Project Description

image34

Complex Brain Networks in Health and Diseases

The cognitive engineering program focuses on studying mental functions and how and where brain encodes information. We develop computational and analytical tools to analyze brain rhythms, mainly the EEG signal and functional MIR (fMRI) images. We develop network and graph models of the brain signals from different areas, study their interactions and connectivity. The goal is to use brain monitoring to assess mental workload, fatigue, alertness and arousal. This would have application in activities like driving and flying where both monotony or alertness can be a problem, and in human-machine interactions such as in autonomous driving. For elderly, we may be able to study onset of dementia, while in children we may be able study autism spectrum disorder.

  


image35

Decoding Olfactory Cognition

 Objective brain-based assessment of olfactory response to different odors holds the potential to minimize inconsistencies between screening consumer tests and actual, in-use tests, or market performance of odor products. Particularly, the use of electroencephalogram (EEG)-based technologies in developing such objective assessment solutions is attractive due to the fact that it provides a fast, non-invasive strategy for probing olfactory perception. To capture the complex nature of brain function involved in olfaction we developed an approach integrating different levels of information contained in the brain response to odor stimuli: local information scrutinized at different frequency bands and global functional information by means of interdependencies in the activity of different brain regions, which reflects how information is processed and transferred across the brain. 

Goals

The main goals of this project are: a) feasibility assessment for the objective categorization of the olfactory response to odor stimuli of different levels of perceived pleasantness (loved versus liked) and b) the development of a portable EEG-based system implementing the algorithms for olfactory stimuli discrimination . To this goal, a machine learning framework is developed to extract relevant information from experimental EEG data obtained from a population of panelists andto objectively classify the olfactory response to odor stimuli inducing different levels of perceived pleasantness.

image36

Mental Fatigue Prediction Using Brain Connectivity (Brainteaser project)

Fatigue is a complex state, manifesting in general in the form drowsiness, deterioration in the vigilance level and reduced mental or physical performance, which may result in car crashes. Therefore, we developed a driving simulator system for driving fatigue tracking in order to prevent mental fatigue-related accidents. We developed two parallel analysis frameworks, which are power spectrum density based metrics for driving fatigue monitoring and functional connectivity based measures for fatigue assessment. We aim to develop an analysis framework for fatigue states monitoring in real time based on dry EEG systems. The estimated mental states can be used as bio-markers to automate the system when human operator is in risk-prone conditions. This design is potentially beneficial to other safety-critical areas including industrial control and air traffic management. 

image37

Human-Intelligent Machine Coexistence (HELIOS)

    The HELIOS project focuses on developing a novel integrative framework for human machine interaction system (HMI) as a collaboration between human and modern machines, which will be applied to enhance motor, speech and neurocognition restoration of stroke patients. HELIOS will incorporate feedback to facilitate therapy course by establishing a trusted human-machine relationship through collaboration, conversation, and cognitive association. The overarching goal is to demonstrate the implementation of the devised framework in stroke rehabilitation therapy, targeting neurocognition and neuromotor restoration and enhancement through feedback and plasticity. Additionally,the research on machine intelligence will address both human and machine adaptation within real-life conditions. The research program has three main research pillars, which are Physical HMI (Assistive and augmentative motor control systems), Communication HMI (human-machine ‘speech chain’ for speech rehabilitation), and BM-I (HMI through Brain-Machine).

image38

Biomarker for Creation Ideation

  Creativity is defined as the ability to produce ideas that are both novel and useful.  It is a crucial skill for effective problem-solving and decision-making, especially under extreme circumstances, in volatile, uncertain and increasingly complex environments. We designed an experimental paradigm where the participants were asked to perform Alternative Uses (AU, which participants were asked to think of alternative/unconventional ways to use everyday objects) task and Object Characteristics (OC, which participants were asked to list typical characteristics or properties of an object) task. We estimated relative power spectrum, global efficiency from brain networks constructed with the imaginary part of coherence and phase-to-amplitude coupling (PAC) as potential biomarker of creativity. Statistically significant differences between AU and OC were detected with PAC estimated within sensors in certain frequency pairs, which can be considered as the ground for both detecting and designing a connectomic biomarker of creativity.

image39

Cognitive AI Frontiers for Autonomous Driving and Flying

 Autonomous driving is becoming increasingly popular. What is the role of humans in autonomous driving? How do humans and machines (car) interact? We have developed a full virtual reality simulator for autonomous driving. We have developed another simulator for autonomous flying. The driver/student works in this simulator and his brain/mind is monitored during the autonomous experience. We study brain waves, eye movements, and give haptic/touch feedback. This project may be of interest to students interested in AI, augmented reality, autonomous driving. Good programming, AI/machine learning, and other skills or interests are desirable. This project has very practical real-life applications in human-machine interaction, and in advanced topics of AI and brain information processing. 

