CURRENT AFFILIATION

September 2019

University of Washington, Seattle

Masters Student, Department of Electrical and Computer Engineering

WORK EXPERIENCE

November 2017 — Feb 2019

International Institute of Information Techonology - Hyderabad

Research Assistant - Applied Research Lab, under Prof. C.V. Jawahar, CVIT, IIIT-Hyderabad, India

I worked on detection of Cancerous regions from Kidney tissue Images and prediction of survivability using Deep Learning techniques.

• Cancer and its subtype detection
  • Experimented with various Deep CNN’s to distinguish Cancerous regions from Kidney Cancer slides(~60000*100k pixels) from the normal ones, dataset of which was obtained from TCGA.
  • Experimented for distinguishing the subtypes within the same Cancerous tissues using similar methods.
  • Experimented using various methods such as DAGSVM, SMOTE to deal with the inherent data imbalance.
• Survival Prediction
  • Built a pipeline which could automatically extract high probability regions as detected from the Cancer detection model and extract relevant tissue and Nuclei information such as area, perimeter, eccentricity etc. without any supervision of a pathologist.
  • Built a survival prediction system using a COX-model trained on the above features.

A research paper based on this work has been published in Nature Scientific Reports.

Research paper: Sairam Tabibu, P.K Vinod and C. V. Jawahar. “Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images using deep learning” Nature Scientific Reports 2019

November 2018 — May 2019

Great Learning

Mentor, Deep Learning Certificate Program

This is a certificate program by Great Learning. I took online sessions, teaching fundamentals of Machine Learning and Computer Vision to working professionals. I also assisted in grading the assignments of the participants.

RESEARCH & TECHNICAL INTERNSHIPS

Summer 2017

Crowd simulation

Rutgers University, New Brunswick — under Prof. Mubbassir Kapadia, Computer Science Department

[Remote Project] Worked on crowd simulations investigating the variety of social forces and various optimizations which comes into play while trying to imitate a real time situation using the SteerSuite framework.

A Youtube Channel displaying the simulations.

Summer 2016

Infrared image/video processing in the Maritime environment

NTU, Singapore — under Prof. Deepu Rajan, School of Computer Science and Engineering

Worked on Detecting and tracking ships, boats, frigates using IR cameras along the Singapore coastline with every possible variation in orientation,shape, distance and surrounding effects. Selective search using graph methods and combining them on the basis of several similarity measures such as color shape to get probable Bounding boxes. CNN used to extract features and SVM’s to classify them .

Report containing details of project. Certificate of the project.

Summer 2015

Real-Time Illumination Invariant Face Recognition Using Higher Order Local Discrete Patterns

Changwon National University, South Korea — under Prof. Oh Seol Kwon, Electrical Electronics and Control & Instrumentation Engineering

Worked on Improving and implementation of Real time face recognition algorithm on Embedded systems such as Raspberry Pi to be deployed as a low cost product. Illumination invariance brought by introducing CLAHE and MLBOHE with minimal processing and significant accuracy improvement.

Presentation containing details of the project. Certificate of the project.

EDUCATION

2013 — 2017

Indian Institute of Technology, (BHU), Varanasi, India

Bachelors Degree in Electronics Engineering

RESEARCH PROJECTS

January-2017 — April-2017

Lexical and Visual Analysis to Identify Posts Warranting Empathetic Responses

NTU, Singapore — under Prof. Erik Cambria, School of Computer Science and Engineering

We worked on understanding the sentiment that a person elicits on different posts present on different social media sites, on the topics of abuse or mental health. We propose a method supported by hand-crafted features to judge if the post requires an empathetic response. The model is trained upon posts from various web-pages and corresponding comments, on both the captions and the Images. We were able to obtain 80% accuracy in tagging posts requiring empathetic responses.

A research paper based on this work has been published in AAAI Publications in proceedings of the Proceedings of the Thirtieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2017.

Research paper: Mimansa Jaiswal, Sairam Tabibu, and Erik Cambria. ““Hang in There”: Lexical and Visual Analysis to Identify Posts Warranting Empathetic Responses.” (2017).

September-2016 — December-2016

Multimodal Analysis for Deception Detection

IIT BHU, Varanasi — with Dr. Rajiv Bajpai, School of Computer Science and Engineering, NTU Singapore

We worked on developing a data driven method for automatic deception detection in real-life trial data using visual and verbal cues. Using OpenFace with facial action unit recognition, we analyze the movement of facial features of the witness when posed with questions and the acoustic patterns using OpenSmile. We then perform a lexical analysis on the spoken words, emphasizing the use of pauses and utterance breaks, feeding that to a Support Vector Machine to test deceit or truth prediction. We then try out a method to incorporate utterance-based fusion of visual and lexical analysis, using string based matching.

A research paper based on this work has been published in IEEE Explore in proceedings of the 16th International Conference on Data Mining Workshops, ICDM 2016.

Research paper: Mimansa Jaiswal, Sairam Tabibu, and Rajiv Bajpai. “The Truth and Nothing But the Truth: Multimodal Analysis for Deception Detection.” ICDM Workshops. 2016.