Understanding Crowd Behavior using Unsupervised Deep Neural Networks
- For this project we proposed two individual models for simulating crowd movement behavior in public places, such as railway stations.
- The proposed approaches include non-linear PCA based networks belonging to the autoencoders family (variational autoencoders among others), as well as deep generative models trained under an adversarial setting (generative adversarial network or GAN).
- We also developed a unique approach for crowd movement representation, it used probabilistic heat map generated with overlapping Gaussian kernels to simulate crowd densities.
Project report: On request
Proposing a Novel Method for Fake News Classification
- In this project after exhaustive study of current methods for fake news detection, we came up with ensemble model consisting two classifiers.
- First was a model with an information retrieval module and a feed forward neural network to integrate the knowledgebase for fake news detection. Second was style based classification model utilizing word embeddings and Bi-LSTM.
Read project report here
- I worked on this project with Dr. Xiang Liu as part of my job at Center for Advance Infrastructure and Transportation (CAIT).
- For this project I developed a computer vision program to analyze the traffic from CCTV footage for Center for Advanced Infrastructure and Transportation.
- The program would take a video file consisting CCTV footage at a railway crossing and computed count, relative speed, direction and time of crossing for both pedestrians and vehicles.
- The program achieved accuracy of 94% and computation time 60% less than actual video time, making it suitable for real time application.
- The project was oriented on creating computationally light weight video processing solution which can potentially be used on light weight systems (like raspberry pi) in real time.
- The program used background subtraction and Kalman filter for tracking and counting.
As this project is confidential, currently I am unable to share code and other details. I have asked for permission to share more.
Demonstration of text based convolutional neural networks for toxic comment classification. Check git repository here.
Traffic Sign Recognition using Deep Neural Network
Implementation convolutional neural networks using Keras to recognize GTSRB traffic signs. Check git repository here.