Sansiri Tarnpradab
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Sansiri Tarnpradab has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Kien A. Hua
University of Central Florida † Facebook
3 shared publications - Phond Phunchongharn
Department of Computer Engineering, King Mongkut’s University of Technology Thonburi, Bangkok 10140, Thailand
2 shared publications - Antoun Yaacoub
Learning Data and Robotics (LDR) ESIEA Lab ESIEA Paris France
1 shared publication - Arnatchai Techaviseschai
Department of Computer Engineering, King Mongkut’s University of Technology Thonburi, Bangkok 10140, Thailand
1 shared publication - Fereshteh Jafariakinabad
Florida Computer Science Department University of Central
1 shared publication - Gunn Wangwichit
Computer Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand
1 shared publication
Latest Publications
- 26 September 2026
- Published by Springer Nature
- p. 262-272
HiFi-Rep: Leveraging High-Resolution Vision Foundation Models with Tri-planar Slice Context for CT Report Generation
- 26 September 2026
- Published by Springer Nature
- p. 262-272
HiFi-Rep: Leveraging High-Resolution Vision Foundation Models with Tri-planar Slice Context for CT Report Generation
- Open Access
- 17 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 298-303
A Label-Free U-Net LSTM Autoencoder for Anomaly Detection and Root Cause Analysis in Rotating Machinery
- 17 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 298-303
Open AccessA Label-Free U-Net LSTM Autoencoder for Anomaly Detection and Root Cause Analysis in Rotating Machinery
- Open Access
- 17 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 89-95
Enhancing Technical Knowledge Retrieval Through Hybrid Retrieval-Augmented Generation
High-precision knowledge retrieval within specialized scientific infrastructures, such as CERN's large-scale data ecosystem, presents unique challenges for standard Large Language Models (LLMs). Conventional Retrieval-Augmented Generation (RAG) frameworks often suffer from structural fragmentation and inadequate retrieval of technical identifiers. This paper proposes an optimized RAG framework utilizing a Hybrid Similarity Scoring mechanism that integrates BM25 lexical matching with dense semantic retrieval. The methodology focuses on enhancing technical factuality through a neural re-ranking pipeline and instruction-formatted system prompting. Extensive experiments were conducted to evaluate three distinct chunking strategies and the influence of various LLM hyperparameters on model grounding. Results indicate that the proposed framework achieves a 2–8% improvement in retrieval relevance and a 2% reduction in hallucinations compared to standard RAG baselines, providing a robust solution for complex technical domain interaction.
- 17 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 89-95
Open AccessEnhancing Technical Knowledge Retrieval Through Hybrid Retrieval-Augmented Generation
High-precision knowledge retrieval within specialized scientific infrastructures, such as CERN's large-scale data ecosystem, presents unique challenges for standard Large Language Models (LLMs). Conventional Retrieval-Augmented Generation (RAG) frameworks often suffer from structural fragmentation and inadequate retrieval of technical identifiers. This paper proposes an optimized RAG framework utilizing a Hybrid Similarity Scoring mechanism that integrates BM25 lexical matching with dense semantic retrieval. The methodology focuses on enhancing technical factuality through a neural re-ranking pipeline and instruction-formatted system prompting. Extensive experiments were conducted to evaluate three distinct chunking strategies and the influence of various LLM hyperparameters on model grounding. Results indicate that the proposed framework achieves a 2–8% improvement in retrieval relevance and a 2% reduction in hallucinations compared to standard RAG baselines, providing a robust solution for complex technical domain interaction.
- Open Access
- 23 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (11) , 5901
A Real-Time Semi-Supervised Log Anomaly Detection Framework for ALICE O2 Facilities
The ALICE (A Large Ion Collider Experiment) detector at the Large Hadron Collider (LHC), operated by the European Organization for Nuclear Research (CERN), is dedicated to heavy-ion collisions. Within ALICE, the application logs of the online computing systems are consolidated through a logging system known as Infologger, which integrates data from various sources. To identify potential anomalies, shifters in the control room manually review logs for anomalies, which require significant expertise and pose challenges due to the frequent onboarding of new personnel. To address this issue, we propose a real-time semi-supervised log anomaly detection framework designed to automatically detect anomalies in ALICE operations. The framework leverages BERTopic, a topic modeling technique, to provide real-time insights for incoming log messages for shifters. This includes an analytical dashboard that represents the anomaly status in log messages, facilitating informative monitoring for shifters. Through evaluation, including Infologger and BGL (BlueGene/L supercomputer), we analyze the effects of word embeddings, clustering algorithms, and HDBSCAN hyperparameters on model performance. The result demonstrates that the BERTopic can enhance the log anomaly detection process over traditional topic models, achieving remarkable performance metrics and attaining F1-scores of 0.957 and 0.958 for the InfoLogger and BGL datasets, respectively, even without the preprocessing technique.
- 23 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (11) , 5901
Open AccessA Real-Time Semi-Supervised Log Anomaly Detection Framework for ALICE O2 Facilities
The ALICE (A Large Ion Collider Experiment) detector at the Large Hadron Collider (LHC), operated by the European Organization for Nuclear Research (CERN), is dedicated to heavy-ion collisions. Within ALICE, the application logs of the online computing systems are consolidated through a logging system known as Infologger, which integrates data from various sources. To identify potential anomalies, shifters in the control room manually review logs for anomalies, which require significant expertise and pose challenges due to the frequent onboarding of new personnel. To address this issue, we propose a real-time semi-supervised log anomaly detection framework designed to automatically detect anomalies in ALICE operations. The framework leverages BERTopic, a topic modeling technique, to provide real-time insights for incoming log messages for shifters. This includes an analytical dashboard that represents the anomaly status in log messages, facilitating informative monitoring for shifters. Through evaluation, including Infologger and BGL (BlueGene/L supercomputer), we analyze the effects of word embeddings, clustering algorithms, and HDBSCAN hyperparameters on model performance. The result demonstrates that the BERTopic can enhance the log anomaly detection process over traditional topic models, achieving remarkable performance metrics and attaining F1-scores of 0.957 and 0.958 for the InfoLogger and BGL datasets, respectively, even without the preprocessing technique.
