Toktam Zoughi

Toktam Zoughi

lecturer|PhD, Amirkabir University of Technology - Computer Engineer

Research Areas

  • Deep Neural network
  • Speech recognition
  • Speech processing
  • Signal processing
  • Statistical Pattern Recognition
  • Image processing
  • Machine vision
  • Biomedical signal processing
  • Machine Learning
  • Chaotic signal and non-linear time-frequency analysis of EEG signals


  • Deep neural networks
  • Speech recognition
  • Speech signal processing
  • Signal processing
  • Statistical Pattern Recognition methods
  • Image processing
  • Machine vision
  • Analysis EEG signals with different existing method
  • Determining the depth of Anesthesia from the EEG signals
  • Video processing
  • Neural network
  • Biomedical signal processing
  • Programming in Matlab, C, C++, Pascal, …
  • Strong verbal communicator and presenter through different conference presentations
  • Non-linear time-frequency analysis of (EEG) signals
  • Collecting EEG signal during anesthesia
  • Design of classifiers and feature selection algorithms


  1. T. Zoughi, M. M. Homayounpour, “DBMiP: A Pre-training Method for Information Propagation over Deep Networks," Computer Speech & Language, In Press, 2018.[Online]. Available:
  2. T. Zoughi, M. M. Homayounpour, “A Gender Aware Deep Neural Network Structure for Speech Recognition,” Iranian Journal of Science and Technology, accepted.
  3. T. Zoughi, M. M. Homayounpour, “Adaptive Windows Multiple Deep Residual networks for Speech Recognition,” Expert Systems with Applications, submitted (revised).
  4. T. Zoughi, R. Boostani, “A wavelet-based estimating depth of anesthesia”, Engineering Applications of Artificial Intelligence, vol. 25, no. 8, pp. 1710-1722, 2012.
  5. M. Deypir, S. Alizadeh, T. Zoughi, & R. Boostani, “Boosting a multi-linear classifier with application to visual lip reading”, Expert Systems with Applications, vol. 38, no. 1, pp. 941-948, 2011.
  6. M. Sabeti, R. Boostani, T. Zoughi, “Using genetic programming to select the informative EEG-based features to distinguish schizophrenic patients”, Neural Network World, vol. 22, no. 1, pp. 3-11, 2012.
  7. M. Deypir, R. Boostani, T. Zoughi, “Ensemble based multi-linear discriminant analysis with boosting and nearest neighbor”, Scientia Iranica, vol. 19, no. 3, pp. 654- 661, 2012.

Journal Papers in Persian (ISC):

  1. T. Zoughi, M. M. Homayounpour, “Adaptive Windows Convolutional Neural Network for Speech Recognition," Signal and Data Processing, vol. 37, no. 3, pp. 13-29, 2018.
  2. T. Zoughi, R. Boostani, “Proposing New Methods to Determine Depth of Anesthesia”, journal of control-khaje Nasir Toosi University of technology, 2011.
  3. M. J. Zoughi, T. Zoughi, “Prediction of COD and NH4+-N concentrations in Leachate from Lab-scale Landfill Bioreactors Using Artificial Neural Networks”, Water and wastewater, vol. 21, no. 2, 2010.

PRESENTATIONS (Conference Papers):

  1. T. Zoughi, M. M. Homayounpour, “pre-training deep neural network based on deep Boltzmann machine for phone recognition,” in Computer Society of Iran Computer Conference (CSICC), 2015, pp. 625-630.
  2. T. Zoughi, M. M. Homayounpour, “Gender aware deep Boltzmann machines for phone recognition,” in International Joint Conference on Neural Networks (IJCNN), 2015, pp. 1-5. doi: 10.1109/IJCNN.2015.7280605.
  3. T. Zoughi, R. Boostani, “Analyzing autocorrelation fluctuation of EEG signal for estimating depth of anesthesia”, in Electrical Engineering (ICEE), 2010 18th Iranian Conference, 2010, pp. 24-29.
  4. T. Zoughi, R. Boostani, P. Gifani, “New Method for Improving Smoothed Pseudo Wigner-Ville Algorithm for Estimating Depth of Anesthesia”, in International CSI computer conference, Iran, Tehran, 2009.