Ambient intelligence for healthcare
Abstract/Contents
- Abstract
- Advances in machine learning and contactless sensors have given rise to ambient intelligence--physical spaces that are sensitive and responsive to the presence of humans. In this dissertation, I will discuss how ambient intelligence could improve our understanding of the metaphorically dark, unobserved spaces of healthcare. In hospitals, I will describe how computer vision can improve patient safety in intensive care units and streamline surgical workflows in operating rooms. Specifically, I describe my technical work on human pose estimation, person re-identification, and pedestrian detection. I then discuss how to apply and evaluate these methods for monitoring hospital hand hygiene. In the operating room, I review computer vision methods for inventorying small surgical objects during operative procedures. In daily living spaces outside the hospital, I will describe how speech recognition and natural language processing can identify depressive mental health symptoms and streamline psychotherapy research. Using ambient microphones, I propose several technical methods for recognizing human emotions and transcribing speech from audio recordings. These methods are then applied to de-identified recordings of real therapy sessions from clinics. Similar to other technologies in healthcare, ambient intelligence must overcome challenges such as rigorous clinical validation and appropriate data privacy. I discuss the tradeoff between privacy and algorithm performance, and propose a method for making inferences directly from encrypted data.
Description
| Type of resource | text |
|---|---|
| Form | electronic resource; remote; computer; online resource |
| Extent | 1 online resource. |
| Place | California |
| Place | [Stanford, California] |
| Publisher | [Stanford University] |
| Copyright date | 2020; ©2020 |
| Publication date | 2020; 2020 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Author | Haque, Albert |
|---|---|
| Degree supervisor | Li, Fei Fei, 1976- |
| Thesis advisor | Li, Fei Fei, 1976- |
| Thesis advisor | Jurafsky, Dan, 1962- |
| Thesis advisor | Shah, Nigam |
| Degree committee member | Jurafsky, Dan, 1962- |
| Degree committee member | Shah, Nigam |
| Associated with | Stanford University, Computer Science Department |
Subjects
| Genre | Theses |
|---|---|
| Genre | Text |
Bibliographic information
| Statement of responsibility | Albert Haque. |
|---|---|
| Note | Submitted to the Computer Science Department. |
| Thesis | Thesis Ph.D. Stanford University 2020. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2020 by Albert Haque
- License
- This work is licensed under a Creative Commons Attribution 3.0 Unported license (CC BY).
Also listed in
Loading usage metrics...