KMITL

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

Browse

Settings

Author: search.filters.author.Sangnark, SoravittHas files: No

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    EEG-BBNet: A Hybrid Framework for Brain Biometric Using Graph Connectivity
    (2025-01-01)
    Lakhan, Payongkit
    ;
    Banluesombatkul, Nannapas
    ;
    Sricom, Natchaya
    ;
    Sawangjai, Phattarapong
    ;
    Sangnark, Soravitt
    Most EEG-based biometrics rely on either convolutional neural networks (CNNs) or graph convolutional neural networks (GCNNs) for personal authentication, potentially overlooking the limitations of each approach. To address this, we propose EEG-BBNet, a hybrid network that combines CNNs and GCNNs. EEG-BBNet leverages CNN’s capability for automatic feature extraction and the GCNN’s ability to learn connectivity patterns between EEG electrodes through graph representation. We evaluate its performance against solely CNN-based and graph-based models across three brain–computer interface tasks, focusing on daily motor and sensory activities. The results show that while EEG-BBNet with Rho index functional connectivity metric outperforms graph-based models, it initially lags behind CNN-based models. However, with additional fine-tuning, EEG-BBNet surpasses CNN-based models, achieving a correct recognition rate of approximately 90%. This improvement enables EEG-BBNet to adapt its learning in new sessions and to acquire different domain knowledge across various BCI tasks (e.g., motor imagery to steady-state visually evoked potentials), demonstrating promise for practical authentication.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Thai music emotion recognition by linear regression
    (2018-10-12)
    Sangnark, Soravitt
    ;
    Lertwatechakul, Mayuree
    ;
    Benjangkaprasert, Chawalit
    Music emotion recognition has rapidly grown in the present because the listener’s behavior is changing. Therefore, music emotion recognition helps to understand the emotion of music, listener, and support many careers in the music industry including general people. Many researchers have studied western music, but a few studied Thai music. In this work, we are interested to use 155 popular Thai music for explore emotion and use valence-arousal(energy) values from Spotify API to investigate the results. We select multiple linear regression (MLR) and support vector regression (SVR), kinds of ‘Linear’ function for valence-arousal values prediction. Experimental results demonstrate that the multiple linear regression provides highest accuracy (61.29%), precision (65%), recall (61%) and f-measure (60%) which is more than support vector regression.