Chapter Early Detection and Reconstruction of Abnormal Data Using Hybrid VAE-LSTM Framework

Early failure detection and abnormal data reconstruction in sensor data provided by building ventilation control systems are critical for public health. Early detection of abnormal data can help prevent failures in crucial components of ventilation systems, which can result in a variety of issues, f...

पूर्ण विवरण

में बचाया:
ग्रंथसूची विवरण
मुख्य लेखकों: Hou, Fangli, Ma, Jun, Cheng, Jack C. P., Kwok, Helen H.L.
स्वरूप: Online
भाषा:अंग्रेज़ी
प्रकाशित: Firenze University Press 2024
विषय:
ऑनलाइन पहुंच:ONIX_20240402_9791221502893_8
टैग: टैग जोड़ें
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
_version_ 1869526575610855424
author Hou, Fangli
Ma, Jun
Cheng, Jack C. P.
Kwok, Helen H.L.
author_browse Cheng, Jack C. P.
Hou, Fangli
Kwok, Helen H.L.
Ma, Jun
author_facet Hou, Fangli
Ma, Jun
Cheng, Jack C. P.
Kwok, Helen H.L.
author_sort Hou, Fangli
collection Directory of Open Access Books
description Early failure detection and abnormal data reconstruction in sensor data provided by building ventilation control systems are critical for public health. Early detection of abnormal data can help prevent failures in crucial components of ventilation systems, which can result in a variety of issues, from energy wastage to catastrophic outcomes. However, conventional fault detection models ignore valuable features of dynamic fluctuations in indoor air quality (IAQ) measurements and early warning signals of faulty sensor data. This study introduces a hybrid framework for early failure detection and abnormal data reconstruction applying variance analysis and variational autoencoders (VAE) coupled with the long short-term memory network (VAE-LSTM). The periodicity and stable fluctuation of IAQ data are exploited by variance analysis to detect unusual variations before failure occurs. The IAQ dataset which is corrupted by introducing complete failure, bias failure and precision degradation fault is then used to verify the feasibility of the VAE-LSTM model. The results of variance analysis reveal that unusual behavior of the data can be detected as early as 12 hours before failure occurs. The reconstruction performance of the developed method is shown to be superior to other methods under different abnormal data scenarios
format Online
id doab-20.500.12854ir-136084
institution Directory of Open Access Books
language eng
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Firenze University Press
publisherStr Firenze University Press
record_format ojs
spelling doab-20.500.12854ir-1360842025-07-18T09:46:45Z Chapter Early Detection and Reconstruction of Abnormal Data Using Hybrid VAE-LSTM Framework Hou, Fangli Ma, Jun Cheng, Jack C. P. Kwok, Helen H.L. Early failure detection Abnormal data reconstruction Variational autoencoder (VAE) Long short-term memory network (LSTM) Sustainable IAQ management thema EDItEUR::U Computing and Information Technology thema EDItEUR::U Computing and Information Technology Early failure detection and abnormal data reconstruction in sensor data provided by building ventilation control systems are critical for public health. Early detection of abnormal data can help prevent failures in crucial components of ventilation systems, which can result in a variety of issues, from energy wastage to catastrophic outcomes. However, conventional fault detection models ignore valuable features of dynamic fluctuations in indoor air quality (IAQ) measurements and early warning signals of faulty sensor data. This study introduces a hybrid framework for early failure detection and abnormal data reconstruction applying variance analysis and variational autoencoders (VAE) coupled with the long short-term memory network (VAE-LSTM). The periodicity and stable fluctuation of IAQ data are exploited by variance analysis to detect unusual variations before failure occurs. The IAQ dataset which is corrupted by introducing complete failure, bias failure and precision degradation fault is then used to verify the feasibility of the VAE-LSTM model. The results of variance analysis reveal that unusual behavior of the data can be detected as early as 12 hours before failure occurs. The reconstruction performance of the developed method is shown to be superior to other methods under different abnormal data scenarios 2024-04-04T04:15:30Z 2024-04-04T04:15:30Z 2024-04-02T15:44:27Z 2023 chapter ONIX_20240402_9791221502893_8 2704-5846 https://library.oapen.org/handle/20.500.12657/89039 9791221502893 https://directory.doabooks.org/handle/20.500.12854/136084 eng Proceedings e report open access image/jpeg n/a https://library.oapen.org/bitstream/20.500.12657/89039/1/9791221502893_93.pdf Firenze University Press 10.36253/979-12-215-0289-3.93 10.36253/979-12-215-0289-3.93 2ec4474d-93b1-4cfa-b313-9c6019b51b1a 9791221502893 10 Florence open access
spellingShingle Early failure detection
Abnormal data reconstruction
Variational autoencoder (VAE)
Long short-term memory network (LSTM)
Sustainable IAQ management
thema EDItEUR::U Computing and Information Technology
thema EDItEUR::U Computing and Information Technology
Hou, Fangli
Ma, Jun
Cheng, Jack C. P.
Kwok, Helen H.L.
Chapter Early Detection and Reconstruction of Abnormal Data Using Hybrid VAE-LSTM Framework
title Chapter Early Detection and Reconstruction of Abnormal Data Using Hybrid VAE-LSTM Framework
title_full Chapter Early Detection and Reconstruction of Abnormal Data Using Hybrid VAE-LSTM Framework
title_fullStr Chapter Early Detection and Reconstruction of Abnormal Data Using Hybrid VAE-LSTM Framework
title_full_unstemmed Chapter Early Detection and Reconstruction of Abnormal Data Using Hybrid VAE-LSTM Framework
title_short Chapter Early Detection and Reconstruction of Abnormal Data Using Hybrid VAE-LSTM Framework
title_sort chapter early detection and reconstruction of abnormal data using hybrid vae lstm framework
topic Early failure detection
Abnormal data reconstruction
Variational autoencoder (VAE)
Long short-term memory network (LSTM)
Sustainable IAQ management
thema EDItEUR::U Computing and Information Technology
thema EDItEUR::U Computing and Information Technology
topic_facet Early failure detection
Abnormal data reconstruction
Variational autoencoder (VAE)
Long short-term memory network (LSTM)
Sustainable IAQ management
thema EDItEUR::U Computing and Information Technology
thema EDItEUR::U Computing and Information Technology
url ONIX_20240402_9791221502893_8
work_keys_str_mv AT houfangli chapterearlydetectionandreconstructionofabnormaldatausinghybridvaelstmframework
AT majun chapterearlydetectionandreconstructionofabnormaldatausinghybridvaelstmframework
AT chengjackcp chapterearlydetectionandreconstructionofabnormaldatausinghybridvaelstmframework
AT kwokhelenhl chapterearlydetectionandreconstructionofabnormaldatausinghybridvaelstmframework