Haidar K Khan

Haidar K Khan

Computer scientist and programming enthusiast. My interests revolve around applying machine learning to solve hard problems.

Publications

Learning filter widths of spectral decompositions using wavelets

Published in Advances in Neural Information Processes (NeurIPS), 2018

A novel approach for end-to-end time series classification using neural networks is presented in this work. The wavelet transform is used to learn the optimal spectral decomposition of the time series for any classification task.

Recommended citation: Khan, H., & Yener B. (2018). "Learning filter widths of spectral decompositions using wavelets." Advances in Neural Information Processes (NeurIPS). http://haidark.github.io/files/wavelet_deconv_2018.pdf

Focal onset seizure prediction using convolutional networks

Published in IEEE Transactions on Biomedical Engineering, 2017

We apply convolutional neural networks to wavelet tensors for focal onset seizure prediction using a change point detection algorithm to set the prediction horizon.

Recommended citation: Khan, H., Marcuse, L., Fields, M., Swann, K., & Yener, B. (2017). "Focal onset seizure prediction using convolutional networks." IEEE Transactions on Biomedical Engineering. http://haidark.github.io/files/seizure_pred_2017.pdf

Interaction recognition using sparse portraits

Published in International Conference on Pattern Recognition (ICPR), 2014

We propose a method for classifying human-object interactions in videos by combining motion and appearance information.

Recommended citation: Bogun, I., Khan, H., Chen, J., & Ribeiro, E. (2014). "Interaction recognition using sparse portraits." International Conference on Pattern Recognition (ICPR). http://haidark.github.io/files/inter_rec.pdf