KMITL

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

Browse

Settings

Subject: search.filters.subject.k-nearest neighbors

Search Results

Now showing 1 - 5 of 5
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An k-Nearest Neighbors Machine Learning Algorithm for the PM2.5 Early Warning System in Bang Khun Tian, Bangkok, Thailand
    (2024-12-02)
    Thongtha, Kaboon
    ;
    Pochai, Nopparat
    The problem of particulate matter with a diameter of less than 2.5-10 microns, such as PM2.5-PM10 in Bangkok, affects the health of people because there are small particles that can penetrate deep into the alveoli. If there is an early warning system to warn people about the harmful levels of PM2.5 in Bangkok, such as an early warning of 2-3 days, it can help the people have time to prevent themselves. In this research, an early warning system to warn people about the harmful levels of PM2.5 in Bangkok is proposed. The air quality data of the Bang Khun Tian station, Bangkok, for 2 months, from December 1, 2020, to January 31, 2021, were selected because the area is an air-quality-worrying area. A proposed early warning system for the harmful levels of PM2.5 around Bang Khun Tian, Bangkok, was developed using the k-nearest neighbors machine learning algorithm. As the results show, the proposed technique gives an agreeable prediction for the earliest warning by 4 days.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A PM2.5 Forewarning Algorithm Using k-Nearest Neighbors Machine Learning at Changpuek, Chiang Mai, Thailand
    (2023-08-29)
    Pochai, Nopparat
    ;
    Thongtha, Kaboon
    In Chiang Mai, Thailand, the air pollution issue caused by atmospheric particulate matter with a diameter of less than 2.5 μm, or PM2.5, has been identified as an ongoing crisis. PM2.5 not only has a direct impact on people's health and way of life, but it also has a negative impact on the national economy. Residents in such PM2.5-polluted locations are particularly susceptible to respiratory diseases, skin diseases, inflammatory eye diseases, and cardiovascular problems. As a result, this study is going to analyze PM2.5 data using the k-nearest neighbors machine learning algorithm as a guideline to warn people, particularly in Changpuek, Chiang Mai, Thailand, to handle the PM2.5 characterization problem.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Effect of noise signals on partial discharge classification models
    (2015-01-26)
    Pattanadech, Norasage
    ;
    Nimsanong, Phethai
    This document proposes the comparison of four statistical classification models for partial discharge (PD) classification as follows: k-nearest neighbors (KNN) model, probabilistic neural network (PNN) model, and other two statistical models using principal component analysis (PCA) for a data reduction approach combined with KNN and PNN models, so called, PCA-KNN model and PCA-PNN model. PD phenomena, corona at high voltage side in air (CHV), corona at low voltage side in air (CLV), surface discharge (SF), and internal discharge (IN) were simulated and measured in the shielding room. Electromagnetic wave due to PD phenomena was detected using a log-periodic antenna and recorded employing a spectrum analyzer. 80 experiments in total were performed for CHV, CLV, SF, and IN. The original independent variables for each classification model, skewness and kurtosis of each period of the captured signals, were calculated. Then, 60% of experimented data was used as a training data for the PD classification model. Another 40% experimented data was used to evaluate the performance of the designed PD classification models. Besides, noise signals were generated with computer program and trained into the PD classification model as well. The peak of noise signal was set up at 10%, 20% and 30% of the peak value of the PD signal. These noise signals were added with the PD signals to generate a mixed noise - PD signal. Then, the mixed noise - PD signals were used to evaluate the performance of the PD classification models. It was found that the designed KNN, PNN, PCA-KNN and PCA - PNN model can predict PD patterns without noise signal with the accuracy 100%. Noise signals with amplitude of 20% or more of peak value of PD signal have obviously influence the accuracy of PD pattern classification. The combination of PCA with KNN model can improve the ability of PD classification compared with KNN PD classification model. However, it seems that PCA provided negative effect when PCA was combined with PNN model and evaluated with the mixed-noise PD signals.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Effect of training methods on the accuracy of PCA-KNN partial discharge classification model
    (2015-01-26)
    Pattanadech, Norasage
    ;
    Nimsanong, Phethai
    The aim of this paper is to describe the effect of training methods on the accuracy of PCA-KNN partial discharge (PD) classification model. This model used principal component analysis (PCA) combined with k-nearest neighbor (KNN) model, so called, PCA-KNN PD classification model for PD pattern classification. PD phenomena, corona at high voltage side in air (CHV), corona at low voltage side in air (CLV), surface discharge (SF), and internal discharge (IN) were experimented in the shielding room. Electromagnetic wave due to PD phenomena was detected using a log-periodic antenna and recorded employing a spectrum analyzer. 80 PD experiments in total were performed. The original independent variables for the classification model, skewness and kurtosis of each period of the captured signals, were calculated. To study the effect of training methods: two patterns for data training, odd/even and block training methods were investigated. In case of the block training method, the effect of training data number can be examined as well. Besides, noise signals were generated with the computer program and trained into the PD classification models. The peak of noise signal was set up at 30% of the peak value of the PD signal. These noise signals were added with the PD signals to generated a mixed noise - PD signal. Then, the mixed noise - PD signals were used to evaluate the performance of the PCA-KNN PD classification model. It was found that the block data training method provided the higher accuracy PD classification compared with the odd/event data training method. The block training method with 80% training data/20% testing data gave the highest accuracy (95% correction) for PD classification without noise signal. However, this training technique provided the lowest accuracy (56.25% correction) for PD classification with the mixed noise-PD signals.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Fat detection algorithm for liver biopsy images
    (2014-10-15)
    Sumitpaibul, Pawesuda
    ;
    Damrongphithakkul, Anurak
    ;
    Watchareeruetai, Ukrit
    This paper presents an image-processing-based method for analyzing the fat proportion in liver biopsy images. Firstly, the proposed method extracts the area of candidate fat blobs, as well as the background area, from the input image. Then the features of each candidate blobs will be computed. Finally a classification technique called k-nearest neighbors is used to classify each candidate blob if it is fat. Experimental results show that the proposed method can detect fat in the liver biopsy images with the accuracy of 97.52%.