KMITL

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

Browse

Settings

Subject: search.filters.subject.MATLAB

Search Results

Now showing 1 - 5 of 5
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Baseline Performance of Pre-trained Models on Movie Genre Classification from Spectrograms
    (2025-04-01)
    Visutsak, Porawat
    ;
    Treeraphapkajondet, Kavin
    ;
    Sakphet, Visaroot
    ;
    Nitinuntatip, Wachirawit
    ;
    Satthong, Pawwinkan
    This study investigates the use of deep learning for classifying movie genres based on audio spectrograms. We construct a dataset of movie trailers, transform them into spectrograms, and label them by genre. Then, we utilize MATLAB's pre-trained convolutional neural networks (CNNs) for classification, comparing the performance of 9 different architectures, including MobileNet-v2, RestNet-18, DenseNet-201, Places365-GoogLeNet, VGG-16, VGG-19, Inception-RestNet-v2, Inception-v3, and NASANet-Mobile. We evaluated all models based on their ability to classify movie trailers into five genres: action, romance, drama, comedy, and thriller. Our results, based on accuracy and F1-score across genres, indicate that VGG16 achieves the highest overall performance with an accuracy of 86.27%, an F1-score of 86.69%, a recall of 86.87%, and a precision of 87.28%. This research demonstrates the potential of leveraging pre-trained CNNs, particularly VGG-16, for effcient and effective audio-based genre classification in movie trailers.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Deep Learning for Arm Movement Simulation with EMG Signals
    (2025-01-01)
    Boonyasurat, Kongkridakorn
    ;
    Htunn, Sue Sha
    This paper presents a real-time electromyography (EMG)-based arm movement detection system using deep learning for prosthetics and rehabilitation. Dual-channel EMG sensors capture grip and release actions, processed through hardware-level thresholding. A CNN-BiLSTM model classifies the signals, and real-time hand animation is rendered via MATLAB SynGrasp. Thresholding was chosen over raw analog processing due to noise, grounding issues, and signal instability. The system demonstrates high classification accuracy, low latency, and robust real-world performance.
      1
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Uncertainty Quantification Code Written in MATLAB
    (2024-01-01)
    Suratemeekul, Napat
    ;
    Kumkam, Noppawit
    ;
    Sleesongsom, Suwin
    This research presents examples of MATLAB code for a classroom of uncertainty quantification. The codes are developed for educational purposes and newcomers or researchers. Demonstration codes are presented in form of a general design conditions. Examples are chosen from mechanical components, which are simply understood. The mechanical components are shafts, connecting rod, rear shaft housing, and bolt etc. The quantification techniques are in the group of probabilistic such as Monte Carlo Simulation (MCS) and Latin Hypercube Sampling (LHS). These examples can help the newcomers to understand the difficulty in uncertainty quantify and extend to calculate reliability value and probability of failure. Example computer codes are included in all parts.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    The effects of multi-distributed generator on distribution system reliability
    (2018-06-08)
    Ngaopitakkul, A.
    ;
    Jettanasen, C.
    The paper investigates on the effects of multi- distributed generators (multi-DG) integrated to distribution system in terms of reliability indices. The distributed generators (DGs) under this study are solar photovoltaic (PV) connected to a 22 kV distribution system. In addition, it presents to determine the system average interruption frequency index (SAIFI), the system average interruption duration index (SAIDI) and outage cost as reliability indices by comparing the SAIFI, SAIDI and outage cost (ECOST) of the cases that multi-DG is connected to a distribution system. The reliability indices will be calculated using data obtaining from simulation and analysis of power distribution system model created in DIgSILENT PowerFactory. The overall results can be summarized by focusing on the capacity of DGs and the location of DGs, which are important factors capable of affecting the reliability indices.
      1
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Servo state feedback control of the self balancing robot using MATLAB
    (2012-12-01)
    Kongratana, V.
    ;
    Gulphanich, S.
    ;
    Tipsuwanporn, V.
    ;
    Huantham, P.
    In this paper, the servo state feedback control of the self balancing robot is proposed. Balancing robot system to control is used ADXL3xx accelerometer as sensors to measure the angle and angle changes and then sends signals to the Servo motor for robot can balance the stability, respectively. Self Balancing robot control are application of MATLAB / Simulink program which served to simulation the process system and control self balancing robot in real-time by FiO board. More importantly, the robot system use Servo state feedback control that is implemented on FiO Board. Finally, the results from simulation with the experimental results from to comparison. The results shown that servo state feedback control system designed and implement to the FiO Board can stabilize the self balancing robot are satisfied. © 2012 ICROS.