- Open Access
Enhancing AI-Driven Education: Integrating Cognitive Frameworks, Linguistic Feedback Analysis, and Ethical Considerations for Improved Content Generation
Artificial intelligence (AI) is rapidly transforming education, presenting unprecedented opportunities for personalized learning and streamlined content creation. However, realizing the full potential of AI in educational settings necessitates careful consideration of the quality, cognitive depth, and ethical implications of AI-generated materials. This paper synthesizes insights from four related studies to propose a comprehensive framework for enhancing AI-driven educational tools. We integrate cognitive assessment frameworks (Bloom's Taxonomy and SOLO Taxonomy), linguistic analysis of AI-generated feedback, and ethical design principles to guide the development of effective and responsible AI tools. We outline a structured three-phase approach encompassing cognitive alignment, linguistic feedback integration, and ethical safeguards. The practical application of this framework is demonstrated through its integration into OneClickQuiz, an AI-powered Moodle plugin for quiz generation. This work contributes a comprehensive and actionable guide for educators, researchers, and developers aiming to harness AI's potential while upholding pedagogical and ethical standards in educational content generation.
Open AccessEnhancing AI-Driven Education: Integrating Cognitive Frameworks, Linguistic Feedback Analysis, and Ethical Considerations for Improved Content Generation
Artificial intelligence (AI) is rapidly transforming education, presenting unprecedented opportunities for personalized learning and streamlined content creation. However, realizing the full potential of AI in educational settings necessitates careful consideration of the quality, cognitive depth, and ethical implications of AI-generated materials. This paper synthesizes insights from four related studies to propose a comprehensive framework for enhancing AI-driven educational tools. We integrate cognitive assessment frameworks (Bloom's Taxonomy and SOLO Taxonomy), linguistic analysis of AI-generated feedback, and ethical design principles to guide the development of effective and responsible AI tools. We outline a structured three-phase approach encompassing cognitive alignment, linguistic feedback integration, and ethical safeguards. The practical application of this framework is demonstrated through its integration into OneClickQuiz, an AI-powered Moodle plugin for quiz generation. This work contributes a comprehensive and actionable guide for educators, researchers, and developers aiming to harness AI's potential while upholding pedagogical and ethical standards in educational content generation.
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 14-21
Anomaly Detection in Large-Scale Monitoring Systems using a Language Model
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 14-21
Open AccessAnomaly Detection in Large-Scale Monitoring Systems using a Language Model
- 7 August 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (20) , 22655-22679
Real-time masked face recognition and authentication with convolutional neural networks on the web application
- 7 August 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (20) , 22655-22679
Real-time masked face recognition and authentication with convolutional neural networks on the web application
- 9 February 2024
- Published by Springer Nature in SN Computer Science
- Vol. 5 (2) , 1-16
End-to-End Deep Networks with Hierarchical Attention and Capsule Capabilities for Misinformation Detection on Microblogging Platforms
- 9 February 2024
- Published by Springer Nature in SN Computer Science
- Vol. 5 (2) , 1-16
End-to-End Deep Networks with Hierarchical Attention and Capsule Capabilities for Misinformation Detection on Microblogging Platforms
- 30 June 2023
- Published by Springer Nature
- p. 322-333
An Empirical Study on the Effectiveness of Bi-LSTM-Based Industry Rotation Strategies in Thai Equity Portfolios
- 30 June 2023
- Published by Springer Nature
- p. 322-333
An Empirical Study on the Effectiveness of Bi-LSTM-Based Industry Rotation Strategies in Thai Equity Portfolios
- Open Access
Improving Online Forums Summarization via Hierarchical Unified Deep Neural Network
Online discussion forums are prevalent and easily accessible, thus allowing people to share ideas and opinions by posting messages in the discussion threads. Forum threads that significantly grow in length can become difficult for participants, both newcomers and existing, to grasp main ideas. To mitigate this problem, this study aims to create an automatic text summarizer for online forums. We present Hierarchical Unified Deep Neural Network to build sentence and thread representations for the forum summarization. In this scheme, Bi-LSTM derives a representation that comprises information of the whole sentence and whole thread; whereas, CNN captures most informative features with respect to context from sentence and thread. Attention mechanism is applied on top of CNN to further highlight high-level representations that carry important information contributing to a desirable summary. Extensive performance evaluation has been conducted on three datasets, two of which are real-life online forums and one is news dataset. The results reveal that the proposed model outperforms several competitive baselines.
Open AccessImproving Online Forums Summarization via Hierarchical Unified Deep Neural Network
Online discussion forums are prevalent and easily accessible, thus allowing people to share ideas and opinions by posting messages in the discussion threads. Forum threads that significantly grow in length can become difficult for participants, both newcomers and existing, to grasp main ideas. To mitigate this problem, this study aims to create an automatic text summarizer for online forums. We present Hierarchical Unified Deep Neural Network to build sentence and thread representations for the forum summarization. In this scheme, Bi-LSTM derives a representation that comprises information of the whole sentence and whole thread; whereas, CNN captures most informative features with respect to context from sentence and thread. Attention mechanism is applied on top of CNN to further highlight high-level representations that carry important information contributing to a desirable summary. Extensive performance evaluation has been conducted on three datasets, two of which are real-life online forums and one is news dataset. The results reveal that the proposed model outperforms several competitive baselines.