The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
스마트 공간의 사물인터넷(IoT) 기기에서 생성된 데이터는 상황 인식, 서비스 추천, 이상 탐지 등 다양한 분야에 활용됩니다. 그러나 IoT 장치의 데이터 스트림에서 누락된 값은 다양한 데이터 스트림의 다양한 누락 패턴과 이질적인 데이터 유형으로 인해 여전히 어려운 문제로 남아 있습니다. 이에, 여러 IoT 디바이스가 설치된 스마트 공간에서 수집된 데이터 세트를 분석하던 중, 기존 결측값 패턴과 사뭇 다른 연속 결측 패턴을 발견했습니다. 패턴에는 몇 초에서 최대 몇 시간에 걸쳐 연속된 누락 값 블록이 있습니다. 따라서 패턴은 IoT 애플리케이션의 가용성과 안정성에 중요한 요소입니다. 그러나 기존의 결측값 대치 방법으로는 해결할 수 없습니다. 따라서 연속 결측 패턴의 결측값 대치를 위한 새로운 접근 방식이 필요합니다. 하나의 데이터 스트림에서 연속 결측 패턴의 결측값이 발생하더라도 이 데이터 스트림과 상관관계가 있는 다른 데이터 스트림을 학습함으로써 결측값 대치가 가능하다는 점을 고려하였다. 연속 결측 패턴 문제의 결측값을 해결하기 위해 스마트 공간 내 다수의 IoT 데이터 스트림을 분석하고, 스마트 공간 내 IoT 디바이스의 데이터 스트림 간 상호의존성인 이들 간의 상관관계를 파악하였다. 연속 결측 패턴의 결측값을 귀속시키기 위해 스마트 공간에서 상관 정보를 활용한 딥러닝 기반 결측값 대치 모델, 즉 DeepIN(Deep Imputation Network)을 제안한다. DeepIN은 각 IoT 데이터 스트림의 상관 정보에 따라 여러 개의 장단기 메모리가 구성되는 방식을 사용합니다. 우리는 캠퍼스 IoT 테스트베드의 실제 데이터 세트에서 DeepIN을 평가했으며, 실험 결과에 따르면 우리가 제안한 접근 방식이 최첨단 결측값 대치 알고리즘에 비해 대치 성능을 57.36% 향상시키는 것으로 나타났습니다. 따라서 우리의 접근 방식은 IoT 환경에서 장기적인 값 블록이 누락된 경우에도 평균적으로 합리적인 결측값 대치 정확도(80~85%)로 IoT 애플리케이션 및 서비스를 가능하게 하는 유망한 방법론이 될 수 있습니다.
Minseok LEE
KAIST
Jihoon AN
KAIST
Younghee LEE
KAIST
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Minseok LEE, Jihoon AN, Younghee LEE, "Missing-Value Imputation of Continuous Missing Based on Deep Imputation Network Using Correlations among Multiple IoT Data Streams in a Smart Space" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 2, pp. 289-298, February 2019, doi: 10.1587/transinf.2018EDP7257.
Abstract: Data generated from the Internet of Things (IoT) devices in smart spaces are utilized in a variety of fields such as context recognition, service recommendation, and anomaly detection. However, the missing values in the data streams of the IoT devices remain a challenging problem owing to various missing patterns and heterogeneous data types from many different data streams. In this regard, while we were analyzing the dataset collected from a smart space with multiple IoT devices, we found a continuous missing pattern that is quite different from the existing missing-value patterns. The pattern has blocks of consecutive missing values over a few seconds and up to a few hours. Therefore, the pattern is a vital factor to the availability and reliability of IoT applications; yet, it cannot be solved by the existing missing-value imputation methods. Therefore, a novel approach for missing-value imputation of the continuous missing pattern is required. We deliberate that even if the missing values of the continuous missing pattern occur in one data stream, missing-values imputation is possible through learning other data streams correlated with this data stream. To solve the missing values of the continuous missing pattern problem, we analyzed multiple IoT data streams in a smart space and figured out the correlations between them that are the interdependencies among the data streams of the IoT devices in a smart space. To impute missing values of the continuous missing pattern, we propose a deep learning-based missing-value imputation model exploiting correlation information, namely, the deep imputation network (DeepIN), in a smart space. The DeepIN uses that multiple long short-term memories are constructed according to the correlation information of each IoT data stream. We evaluated the DeepIN on a real dataset from our campus IoT testbed, and the experimental results show that our proposed approach improves the imputation performance by 57.36% over the state-of-the-art missing-value imputation algorithm. Thus, our approach can be a promising methodology that enables IoT applications and services with a reasonable missing-value imputation accuracy (80∼85%) on average, even if a long-term block of values is missing in IoT environments.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7257/_p
부
@ARTICLE{e102-d_2_289,
author={Minseok LEE, Jihoon AN, Younghee LEE, },
journal={IEICE TRANSACTIONS on Information},
title={Missing-Value Imputation of Continuous Missing Based on Deep Imputation Network Using Correlations among Multiple IoT Data Streams in a Smart Space},
year={2019},
volume={E102-D},
number={2},
pages={289-298},
