Mohammad Hossein Behboudi

Ph.D. Researcher in Cognition & Neuroscience

About Me Email Me
Scroll to About

About Me

Portrait of Mohammad H. Behboudi

Hi, I’m Mohammad Hossein Behboudi—a Ph.D. candidate in Cognition & Neuroscience at UT Dallas with an Electrical Engineering foundation. I work at the intersection of biosignals and behavioral data. My expertise includes designing well-controlled experiments, signal processing, and building ML-driven, statistically sound pipelines that turn real-world EEG/MEG and behavioral data into reliable, explainable insights. Recent projects span BCI explorations using end-to-end foundational models and the use of large language models to analyze the home language environment, with practical impact in health and education. I collaborate across multidisciplinary teams to transform raw, noisy data into practical tools and clear findings, enhancing people’s lives.

Education

Ph.D. Student in Cognition and Neuroscience

The University of Texas at Dallas, Dallas, TX | Expected 2026

Callier Center for Communication Disorders

Thesis: Development of Large-Scale Brain Networks During Semantic and Syntactic Error Processing: An EEG Connectivity and Graph Theory Analysis

M.Sc. in Applied Cognition and Neuroscience

The University of Texas at Dallas, Dallas, TX | May 2024

B.Sc. in Electrical Engineering

K. N. Toosi University of Technology, Tehran, Iran | Jan 2020

Final Project: 6-Classes Sleep Apnea Classification Based on Single Channel EEG

Skills & Expertise

Biosignal Processing & Time-Series

  • Time-series analysis; Multi-channel signals & Source separation
  • EEG/MEG preprocessing; interpolation & re-referencing
  • FIR/IIR design (Butterworth/Chebyshev), bandpass/notch, zero-phase
  • Adaptive & state-space filters (LMS/RLS, Kalman/RKF)
  • Artifact removal, Independent Component Analysis(ICA), baseline/drift correction
  • FFT, STFT, Morlet wavelets, ERSP; connectivity (coherence, PLV/PLI), graph metrics
  • Multidimensional Pattern Connectivity (MDPC), Current Source Density (CSD)

ML for Biosignals

  • Feature engineering (time/freq/time-freq; entropy/complexity)
  • Feature selection (MRMR, Mutual Info, Ensemble)
  • Classical models: SVM/KNN, HMMs, tree ensembles, RUSBoost
  • Sequence models: 1D-CNN, LSTM/GRU, TCN
  • Rigorous eval: cross-subject vs. within-subject CV; imbalance handling

Deep Learning, Foundation Models & LLMs

  • PyTorch/TensorFlow; Lightning; mixed-precision & profiling
  • Self-supervised learning for time-series; contrastive & masked modeling
  • Transformers & long-sequence models; GNNs for sensor topology
  • LLMs: conversation analytics (ASR, diarization, sentiment)

Statistics

  • GLM/LMM; linear mixed-effects; repeated-measures & longitudinal models
  • Quasi-experimental design: matching/weighting
  • Linear Models: Regression, ANOVA, MANOVA
  • Power analysis, permutation tests, multiple-comparison control

Experimental & Study Design

  • Protocol design,counterbalancing, randomization
  • Sample-size planning; preregistration & analysis plans
  • Data visualizations

Tools

  • Python (NumPy, SciPy, pandas, statsmodels, scikit-learn, PyTorch)
  • MNE-Python, EEGLAB, FieldTrip; MATLAB; R (tidyverse, lme4)
  • Visualization: matplotlib, Plotly, ggplot2
  • FreeSurfer, SPM

Featured Projects

Cross-Frequency EEG Connectivity Pipeline project

Cross-Frequency EEG Connectivity Pipeline

End-to-end MATLAB, Python, and R pipeline for preprocessing and analyzing EEG data. Implements Time-Lagged Cross-Frequency Multidimensional Connectivity to study neural oscillations during speech perception in noise.

