Sarun Duangsuwan

Dr. Sarun Duangsuwan

King Mongkut's Institute of Technology Ladkrabang, Bangkok, Krung Thep Maha Nakhon, Thailand
orcid
UAV-DigitalTWIN Lab.

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2018
Verified
Conference Paper
Closed access
Sarun DuangsuwanSarun Duangsuwan
Sarun Duangsuwan
ATAekarong Takarn
Aekarong Takarn
RNRachan Nujankaew
Rachan Nujankaew
PJPunyawi Jamjareegulgarn
Punyawi Jamjareegulgarn
The problem of air pollutant has to improve urgently, in particular, approach to smart city in 2024 of Thailand 4.0. This paper presents a development of smart sensors of air pollution to monitor the air quality in smart city. We propose the smart sensors that consist of the particulate matter (PM 10 ) or dust sensor, carbon monoxide (CO), carbon dioxide (CO 2 ), noise level (dB), and ozone (O 3 ) respectively. These sensors are solution of a low power wide area network (LPWAN). In the experiment, the measurement has been investigated in Bangkok metropolitan, and the results show air quality index (AQI) via Norrowband Internet of Things (NB-IoT). The proposed of this paper can help the people know the real-time air quality via IoT as a service.

1 September 2018
Verified
Conference Paper
Closed access
Sarun DuangsuwanSarun Duangsuwan
Sarun Duangsuwan
ATAekarong Takarn
Aekarong Takarn
PJPunyawi Jamjareegulgarn
Punyawi Jamjareegulgarn
Currently, air pollution is a big problem for people health in cities that suffered from the more factors such as the traffic, industrial, or forest fire or polluted skies. This paper presents a development of air pollution detection sensors and monitoring for smart city, Thailand 4.0. The development is designed by using five standard sensors such as carbon dioxide: CO, ozone: O 3 , particulate matter: PM 10 , nitrogen dioxide: NO 2 , and sulfur dioxide: SO 2 respectively, and web monitor shows the graph of the air quality index (AQI). To monitor the air quality, the data processing is computed by using Arduno MEGA 2560 and Respberri Pi 3 to connect with Narrowband Internet of Things (NB-IoT) module network. Experimental setup, the measurement location is examined at Sai Mai District, Bangkok. As the result, we found that the AQI level of measured location is good air quality. We emphasize that the monitoring of air pollution in smart cities is very important.

29 July 2022 in Drones
Verified
Journal Article
Open access
PDF file
Sarun DuangsuwanSarun Duangsuwan
Sarun Duangsuwan
PPPhoowadon Prapruetdee
Phoowadon Prapruetdee
MSMallika Subongkod
Mallika Subongkod
KKKatanyoo Klubsuwan
Katanyoo Klubsuwan
Air pollution primarily originates from substances that are directly emitted from natural or anthropogenic processes, such as carbon monoxide (CO) gas emitted in vehicle exhaust or sulfur dioxide (SO2) released from factories. However, a major air pollution problem is particulate matter (PM), which is an adverse effect of wildfires and open burning. Application tools for air pollution monitoring in risk areas using real-time monitoring with drones have emerged. A new air quality index (AQI) for monitoring and display, such as three-dimensional (3D) mapping based on data assessment, is essential for timely environmental surveying. The objective of this paper is to present a 3D AQI mapping data assessment using a hybrid model based on a machine-learning method for drone real-time air pollution monitoring (Dr-TAPM). Dr-TAPM was designed by equipping drones with multi-environmental sensors for carbon monoxide (CO), ozone (O3), nitrogen dioxide (NO2), particulate matter (PM2.5,10), and sulfur dioxide (SO2), with data pre- and post-processing with the hybrid model. The hybrid model for data assessment was proposed using backpropagation neural network (BPNN) and convolutional neural network (CNN) algorithms. Experimentally, we considered a case study detecting smoke emissions from an open burning scenario. As a result, PM2.5,10 and CO were detected as air pollutants from open burning. 3D AQI map locations were shown and the validation learning rates were apparent, as the accuracy of predicted AQI data assessment was 98%.

