Umut Orhan

My research interests are brain computer interfaces, statistical signal processing, information theory and machine learning.

I am currently with Cognitive Systems Laboratory (CSL).

In CSL, we are always in need of smart undergraduate and graduate students. If you are interested in biomedical signal processing, you can contact me with your CV.


Ph.D. in Electrical and Computer Engineering
Northeastern University, Boston, MA
Advisor: Deniz Erdogmus

B.Sc. in Electrical and Electronics Engineering
Bilkent University, Ankara, Turkey

High School: Izmir Scientific High School (Izmir Fen Lisesi)

Peer-Reviewed Journal Publications

[5] Murat Akcakaya, Betts Peters, Mohammad Moghadamfalahi, Aimee Mooney, Umut Orhan, Barry Oken, Deniz Erdogmus, Melanie Fried-Oken. Noninvasive Brain Computer Interfaces for Augmentative and Alternative Communication Biomedical Engineering, IEEE Reviews in , vol.PP, no.99, pp.1,1 (2013)

[4] Barry Oken, Umut Orhan, Brian Roark, Deniz Erdogmus, Andrew Fowler, Aimee Mooney, Betts Peters, Meghan Miller, Melanie Fried-Oken. Brain-computer interface with language model-EEG fusion for locked-in syndrome Neurorehabilitation and Neural Repair (2013).

[3] Esra Ataer-Cansizoglu, Murat Akcakaya, Umut Orhan, Deniz Erdogmus, Manifold learning by preserving distance orders, Pattern Recognition Letters, Volume 38, 1 March 2014, Pages 120-131

[2] Umut Orhan, Deniz Erdogmus, Brian Roark, Barry Oken, Melanie Fried-Oken. Offline Analysis of Context Contribution to ERP-based Typing BCI Performance J Neural Eng. 2013 Oct 8;10(6):066003

[1] Hooman Nezamfar, Umut Orhan, Shalini Purwar, Kenneth E. Hild II, Barry Oken, Deniz Erdogmus. Decoding of multichannel EEG activity from the visual cortex in response to pseudorandom binary sequences of visual stimuli. International Journal of Imaging Systems and Technology, vol. 21, pp. 139-147. (2011)

Peer-Reviewed Conference Publications

[8] M. Higger, M. Akcakaya, U. Orhan, D. Erdogmus. "Robust Classification in RSVP Keyboard". In Foundations of Augmented Cognition (pp. 443-449). Springer Berlin Heidelberg (2013).

[7] U. Orhan, D. Erdogmus, B. Roark, B. Oken, S. Purwar, K.E. Hild, A. Fowler, and M. Fried-Oken. "Improved Accuracy Using Recursive Bayesian Estimation Based Language Model Fusion in ERP-Based BCI Typing Systems" In Engineering in Medicine and Biology Society, EMBC, 2012 Annual International Conference of the IEEE, 2012

[6] Umut Orhan, Ang Li, and Deniz Erdogmus. "Online regularized discriminant analysis." In Machine Learning for Signal Processing (MLSP), 2012 IEEE International Workshop on, pp. 1-6. IEEE, 2012.

[5] Umut Orhan, Kenneth E. Hild II, Deniz Erdogmus, Brian Roark, Barry Oken, Melanie Fried-Oken. 2012. RSVP Keyboard: An EEG based typing interface. Accepted to ICASSP 2012.

[4] Umut Orhan, Kenneth E. Hild II, Deniz Erdogmus, Brian Roark, Barry Oken, Melanie Fried-Oken. 2011. Context Information Significantly Improves Brain Computer Interface Performance - a Case Study on Text Entry Using a Language Model Assisted BCI. Accepted to Asilomar, 2011.

[3] Umut Orhan, Deniz Erdogmus, Brian Roark, Shalini Purwar, Kenneth E. Hild II, Barry Oken, Hooman Nezamfar, Melanie Fried-Oken. 2011. Fusion with Language Models Improves Spelling Accuracy for ERP-based Brain Computer Interface Spellers. In 33nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC'11).

[2] Kenneth E. Hild II, Umut Orhan, Deniz Erdogmus, Brian Roark, Barry Oken, Shalini Purwar, Hooman Nezamfar, Melanie Fried-Oken. 2011. An ERP-based Brain-Computer Interface for text entry using Rapid Serial Visual Presentation and Language Modeling. In Proceedings of the ACL-HLT 2011 System Demonstrations, pp. 38-43.

[1] Hooman Nezamfar, Umut Orhan, Deniz Erdogmus, Kenneth E. Hild II, Shalini Purwar, Barry Oken, Melanie Fried-Oken. 2011. On visually evoked potentials in eeg induced by multiple pseudorandom binary sequences for brain computer interface design. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011 ,  pp.2044-2047, 22-27 May 2011

Research Projects

RSVP Keyboard

People with severe speech and physical impairments can benefit from a direct brain computer interface for their communication needs. This project aims to develop an AAC interface using noninvasive EEG sensors to infer the user's intent regarding desired letters and symbols during text generation. The designed RSVP Keyboard system will utilize rapid serial visual presentation of letter sequences coupled with probabilistic and adaptive open vocabulary language models and EEG signal processing and classification algorithms. The designed brain interface relies on event related potentials including the P300 signal. The project design tightly couples feedback from locked-in consultants who will test the system design at regular intervals and provide critical feedback in future design improvements.


Most existing BCI research for assistive communication interfaces focus on the use letters to generate written text. This requires the subjects to be literate and comfortable with typing in general. As an alternative approach, in this project, we seek to design a BCI that enables the user to generate language using an iconic language called iconCHAT developed by Dr. Rupal Patel. Expected benefits include increased speed of communication as each icon might represent a word or phrase so equal number of item selection can construct a sentence instead of a word compared to RSVP Keyboard. A potential drawback is the necessity for the subject to become familiar with the icon set; this also means a closed vocabulary language generation system which is suitable for limited context interactions. An option to switch to letters for open vocabulary text generation can be incorporated to the final design for users that prefer to have this option.

SSVEP-based BCI Design

Steady state visually evoked potentials (SSVEP) of the visual cortex provide an alternative means for enabling communication between a brain and a computer system. Being relatively easy to induce, and requiring almost no subject training and minimal calibration time, SSVEP signals are prime candidates for developing BCI controlled applications. We are exploring the use of SSVEP-inducing stimuli and associated signal processing and classification algorithms primarily in environmental control applications such as navigating a robot/wheelchair. The reliable and robust nature of these signals also make them ideal for undergraduate research activities in BCI technology and application development .



Umut Orhan, Ph.D.
Electrical and Computer Engineering
Northeastern University

Contact Address:
409 Dana Research Center
Northeastern University
360 Huntington Ave
Boston, MA 02115

Office: 140 Fenway

Email: MyLastName[at]ece[dot]neu[dot]edu