Latest Project

Identifying Mosquito Species Using Smartphone Cameras

According to WHO (World Health Organization) reports, among all disease transmitting insects, a mosquito is the most hazardous insect. In 2015 alone, 214 million cases of malaria were registered worldwide. The Zika virus is another deadly disease transmitted from mosquitos. The classification between hazardous and regular mosquitos is very important. With our approach, we want to enable the non-expert population to identify the risk early, and then act proactively.

Professional Interests

  • Design, build, and deploy machine learning applications to solve real-world problems

  • Work with any kind of practical data, including sensors, image, audio, text, video, motion capture, and other high-dimensional data

  • Languages used are Java*, C++, and Python*

  • Supervised learning includes Naive Bayes algorithm, support vector machine (SVM), decision tree, random forest, neural network, KNN, bagging and boosting, deep neural network, hidden Markov model (HMM), and conditional random fields (CRF) recommender system

  • Unsupervised learning includes clustering K-means, expectation–maximization (EM) algorithm, generative probabilistic modeling