image40

Brain Chimera-like States

Neural synchronization plays a crucial role in cognitive functions and in performing tasks as it facilitates the transmission of information among the various brain sub-regions, and thus their communication. In this project, we analysis the emergence of synchronization patterns in neural ensembles recorded in the macaque brain to study the chimera-like states. And we also study on modeling the bi-directional communication of neural ensembles via chimera state principles  

TEam

PI: Prof. Anastasios Bezerianos

PI: Prof. Anastasios Bezerianos

PI: Prof. Anastasios Bezerianos

Prof. Nitish Thakor

PI: Prof. Anastasios Bezerianos

PI: Prof. Anastasios Bezerianos

Dr. Andrei Dragomir

PI: Prof. Anastasios Bezerianos

Dr. Andrei Dragomir

Collaborators

Prof. Fabio Babiloni

Prof. Fabio Babiloni

Prof. Fabio Babiloni

Sapienza University of Rome

Dr. Josh Ewen

Prof. Fabio Babiloni

Prof. Fabio Babiloni

 Kennedy Krieger Institute, Johns Hopkins Medical School 

Students And Postdoctoral FEllows

Nida Abbasi

Nida Abbasi

Nida Abbasi

Research Assistant

Wang Tian

Nida Abbasi

Nida Abbasi

Research Assistant

Manuel Seet

Jonathan Harvy

Jonathan Harvy

Research Assistant

Jonathan Harvy

Jonathan Harvy

Jonathan Harvy

Research Assistant

Alumni

Fumihiko Taya

Fumihiko Taya

Fumihiko Taya

Postdoctoral Fellow

Yu Sun

Fumihiko Taya

Fumihiko Taya

Postdoctoral Fellow

Junhua Li

Stavros Dimitriadis

Stavros Dimitriadis

Postdoctoral Fellow

Stavros Dimitriadis

Stavros Dimitriadis

Stavros Dimitriadis

Research Assistance

Publications

Reviews

 Qi P., Ru H., Gao L., Zhang X., Zhou T., Tian Y., Thakor N., Bezerianos A., Li J., Sun Y., “Neural Mechanisms of mental fatigue revisited: New insights from the brain connectome,” Engineering, Vol. 5, pp. 276-286, 2019.  

Original Works

  Sun Y., Lim J., Meng J., Kenneth K., Ph.D., Thakor N., Bezerianos A., “Discriminative analysis of brain functional connectivity patterns for mental fatigue classification,” Annals Biomed. Eng., Vol. 42, Issue 10, pp 2084-2094, 2014. 


Borghini G., Arico P., Graziani I., Salinari S., Sun Y., Taya F., Bezerianos A., Thakor N.V., and Babiloni F., “Quantitative assessment of      the training improvement in a motor-cognitive task by using eeg, ecg and      eog signals,” Brain Topography, pp. 1–13, 2015.


Sun Y., Lee, R., Chen Y., Collinson S., N. Thakor, A. Bezerianos, Sim K., “Progressive gender differences of structural brain networks in      healthy adults: a longitudinal diffusion tensor imaging study,” PLoS One, 10(3), e0118857, 2015, doi: 10.1371/journal.pone.0018857.


Taya, F., Sun, Y., F. Babiloni, N. Thakor, A. Bezerianos, “Brain enhancement through cognitive training: a new insight from brain connectome,”      Frontiers Systems Neurosci., 9: e44, 2015. 


Xu N., Sun T., Tsang W. M., Delgado-Martinez I., Lee S-H., Seshadri S., Xiang Z., Merugu S., Gu Y., Yen S-C., Thakor N. V. “Polymeric C-shaped cuff electrode for recording of      peripheral nerve signal,” Sensors and Actuators B: Chemical, 210, 640-648, 2015.


Dimitriadis S., Sun Y., Laskaris, N., Thakor, N., Bezerianos, A., “Cognitive workload assessment based on the tensorial treatment of EEG estimates of      cross-frequency phase interactions,” Annals Biomed. Eng., 43(4),      977-989, 2015. 


Lee WW, Kukreja SL, Thakor NV., “CONE: Convex-optimized-synaptic      efficacies for temporally precise spike mapping,” IEEE Trans Neural Netw Learn Syst., 2016 Mar 24. [Epub ahead of print] PMID: 27046881.


Li J., Lim J., Yu Chen, Wong K., Thakor N., Bezerianos A., and Sun      Y., “Mid-task break Improves global integration of functional connectivity      in lower alpha band,” Front. Hum. Neurosci., Jun 17;10:304. Doi:      10.3389/fnhum.2016.00304. eCollection 2016., PMCID: 27378894.


Cetinkaya-Fisgin A., Joo M. G., Ping X., Thakor N. V., Ozturk C.,Hoke A., Yang I. H., “Identification of fluocinolone acetonide to prevent paclitaxel induced peripheral neuropathy,” J Peripheral Nervous System, DOI: 10.1111/jns.12172, 2016. PMID: PMID: 27117347.


Taya F., de Souza J., Thakor N. V., Bezerianos A., “Comparison method for community detection on brain networks from neuroimaging data, Appl Netw Sci 1: 8, 2016. DOI: 10.1007/s41109-016-0007-y. 


Dimitrakopoulos G. N., Sun Y., Ardian K., Thakor N. V., and Bezerianos A., “A method for cross-task mental workload classification based on brain connectivity,” Frontiers  Human Neurosci., 2016. DOI=10.3389/conf.fnhum.2016.220.00002Borghini  


G., Aricò P., Graziani I., Salinari S., Sun Y., Taya F, Bezerianos A.. Thakor N. V., Babiloni F.,  “Quantitative      assessment of the training improvement in a motor-cognitive task by using  EEG, ECG and EOG signals,” Brain Topography, Vol. 29  (Issue 1), pp 149-161, 2016.


Dimitriadis S., Sun Y., Laskaris N., Thakor N. and Bezerianos A., “ Revealing cross-frequency  causal interactions during a mental arithmetic task through symbolic transfer      entropy: a novel vector-quantization approach, IEEE Trans. Neural  Systems Rehab Eng, vol. 24(1),  pp. 1017-1028, 2016. 10.1109/TNSRE.2016.2516107


Taya F, Sun Y, Babiloni F, Thakor N, Bezerianos A., “Topological  changes in the brain network induced by the training on a piloting task: An EEG-based functional connectome approach,” IEEE Trans Neural Syst      Rehabil Eng., Vol. 26(2), pp. 263 – 271, 2016 Jun 16. [Epub ahead of print], PMID: 27333606 10.1109/TNSRE.2016.2581809.      


Ren S., Li J., Taya F., deSouza J., Thakor N., Bezerianos A., “Dynamic functional segregation and Integration in human brain network      during complex tasks,” IEEE Trans Neural Syst Rehabil Eng., Vol 25      (6) pp. 547-556, 2016, DOI: 10.1109/TNSRE.2016.2597961.


Sun Y., Lim J., Dai Z., Wong K.F., Taya F., Chen Y., Li J., Thakor N. V., Bezerianos A., “The effects of a mid-task break on the brain connectome in healthy participants: A resting-state functional MRI study,” NeuroImage, Vol. 152, 19-30, 2017. 


Dai Z., de SouzaJ., Lim J., Ho P., Chen Y., Li J., Thakor N., Bezerianos A., Sun Y., “EEG      cortical connectivity analysis of working memory reveals topological reorganization in theta and alpha bands,” Frontiers Human Neurosci., Front Hum. Neurosci., 12 May 2017 | https://doi.org/10.3389/fnhum.2017.00237


Sciaraffa N., Borghini G., Aricò P.., Di Flumeri G., Colosimo A.,      Bezerianos A., Thakor N. V., and Babiloni F., “Brains interaction during cooperation: evaluating local properties of multiple-brain network,” Brain Sci., 7 (7), 90, 2017.


Li J-H, Thakor N. V., Bezerianos A., “Hemispherical Asymmetry of spectral power density in Beta band: A Study with and without      Eexoskeleton,” Sci. Reports. Sci Rep. 2018; 8: 13470.. doi: 10.1038/s41598-018-31828-1, PMCID: PMC6128944, PMID: 30194397


Harvy J., Thakor N., Bezerianos A., Li J. “Between-frequency  topographical and dynamic high-order functional connectivity for driving  drowsiness assessment, “ IEEE Trans. Neural Systems Rehab Eng., 2019  (accepted).


Fumihiko T., Dimitriadis S.; Dragomir A., Lim J.; Sun, Y., Wong, Foong K., Thakor N. V., A. Bezerianos, “Fronto-parietal subnetworks flexibility compensates for cognitive decline due to mental fatigue,” Human Brain Mapping