ACM SouthEast Conference, Apr 2020.
Representation Learning for Emotion
Recognition from Smartphone Keyboard Interactions
Surjya Ghosh, Shivam Goenka, Niloy Ganguly, Bivas Mitra, Pradipta
De
In The 8th International Conference on Affective Computing and
Intelligent Interaction (ACII), Oct 2019.
Exploiting Diversity in Android TLS
Implementations for Mobile App Traffic Classification
Satadal Sengupta, Niloy Ganguly, Pradipta De, Sandip Chakraborty
In The Web Conference, May 2019.
Does
emotion influence the use of auto-suggest during smartphone
typing?
Surjya Ghosh, Kaustubh Hiware, Niloy Ganguly, Bivas Mitra,
Pradipta De
In Proceedings of the 24th International Conference on Intelligent
User Interfaces, Mar 2019.
EmoKey:
An Emotion-aware Smartphone Keyboard for Mental Health
Monitoring
Surjya Ghosh, Sumit Sahu, Niloy Ganguly, Bivas Mitra, Pradipta De
In COMSNETS, Jan 2019.
HotDash:
Hotspot Aware Adaptive Video Streaming using Deep
Reinforcement Learning
Satadal Sengupta, Niloy Ganguly, Sandip Chakraborty, Pradipta De
In 26th International Conference on Network Protocols, Sep 2018.
Effectiveness
of Deep Neural Network Model in Typing-based Emotion Detection
on Smartphones
Surjya Ghosh, Niloy Ganguly, Bivas Mitra, Pradipta De
In International Conference on Mobile Computing and Networking,
Oct 2018.
Next Generation Business Intelligence and
Analytics
Quoc Duy Vo, Shinyoung Cho, Jaya Thomas, Pradipta De, Bong Jun
Choi
In International Conference on Business and Information
Management, Sep 2018.
Evaluating Effectiveness of Smartphone Typing
as an Indicator of User Emotion
Surjya Ghosh, Niloy Ganguly, Bivas Mitra, Pradipta De
In 7th Affective Computing and Intelligent Interfaces (ACII), San
Antonio, Oct 2017
TapSense:
Combining Self-Report Patterns and Typing Characteristics for
Smartphone based Emotion Detection
Surjya Ghosh, Niloy Ganguly, Bivas Mitra, Pradipta De
In 19th International Conference on Human-Computer Interaction
with Mobile Devices and Services (MobileHCI), Vienna, Austria, Sep
2017
Candid
with YouTube: Adaptive Streaming Behavior and Implications on
Data Consumption
Abhijit Mondal, Satadal Sengupta, Bachu Rikith Reddy, M.J.V.
Koundinya, Chander Govindarajan, Pradipta De, Niloy Ganguly and
Sandip Chakraborty
27th ACM SIGMM Workshop on Network and Operating Systems Support
for Digital Audio and Video (ACM NOSSDAV), Jun 2017.
MoViDiff: Enabling
Online Service Differentiation for Mobile Video Apps
Satadal Sengupta, Vinay Kumar Yadav, Yash Saraf, Harshit Gupta,
Niloy Ganguly, Sandip Chakraborty, Pradipta De
Mini-Conference track of the 2017 IFIP/IEEE International
Symposium on Integrated Network Management (IM), Lisbon, Portugal,
May, 2017