Bio

Prerna ChikersalI’m an incoming PhD student at the Human-Computer Interaction Institute at Carnegie Mellon University (CMU), where I will be advised by Prof. Anind Dey. For my first year, I have also been awarded a fellowship by the Center for Machine Learning and Health at CMU launched under the umbrella of Pittsburgh Health Data Alliance.

In August 2017, I will graduate with a Master of Science in Robotics from Carnegie Mellon University, where I was advised by Prof. Laura Dabbish at the Human-Computer Interaction Institute. For my Master’s thesis, I studied the physiological and behavioral underpinnings of collaboration, with the goal of developing interventions to make teams smarter. I drew on machine learning to model collaborative performance and communicative phenomena in datasets containing data from multiple modalities (or sources) like audio, video, transcriptions (text), electrodermal activity, heart rate, motion capture, and EEG. In future, these models may be used by intelligent systems to give participants feedback on their collaboration. For this project, I collaborated with Prof. Anita Wolley, Prof. LP Morency, Dr. Maria Tomprou, and Dr. Young Ji Kim.

In May 2015, I graduated summa cum laude with a Bachelor of Engineering in Computer Science and a specialization in Intelligent Systems, from Nanyang Technological University (NTU) in Singapore. I was advised by Prof. Erik Cambria for my bachelor thesis on “Modeling Public Sentiment in Twitter”.

During my undergraduate, I also worked as a research intern at the Computer Graphics Lab and the Computer Vision Lab at École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland, where I was advised by Dr. Andrea Tagliasacchi and Dr. Horesh Ben Shitrit. I was awarded a research scholarship by EPFL for NTU-EPFL’s research exchange program, and was one of the 50 candidates out of 1500 chosen to participate in the Summer@EPFL program in 2013.

My research interests include:

  • Modeling affective, communicative, and physiological phenomena by fusing data from multiple modalities (or sources).
  • Developing technological interventions informed by these models, with the goal of improving our health, or augmenting our interactions with each other and with machines.