I2I - From illusion to illumination: A neoteric deep learning model for recognizing medical situation actions using depth sensors data
Saima Sultana, Eraj Tanweer, Muhammad Mansoor Alam, Sadia Nazim, Mukesh Prasad, Jawahir Che Mustapha, Mazliham Mohd Su’ud · 2026
Read I2I - From illusion to illumination: A neoteric deep learning model for recognizing medical situation actions using depth sensors data by Saima Sultana, Eraj Tanweer, Muhammad Mansoor Alam, Sadia Nazim, Mukesh Prasad, Jawahir Che Mustapha, Mazliham Mohd Su’ud (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0337646.txt.
Description
Saima Sultana and colleagues built a computer model that recognises medical actions from depth sensor data, even when the room is poorly lit. Ordinary cameras struggle in dim light, and a robot that misreads a medical action could cause real harm. Their model, called I2I, works from depth readings rather than colour images, pulling out the most telling features before classifying what a person is doing.
Tested on a large public dataset of recorded actions, the model reached just over ninety-one percent accuracy and beat earlier methods the authors compared it against. The work matters for hospital and care robots that must keep working through the night or in dark wards. The authors frame depth sensing as a way to keep recognition reliable when lighting cannot be trusted.
Catalog record
| CREATOR | Saima Sultana, Eraj Tanweer, Muhammad Mansoor Alam, Sadia Nazim, Mukesh Prasad, Jawahir Che Mustapha, Mazliham Mohd Su’ud |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42762 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |