Research Domain

Existing research highlights the importance of personalized instruction, multi-sensory learning support, and assistive technologies for learners with special needs. Voice interfaces can reduce cognitive load for some learners, while haptic feedback supports guided practice and motor learning.

AI-driven adaptation can tailor difficulty and pacing, and computer vision tools can connect learning content to real-world objects and contexts. However, many systems lack an integrated approach that balances usability, affordability, and accessible design.

• Limited integration of voice guidance, adaptive learning, and IoT feedback within a single learning hub.
• Insufficient accessibility-first design (keyboard support, contrast, readable layouts) in many prototypes.
• Few solutions provide both classroom-friendly evaluation views and student-friendly interaction modes.
• Gaps in measurable progress tracking aligned with specific learning activities and assistive tools.

How can we design and implement a fast, accessible, and unified learning platform that supports students with special needs using voice interaction, personalized adaptation, and IoT-based feedback — while remaining practical for academic evaluation and real-world educational use?

• Design a voice-based learning assistant to guide learners through activities and navigation.
• Develop an IoT smart glove to deliver haptic feedback via BLE for guided learning tasks.
• Implement an adaptive learning module to personalize content based on performance and interaction.
• Create an object recognition learning tool that links real-world items to guided educational prompts.
• Ensure WCAG-friendly UI with high contrast, readable typography, and keyboard-friendly navigation.

The project follows an iterative design and evaluation cycle: requirements gathering, prototyping, implementation, integration, and user-centered testing. Usability and accessibility are considered early, with validation through measurable learning outcomes and interaction feedback.

• Requirement analysis: stakeholder needs (lecturers, students, parents/educators).
• Design: accessible UI, consistent navigation, and component-based feature architecture.
• Implementation: web application + IoT glove integration and AI services.
• Evaluation: task completion, feedback quality, and content adaptation effectiveness.

The following technologies are proposed/used for implementation. Replace or refine according to your final stack.

• AI: personalization logic, progress modeling, and analytics.
• Computer Vision: object recognition for learning activities.
• IoT + BLE: ESP32-based smart glove with haptic feedback.
• Frontend: React (optional) or modern HTML/CSS/JS for a lightweight UI.
• Backend: Flask (Python) or Node.js for APIs and model services.
• Hardware: ESP32, sensors/actuators for vibration feedback, BLE communication.