Seyed Yahya Shirazi

From 1,052 to 8,563: How AI Coding Agents Transformed My Research Workflows

1,052 GitHub contributions in 2024. 8,563 in the last year. This post covers how AI coding agents transformed my research workflows, the open-source plugins I built along the way, and a 10-week course to help the …

Blog

Personal and Professional Experiences

This section is dedicated to my personal and professional experiences that I don’t want to forget and might be worth sharing. The blogs span from technical details on using …

Image Annotation Tool: VLM-Based Annotation for Neuroscience

An annotation bank for the NSD Shared 1000 images generated using open-source Vision Language Models. The tool supports batch processing across multiple VLMs with plans to integrate Hierarchical Event Descriptors (HED) …

Annotation Garden Initiative: Collaborative Annotation for Neuroscience

AGI addresses the critical gap between increasingly complex naturalistic stimuli and the need for standardized, reusable annotations. Through GitHub-based version control and modern web interfaces, AGI enables …

Papers

Age-related Reorganization of Corticomuscular Connectivity During Locomotor Perturbations

How does the brain communicate with muscles during unexpected perturbations, and how does this change with age? We investigated corticomuscular connectivity during perturbed recumbent stepping in young and older adults …

The Lab Streaming Layer for Synchronized Multimodal Recording

The Lab Streaming Layer (LSL) presents a software-based solution for synchronizing data streams across multiple instruments in neurophysiological research. Utilizing per-sample time stamps and LAN-based time …

Signal Processing for Wearable Biosensors: Fundamentals and Techniques for Ring-Based Devices

Explore the theoretical foundations and practical implementation of signal processing techniques for ring-based wearable biosensors. This guide covers digital filter theory, z-transforms, real-time processing …

Health-Specific Evaluation for AI Systems

Learn how to evaluate AI systems in healthcare using specialized metrics and frameworks that address clinical validity, FDA regulatory requirements, bias detection, safety assessment, and practical implementation …

Statistical Analysis for Evaluation

Learn how to apply statistical methods for robust evaluation of models, including power analysis, mixed-effects models, bootstrap confidence intervals, multiple comparison corrections, and effect size calculations. This …

LLM Evaluation Methods

Learn about various methods for evaluating large language models (LLMs), including automatic metrics like BLEU and ROUGE, the LLM-as-judge paradigm, human-in-the-loop strategies, and specialized approaches for …

Human Evaluation & Psychometrics for AI Systems

This post provides a detailed overview of human evaluation and psychometrics in the context of AI systems, covering key concepts, reliability metrics, scale design, and practical implementation strategies. It includes …

NEMAR Dataset Citations Analysis Dashboard

This dashboard provides comprehensive analysis of dataset citations within the NEMAR ecosystem, revealing collaboration patterns, research trends, and the impact of open neuroscience data sharing on the research …

HBN Dataset Insights Dashboard

This is a data visualization dashboard for exploring the Healthy Brain Network EEG dataset. Features age and sex distributions, task availability metrics, mental health correlations, and per-release analysis across 11 …

Creating Interactive Dashboards in Hugo: A Complete Guide

Learn how to transform your Hugo static site into an interactive dashboard powerhouse using Chart.js, structured JSON data, and modern web development practices.

Adding Mermaid Diagrams to Hugo: From Partials to Production

Learn how to seamlessly integrate Mermaid diagram functionality into your Hugo website using partials, enabling beautiful flowcharts, sequences, and technical diagrams directly in markdown.

Simulating Scalp EEG from Ultrahigh-Density ECoG Data Illustrates Cortex to Scalp Projection Patterns

Using 1024-electrode ultrahigh-density electrocorticography (μECoG) data as ground truth, this study demonstrates that cortical activity from a small 3×3 cm patch projects broadly across the entire scalp surface, not …

Python's venv: A Comparison with Conda for Research Computing

This post explores Python’s built-in venv module, highlighting its advantages for research computing while comparing it with Conda to help researchers choose the right tool for their workflows.

Setting Up and Managing Git-Annex with Backblaze B2 Storage

This guide walks you through setting up git-annex with Backblaze B2 as remote storage, and covers common usage scenarios for managing large files in git repositories.

A Standardized Framework for Sensor Placement in Human Motion Capture and Wearable Applications

We present a comprehensive framework that standardizes sensor placement in human movement and physiological monitoring applications. Through precise definitions of anatomical landmarks, coordinate systems, and placement …

HBN-EEG: The FAIR implementation of the Healthy Brain Network (HBN) electroencephalography dataset

The HBN-EEG dataset provides a comprehensive collection of high-density EEG recordings from the Healthy Brain Network project, formatted in the Brain Imaging Data Structure (BIDS) standard. This dataset includes …

HBN-EEG: Healthy Brain Network EEG Datasets

The Healthy Brain Network EEG Datasets (HBN-EEG) includes 11 dataset releases containing EEG, behavioral data, and rich event annotations from participants aged 5-21 years, supporting large-scale analyses and …

Older adults use fewer muscles to overcome perturbations during a seated locomotor task

Older adults often demonstrate greater co-contraction and motor errors than young adults in response to motor perturbations. We demonstrated that older adults reduced their motor errors more than young adults with brief …

System and methods for biosignal detection and active noise cancellation

We developed a novel EEG system with a dual-electrode net structure for noise reduction and precise biosignal capture. Incorporating advanced software for signal processing, this invention enhances EEG accuracy, reduces …

Non-Parametric Functional Muscle Network as a Robust Biomarker of Fatigue

We show that the effects of fatigue on muscle coordination and neural drive can be reliably characterized using a non-parametric functional muscle network. The network demonstrated a consistent decrease in connectivity …

Re-Referencing Methods for High-Density EEG

This project investigates different re-referencing approaches for high-density EEG recordings, evaluating their effectiveness in reducing artifacts and improving source localization accuracy. The work contributes to best …

Nonlinear functional muscle network based on information theory tracks sensorimotor integration post stroke

We show that InfoMuNet, a novel functional biomarker based on a nonlinear network graph of muscle connectivity, can quantify the role of sensory information on motor performance. We demonstrate its potential use in …

Perilaryngeal-Cranial Functional Muscle Network Differentiates Vocal Tasks: A Multi-Channel sEMG Approach

We explored the potential of a functional muscle network to differentiate vocal tasks. The network robustly differentiated vocal tasks, while classic muscle activation assessment failed to differentiate. The study also …

Sensory feedback and assistive motor control for desk cycling

This project explores how sensory feedback can enhance motor control during desk cycling, with applications in rehabilitation and workplace wellness. The research focuses on optimizing user experience and therapeutic …

Differential Theta-Band Signatures of the Anterior Cingulate and Motor Cortices During Seated Locomotor Perturbations

We demonstrate that seated locomotor perturbations produce differential theta-band responses in the anterior cingulate and supplementary motor areas, suggesting that tuning perturbation parameters can potentially modify …

Influence of Mismarking Fiducial Locations on EEG Source Estimation

Mismarking fiducial locations can systematically change EEG source locations. We inestigated this effect by systematically moving the fiducial locations to simulate such errors.