Sarun Sumriddetchkajorn
Sarun Sumriddetchkajorn has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
Kosom Chaitavon
National Science and Technology Development Agency (Thailand)
6 shared publications- Sataporn Chanhorm
National Electronics and Computer Technology Center, National Science and Technology Development Agency, Ministry of Higher Education, Science, Research, and Innovation , 112 Thailand Science Park, Phahonyothin Road, Khlong Nueng, Khlong Luang, Pathum Thani 12120, Thailand
4 shared publications - Armote Somboonkaew
Photonics Technology Laboratory, National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Thailand Science Park, Pahol Yothin Rd., Klong Luang, Pathumthani 12120, Thailand
3 shared publications - Ratthasart Amarit
Photonics Technology Laboratory, National Electronics and Computer Technology Center (NECTEC), National Science and Technology Development Agency (NSTDA), 112 Thailand Science Park, Pahol Yothin Rd., Klong Luang, Pathumthani 12120, Thailand
3 shared publications Armote Somboonkaew
National Science and Technology Development Agency (Thailand)
2 shared publications- Kanin Aungskunsiri
National Electronics and Computer Technology Center, 112 Thailand Science Park, Phahonyothin Road, Khlong Nueng, Khlong Luang, Pathum Thani 12120, Thailand
2 shared publications
Latest Publications
- Open Access
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
An Agentic AI Approach for Planning Improvement of Government Agency in Thailand
Strategic alignment between national blueprints and execution of government agencies is vital for a nation's development. However, Thailand's traditional action plans remain a manual, "inward-looking" style that often results in activity-based key performance indicators (KPIs) focused on budget disbursement rather than tangible outcomes. This paper introduces an agentic AI approach to assist public policy planning by utilizing large language models (LLMs) as an autonomous "coworker". Implemented on a no-code agentic AI platform, the workflow automates data extraction from current national strategy reports, identifies gaps, and synthesizes structured action plans. A proof of concept demonstrates that this agentic approach can successfully assist in proposing "meaningful KPIs" and associated ministries for joint KPIs that shift from routine administrative tasks to proactive, outcome-oriented benchmarks aligned with global indices and national strategic goals. The results indicate that agentic AI has potential in reducing human effort and organizational silos and providing a scalable model for modernizing government administration.
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessAn Agentic AI Approach for Planning Improvement of Government Agency in Thailand
Strategic alignment between national blueprints and execution of government agencies is vital for a nation's development. However, Thailand's traditional action plans remain a manual, "inward-looking" style that often results in activity-based key performance indicators (KPIs) focused on budget disbursement rather than tangible outcomes. This paper introduces an agentic AI approach to assist public policy planning by utilizing large language models (LLMs) as an autonomous "coworker". Implemented on a no-code agentic AI platform, the workflow automates data extraction from current national strategy reports, identifies gaps, and synthesizes structured action plans. A proof of concept demonstrates that this agentic approach can successfully assist in proposing "meaningful KPIs" and associated ministries for joint KPIs that shift from routine administrative tasks to proactive, outcome-oriented benchmarks aligned with global indices and national strategic goals. The results indicate that agentic AI has potential in reducing human effort and organizational silos and providing a scalable model for modernizing government administration.
- Open Access
- 30 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Generative Artificial Intelligence-Augmented Evaluation of Thailand’s Government Action Plans
This study explores, for the first time, the application of generative artificial intelligence (Gen-AI) for evaluating Thailand’s national action plans to see how well they answer the goal in the national strategy and can leverage global indices of Thailand. A prototype Gen-AI platform, integrating user management, retrieval-augmented generation, and a large language model, was implemented using publicly available data. By analyzing action plans from all 20 ministries, the platform provided rapid insights and key suggestions for improvement. This Gen-AI augmented evaluation process demonstrated significant improvements in time and cost efficiency, completing comprehensive analysis of ministry-level plans in under eight hours rather than through cost-inefficient and time-consumed committee meetings. In the future, this Gen-AI augmented platform can be extended to facilitate continuous, real-time policy evaluation, create dynamic feedback loops, and support evidence-based reforms, ultimately enhancing the effectiveness of national governance and strategic planning.
- 30 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessGenerative Artificial Intelligence-Augmented Evaluation of Thailand’s Government Action Plans
This study explores, for the first time, the application of generative artificial intelligence (Gen-AI) for evaluating Thailand’s national action plans to see how well they answer the goal in the national strategy and can leverage global indices of Thailand. A prototype Gen-AI platform, integrating user management, retrieval-augmented generation, and a large language model, was implemented using publicly available data. By analyzing action plans from all 20 ministries, the platform provided rapid insights and key suggestions for improvement. This Gen-AI augmented evaluation process demonstrated significant improvements in time and cost efficiency, completing comprehensive analysis of ministry-level plans in under eight hours rather than through cost-inefficient and time-consumed committee meetings. In the future, this Gen-AI augmented platform can be extended to facilitate continuous, real-time policy evaluation, create dynamic feedback loops, and support evidence-based reforms, ultimately enhancing the effectiveness of national governance and strategic planning.
