Hey! I'm Sarang.
I'm a student at Stanford University, pursuing a B.S. in Computer Science. With a passion for wearable technology, I have strong technical skills in the fields of embedded systems, artificial intelligence, and software development.
Contact me!
Projects
IVY: An Intelligent Vision System for the Visually Impaired
Built an eyeglasses device consisting of automated mapping and navigation algorithms, object detection model and object avoidance algorithms, an audio infrastructure and smartphone app, and a GPT-powered guided user interaction system to provide navigational and mobility assistance for individuals with visual impairment.
View Project
Detection and Intervention of FoG Events in Parkinson’s Disease Patients
Designed an AI-based user-friendly wearable device for real-time detection and active intervention of Freezing of Gait (FoG) events in Parkinson's disease patients. The device delivers cueing and mobility stimulation interventions, utilizing soft vibrations to support normal gait and strong, directed vibrations to assist in overcoming detected FoG episodes.
View Project
Method for Determining Recirculation Mode in Vehicles
Invented and self-patented a sensor-less method to regulate air quality in vehicles, utilizing camera-based traffic analysis to close the air inlet valve during toxic pollution conditions and reopen it based on high CO2 buildup in the vehicle cabin space.
View Project
iLog 2.0: A Novel Method for Food Nutritional Value Automatic Quantification in Smart Healthcare
Developed NuTRILog, an app for automatically estimating the nutritional value of food to encourage a more healthy, balanced diet. The app utilizes a novel deep learning-based food quantification system composed of an SSD EfficientNetB0 with FPN food classification and localization model and an OpenCV standard-size card edge-detection algorithm.
View Project
Deep Learning-Based Segmentation for Automated Region of Interest Selection of Hyper-Reflective Foci in Optical Coherence Tomography Images Improves
Created an automated region of interest selection methodology to improve deep learning-based segmentation of hyper-reflective foci (HRF) in optical coherence tomography (OCT) images. The methodology implements a patch-based semantic segmentation model using a ResNet34 architecture with Binary Cross-Entropy loss, achieving high IOU scores for identifying HRF biomarkers in OCT data.
View Project
Therms: Thermoregulation Wearable with AI-powered Insights
Therms combines advanced thermoelectric technology with a deep understanding of human physiology to create a wearable system that actively supports thermal homeostasis. By targeting the glabrous skin on the feet, Therms achieves efficient, non-invasive thermoregulation while integrating AI-powered insights to improve health outcomes and performance.
View ProjectSkills
Languages
Embedded Systems
Machine Learning Frameworks
Computer Vision Libraries
Data Science Libraries
awards
- TreeHacks Healthcare Grand Prize Award
Issued by TreeHacks · Feb 2025
- Gold Award at International Olympiad in Artificial Intelligence (IOAI)
Issued by IOAI Hosted in Burgas, Bulgaria · Aug 2024
- Barry M. Goldwater Scholar
Issued by Barry M. Goldwater Foundation · Mar 2024
- Top 40 Regeneron STS Finalist
Issued by Regeneron and Society for Science · Jan 2024
- Regeneron International Science and Engineering Fair: 2nd and 3rd Place Grand Awards
Issued by Regeneron and Society for Science · May 2022, May 2023
- National Gallery for America's Young Inventors Inductee
Issued by National Museum of Education · Feb 2023
- Research Science Institute (RSI) Scholar
Issued by Center for Excellence in Education · Feb 2023
contact
I'm always open to collaborations! Feel free to connect with me through any of my socials.