@article{ART003317699},
author={Kyeong-il Ko and Byeongbeom Kang and Hyun Yoe},
title={Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2026},
volume={31},
number={3},
pages={199-208}
TY - JOUR
AU - Kyeong-il Ko
AU - Byeongbeom Kang
AU - Hyun Yoe
TI - Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data
JO - Journal of The Korea Society of Computer and Information
PY - 2026
VL - 31
IS - 3
PB - The Korean Society Of Computer And Information
SP - 199
EP - 208
SN - 1598-849X
AB - Securing data quality is essential for precision environmental control in smart farms. In particular, data integrity is a prerequisite for ensuring the effectiveness of the recently established national standards, such as ‘Smart Greenhouse Sensor/Node Metadata (KS X 3269, KS X 3287).’ However, existing research has limitations in treating outliers uniformly without distinguishing their causes, which hinders control continuity. To address this, this study proposes an intelligent data cleaning framework that automatically classifies outliers into ‘transient outliers (noise)’ and ‘persistent outliers (failure)’ using an LSTM-based prediction model and time-series persistence analysis (K-Counter). The proposed method corrects transient outliers with predicted values to maintain data continuity, while for persistent outliers, it updates the node status to ‘ERROR’ in accordance with the KS X 3287 standard, thereby immediately excluding them from the control logic. Experimental results adhering to the KS X 3269 standard ranges demonstrated a classification accuracy of 98.1%. This study contributes to enhancing the interoperability and stability of national standard-based smart farm control systems.
KW - Smart Farm;Outlier Detection;Data Cleaning;KS Standards;LSTM;Time-Series Analysis
DO -
UR -
ER -
Kyeong-il Ko, Byeongbeom Kang and Hyun Yoe. (2026). Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data. Journal of The Korea Society of Computer and Information, 31(3), 199-208.
Kyeong-il Ko, Byeongbeom Kang and Hyun Yoe. 2026, "Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data", Journal of The Korea Society of Computer and Information, vol.31, no.3 pp.199-208.
Kyeong-il Ko, Byeongbeom Kang, Hyun Yoe "Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data" Journal of The Korea Society of Computer and Information 31.3 pp.199-208 (2026) : 199.
Kyeong-il Ko, Byeongbeom Kang, Hyun Yoe. Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data. 2026; 31(3), 199-208.
Kyeong-il Ko, Byeongbeom Kang and Hyun Yoe. "Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data" Journal of The Korea Society of Computer and Information 31, no.3 (2026) : 199-208.
Kyeong-il Ko; Byeongbeom Kang; Hyun Yoe. Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data. Journal of The Korea Society of Computer and Information, 31(3), 199-208.
Kyeong-il Ko; Byeongbeom Kang; Hyun Yoe. Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data. Journal of The Korea Society of Computer and Information. 2026; 31(3) 199-208.
Kyeong-il Ko, Byeongbeom Kang, Hyun Yoe. Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data. 2026; 31(3), 199-208.
Kyeong-il Ko, Byeongbeom Kang and Hyun Yoe. "Research on KS Standard-based Outlier Classification and Intelligent Cleaning Framework for Smart Greenhouse Sensor Data" Journal of The Korea Society of Computer and Information 31, no.3 (2026) : 199-208.