- 19 February 2025
- Published by SPIE-Intl Soc Optical Eng
- Vol. 13518, 37-44
Wide-band multispectral imaging system for classification of durian maturity
Durian is a kind of editable fruit mostly planted in Southeast Asia. Thailand is the world’s largest durian exporter with over USD500M since 2016. Since ripe durians have unique flavors and textures different from immature ones, the maturity levels of durians have to be investigated before supplying to both local and global markets. In this work, we propose and experimentally demonstrate a multispectral imaging system that can provide spectral images ranging from visible to far-infrared bands. Several machine learning (ML) models are employed to assist in classifying durian maturity levels. Experimental results show that the ML models provide higher accuracy when wider-band spectral data are used. The proposed system opens an avenue for determining the level of durian maturity, which highly impacts the process of quality control, trustworthiness to consumers, and economy of the exported countries.
- 19 February 2025
- Published by SPIE-Intl Soc Optical Eng
- Vol. 13518, 37-44
Wide-band multispectral imaging system for classification of durian maturity
Durian is a kind of editable fruit mostly planted in Southeast Asia. Thailand is the world’s largest durian exporter with over USD500M since 2016. Since ripe durians have unique flavors and textures different from immature ones, the maturity levels of durians have to be investigated before supplying to both local and global markets. In this work, we propose and experimentally demonstrate a multispectral imaging system that can provide spectral images ranging from visible to far-infrared bands. Several machine learning (ML) models are employed to assist in classifying durian maturity levels. Experimental results show that the ML models provide higher accuracy when wider-band spectral data are used. The proposed system opens an avenue for determining the level of durian maturity, which highly impacts the process of quality control, trustworthiness to consumers, and economy of the exported countries.
- 15 April 2024
- Published by Optica Publishing Group in Applied Optics
- Vol. 63 (12) , 3148-3155
Infrared-based temperature measurement in three dimensions
A highly accurate and low-cost mobile platform for multiple object temperature measurement in 3D coordinate positions is introduced. The key idea relies on not only a combination of a 3D optical depth sensor and the 2D infrared thermal imager but also a determined distant-dependent compensation model. As a result, a cost-effective yet wider (>100.0∘C) temperature measurement range under the fluctuation of working distant shift is realized with a low standard deviation of 0.16°C at the working distance of 1.0 m. Accurate temperature measurement at different positions of objects along the suitable working distance is also demonstrated.
- 15 April 2024
- Published by Optica Publishing Group in Applied Optics
- Vol. 63 (12) , 3148-3155
Infrared-based temperature measurement in three dimensions
A highly accurate and low-cost mobile platform for multiple object temperature measurement in 3D coordinate positions is introduced. The key idea relies on not only a combination of a 3D optical depth sensor and the 2D infrared thermal imager but also a determined distant-dependent compensation model. As a result, a cost-effective yet wider (>100.0∘C) temperature measurement range under the fluctuation of working distant shift is realized with a low standard deviation of 0.16°C at the working distance of 1.0 m. Accurate temperature measurement at different positions of objects along the suitable working distance is also demonstrated.
- 1 January 2023
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 94 (1) , 014704
Multiplexing quantum tunneling diodes for random number generation
Random numbers are indispensable resources for application in modern science and technology. Therefore, a dedicated entropy source is essential, particularly for cryptographic tasks and modern applications. In this work, we experimentally demonstrated a scheme to generate random numbers by multiplexing eight tunnel diodes onto a single circuit. As a result, the data rate of random number generation was significantly enhanced eightfold. In comparison to the original scheme that employed one diode, this multiplexing scheme produced data with higher entropy. These data were then post-processed with the Toeplitz-hashing extractor, yielding final outputs that achieved almost full entropy and passed the U.S. National Institute of Standards and Technology (NIST) Special Publication 800-90B validation. These data also passed the NIST Special Publication 800-22 statistical randomness examination and had no sign of patterns detected from an autocorrelation analysis.
- 1 January 2023
- Published by AIP Publishing in Review of Scientific Instruments
- Vol. 94 (1) , 014704
Multiplexing quantum tunneling diodes for random number generation
Random numbers are indispensable resources for application in modern science and technology. Therefore, a dedicated entropy source is essential, particularly for cryptographic tasks and modern applications. In this work, we experimentally demonstrated a scheme to generate random numbers by multiplexing eight tunnel diodes onto a single circuit. As a result, the data rate of random number generation was significantly enhanced eightfold. In comparison to the original scheme that employed one diode, this multiplexing scheme produced data with higher entropy. These data were then post-processed with the Toeplitz-hashing extractor, yielding final outputs that achieved almost full entropy and passed the U.S. National Institute of Standards and Technology (NIST) Special Publication 800-90B validation. These data also passed the NIST Special Publication 800-22 statistical randomness examination and had no sign of patterns detected from an autocorrelation analysis.
