Poonpakdee, Pasu

Loading...
Thumbnail Image
Preferred name
Poonpakdee, Pasu
Alternative Name
Poonpakdee, P.
Main Affiliation
Email
pasu.po@kmitl.ac.th

Settings

Now showing 1 - 5 of 5
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Interpretable ANN-Based Computer Vision System for Mangosteen Ripeness Detection for Export Markets
    (2026-01-21)
    Lapcharoensuk, Ravipat
    ;
    Tosribunjerd, Naphon
    ;
    Poonpakdee, Pasu
    Mangosteen is a high-value tropical fruit widely consumed and exported from Thailand. Mangosteen ripeness classification is crucial for export quality control, but manual grading leads to inconsistency and inefficiency. This study presents a computer vision system using an Artificial neural network to classify mangosteen into ripe, semi-ripe, and unripe stages based on peel color. A dataset of 378 images was collected and processed to extract 40 color-based features across multiple color spaces. Principal Component Analysis demonstrated non-linear separability among the ripeness classes. SMOTE and Gaussian noise augmentation were used to tackle data imbalance and enhance generalizability. The model reached a 95% accuracy rate and displayed flawless precision and recall for the ripe class. Integrated Gradients analysis highlighted the importance of the red-green color component (CIELAB a*) in the classification process. The proposed method demonstrates a low-cost, interpretable, and efficient solution suitable for real-world application in the mangosteen export industry.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Heat Transfer Intensification in a Heat Exchanger by Means of Twisted Tapes in Rib and Sawtooth Forms
    (2022-12-01)
    Poonpakdee, Pasu
    ;
    Samutpraphut, Boonsong
    ;
    Thianpong, Chinaruk
    ;
    Chokphoemphun, Suriya
    ;
    Eiamsa-ard, Smith
    This experimental study aimed to intensify the aerothermal performance index (API) in a round tube heat exchanger employing twisted tapes in rib and sawtooth forms (TTRSs) as swirl/vortex flow generators. The TTRSs have a constant twist ratio of 3.0, a constant rib pitch ratio (p/e) of 1.0, and six different sawtooth angles (α = 20°, 30°, 40°, 50°, 60°, and 70°). Experiments were carried out in an open flow using air as the working fluid for Reynolds numbers between 6000 and 20,000 in the current study, which was conducted in a heated tube under conditions of uniform wall heat flux. A typical twisted tape (TT) was also tested for comparison. The experimental results suggest that TTRSs yield Nusselt numbers ranging from 1.42 to 2.10 times of those of a plain tube. TTRSs with larger sawtooth angles (α) offer superior heat transfer. The TTRSs with α = 20°, 30°, 40°, 50°, 60°, and 70° respectively, enhance average Nusselt numbers by 158%, 162%, 166%, 172%, 180%, and 187% with average friction factors of 3.51, 3.55, 3.60, 3.67, 3.75 and 3.82 times higher than a plain tube. Additionally, TTRSs with sawtooth angles (α) of 20°, 30°, 40°, 50°, 60°, and 70° offer APIs in the ranges of 0.99 to 1.19, 1.01 to 1.21, 1.03 to 1.26, 1.05 to 1.31, 1.07 to 1.42, and 1.09 to 1.48, respectively, which are higher than those of the typical twisted tape (TT) by around 5%, 7%, 11%, 16%, 25%, and 31%, respectively. This demonstrates that twisted tapes in rib and sawtooth form (TTRSs), with appropriate geometries, give a promising trade-off between enhanced heat transfer and an increased friction loss penalty.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Global Convergence Detection in Decentralized IoT Networks based on Epidemic Approach
    (2024-01-01)
    Poonpakdee, Pasu
    ;
    Pongnukrohsiri, Ananyalux
    ;
    Santangjai, Chaiyaporn
    The concept of decentralization has involved in the varieties of the research area including computer science, management, politics. Bitcoin is the first cryptocurrency that indicates the power of decentralization from blockchain, the emergence of blockchain has established a new solution to solve the problem in centralization. The technology avoids the centralized controller and creates a trusted network in which all participants have a right to verify the information that flows all over the network. Considering the network layer of system architecture, an important aspect of any decentralized distributed systems including blockchain is the epidemic (gossip-based) protocols which maintain the network consistency properties namely, robustness, scalability, convergence speed, and accuracy, across the distributed systems. Epidemic protocols are bio-inspired paradigm