Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
3D Visual Feedback System for Neuroprosthetics Control
This project introduces the Reviewer, a novel 3D visual feedback system that enhances myoelectric prosthesis control by allowing users to visualize their EMG signals in real-time. This system clarifies the relationship between muscle activity and the machine learning algorithms behind prosthetic control. With intuitive feedback, it tackles challenges like learning curves and misclassifications, helping users produce clearer, more consistent signals for improved neuroprosthetic usability. 
Processing and Evaluation Pipeline for Neuromodulation of Respiratory Muscles
Respiratory complications are a leading cause of death in patients with chronic spinal cord injury (SCI), significantly impacting their quality of life. Neuromodulation, a promising therapeutic approach, involves electrical stimulation to modulate nerve activity and enhance respiratory function. To support this effort, a comprehensive MATLAB pipeline was developed to automatically detect, analyze, and compare electromyography (EMG) properties in SCI patients undergoing neuromodulation therapy, contributing to the development of improved diagnostic and therapeutic strategies aimed at alleviating respiratory complications in this population. 
Manufacturing of a Multi-Function Implantable Microcontroller: Recorder, Stimulator, and Wireless Charger
The Bionode is a compact, all-in-one implantable device combining a recorder, stimulator, and wireless charger, designed by Professor Pedro Irazoqui’s lab. Engineered for implantation, the device’s versatility and small size make it ideal for advanced studies in neuromuscular function. This project focuses on adapting and manufacturing the Bionode to record Electromyography (EMG) data from rats’ soleus muscles, enabling real-time data transmission to a PC for wavelet compression and detailed analysis of motor unit activity, supporting advancements in neuroengineering research. 
Automated MRI Toolkit for Brain Structure Analysis
Introducing an Automated MRI Toolkit that synthesizes T2-weighted images from T1-weighted MRI scans, enabling precise brain structure analysis without requiring multiple imaging modalities. This toolkit simplifies research workflows and reduces patient scan time. 
publications
Maximum Dorsiflexion Detection Based on an On-Board Adaptive Algorithm for Transtibial Amputees With Robotic Prostheses
Published in IEEE Transactions on Automation Science and Engineering, 2020
This paper explores adaptive algorithms employed during gait cycles, which were later integrated into the robotic prosthetic device P104.
Recommended citation: Xu, D., Yang, Y., Yang, R., & Wang, Q. (2020). Maximum dorsiflexion detection based on an on-board adaptive algorithm for transtibial amputees with robotic prostheses. IEEE Transactions on Automation Science and Engineering, 18(2), 437-447.
Download Paper
Projection-based visual feedback of classification outputs improves efficacy of prosthesis training for myoelectric pattern recognition
Published in American Academy of Orthotists and Prosthetists, 2023
The AAOP Annual Meeting and Scientific Symposium is the preeminent yearly forum for O&P professionals to gather with colleagues to explore and discuss the current and future prospects for the O&P profession. This paper presents preliminary findings demonstrating the potential of 3D visual feedback for enhancing pattern recognition in prosthetic control. Our initial studies reveal significant improvements in completion rates compared to traditional training methods. Future research will conduct more extensive experiments, comparing a comprehensive range of metrics across both our proposed solution and existing methods of prosthesis control.
Recommended citation: L´evay, G. M., Yang, R., Hunt, C. L., Hodgson, M. C., Kaliki, R. R., Thakor, N. V. (2023). Projection-based visual feedback of classification outputs improves efficacy of prosthesis training for myoelectric pattern recognition. Paper presented at the American Academy of Orthotists and Prosthetists Annual Meeting.
Download Paper | Download Slides
Patter Seperability Visual Feedback To Improve Pattern Recogntion Decoding Performance
Published in Myoelectric Control Symposium, 2024
MEC is a triennial symposium of special interest to those who work in the fields of upper limb prosthetics and myoelectric control (including upper and lower limb), recognized worldwide for its pioneering work in myoelectric controls. This paper reports significant improvements in subjects using 3D feedback for pattern recognition over traditional training, measured by completion rate, trial overshoot, efficiency, and throughput. Retention tests 30 days post-trial suggest potential long-term benefits of 3D feedback. Future studies will include recalibration frequency, training time, and amputee trials, with findings to be published in a journal extension.
Recommended citation: Levay, G. M., Yang, R., Hunt, C. L., Hodgson, M. C., Kaliki, R. R., & Thakor, N. V. (2024). PATTERN SEPARABILITY VISUAL FEEDBACK TO IMPROVE PATTERN RECOGNITION DECODING PERFORMANCE. Myoelectric Controls Symposium . https://doi.org/10.57922/mec.2515
Download Paper
teaching
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.
Myoelectric Control 3D Visualization Project
Advisor: Nitish V. Thakor, Johns Hopkins University and Infinite Biomedical Technologies, 2021
The project enhances myoelectric prosthesis control with a novel 3D visual feedback system called Reviewer, which allows users to see their EMG signals in real-time. This helps them understand how their muscle activity affects control. In a 10-session study with 12 participants, the Reviewer outperformed standard virtual feedback, improving accuracy and adaptability. By offering intuitive visual feedback, it addresses issues like the steep learning curve and misclassifications, enabling users to generate clearer, more consistent signals, ultimately enhancing prosthetic control.