- 28 January 2022
- Published by Optica Publishing Group in Applied Optics
- Vol. 61 (8) , E14-E20
Mobile-device-based two-dimensional measurement for estimating the embryo and endosperm areas of brown rice
The rice kernel inside a hull is composed of the embryo and endosperm. The embryo or germ of the rice seed will grow and become the shoot and the root parts of a seedling, while the endosperm is an important nutrient source for the embryo in the early stages. Hence, the health of seedlings depends particularly on the sizes of the embryo and endosperm. In this work, we propose and experimentally demonstrate how the embryo and endosperm areas of brown rice can simply be determined. Our key idea is based on the utilization of a smart mobile device equipped with our specifically designed lens module arranged in a simple cross-polarization imaging configuration for acquiring a rice grain image upon the illumination of a white light source and then spatially analyzing the sizes of embryo and endosperm areas. The prototype shows promising results in identifying the sizes of the embryo and endosperm within 2 s per seed with a measurement error of < 9 % compared with the use of off-the-shelf image editing software. In addition, the prototype is in a small package of 20 × 32.5 × 6.5 c m 3 with 4 kg weight, thus showing high potential to perform in the real scenario.
- 28 January 2022
- Published by Optica Publishing Group in Applied Optics
- Vol. 61 (8) , E14-E20
Mobile-device-based two-dimensional measurement for estimating the embryo and endosperm areas of brown rice
The rice kernel inside a hull is composed of the embryo and endosperm. The embryo or germ of the rice seed will grow and become the shoot and the root parts of a seedling, while the endosperm is an important nutrient source for the embryo in the early stages. Hence, the health of seedlings depends particularly on the sizes of the embryo and endosperm. In this work, we propose and experimentally demonstrate how the embryo and endosperm areas of brown rice can simply be determined. Our key idea is based on the utilization of a smart mobile device equipped with our specifically designed lens module arranged in a simple cross-polarization imaging configuration for acquiring a rice grain image upon the illumination of a white light source and then spatially analyzing the sizes of embryo and endosperm areas. The prototype shows promising results in identifying the sizes of the embryo and endosperm within 2 s per seed with a measurement error of < 9 % compared with the use of off-the-shelf image editing software. In addition, the prototype is in a small package of 20 × 32.5 × 6.5 c m 3 with 4 kg weight, thus showing high potential to perform in the real scenario.
- 23 December 2021
- Published by Optica Publishing Group in Optical Materials Express
- Vol. 12 (1) , 308-316
Rubidium copper chloride scintillator for X-ray imaging screen
Metal halide-based perovskite materials have received great attention in scintillating applications because they can emit strong visible light when interacting with X-ray particles. Here, we report a scintillator based on rubidium copper chlorine incorporated in the polydimethylsiloxane matrix. The scintillator shows a bright violet emission under ultraviolet and ionizing radiation. The temperature-dependent photoluminescence and radioluminescence shows maximum thermal enhancement at 80°C and 60°C, respectively. Moreover, the first X-ray image from this material reveals the detailed information of the object captured by a commercially available digital camera, indicating a potent scintillator for creating X-ray imaging screens.
- 23 December 2021
- Published by Optica Publishing Group in Optical Materials Express
- Vol. 12 (1) , 308-316
Rubidium copper chloride scintillator for X-ray imaging screen
Metal halide-based perovskite materials have received great attention in scintillating applications because they can emit strong visible light when interacting with X-ray particles. Here, we report a scintillator based on rubidium copper chlorine incorporated in the polydimethylsiloxane matrix. The scintillator shows a bright violet emission under ultraviolet and ionizing radiation. The temperature-dependent photoluminescence and radioluminescence shows maximum thermal enhancement at 80°C and 60°C, respectively. Moreover, the first X-ray image from this material reveals the detailed information of the object captured by a commercially available digital camera, indicating a potent scintillator for creating X-ray imaging screens.
- 16 August 2021
- Published by AIP Publishing in Applied Physics Letters
- Vol. 119 (7) , 074002
Random number generation from a quantum tunneling diode
Random numbers are important in many activities, including communication, encryption, science, gambling, finance, and decision making. There is a strong demand for a hardware random number generator that could support cryptographic applications. In this work, we propose a quantum tunneling diode as a source of true randomness achieved by applying electrical current sweeps through the device and then harnessing a time-counting unit to measure fluctuation of current flows. Our approach can be implemented with inexpensive electronics and could be integrated into systems that require random numbers such as portable communication devices.
