Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Online Access: | https://doi.org/10.5281/zenodo.18375151 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901877131575296 |
|---|---|
| author | Kanishka Raj, N Harini, Shashank P, Kamaleswari Pandurangan |
| author_facet | Kanishka Raj, N Harini, Shashank P, Kamaleswari Pandurangan |
| contents | <div> <div>Healthcare assistance for paralyzed and physically challenged individuals requires reliable and continuous monitor- ing, as such patients sometimes lack in expressing the distress they are going through and even a minor inconvenience that their inner self might be feeling. Traditional patient monitoring systems depend largely on manual observation, which may lead to delayed responses in critical situations. This project presents an AI-powered virtual assistant designed to improve communication between patients and caretakers using computer vision, deep learning, and speech processing techniques which not only re- duces the need to rely on conventional systems but also automate the process of monitoring the patients in need. The system captures real-time facial expressions, hand gestures, and voice inputs from patients through a webcam and microphone. Facial emotions are identified using a Convolutional Neural Network (CNN), hand gestures are recognized using MediaPipe-based landmark detection combined with a deep learning classifier, and speech input is converted into text using speech-to-text techniques. The processed information is displayed on a webbased dashboard provided for the caretaker, developed using the Flask framework. Initial testing indicates that the system is capable of functioning in real-time under controlled conditions</div> </div> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_18375151 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | AI Powered Virtual Assistant for Alerting Home / Hospital-Disabled / Paralytic Patients Kanishka Raj, N Harini, Shashank P, Kamaleswari Pandurangan <div> <div>Healthcare assistance for paralyzed and physically challenged individuals requires reliable and continuous monitor- ing, as such patients sometimes lack in expressing the distress they are going through and even a minor inconvenience that their inner self might be feeling. Traditional patient monitoring systems depend largely on manual observation, which may lead to delayed responses in critical situations. This project presents an AI-powered virtual assistant designed to improve communication between patients and caretakers using computer vision, deep learning, and speech processing techniques which not only re- duces the need to rely on conventional systems but also automate the process of monitoring the patients in need. The system captures real-time facial expressions, hand gestures, and voice inputs from patients through a webcam and microphone. Facial emotions are identified using a Convolutional Neural Network (CNN), hand gestures are recognized using MediaPipe-based landmark detection combined with a deep learning classifier, and speech input is converted into text using speech-to-text techniques. The processed information is displayed on a webbased dashboard provided for the caretaker, developed using the Flask framework. Initial testing indicates that the system is capable of functioning in real-time under controlled conditions</div> </div> |
| title | AI Powered Virtual Assistant for Alerting Home / Hospital-Disabled / Paralytic Patients |
| url | https://doi.org/10.5281/zenodo.18375151 |