8 results
Search Results
Now showing 1 - 8 of 8
Item Metadata only AutoGPT Devloop: An Autonomous AI Development Framework for End-to-End Software Generation, Execution, and Self-Repair(2025-01-01) Asavathongkul T.; Sa-Nga-Ngam P.; Kiattisin S.; Asavathongkul T.; Mahidol Universitydecomposition, (ii) a semantic code memory (vector database), (iii) virtualized environment management, and (iv) automated file/version control to achieve autonomy across the software lifecycle. Using a Design Science Research approach, we evaluate AADF on a... on environment setup, boilerplate, and repetitive file operations. We discuss error taxonomies (credentials, heavyweight downloads, concurrency), autonomy-speed trade-offs, and actionable design guidelines for safe deployment in practice.Publication Metadata only Motivational factors for knowledge sharing in co-working spaces(2020-01-31) Suthiluk Lapsomboonkamol; Mongkolchai Wiriyapinit; Pattarasinee Bhattarakosol; Kittichai Rajchamaha; Chulalongkorn University; Mahidol University-working spaces in Thailand. The results of this study identify intrinsic motivational factors such as interests, altruism and job autonomy and extrinsic motivational factors such as career opportunities, networking and rewards through knowledge sharingPublication Metadata only Technology acceptance toward e-government initiative in Royal Thai Navy(2008-08-01) Vichita Vathanophas; Nattapon Krittayaphongphun; Chalalai Klomsiri; Mahidol University, and autonomy. However, training and infrastructure problems are other important factors that can also lead to the acceptance of internet use. Originality/value The study outcome can provide useful information to help the organization improve its capacityItem Metadata only AI-Driven Corrective Feedback for Low-Proficiency Learners: A Study on Writing Skill Development(2025-01-01) Wiboolyasarin W.; Kiti T.; Wiboolyasarin K.; Tiranant P.; Jinowat N.; Wiboolyasarin W.; Mahidol Universityautonomy among low-proficiency learners. These findings contribute valuable insights for educators, researchers, and developers aiming to integrate AI technologies into effective language learning frameworks.Item Metadata only Designing chatbots in language classrooms: an empirical investigation from user learning experience(2024-12-01) Wiboolyasarin W.; Wiboolyasarin K.; Tiranant P.; Boonyakitanont P.; Jinowat N.; Wiboolyasarin W.; Mahidol Universityattitudes toward chatbot design, and semi-structured interviews with teachers, educators, and experts to offer qualitative insights. Our findings reveal five key factors influencing chatbot design: learner autonomy and self-directed learning, contentItem Metadata only Exploring factors affecting communication in three-dimensional virtual worlds for second language learning: development and validation of a scale(2024-01-30) Wiboolyasarin K.; Wiboolyasarin W.; Kamonsawad R.; Tiranant P.; Boonyakitanont P.; Jinowat N.; Wiboolyasarin K.; Mahidol Universityof the EFA revealed four factors that contribute to communication in 3DVWs, namely learner motivation, interaction pattern, language development and learner autonomy. CFA results provided support for the updated model, with statistically significant ChiItem Metadata only Safe Spaces Online: Usability Testing of a Virtual Space to Foster Digital Resilience Among LGBTQI+ Youth(2026-01-01) Samoh N.; Choemprayong S.; Khlaisang J.; Guadamuz T.E.; Samoh N.; Mahidol Universitythe development of key usability components for youth virtual spaces. Findings indicate that the platform was well-received in terms of accessibility, emotional safety, and user autonomy. However, participants recommended enhancements such as adding shortcut menusItem Metadata only Integrating Agentic Artificial Intelligence to Automate International Classification of Diseases, Tenth Revision, Medical Coding(2026-03-01) Akkhawatthanakun K.; Narupiyakul L.; Wongpatikaseree K.; Hnoohom N.; Termritthikun C.; Muneesawang P.; Akkhawatthanakun K.; Mahidol Universityper case, LLM-only generation with full autonomy, and a hybrid approach where PLM-ICD drafts candidates for an agentic LLM audit to accept or reject. All strategies were evaluated on 19,801 MIMIC-IV summaries using four LLMs spanning compact (Qwen2.5-3