KMITL

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

Browse

Settings

Start date: 2024Subject: search.filters.subject.ensemble method

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Virtue-Based Thai Folktale Recommendation with Ensemble LLMs
    (2026-06-16)
    Daeng-Am, Wassana
    ;
    Anuntachai, Anuntapat
    ;
    Netisopakul, Ponrudee
    Moral learning plays an important role in early childhood education, yet teachers often spend considerable time identifying moral lessons in stories and deciding which virtues they represent. This study investigates whether a multi-model ensemble strategy can produce more teacher-aligned moral extractions from Thai folktales than a single-LLM baseline. We propose an LLM-based ensemble framework that extracts concise moral statements and classifies them into eight core virtues promoted by the Thai Ministry of Education: diligence, frugality, honesty, discipline, politeness, cleanliness, unity, and kindness. The framework combines outputs from Google Gemini 2.0 Flash, OpenAI GPT-4o-mini, and Anthropic Claude 3.5 Sonnet through a semantic consensus mechanism using BGE-M3 embeddings and majority voting. The system is evaluated on a corpus of 200 Thai folktales annotated by three experienced early childhood educators using multi-label metrics including Hamming Loss, Jaccard Similarity, and Exact Match. The results show that the ensemble approach achieves a Hamming Loss of 0.208, Jaccard Similarity of 0.564, and Exact Match of 0.175, consistently outperforming all single-model baselines. These findings suggest that consensus-driven ensemble inference provides a more robust and teacher-aligned foundation for automated moral education tools in Thai NLP.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Ensemble of CNN classifiers using Choquet Fuzzy Integral Technique for PCB Defect Classification
    (2024-01-01)
    Purahong, Boonchana
    ;
    Krungseanmuang, Woranidtha
    ;
    Tenghongsakul, Kasi
    ;
    Archevapanich, Tuanjai
    ;
    Khunthawiwone, Parkpoom
    This paper presents a novel method for detecting defects in printed circuit boards (PCBs) using an ensemble of classifiers based on the Choquet fuzzy integral. Our approach employs convolutional neural network (CNN) models, specifically ResNet152, VGG19, and InceptionV3 as base classifiers to identify six types of PCB defects: spurs, mouse bites, short circuits, open circuits, spurious copper, and pinholes. Given the critical role of PCBs in ensuring electronic equipment reliability, effective defect detection methods like ours are essential. We employ pre-trained CNN models for feature extraction and classification of PCB defects. Following this, we combine the prediction scores using the Choquet fuzzy integral to derive more accurate final labels, exceeding the accuracy of standalone models. Our approach is tested on PCB images obtained from public repositories, captured using a linear scan CCD. The evaluation results demonstrate average precision, recall, F-score, and accuracy of 93.0%, 95.2%, 95.1%, and 95.1%, respectively.