KMITL

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

Browse

Settings

Subject: search.filters.subject.Support Vector Regression

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    DEVELOPING A MACHINE LEARNING FORECASTING FRAMEWORK FOR EXCHANGE RATES IN THE CONTEXT OF CROSS-BORDER BUSINESS
    (2025-01-01)
    Chen, Wei
    ;
    Rojniruttikul, Nuttawut
    Traditionally, this matter was regarded as a largely technical undertaking; however, recent market disruptions have demonstrated that the issue extends far beyond purely technical considerations. This study addresses the subject from two interconnected perspectives. The first concern centers upon the capacity of different Machine Learning (ML) models to maintain performance during periods in which financial markets deviate from conventional behavioural patterns. The second concern focuses on the way professionals who depend upon such predictive outputs interpret, evaluate, and integrate these forecasts into routine operational decision-making. The empirical findings revealed that several ML approaches, particularly Long Short-Term Memory (LSTM) architectures and selected ensemble-based methods, adapted more consistently to abrupt market fluctuations than the econometric benchmark models employed within the study. Such resilience became especially apparent throughout the COVID-19 crisis, when exchange-rate dynamics departed substantially from the assumptions underpinning traditional forecasting frameworks. The interview findings produced a somewhat different perspective. Although most practitioners recognised the practical potential associated with ML-driven forecasting systems, their evaluations remained notably cautious. Collectively, these findings suggest that high predictive performance alone is insufficient to secure widespread organisational acceptance of ML applications within cross-border commercial activities. For these systems to become genuinely effective, they must integrate smoothly into existing organisational procedures and risk-management cultures while remaining comprehensible to end users. Consequently, effective forecasting frameworks should not only possess strong technical capability but must also remain interpretable, adaptable, and sufficiently resilient to withstand major structural transformations within financial markets.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Machine learning approach in predicting post-transfusion packed cell volume in anemic dogs
    (2018-08-13)
    Srinilta, Chutimet
    ;
    Sunhem, Wisuwat
    ;
    Sangunwong, Pongsak
    ;
    Chanchartree, Satthathan
    Blood transfusion is commonly used to treat anemia. Blood transfusion is vital to life in many cases. Blood donation is a voluntary activity. In Thailand, blood supply for small animals are very limited. Therefore, blood must be used with extra care to save as many lives as possible. Success of whole blood transfusion where all blood components are transfused is determined by the rise of Packed Cell Volume (PCV) after transfusion. Veterinarians rely on formula to estimate the transfusion volume that can raise patient's PCV to the target. This paper attempted to use machine learning models to predict post-transfusion PCV in anemic dogs. Linear regression, XGBoost and Support Vector Regression algorithms were used in machine learning prediction models. Transfusion records from Kasetsart University Veterinary Teaching Hospital at Hua Hin were employed to assess model performance. The formula commonly used by veterinarians was performance comparison baseline. Wilcoxon signed-rank test was used to assess significant differences of the result. It was statistically confirmed with confidence interval of 90% that Support Vector Regression performed better than the baseline method on conventional input set alone and when certain red blood cell attributes were added to the conventional input set.