- 16 August 2021
- Published by AIP Publishing in Applied Physics Letters
- Vol. 119 (7) , 074002
Random number generation from a quantum tunneling diode
Random numbers are important in many activities, including communication, encryption, science, gambling, finance, and decision making. There is a strong demand for a hardware random number generator that could support cryptographic applications. In this work, we propose a quantum tunneling diode as a source of true randomness achieved by applying electrical current sweeps through the device and then harnessing a time-counting unit to measure fluctuation of current flows. Our approach can be implemented with inexpensive electronics and could be integrated into systems that require random numbers such as portable communication devices.
- 9 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-6
Self-Compensation for the Influence of Working Distance and Ambient Temperature on Thermal Imaging-Based Temperature Measurement
Nowadays, body temperature screening is very important especially in the current global coronavirus disease (COVID-19) epidemic. It can be considered as the first step in monitoring the fever symptom if the body temperature is checked regularly. Aiming at alleviating the influence of working distance and ambient temperature disturbance, this article proposes and demonstrates a self-compensation technique that is built into our low-cost thermal imaging-based temperature screening system. The key idea relies on a combination of a 3-D depth sensor, an electronic temperature sensor, and a reference temperature for realtime data feedback and control. In addition, we obtain simple mathematical models for compensating the influence of ambient temperature and measuring distance variations. Experimental demonstration using a blackbody radiation source as an object confirms that the measured temperature under our self-compensation agrees very well with the blackbody radiation source, showing a very low standard deviation of 0.10 °C under 21.0 °C–40.0 °C ambient temperature. In addition, an improved standard deviation of 0.18 °C and a low 0.020 °C/m for the measured temperature are obtained under the variation in measuring the distance from 0.50 to 2.00 m.
- 9 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-6
Self-Compensation for the Influence of Working Distance and Ambient Temperature on Thermal Imaging-Based Temperature Measurement
Nowadays, body temperature screening is very important especially in the current global coronavirus disease (COVID-19) epidemic. It can be considered as the first step in monitoring the fever symptom if the body temperature is checked regularly. Aiming at alleviating the influence of working distance and ambient temperature disturbance, this article proposes and demonstrates a self-compensation technique that is built into our low-cost thermal imaging-based temperature screening system. The key idea relies on a combination of a 3-D depth sensor, an electronic temperature sensor, and a reference temperature for realtime data feedback and control. In addition, we obtain simple mathematical models for compensating the influence of ambient temperature and measuring distance variations. Experimental demonstration using a blackbody radiation source as an object confirms that the measured temperature under our self-compensation agrees very well with the blackbody radiation source, showing a very low standard deviation of 0.10 °C under 21.0 °C–40.0 °C ambient temperature. In addition, an improved standard deviation of 0.18 °C and a low 0.020 °C/m for the measured temperature are obtained under the variation in measuring the distance from 0.50 to 2.00 m.
- 20 May 2020
- Published by Optica Publishing Group in Applied Optics
- Vol. 59 (17) , E112-E117
Temperature-compensated infrared-based low-cost mobile platform module for mass human temperature screening
As fast human temperature screening is needed in large public areas, this paper proposes a low-cost mobile platform module that combines the advantages of analyzing visible and thermal images. In particular, the key idea relies on face detection in the visible image. Then the coordinates of all faces detected are mapped on to the thermal image to determine their corresponding temperatures. Internal temperature compensation and external reference temperature also are employed to reduce the unwanted temperature fluctuation inside the module and in the surrounding environment. Our mobile platform module, called $\unicode{x00B5} {\rm Therm}$, uses a FLIR ONE camera as our visible and thermal imaging cameras. It can simultaneously determine the temperatures of nine people at a speed of 8 frames/second. A field test operation was performed for four days with 1,170 people, with very promising results of 100% sensitivity, 92.6% specificity, and 92.7% accuracy.- 20 May 2020
- Published by Optica Publishing Group in Applied Optics
- Vol. 59 (17) , E112-E117
Temperature-compensated infrared-based low-cost mobile platform module for mass human temperature screening
As fast human temperature screening is needed in large public areas, this paper proposes a low-cost mobile platform module that combines the advantages of analyzing visible and thermal images. In particular, the key idea relies on face detection in the visible image. Then the coordinates of all faces detected are mapped on to the thermal image to determine their corresponding temperatures. Internal temperature compensation and external reference temperature also are employed to reduce the unwanted temperature fluctuation inside the module and in the surrounding environment. Our mobile platform module, called $\unicode{x00B5} {\rm Therm}$, uses a FLIR ONE camera as our visible and thermal imaging cameras. It can simultaneously determine the temperatures of nine people at a speed of 8 frames/second. A field test operation was performed for four days with 1,170 people, with very promising results of 100% sensitivity, 92.6% specificity, and 92.7% accuracy.