Jan 2021 - Present

• We are developing an innovative initiative - MosquitoAI is dedicated to developing AI-powered systems tailored for classifying various aspects of mosquito biology, including genus, species, instar, and gender and it develops valuable tools for mosquito surveillance and control, ultimately benefiting communities at risk of mosquito-borne diseases. With the capacity to enhance mosquito surveillance, MosquitoAI is at the forefront of cutting-edge technology in the fight against mosquito-related health threats.

• Collects and analyzes extensive datasets, aiming to automate the identification of mosquito characteristics, which traditionally required expert entomological training.

• All the AI models are being hosted through our website, making them accessible for citizen scientists engaged in mosquito monitoring.

Feb 2020 - July 202

• Presented a novel approach to detect cardiac abnormalities in auscultation sounds, addressing challenges like additive noise and sensor-dependent distortion. The method combines linear and logarithmic spectrogram-image features and employs a ResNet classifier, achieving impressive results on minimizing the impact of background noise and sensor variability for classifying phonocardiogram (PCG) signals. 

• Made a promising solution for computer-aided cardiac auscultation using affordable stethoscopes, a project of heart disease classification funded by Kaggle.

• We gathered heart sound data from patients under the supervision of medical professionals in hospital settings, and this dataset is now publicly available on Kaggle.

• Neural Network and Deep Learning (96.50%)

• Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization (95.20%)

• Structuring Machine Learning Projects (86.70%)

• Convolutional Neural Network (95.60%)

• Sequence Models (98.50%) 

• Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks).

• Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning).

• Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI)