Yooyen, Soemsak

Loading...
Thumbnail Image
Preferred name
Yooyen, Soemsak
Alternative Name
Yooyen, S.
Main Affiliation
Email
soemsak.yo@kmitl.ac.th

Settings

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Aircraft trajectory recognition via statistical analysis clustering for Suvarnabhumi International Airport
    (2020-02-01)
    Kamsing, Patcharin
    ;
    Torteeka, Peerapong
    ;
    Yooyen, Soemsak
    ;
    Yenpiem, Siriporn
    ;
    Delahaye, Daniel
    Since Suvarnabhumi International Airport is considered to be the biggest airport in Thailand, a big travelling-hub of southeast Asia and plays a significant part to the economy of Thailand relying on the tourism industry, an aircraft trajectory recognition is essential to support the high traffic management system from around the world. The first and essential stage of airport capacity enhancement is descriptive-analytic in several sections of the airport, including flight trajectory behaviors in order to plan an improvement procedure in the future. This experiment deploys K-mean and Gaussian Mixture clustering to compare results by using available automatic dependent surveillance-broadcast (ADS-B) dataset provided by the bigdata system from various websites. The test varies the number of clustering from three to ten and measures how similar an object is to its cluster by using the Silhouette score. Gaussian Mixture clustering produces at least three unique flight trajectories when setting the number of clustering equal to four, giving the Silhouette score of 0.43. K-mean clustering with the number of clustering equal to ten gives the highest Silhouette score of 0.45. However, its routes are not clearly recognized when compared with the Gaussian Mixture clustering. Although the overall results are not clearly shown in the pattern, it is enough to describe the trajectory patterns of the aircrafts taking off or landing over Suvarnabhumi International Airport.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Vision-based spacecraft pose estimation via a deep convolutional neural network for noncooperative docking operations
    (2020-09-01)
    Phisannupawong, Thaweerath
    ;
    Kamsing, Patcharin
    ;
    Torteeka, Peerapong
    ;
    Channumsin, Sittiporn
    ;
    Sawangwit, Utane
    The capture of a target spacecraft by a chaser is an on-orbit docking operation that requires an accurate, reliable, and robust object recognition algorithm. Vision-based guided spacecraft relative motion during close-proximity maneuvers has been consecutively applied using dynamic modeling as a spacecraft on-orbit service system. This research constructs a vision-based pose estimation model that performs image processing via a deep convolutional neural network. The pose estimation model was constructed by repurposing a modified pretrained GoogLeNet model with the available Unreal Engine 4 rendered dataset of the Soyuz spacecraft. In the implementation, the convolutional neural network learns from the data samples to create correlations between the images and the spacecraft’s six degrees-of-freedom parameters. The experiment has compared an exponential-based loss function and a weighted Euclidean-based loss function. Using the weighted Euclidean-based loss function, the implemented pose estimation model achieved moderately high performance with a position accuracy of 92.53 percent and an error of 1.2 m. The in-attitude prediction accuracy can reach 87.93 percent, and the errors in the three Euler angles do not exceed 7.6 degrees. This research can contribute to spacecraft detection and tracking problems. Although the finished vision-based model is specific to the environment of synthetic dataset, the model could be trained further to address actual docking operations in the future.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An enhanced learning algorithm with a particle filter-based gradient descent optimizer method
    (2020-08-01)
    Kamsing, Patcharin
    ;
    Torteeka, Peerapong
    ;
    Yooyen, Soemsak
    This experiment integrates a particle filter concept with a gradient descent optimizer to reduce loss during iteration and obtains a particle filter-based gradient descent (PF-GD) optimizer that can determine the global minimum with excellent performance. Four functions are applied to test optimizer deployment to verify the PF-GD method. Additionally, the Modified National Institute of Standards and Technology (MNIST) database is used to test the PF-GD method by implementing a logistic regression learning algorithm. The experimental results obtained with the four functions illustrate that the PF-GD method performs much better than the conventional gradient descent optimizer, although it has some parameters that must be set before modeling. The results of implementing the MNIST dataset demonstrate that the cross-entropy of the PF-GD method exhibits a smaller decrease than that of the conventional gradient descent optimizer, resulting in higher accuracy of the PF-GD method. The PF-GD method provides the best accuracy for the training model, 97.00%, and the accuracy of evaluating the model with the test dataset is 90.37%, which is higher than the accuracy of 90.08% obtained with the conventional gradient descent optimizer.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Deep Convolutional Neural Networks for plane identification on Satellite imagery by exploiting transfer learning with a different optimizer
    (2019-07-01)
    Kamsing, Patcharin
    ;
    Torteeka, Peerapong
    ;
    Yooyen, Soemsak
    Object identification is on an available problem. Automating plane identification on Satellite imagery can be applied for activity and traffic patterns to monitoring airports, and including defense intelligence issues. This paper implements Deep Convolutional Neural Networks(CNN) to classify a plane in the planesnet dataset. Pre-trained model and transfer learning are deployed to overcome a limitation of computation resources by adding new top layer consists of a fully-connected layer and softmax layer to identify the new classes and re-train it. Besides, the experimental designs for testing an implementation of a pretrained model with some kinds of the optimizer to comparing a result. There are four types of optimizer. The first two are well-known optimizer namely Stochastic Gradient Descent optimizer and Adam Optimizer, while others are PowerSign and AddSign optimizer. PowerSign and AddSign optimizer are methods to minimize cost, which discover by using Recurrent neural network(RNN) and Reinforcement Learning. A result demonstrates that a plane identification on Satellite imagery can be achieved by implementing the pre-trained model and obtains an exceptional result with Adam optimizer.