國立虎尾科技大學 |

Simulating Future Actions in Speech Therapy Sessions: Development of a Dataset and Predictive Model /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Simulating Future Actions in Speech Therapy Sessions: Development of a Dataset and Predictive Model // Antarpreet Kaur.
作者:	Kaur, Antarpreet,
面頁冊數:	1 electronic resource (47 pages)
附註:	Source: Masters Abstracts International, Volume: 85-12.
Contained By:	Masters Abstracts International85-12.
標題:	Robotics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31299616
ISBN:	9798382831800

Simulating Future Actions in Speech Therapy Sessions: Development of a Dataset and Predictive Model /
Kaur, Antarpreet,

Simulating Future Actions in Speech Therapy Sessions: Development of a Dataset and Predictive Model /Antarpreet Kaur. - 1 electronic resource (47 pages)

Source: Masters Abstracts International, Volume: 85-12.

The increasing demand for speech-language pathologists (SLPs) against their limited availability poses significant challenges in delivering effective pediatric speech therapy. In response, the National AI Institute for Exceptional Education has launched an initiative to enhance the efficiency of speech therapy services through an AI-driven framework that includes components like the AI Orchestrator, AI Screener, and a Simulator to automate and enhance therapeutic decision-making.This thesis focuses on developing a simulator that uses a limited dataset derived from SOAP (Subjective, Objective, Assessment, Plan) notes, which are rich in narrative but lack quantifiable metrics. This necessitated innovative processing to convert these descriptions into structured data suitable for AI analysis, using the BART (Bidirectional and Auto- Regressive Transformers) model. Known for its effectiveness in handling complex textual data, BART is ideal for simulating potential future therapy sessions based on past notes.A conceptual human-in-the-loop system is proposed to refine the AI's outputs with ex- pert SLP input, enhancing its practical utility and providing predictive insights that support more personalized therapy interventions.This thesis demonstrates a novel approach to leveraging AI in healthcare, showcasing the potential of data-driven technologies to transform therapeutic practices and laying groundwork for future research in AI-enhanced speech therapy.

English

ISBN: 9798382831800Subjects--Topical Terms:

561941
Robotics.
Subjects--Index Terms:

Speech-language pathologists

Simulating Future Actions in Speech Therapy Sessions: Development of a Dataset and Predictive Model /
LDR:02903nam a22004213i 4500 001 1157803
005 20250603111418.5
006 m o d
007 cr|nu||||||||
008 250804s2024 miu||||||m |||||||eng d
020 $a 9798382831800
035 $a (MiAaPQD)AAI31299616
035 $a AAI31299616
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Kaur, Antarpreet, $e author. $3 1484077
245 1 0 $a Simulating Future Actions in Speech Therapy Sessions: Development of a Dataset and Predictive Model / $c Antarpreet Kaur.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (47 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 85-12.
500 $a Advisors: Zou, Shaofeng Committee members: Guan, Zhangyu.
502 $b M.S. $c State University of New York at Buffalo $d 2024.
520 $a The increasing demand for speech-language pathologists (SLPs) against their limited availability poses significant challenges in delivering effective pediatric speech therapy. In response, the National AI Institute for Exceptional Education has launched an initiative to enhance the efficiency of speech therapy services through an AI-driven framework that includes components like the AI Orchestrator, AI Screener, and a Simulator to automate and enhance therapeutic decision-making.This thesis focuses on developing a simulator that uses a limited dataset derived from SOAP (Subjective, Objective, Assessment, Plan) notes, which are rich in narrative but lack quantifiable metrics. This necessitated innovative processing to convert these descriptions into structured data suitable for AI analysis, using the BART (Bidirectional and Auto- Regressive Transformers) model. Known for its effectiveness in handling complex textual data, BART is ideal for simulating potential future therapy sessions based on past notes.A conceptual human-in-the-loop system is proposed to refine the AI's outputs with ex- pert SLP input, enhancing its practical utility and providing predictive insights that support more personalized therapy interventions.This thesis demonstrates a novel approach to leveraging AI in healthcare, showcasing the potential of data-driven technologies to transform therapeutic practices and laying groundwork for future research in AI-enhanced speech therapy.
546 $a English
590 $a School code: 0656
650 4 $a Robotics. $3 561941
650 4 $a Speech therapy. $3 715798
653 $a Speech-language pathologists
653 $a Datasets
653 $a Human-in-the-loop system
653 $a Future therapy
690 $a 0800
690 $a 0460
690 $a 0771
710 2 $a State University of New York at Buffalo. $b Engineering Science - Robotics program. $3 1465095
720 1 $a Zou, Shaofeng $e degree supervisor.
773 0 $t Masters Abstracts International $g 85-12.
790 $a 0656
791 $a M.S.
792 $a 2024
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31299616