EmotiBit at CSUN 2026: Using Biometrics for Better Support

EmotiBit at CSUN 2026: Using Biometrics for Better Support

By Chelsea Anne Barlaan on July 16, 2026

At the 2026 CSUN Assistive Technology Conference, EmotiBit founder Sean Montgomery shared how open-source biometric tools are being used across accessibility-focused research and design. Across the presentation, examples ranged from emotional self-awareness and communication to rehabilitation and aging, highlighting projects that use physiological data not simply to measure the body, but to create more responsive, person-centered experiences.

Sean and EmotiBit team member Halley smile for a selfie beneath a large "CSUN Assistive Technology Conference" banner in a busy conference hallway.
Sean and EmotiBit team member Halley at the 2026 CSUN Assistive Technology Conference.

The Possibilities are Endless!

Many wearable devices collect physiological information, but users, researchers, and designers may have limited access to the raw data or little flexibility in how it can be used. To address this gap, EmotiBit was created as a lower-cost, open-source wearable that gives users direct access to physiological data and allows them to adapt it to their needs. By making biometric data more customizable and accessible, EmotiBit provides support that may not be feasible with other consumer wearables or costly research-grade systems.

Image of the EmotiBit being held between Sean's fingers.
Sean holds the EmotiBit wearable biosensor, showing its compact open-source hardware design.
Front and back image of the hardware board and sensors, including: body temperature sensor, EDA sensor, PPG sensor, programmable input button, 9-axis IMU, input/output pins compatible with the Adafruit Feather, strap attachments, and an SD card slot.
Front and back image of the hardware board and sensors, including: body temperature sensor, EDA sensor, PPG sensor, programmable input button, 9-axis IMU, input/output pins compatible with the Adafruit Feather, strap attachments, and an SD card slot.

Making It Personal

To highlight EmotiBit’s features, Sean discussed a MIT Media Lab study by Scheirer, Picard, and Cantrell, titled Personalized Animations for Affective Feedback: Generative AI Helps to Visualize Skin Conductance. The researchers explored how personalized biofeedback could help autistic adults better engage with their physiological states. Live electrodermal activity (EDA) data collected through EmotiBit was translated into interactive visual animations based on each participant’s interests. The experience was designed to make stress-related feedback feel more familiar and engaging. This project shows how accessibility tools can become more effective when people help shape how their internal experiences are represented.

Example of a visual display oriented to a participant’s special interest: here, a Pac Man game. It was designed by a participant to communicate changes in stress level and help with bodily awareness. Image copyright belongs to publication authors Scheirer, Picard, and Cantrell.
Example of a visual display oriented to a participant's special interest: here, a Pac Man game. It was designed by a participant to communicate changes in stress level and help with bodily awareness. Image copyright belongs to publication authors Scheirer, Picard, and Cantrell.

From Signals to Support

Researchers have applied EmotiBit to many exploratory, accessibility-based projects beyond personalized feedback. For example, EmotiBit has been used in research exploring wearable approaches to detect signs of sleep apnea in youth with Down syndrome and portable VR environments made to support anxiety and emotional regulation for neurodivergent users. Additionally, other projects presented focused on communication and physical rehabilitation, including a study using EmotiBit as part of a multimodal physiological dataset for affect recognition in deaf children and augmented-reality systems that guide users through rehabilitation exercises. Together, these examples show how open-source biometric tools can support more responsive systems for care, communication, movement, and recovery.

Presentation slide titled "Applications in Rehabilitation" showing EmotiBit's use in an augmented-reality rehabilitation study. The slide includes text describing the concern of hospital inactivity, the goal of using AR technology for exercise treatment, and EmotiBit's role as an open-source wearable sensor for movement and physiological data. Two images show a user performing leg exercises with an EmotiBit on the ankle and an upper-limb rehab demo using AR guidance.
CSUN presentation slide highlighting EmotiBit's role in rehabilitation research, where augmented reality and wearable sensors were used to support guided exercise and movement-based feedback.

So, What's Next for Us—and You?

Ultimately, the projects shared at CSUN reflect a larger idea behind EmotiBit: accessibility technology should be adaptable, collaborative, and built around the people who use it. In short, open-source biometric sensing gives researchers, makers, clinicians, and communities more freedom to explore meaningful questions about the body and everyday experiences. As these tools continue to evolve, they can help make assistive technology better tailored to each user’s needs.

So, how will you create new possibilities for accessible biometric technology using EmotiBit?

Close-up photo of an EmotiBit device strapped to a person's upper arm with a black band while the person adjusts the strap.
EmotiBit worn on the upper arm, showing its compact wearable design for biometric sensing.

Project References:

Choudhary, K., & Prajapati, G. L. (2026). Affect recognition in deaf children using physiological signal measurements. SN Computer Science, 7, Article 132. https://doi.org/10.1007/s42979-025-04711-w

Engelen, S. N. v. (2023). Evaluation of Physiological Signals in Wearable Assistive Technology to Detect Obstructive Sleep Apnea in Youth with Down Syndrome. ProQuest Dissertations and Theses. https://unr.idm.oclc.org/login?url=https://www.proquest.com/dissertations-theses/evaluation-physiological-signals-wearable/docview/2866082506/se-

Rizzi, J., D’Antona, A., Proto, A., Piva, G., Lamberti, N., Bonfè, M., & Farsoni, S. (2023). A framework integrating augmented reality and wearable sensors for the autonomous execution of rehabilitation exercises. Electronics, 12(24), 4958. https://doi.org/10.3390/electronics12244958

Scheirer, J., Picard, R., & Cantrell, A. (2025). Personalized animations for affective feedback: Generative AI helps to visualize skin conductance. ACM Digital Library, 146–151. https://doi.org/10.1145/3746270.3760237

Skiers, K., Pai, Y. S., Nakagawa, M., Minamizawa, K., & Barbareschi, G. (2025). Portable silent room: Exploring VR design for anxiety and emotion regulation for neurodivergent women and non-binary individuals. arXiv. https://doi.org/10.48550/arXiv.2508.18591

Skiers, K., Peng, D., Barbareschi, G., Pai, Y. S., & Minamizawa, K. (2024). NatureBlendVR: Hybrid space interactive experience for emotional regulation and cognition improvement. SIGGRAPH Asia 2024 XR, Article 12, 1–2. https://doi.org/10.1145/3681759.3688929

Tags: