WPI — BASHLab research

In-ear multimodal sensing device

Medical device R&D · June 2025 — Present · Patent filing in progress

Engineering at the frontier

At Worcester Polytechnic Institute, I'm leading the design and development of a wearable medical earbud capable of tracking vital signs with clinical-grade accuracy — all from a discreet, comfortable device worn behind the ear.

The device targets the sensitive region beneath the ear near the jaw — a site identified in recent biomedical research as an exceptionally rich source of physiological data. From this single contact point, the earbud monitors heart rate, respiratory patterns, vocal activity, and motion simultaneously.

The mechanical design, developed in AutoCAD, prioritizes ergonomics and comfort: the housing must be lightweight, anatomically contoured, and robust enough for continuous wear. The embedded firmware, written in C++, processes sensor data in real time and manages power efficiency for extended battery life.

Inside the platform

LYNX pairs an in-ear and an out-ear microphone with a 9-DOF IMU in a 3D-printed shell — all off-the-shelf parts, open-source firmware, sub-millisecond synchronization between the audio and motion streams. The out-ear microphone exists to be thrown away: it captures the same ambient noise as the in-ear channel, and an adaptive NLMS filter subtracts it, leaving the physiological signal — breathing, speech, chewing — clean enough for downstream analysis.

LYNX system design — circuit diagram of the dual microphones and IMU wired to a Raspberry Pi, and an exploded view of the 3D-printed earbud shell showing mic and IMU placement — System design — dual mics + 9-DOF IMU in a 3D-printed shell, no custom PCB required

Diagram of signal enhancement via reference microphone — outer mic noise and raw in-ear signal combined through an adaptive NLMS filter into a clean filtered signal — The signal path — the outer mic is a reference channel; NLMS subtracts the shared noise

Recording and motion test results — stereo microphone RMS aligned with accelerometer, gyroscope, and magnetometer traces during head tilts, plus raw versus NLMS-filtered signal plots — Test results — IMU head-tilt events align with in-ear audio peaks across a 10-minute session

Key contributions

Led the design and development of a wearable medical earbud capable of tracking vital signs including heart rate, respiratory patterns, vocal activity, and motion.
Identified and targeted the sub-auricular jaw region as the sensing site based on recent physiological research showing its superior data density compared to conventional locations.
Collaborated with a WPI professor to lead the project from initial concept through functional prototype — managing both the mechanical design (AutoCAD) and embedded programming (C++).
Designed the device housing for minimal weight, anatomical comfort, and durability under daily-wear conditions.
Patent filing in progress for the final design; co-authoring a research paper for submission to the MIT Undergraduate Research Technology Conference (URTC).

This project sits at the intersection of mechanical engineering, biomedical sensing, and embedded systems — disciplines I'm merging for the first time at this scale. The goal is a device that doesn't just measure vitals but does so with enough accuracy and comfort to be used continuously in real-world conditions.

Patent filing in progress