KMITL

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

Browse

Settings

Subject: search.filters.subject.open burning

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Accuracy Assessment of Drone Real-Time Open Burning Imagery Detection for Early Wildfire Surveillance
    (2023-09-01)
    Duangsuwan, Sarun
    ;
    Klubsuwan, Katanyoo
    Open burning is the main factor contributing to the occurrence of wildfires in Thailand, which every year result in forest fires and air pollution. Open burning has become the natural disaster that threatens wildlands and forest resources the most. Traditional firefighting systems, which are based on ground crew inspection, have several limits and dangerous risks. Aerial imagery technologies have become one of the most important tools to prevent wildfires, especially drone real-time monitoring for wildfire surveillance. This paper presents an accuracy assessment of drone real-time open burning imagery detection (Dr-TOBID) to detect smoke and burning as a framework for a deep learning-based object detection method using a combination of the YOLOv5 detector and a lightweight version of the long short-term memory (LSTM) classifier. The Dr-TOBID framework was designed using OpenCV, YOLOv5, TensorFlow, LebelImg, and Pycharm and wirelessly connected via live stream on open broadcaster software (OBS). The datasets were separated by 80% for training and 20% for testing. The resulting assessment considered the conditions of the drone’s altitudes, ranges, and red-green-black (RGB) mode in daytime and nighttime. The accuracy, precision, recall, and F1-Score are shown for the evaluation metrics. The quantitative results show that the accuracy of Dr-TOBID successfully detected open burning monitoring, smoke, and burning characteristics, where the average F1-score was 80.6% for smoke detection in the daytime, 82.5% for burning detection in the daytime, 77.9% for smoke detection at nighttime, and 81.9% for burning detection at nighttime.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    3D AQI Mapping Data Assessment of Low-Altitude Drone Real-Time Air Pollution Monitoring
    (2022-08-01)
    Duangsuwan, Sarun
    ;
    Prapruetdee, Phoowadon
    ;
    Subongkod, Mallika
    ;
    Klubsuwan, Katanyoo
    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 (SO<inf>2</inf>) 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 (O<inf>3</inf>), nitrogen dioxide (NO<inf>2</inf>), particulate matter (PM<inf>2.5,10</inf>), and sulfur dioxide (SO<inf>2</inf>), 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, PM<inf>2.5,10</inf> 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%.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Size Distributions of Particulate Matter and Particle-bound Polycyclic Aromatic Hydrocarbons and Their Risk Assessments during Cable Sheath Burning
    (2019-01-01)
    Keawhanu, Thidarat
    ;
    Suriyawong, Achariya
    ;
    Junyapoon, Suwannee
    Burning of electric cable sheath leads to the emission of small particles and toxic pollutants that cause severe air pollution and human health effects. In this study, size distributions of particulate matter and p-PAHs during open burning of cable insulation were examined. Lifetime cancer risk of PAHs was also assessed. The particulate samples were collected on quartz fiber filters using an eight-stage cascade impactor with flow rate of 28. 3 L min<sup>-1</sup>. The exposed filter was extracted with acetonitrile and then measured by GC-MS in the SIM mode for 16 PAHs identification. It was found that average concentrations of ultrafine, fine and coarse particles were 1,045.82 µg m<sup>-3</sup> (11.45 % of the total mass), 3,557. 50 µg m<sup>-3</sup> (38. 96 % of the total mass) and 4,529. 03 µg m<sup>-3</sup> (49. 59 % of the total mass), respectively. The particle size distributions were bimodal with one major peak in the size range of 5. 8-4. 7 µm and another minor peak in the size range of 1. 1-0. 65 µm. The concentrations of 16 PAHs adsorbed on ultrafine, fine and coarse particle were 717. 86 ng m<sup>-3</sup> (11. 47% of the total PAHs), 3,645.43 ng m<sup>-3</sup> (58. 23% of the total PAHs) and 1,897. 19 ng m<sup>-3</sup> (30.30% of the total PAHs), respectively. Distributions of BaA, BaP, DbA and BgP were unimodal with a peak in accumulation mode while those of Acy, Ace and Fla were bimodal with two peaks in accumulation mode. Distributions of Flu, Phe, Ant, Pyr, Chr, BbF and BkF were multimodal with peaks in accumulation and coarse modes whereas InP was not detected. The inhalable particles (PM<inf>10</inf>) contained mainly 5-ring PAHs (55.67% of total PAHs) followed by 4-ring PAHs (27.58% of total PAHs), and 3-ring PAHs ( 14. 98% of total PAHs). Only small amount of 2-ring PAHs (1.36% of total PAHs) and 6-ring PAHs (0.41% of total PAHs) was observed. The fraction of PAHs adsorbed on PM<inf>10</inf> was ranked in the order Group 2B (53. 45%) > Group 3 (33. 86%) > Group 1 (10.71%) > Group 2A (1.98%). The average concentrations of 16 PAHs and B[a]P<inf>eq</inf> were 6,260.47 ng m<sup>-3</sup> and 1,014.35 ng m<sup>-3</sup>, respectively. The estimated lifetime lung cancer risk during wire burning was 8.83E-02.