Projects
Green Growth Explorer: Natural Capital Policy and Finance Mechanisms around the World
The book Green Growth That Works is the first practical guide to bring together pragmatic finance and policy tools that can make investment in natural capital both attractive and commonplace. These examples show how governments, businesses, NGOs and other groups are channeling economic resources towards conservation and restoration, for the benefit of people and nature. This Green Growth Explorer Application gives an overview of the book, and a deep dive in some cases data - users can explore by book chapters or mechanism types (make selections on the left, or read tutorial).
View Project
Movinder - Movie recommendation system for a group of people.
In order to implement a movie recommender system, we use the MovieLens dataset. The data contains 100K ratings from 1K users on 1.7K movies and has been used traditionally for recommender system research. I worked on the recommendation system with Non-Negative Matrix Factorization part and front-end design of the project using Flask. I used scikit-surprise library for matrix factorization.
View Project
Height and Weight Estimation From Unconstrained Images | IEEE ICASSP 2020
We present a deep learning scheme that relies on simultaneous prediction of human silhouettes and skeletal joints as strong regularizers that improve the prediction of attributes such as height and weight. Apart from imparting robustness to the prediction of attributes, our regularization also allows for better visual interpretability of the attribute prediction. For height estimation, our method shows lower mean average error compared to the state of the art despite using a simpler approach. For weight estimation, which has hardly been addressed in the literature, we set a new benchmark.
View Project
A Multi-Dimensional Machine Learning Approach to Predict Advanced Malware | Elsevier Computer Networks Journal
Advanced malware is able to obfuscate much of their traces through many mechanisms, such as metamorphic engines. Therefore, predictions and detections of such malware have become significant challenge for malware analyses mechanisms. In this paper, we propose a multi-dimensional machine learning approach to predict Stuxnet like malware from a dataset that consists of malware samples by using five distinguishing features of advanced malware. Our approach uses regression models to predict advanced malware. Analyses results show that there are high correlations among some features of advanced malware.
View Project