Students in higher education often encounter challenges in sensory processing that can affect their ability to fully engage in lectures, tutorials, and collaborative learning environments. Sensory overload (e.g., from noise, crowded rooms, or prolonged concentration) or under-stimulation (e.g., lack of movement, low arousal) can hinder focus, participation, and retention of information. Smartwatches provide a unique opportunity to collect continuous, unobtrusive physiological and behavioural data (e.g., heart rate, accelerometer data, skin conductance, sleep quality, and activity levels) that can act as proxies for sensory regulation and cognitive load.
By leveraging these data streams, it may be possible to identify patterns of sensory stress or disengagement in real time, and deliver personalised interventions to improve students’ learning experiences.
Aim:
To explore how smartwatch data can be used to detect sensory processing challenges and provide adaptive support that enhances inclusive learning in lecture halls, campus life, and group settings.
Objectives:
- Data Collection & Processing
- Collect smartwatch data from a sample of student participants (e.g., heart rate variability, accelerometer, skin temperature, galvanic skin response if available).
- Correlate physiological signals with self-reported sensory experiences (e.g., overstimulation, distraction, fatigue).
- Modelling Sensory States
- Use AI/ML techniques (e.g., clustering, supervised learning) to identify patterns indicating sensory overload, under-stimulation, or optimal learning states.
- Explore multi-modal analysis by combining physiological signals with contextual factors (e.g., lecture time, activity type).
- Design of Supportive Feedback
- Prototype an intervention system (e.g., gentle haptic feedback, break reminders, grounding strategies) delivered via the smartwatch or companion mobile app.
- Evaluate potential to enhance focus, engagement, and well-being.
- Evaluation
- Conduct user studies with learners to assess system accuracy, usability, and impact on engagement.
- Analyse ethical considerations around privacy, consent, and data ownership.
Methodology:
- Collect smartwatch sensor data during real-world academic activities (lectures, group study, campus events).
- Use surveys/experience sampling to annotate sensory experiences.
- Apply AI/ML techniques to train predictive models of sensory processing states.
- Develop and test a prototype feedback system.
Expected Outcomes:
- A data-driven model linking smartwatch biometrics to sensory states in learning contexts.
- Insights into how sensory processing affects inclusive learning and engagement.
- A prototype tool that demonstrates how wearable technology can provide real-time support.
- Ethical framework for handling personal physiological data in education.
Learning Context & Inclusion:
This project directly supports inclusive education by addressing challenges such as:
- Sensory overload in crowded lecture halls or noisy group work settings.
- Fatigue and low attention during long classes.
- Difficulty regulating arousal in different learning environments.
Potential supports include adaptive prompts, personalised breaks, or sensory regulation reminders that help students maintain focus, participate more fully, and reduce stress.
Â
Title: Supporting Sensory Processing in Inclusive Learning Environments through Headphone Data
Background:
Many learners rely on headphones during study, lectures, or group activities to manage their sensory environments. Headphones, particularly modern smart and noise-cancelling models, can provide rich streams of data such as ambient noise levels, user volume preferences, listening patterns, microphone input, and contextual metadata (e.g., location of use, duration of listening). These data can be used to infer sensory load, distractions, or overexposure to noise.
For students with sensory sensitivities, environmental noise can significantly hinder concentration, engagement, and collaboration. By leveraging headphone data, it may be possible to monitor sensory environments, detect stress-inducing conditions, and offer adaptive interventions to promote inclusive and effective learning.
Aim:
To investigate how data collected from headphones can be used to understand and support sensory processing in students, enhancing focus, participation, and learning outcomes.
Objectives:
- Data Capture & Processing
- Collect headphone-based data: noise exposure (dB levels), volume levels, duration of listening sessions, soundscape classification (e.g., speech, music, traffic, silence).
- Link headphone data with contextual learning situations (lectures, self-study, campus movement).
- Model Sensory Stress & Engagement
- Explore relationships between environmental audio conditions and reported sensory experiences (e.g., distraction, stress, fatigue).
- Develop AI/ML models to predict when a learner may be experiencing sensory overload or disengagement based on headphone/environmental data.
- Adaptive Support Design
- Prototype headphone-based interventions (e.g., automatic adjustment of noise cancellation, recommending volume breaks, suggesting a quieter location, or playing focus-supporting soundscapes).
- Develop a companion mobile interface for personalised recommendations and feedback.
- Evaluation
- User testing in real-world academic environments (lecture halls, libraries, group study sessions).
- Assess improvements in focus, comfort, and engagement.
- Consider privacy, data ownership, and ethical implications of collecting ambient and usage data.
Methodology:
- Use headphones equipped with noise-level sensing and usage logging (or external SDKs/APIs from headphone manufacturers).
- Collect parallel self-reported sensory data using ecological momentary assessments (short questionnaires during study sessions).
- Apply supervised and unsupervised ML methods (e.g., classification of overload vs. comfort states, clustering of soundscapes).
- Prototype an adaptive support system that responds to detected conditions.
Expected Outcomes:
- Models linking headphone/environmental audio data with sensory processing states.
- A prototype system that provides real-time, headphone-based sensory regulation support.
- Evidence of how managing auditory environments can enhance inclusive participation in academic settings.
- Ethical guidelines for collecting and using headphone-derived data in education.
Learning Context & Inclusion:
This project addresses common sensory challenges such as:
- Noise sensitivity in large lecture halls or crowded study spaces.
- Overexposure to sound leading to fatigue and reduced attention.
- Need for personalised sound environments to maintain focus during study.
Potential supports include adaptive noise cancellation, personalised focus soundscapes, reminders for safe listening, and environment-aware suggestions (e.g., prompting a student to move to a quieter space).