View on GitHub →
Python MATLAB R MNE-Python Wavelets/ERSP Mixed Models Connectivity PCA Scientific Writing
Neural Decoding of Speech

Hybrid Deep Learning for Neural Decoding of Speech

Developed an end-to-end ML/DL pipeline using a novel hybrid deep learning architecture for non-invasive brain-computer interfaces. The project combines self-supervised learning, 1D CNNs, Transformer Encoders, and Graph Neural Networks (GNNs) to classify speech vs. silence from MEG data with high accuracy.

View on GitHub →
Deep Learning PyTorch MEG GNN Transformers Python Speech Processing
Sleep Apnea EEG Classification project

Computer-Aided Sleep Apnea Diagnosis

Entropy-based features + mRMR selection with SVM/KNN for accurate apnea event identification from EEG.

Learn More →
EEG Entropy Features mRMR SVM KNN MATLAB Signal Processing
Mobile EEG Stimulus Presenter application

Mobile EEG Stimulus Presenter

Engineered a portable stimulus presentation platform using Python and Tkinter to facilitate mobile EEG research in non-laboratory settings, increasing accessibility for diverse and underrepresented communities.

View on GitHub →
Python Tkinter Pandas EEG Experiment Design Data Logging Data Synchronization
MATLAB GUI for EEG Pre-processing

MATLAB GUI for EEG Pre-processing

A user-friendly MATLAB application designed to streamline the cleaning and pre-processing of raw EEG data using a guided, step-by-step pipeline.

View on GitHub →
MATLAB EEGLAB GUI Signal Processing Neuroscience ICA MARA

Publications

Published

Neural oscillations during predictive sentence processing in young children.

Benítez-Barrera, C. R., Behboudi, M. H., & Maguire, M. J. (2024). Brain and Language, 254, 105437 • doi:10.1016/j.bandl.2024.105437

The necessity of taking culture and context into account when studying the relationship between socioeconomic status and brain development.

Schneider, J. M., Behboudi, M. H., & Maguire, M. J. (2024). Brain Sciences, 14(4), 392 • doi:10.3390/brainsci14040392

Rethinking household size and children’s language environment.

Poudel, S., Denicola-Prechtl, K., Nelson, J. A., Behboudi, M. H., Benítez-Barrera, C., Castro, S., & Maguire, M. J. (2024). Developmental Psychology, 60(1), 159 • doi:10.1037/dev0001650

Development of gamma oscillation during sentence processing in early adolescence: Insights into the maturation of semantic processing.

Behboudi, M. H., Castro, S., Chalamalasetty, P., & Maguire, M. J. (2023). Brain Sciences, 13(12), 1639 • doi:10.3390/brainsci13121639

Sleep apnea diagnosis using complexity features of EEG signals.

Gholami, B., Behboudi, M. H., Khadem, A., Shoeibi, A., & Gorriz, J. M. (2022, May). In International Work-Conference on the Interplay Between Natural and Artificial Computation (pp. 74–83). Cham: Springer International Publishing • doi:10.1007/978-3-031-06242-1_8

Diagnosis of Sleep Apnea Syndrome from EEG Signals using Different Entropy Measures.

Gholami, B., Behboudi, M. H., Mahjani, M. G., & Khadem, A. (2021). 2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS), Tehran, Iran, 1–6 • doi:10.1109/ICSPIS54653.2021.9729367

Under Review

Non-native English-Speaking Young Adults Experience Difficulties Inferencing the Meaning of Novel Words in Noisy Environments in Their Second Language.

Benítez-Barrera, C. R., Behboudi, M. H., Chalamalasetty, P., Castro, S., Leung, E., & Maguire, M. J. (Under review). Language and Speech.

In Preparation

A Time-Lagged Multi-Oscillatory Network: Alpha, Theta, and Beta Coordination During Speech Perception with Varying Noisy Environments and Semantic Constraints.

Behboudi, M. H., Benítez-Barrera, C. R., & Maguire, M. J. (In preparation).

Development of Large-Scale Brain Networks During Semantic and Syntactic Error Processing: An EEG Connectivity and Graph Theory Analysis.

Behboudi, M. H., Schneider, C. J. M., & Maguire, M. J. (In preparation).