KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 5 of 5

Some of the metrics are blocked by your
consent settings
Ontology-Based Learning Assistant Chatbot: Enhancing Accurate and Explanatory Knowledge Provision in Myanmar’s Primary Education
(2025-01-01)
Myo, Su Wai
;
Anutariya, Chutiporn
Large language models (LLMs) and LLM-based generative AI tools have demonstrated considerable effectiveness in educational settings by challenging traditional classroom dynamics. They generate answers based on knowledge acquired during pre-training, making the answer construction process and the sources of information ambiguous. This uncertainty in responses complicates the assurance of appropriateness and reliability for young students, particularly in primary education. This paper, therefore, proposes an ontology-based learning assistant chatbot designed to address students’ inquiries using Subject Ontology (SO), which was developed for primary school teachers to model and verify subject knowledge. The chatbot aims to alleviate common academic challenges in Myanmar’s primary education. From the evaluation, teachers valued the chatbot’s transparency and reliability, as they could maintain direct control over the underlying knowledge base, enabling them to efficiently verify the accuracy of the chatbot’s responses and their sources.
Some of the metrics are blocked by your
consent settings
Evaluation and Optimization of LLM and RAG Components for a Post-Operative Oral Surgery Consultation Chatbot
(2025-01-01)
Lochanachit, Sirasit
;
Bunlaue, Patcharamon
;
Kaewmuneechoke, Chanapat
;
Wilairatanaporn, Nopasorn
;
Trachoo, Vorapat
The increasing demand for dental services highlights the need for efficient post-operative oral surgery consultations. Many patients experience anxiety due to limited knowledge of oral care and treatment. This study introduces a chatbot prototype integrating Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to provide accurate, context-aware responses. The research evaluates various LLMs, embedding models, and chunking techniques to enhance chatbot performance. The multilingual-e5-large embedding model excelled in retrieval tasks due to its multilingual training, instruction tuning, and contrastive pre-training, ensuring high retrieval precision. The Hybrid Chunking method was selected for its ability to segment text contextually, combining Markdown-based, token-based, and semantic segmentation for optimal chunk relevance. The Llama3.3 (70B) model was chosen for its superior fluency, relevance, and ability to handle complex dependencies. The results demonstrate that combining the multilingual-e5-large embedding model, Hybrid Chunking technique, and Llama3.3 (70B) model improves retrieval precision, response accuracy, and relevance, enhancing patient care and operational effectiveness of dental staffs.
Some of the metrics are blocked by your
consent settings
The Effect of Using the Chatbot to Improve Digital Literacy Skill of Thai Elderly
(2024-01-01)
Sriwisathiyakun, Kanyarat
This research aims to demonstrate the learning success and contentment of elderly people in Thailand using a chatbot innovation for improving digital literacy. Three parts of the research were carried out: Phase 1 of the research focused on developing the chatbot and any relevant educational digital media; Phase 2 engaged in pre-experimental by experts’ validation; and Phase 3 involved an experiment where the chatbot was deployed with elderly people. Samples were collected from 33 elderly people. The information was gathered through expert interviews, pretests, and posttests on chatbot usage, and satisfaction surveys. The data was then analyzed using the dependent t-test, percentage, mean, standard deviation, and content analysis. Results showed that our Senior See Net chatbot was simple to use and navigate, with an appropriate artistic appearance. Findings demonstrate that this chatbot was simple to use and access, had an appropriate creative composition, and was made up of sufficiently thorough media and content on digital literacy. Furthermore, the statistical analysis revealed that after using the chatbot, the elderly’s understanding of digital literacy improved statistically significant at the 0.05 level. Furthermore, their overall satisfaction was rated high.
Some of the metrics are blocked by your
consent settings
Enhancing digital literacy with an intelligent conversational agent for senior citizens in Thailand
(2022-06-01)
Sriwisathiyakun, Kanyarat
;
Dhamanitayakul, Chawaporn
Intelligent conversational agents have been implemented as virtual assistants in mobile applications to facilitate, engage, and interact with users for optimal learning experiences. With 24/7 availability, providing instant and consistent responses, chatbots, as a type of intelligent conversational agent, will help benefit the learning communication, makes the entire learning experience more engaging for the learners. They have also been successfully used by the elderly to encourage behavioral change for their intended purpose. This study investigated baseline data on the use of digital platforms of senior citizens in Bangkok Metropolitan and the six regions of Thailand and developed a chatbot from the derived data. The chatbot contained learning media and service function, served as a platform to enhance digital literacy for the senior citizens in Thailand. The study was conducted in 3 phases, the baseline survey on the use of digital platforms of the senior citizens in Thailand, the development of the chatbot and learning media, and the pre-experimental expert validation. The samples were 422 senior citizens. The data were collected by questionnaires, focused group discussion, and interviews with experts, and analyzed by percentage, mean, standard deviation, and content analysis. Results were incorporated in the design and development of the chatbot innovation following the software development life cycle (SDLC) framework. Expert feedback revealed that this chatbot innovation was easy to access, convenient to request for operations, artistically appealing, and comprehensive in content and functionality for enhancing digital literacy skills, which are to access, analyze, evaluate, participate, and act. In the next research sequence, this innovation will subsequently be experimented with more senior citizens to prepare and improve their digital competence to consequently equip them with the necessary capacities to keep up with Thailand’s transition towards a full-blown aging society.
Some of the metrics are blocked by your
consent settings
Intelligent Triage Assistant
(2021-01-01)
Duangdee, Wannarat
;
Lalitrojwong, Pattarachai
The triage of outpatient department is a vital process to screen patients. In addition, assessing the emergency case by the outpatient department can determine the quality of service. In emergency case, the patients have to be treated as soon as they arrive. If the triage of this case is delayed and the patients have major symptoms, it may develop serious complications leading to the cause of death or disability. Accordingly, assessing and making triage decisions, and assigning the level of patient acuity require being accurate, rapid and trustworthy in order to take care and treat them in time. Due to the fact that nowadays there is only one nurse on duty for the triage, he or she cannot well handle a bunch of patients arriving for treatment. According to Hospital and Healthcare Standards, 4th edition, the Healthcare Accreditation Institute (Public Organization) allows the use of technology to improve hospital services. This research aims to develop an intelligent triage assistant. To help the process by making triage decisions for all the patients promptly, assigning an acuity level and screening and assigning the patients to an area based on acuity. If unsuitable results happen, the triage nurse can be on duty promptly. Our intelligent triage assistant has been implemented using Visual Studio C#, Microsoft SQL Server for the database, and QnA Maker for the knowledge base. The application has been tested by outpatient nurses. They are quite satisfied with the primary outcome and recommend further improvements for future work.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results