that provides randomized communication and computation for extreme-scale networked systems. However, one of the drawback of Epidemic protocol is that each node receives multiple duplicated data with high traffic in the data transmission of data can cause high bandwidth in the network. The ability to extract relevant data from an enormous amount of data which is distributed in the network is necessary. In previous research, local convergence detection is proposed to detect global convergence for a given approximation error of the aggregation estimation. This work adapts the concept of local convergence detection to epidemic aggregation protocols to the scenario of decentralized IoT network architecture and evaluates with the standard benchmark. The results show that the adapted protocols can adjust themselves to be capable of dynamic conditions regarding global convergence.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Experimental Verification of Control Strategies for Satellite Magnetic-Based Attitude Control System Under a Three-Axis Helmholtz Cage Environment
    (2023-01-01)
    Panyalert, Thanayuth
    ;
    Manuthasna, Shariff
    ;
    Chaisakulsurin, Jormpon
    ;
    Masri, Tanawish
    ;
    Palee, Kritsada
    During satellite mission planning and operation, the main function of the satellite's attitude determination and control subsystem (ADCS) is to gather information about the satellite's orientation relative to the inertial reference frame. Additionally, this subsystem generates control actions that produce the required torques for adjusting the satellite's orientation, particularly in the context of the Low-Earth Orbit (LEO) regime. This paper focuses on the satellite three-axis attitude control problem for a de-tumbling mode of spacecraft using only magnetorquers as actuators under the presence of noise and investigates their performance through Hardware-in-the-Loop simulation (HiLs) tests, which consisted of a relative Earth's magnetic field generator along with the SGP-4-based satellite orbital propagator high-level control software. The design, development, and verification of proposed satellite attitude control system (ACS) strategies are presented. In detail, as an example of experimentation, the classical B-dot control algorithm is used for the de-tumbling mode to stabilize and reduce the angular rate, along with the pointing algorithm for orienting the satellite to the desired attitude. Then, a cascade Proportional-Integral-Derivative (PID) is implemented to generate enough torque through the three-axis magnetorquers on the frictionless air-bearing platform to verify the performance of the controller using an onboard computer. Finally, the effectiveness of the co-simulation tested as the primary experiment was confirmed through the integrated simulation process.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Estimation of the Weight and Volume of Lime (Citrus aurantifolia (Christm.) Swingle) Fruit Using Computer Vision Based on Traditional Machine Learning and Deep Learning
    (2024-10-01)
    Onmankhong, Jiraporn
    ;
    Poonpakdee, Pasu
    ;
    Lapcharoensuk, Ravipat
    The post-harvest process is important to increasing the market value of limes and requires focus. During this process, limes are graded and categorized based on size, weight, and volume. Therefore, identifying efficient means of estimating these properties is very important and remains an open research area. This study applies the concept of computer vision based on traditional machine learning algorithms (partial least square regression (PLS), epsilon-support vector regression (ε-SVR), decision tree (DT), random forest (RF), adaptive boosting (AB), gradient boosting (GB), Bagging meta-estimator (BME), and extremely randomized trees (ERTs)) and pre-trained deep learning (InceptionV3, MoblieNetV2, ResNet50, and VGG-16) for estimating the weight and volume of limes. Our findings showed that the BME and ResNet50 could yield the highest performance for estimating the weight and volume of limes. The BME produced (Formula presented.) values of 0.954 and 0.882 for weight and volume, respectively, while the (Formula presented.) values of ResNet50 models were between 0.951 and 0.957 for weight and volume, respectively. This study concluded that computer vision based on both traditional machine learning and deep learning could be used to estimate the weight and volume of limes. The approach proposed in this study can be adopted for applications related to computer vision in the post-harvest process.