KMITL

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

Browse

Settings

Author: search.filters.author.Prapruetdee, Phoowadon

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Drone-Enabled AI Edge Computing and 5G Communication Network for Real-Time Coastal Litter Detection
    (2024-12-01)
    Duangsuwan, Sarun
    ;
    Prapruetdee, Phoowadon
    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.
  • 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%.