10 February 2020 in Sensors and Materials
Verified
Journal Article
Open access
Sarun DuangsuwanSarun Duangsuwan
Sarun Duangsuwan
PJPunyawi Jamjareekulgarn
Punyawi Jamjareekulgarn

12 December 2024 in Drones
Verified
Journal Article
Open access
PDF file
Sarun DuangsuwanSarun Duangsuwan
Sarun Duangsuwan
PPPhoowadon Prapruetdee
Phoowadon Prapruetdee
Coastal litter is a severe environmental issue impacting marine ecosystems and coastal communities in Thailand, with plastic pollution posing one of the most urgent challenges. Every month, millions of tons of plastic waste enter the ocean, where items such as bottles, cans, and other plastics can take hundreds of years to degrade, threatening marine life through ingestion, entanglement, and habitat destruction. To address this issue, we deploy drones equipped with high-resolution cameras and sensors to capture detailed coastal imagery for assessing litter distribution. This study presents the development of an AI-driven coastal litter detection system using edge computing and 5G communication networks. The AI edge server utilizes YOLOv8 and a recurrent neural network (RNN) to enable the drone to detect and classify various types of litter, such as bottles, cans, and plastics, in real-time. High-speed 5G communication supports seamless data transmission, allowing efficient monitoring. We evaluated drone performance under optimal flying heights above ground of 5 m, 7 m, and 10 m, analyzing accuracy, precision, recall, and F1-score. Results indicate that the system achieves optimal detection at an altitude of 5 m with a ground sampling distance (GSD) of 0.98 cm/pixel, yielding an F1-score of 98% for cans, 96% for plastics, and 95% for bottles. This approach facilitates real-time monitoring of coastal areas, contributing to marine ecosystem conservation and environmental sustainability.

31 July 2021 in International Journal of Antennas and Propagation
Verified
Journal Article
Open access
PDF file
Sarun DuangsuwanSarun Duangsuwan
Sarun Duangsuwan
PJPhakamon Juengkittikul
Phakamon Juengkittikul
MMMyo Myint Maw
Myo Myint Maw
The purpose of this paper was to predict the path loss characterization of the ground-to-air (G2A) communication channel between the ground sensor (GS) and unmanned aerial vehicle (UAV) using machine learning (ML) models in smart farming (SF) scenarios. Two ML algorithms such as support vector regression (SVR) and artificial neural network (ANN) were studied to analyze the measured data in different scenarios with Napier and Ruzi grass farms as the measurement locations. The proposed empirical GS-to-UAV two-ray (GUT-R) model and the ML models were compared to characterize path loss prediction models. The performances of the path loss prediction models were evaluated using the statistical error indicators in different measurement locations and UAV trajectories. To obtain the statistical error indicators, the accuracy path loss results of UAV trajectory at 2m altitudes showed the SVR model (MAE=1.252dB, RMSE=3.067dB, and R2=0.972) and the ANN model (MAE=1.150dB, RMSE=2.502dB, and R2=0.981) for the Napier scenario. In the Ruzi scenario, the SVR model (MAE=1.202dB, RMSE=2.962dB, and R2=0.965) and the ANN model (MAE=1.146dB, RMSE=2.507dB, and R2=0.983) were presented. For UAV trajectory at 5m altitudes, the SVR model (MAE=2.125dB, RMSE=4.782dB, and R2=0.933) and the ANN model (MAE=2.025dB, RMSE=4.439dB, and R2=0.950) were resulted in the Napier scenario. In the Ruzi scenario, the SVR model (MAE=2.112dB, RMSE=4.682dB, and R2=0.935) and the ANN model (MAE=2.016dB, RMSE=4.407dB, and R2=0.954) were displayed. The proposed ML models using SVR and ANN can optimally predict the path loss characterization in SF scenarios, where the accuracy was 95 for the SVR and 97 for the ANN.