Edge-IoT and MLLMs for Education and Scene Understanding: Assisting Vision and Hearing-Impaired Individuals
Bibliographic record
Abstract
The rapid advancement of IoT and edge computing technologies has opened new horizons for creating assistive solutions tailored to individuals with sensory impairments, particularly those with hearing and vision disabilities. This article presents a novel edge-IoT-based framework that integrates multimodal large language models (MLLMs), multi-object tracking, and scene understanding to develop real-time, responsive assistance for impaired individuals. Our proposed system is designed to enhance accessibility and quality of life by providing educational tools and entertainment options that cater specifically to the needs of this community. The proposed solution leverages the computational power of edge devices to process data locally, ensuring low latency and high responsiveness, which are critical for real-time applications. Furthermore, we explore the potential of generative AI models in improving autonomy, with a particular focus on real-time transcription services for the hearing impaired and scene description services for the visually impaired. This work demonstrates the feasibility and effectiveness of using edge-IoT technologies combined with advanced AI techniques to create inclusive environments that empower disabled individuals, ensuring that technological advancements are leveraged to foster accessibility and independence.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".