• Title/Summary/Keyword: Anomaly Segmentation

Search Result 12, Processing Time 0.017 seconds

A Study on the Air Pollution Monitoring Network Algorithm Using Deep Learning (심층신경망 모델을 이용한 대기오염망 자료확정 알고리즘 연구)

  • Lee, Seon-Woo;Yang, Ho-Jun;Lee, Mun-Hyung;Choi, Jung-Moo;Yun, Se-Hwan;Kwon, Jang-Woo;Park, Ji-Hoon;Jung, Dong-Hee;Shin, Hye-Jung
    • Journal of Convergence for Information Technology
    • /
    • v.11 no.11
    • /
    • pp.57-65
    • /
    • 2021
  • We propose a novel method to detect abnormal data of specific symptoms using deep learning in air pollution measurement system. Existing methods generally detect abnomal data by classifying data showing unusual patterns different from the existing time series data. However, these approaches have limitations in detecting specific symptoms. In this paper, we use DeepLab V3+ model mainly used for foreground segmentation of images, whose structure has been changed to handle one-dimensional data. Instead of images, the model receives time-series data from multiple sensors and can detect data showing specific symptoms. In addition, we improve model's performance by reducing the complexity of noisy form time series data by using 'piecewise aggregation approximation'. Through the experimental results, it can be confirmed that anomaly data detection can be performed successfully.

Aeromagnetic Pre-processing Software Based on Graphic User Interface, KMagLevellingTM (그래픽 사용자 인터페이스 기반 항공자력탐사 전처리 S/W, KMagLevellingTM)

  • Ko, Kwang-Beom;Jung, Sang-Won
    • Geophysics and Geophysical Exploration
    • /
    • v.17 no.3
    • /
    • pp.171-178
    • /
    • 2014
  • Aeromagnetic survey generally require much more pre-processing steps than that of common land survey due to several complex and cumbersome steps included in pre-processing stage. Therefore it is desirable to use specific processing tool especially based on graphic user interface. For this purpose, aeromagnetic pre-processing software based on graphic user interface under the Windows environment, called $KMagLevelling^{TM}$ was developed and briefly introduced. In an aspect of its user-friendliness and originality, three noticeable features of $KMagLevelling^{TM}$ are summarized as the following (1) function of representation and handling for large amount of aeromagnetic data set as a visualization in the form of flight-path (2) function of selective exclusion of unwanted data by using survey area information expressed as polygon, and (3) function of selective removal processing for the irregular flight-path data acquired within the entire survey area by implementing the segmentation of flight-path technique.