KMITL

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

Browse

Settings

Author: search.filters.author.Chalapat, KhattiyaSubject: search.filters.subject.electronic nose

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A Hybrid of Shallow and Deep Learning for Odor Classification Based on Adaptive Boosting
    (2019-11-01)
    Grodniyomchai, Boonyawee
    ;
    Chalapat, Khattiya
    ;
    Jitkajornwanich, Kulsawasd
    ;
    Jaiyen, Saichon
    An electronic nose is very useful for identifying an odor that is harmful to humans. To get the most accurate odor predictions from an electronic nose, we combined the models of traditional machine learning and deep learning, including deep neural network (DNN), support vector machine (SVM) and decision tree, to make a new hybrid model that adopts the AdaBoost algorithm to adjust the weights of weak classifiers to build a strong classifier using odor data. Experimental results from our model were compared with other models, including a single deep neural network, an ensemble of SVM models and an ensemble of decision trees. Our model achieved an averaged accuracy of 99.58%, which is better than other models, and the standard deviation, 0.67%, is also less than other models.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A deep learning model for odor classification using deep neural network
    (2019-07-01)
    Grodniyomchai, Boonyawee
    ;
    Chalapat, Khattiya
    ;
    Jitkajornwanich, Kulsawasd
    ;
    Jaiyen, Saichon
    The odor is an environment that surrounds us. However, to identify the odor by using the human nose in order to prove the odor is very dangerous. Therefore, the artificial intelligent (AI) system should be built based on machine learning in order to achieve more accurate results. This research adopts the Deep Neural Network (DNN) model to identify some types of odor including odorless, beer odor, whisky odor, and wine odor. Each contains 60 instances that are obtained from seven sensors of the electronic nose. The experiments are conducted, and the results are compared to the comparative machine learning methods including Multilayer Perceptron (MLP), Decision Tree and Naïve Bayes (NB). From the experimental results, it can signify that the proposed deep learning model can achieve the best average accuracy.