abstract={Data generated from the Internet of Things (IoT) devices in smart spaces are utilized in a variety of fields such as context recognition, service recommendation, and anomaly detection. However, the missing values in the data streams of the IoT devices remain a challenging problem owing to various missing patterns and heterogeneous data types from many different data streams. In this regard, while we were analyzing the dataset collected from a smart space with multiple IoT devices, we found a continuous missing pattern that is quite different from the existing missing-value patterns. The pattern has blocks of consecutive missing values over a few seconds and up to a few hours. Therefore, the pattern is a vital factor to the availability and reliability of IoT applications; yet, it cannot be solved by the existing missing-value imputation methods. Therefore, a novel approach for missing-value imputation of the continuous missing pattern is required. We deliberate that even if the missing values of the continuous missing pattern occur in one data stream, missing-values imputation is possible through learning other data streams correlated with this data stream. To solve the missing values of the continuous missing pattern problem, we analyzed multiple IoT data streams in a smart space and figured out the correlations between them that are the interdependencies among the data streams of the IoT devices in a smart space. To impute missing values of the continuous missing pattern, we propose a deep learning-based missing-value imputation model exploiting correlation information, namely, the deep imputation network (DeepIN), in a smart space. The DeepIN uses that multiple long short-term memories are constructed according to the correlation information of each IoT data stream. We evaluated the DeepIN on a real dataset from our campus IoT testbed, and the experimental results show that our proposed approach improves the imputation performance by 57.36% over the state-of-the-art missing-value imputation algorithm. Thus, our approach can be a promising methodology that enables IoT applications and services with a reasonable missing-value imputation accuracy (80∼85%) on average, even if a long-term block of values is missing in IoT environments.},
keywords={},
doi={10.1587/transinf.2018EDP7257},
ISSN={1745-1361},
month={February},}
부
TY - JOUR
TI - Missing-Value Imputation of Continuous Missing Based on Deep Imputation Network Using Correlations among Multiple IoT Data Streams in a Smart Space
T2 - IEICE TRANSACTIONS on Information
SP - 289
EP - 298
AU - Minseok LEE
AU - Jihoon AN
AU - Younghee LEE
PY - 2019
DO - 10.1587/transinf.2018EDP7257
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2019
AB - Data generated from the Internet of Things (IoT) devices in smart spaces are utilized in a variety of fields such as context recognition, service recommendation, and anomaly detection. However, the missing values in the data streams of the IoT devices remain a challenging problem owing to various missing patterns and heterogeneous data types from many different data streams. In this regard, while we were analyzing the dataset collected from a smart space with multiple IoT devices, we found a continuous missing pattern that is quite different from the existing missing-value patterns. The pattern has blocks of consecutive missing values over a few seconds and up to a few hours. Therefore, the pattern is a vital factor to the availability and reliability of IoT applications; yet, it cannot be solved by the existing missing-value imputation methods. Therefore, a novel approach for missing-value imputation of the continuous missing pattern is required. We deliberate that even if the missing values of the continuous missing pattern occur in one data stream, missing-values imputation is possible through learning other data streams correlated with this data stream. To solve the missing values of the continuous missing pattern problem, we analyzed multiple IoT data streams in a smart space and figured out the correlations between them that are the interdependencies among the data streams of the IoT devices in a smart space. To impute missing values of the continuous missing pattern, we propose a deep learning-based missing-value imputation model exploiting correlation information, namely, the deep imputation network (DeepIN), in a smart space. The DeepIN uses that multiple long short-term memories are constructed according to the correlation information of each IoT data stream. We evaluated the DeepIN on a real dataset from our campus IoT testbed, and the experimental results show that our proposed approach improves the imputation performance by 57.36% over the state-of-the-art missing-value imputation algorithm. Thus, our approach can be a promising methodology that enables IoT applications and services with a reasonable missing-value imputation accuracy (80∼85%) on average, even if a long-term block of values is missing in IoT environments.
ER -