Projects

Bangla Newspaper Article Classification with Bidirectional LSTM

Prepared a bangla newspaper dataset (400k+ bangla news samples, 25+ categories) for bangla news classification and generation experiments. Provided a classification benchmark with Bidirectional LSTM.

Kaggle URL: https://www.kaggle.com/furcifer/bangla-newspaper-dataset

NLP, Machine Learning, Text Classification, RNN

Residual Net for Car Detection with spatial transformation

In spite of the immense success of deep neural networks for classification tasks, it’s challenging to use them to extend the usage for industrial applications. The struggle comes from the nature of variation in data sources and the distribution of data. For image classification and detection schemes, it’s significant to design models that are less prone to transformation shifts. In this work, we propose LadonNet, a CNN which trains with multiple spatial transformations of the input instance ...

Conference: ICCA 2020 [Submitted]

ResNet, HydraNet, Computer Vision, Image Processing

Autonomous driving system with Machine Learning in Matlab

Developed a toolbox to calibrate the car and get the images for training mode easily, used a simple distributed computing system with two laptops to speed up processing, ad-hoc image processing technique for lane detection and cascade classifiers for road sign detection.

Youtube Demo: https://youtu.be/jWo3Bg04RmQ

IoT, Machine Learning, Computer Vision, Image Processing

Flask RESTful API with DeepLab & YOLO

A RESTful API to detect objects, and get semantic segmentation masks with YOLO, and DeepLab.

Youtube Demo: https://www.youtube.com/watch?v=CuBqLla3fog

RESTful API, Computer Vision, Semantic Segmentation, Object Detection

Software

PyEmotivCortexv2

Simply written emotiv cortex API v2 in python to get data from emotiv headsets.

Youtube Demo: https://www.youtube.com/watch?v=dtzQA_DyNNI

EEG, Emotiv, Communication