A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Imputing missing indoor air quality data with inverse mapping generative adversarial network
https://orcid.org/0000-0001-7864-9297
https://orcid.org/0000-0002-7443-6267
https://orcid.org/0000-0002-2044-0965
https://orcid.org/0000-0001-9897-1953
https://orcid.org/0000-0003-1237-0079
https://orcid.org/0000-0001-6279-2988
Abstract Sensors deployed all over the buildings are nowadays collecting a large amount of data, such as the Indoor Air Quality (IAQ) data which can provide valuable suggestions on improving indoor environments and energy consumption strategies. However, as treated as Multivariate Time Series (MTS), IAQ data often contain missing values that severely limit further analysis on them. Unfortunately, most of the existing methods fail to handle a couple of technical issues due to the complexity of MTS data, such as data distribution approximation, removing the redundancy, and so on. In this paper, we formulate the IAQ missing data imputation problem and propose an Inverse Mapping Generative Adversarial Network (IM-GAN) to tackle that problem. IM-GAN takes advantage of Bi-directional Recurrent Neural Network (BRNN), Denoising Auto-Encoder (DAE), and Generative Adversarial Network (GAN) to overcome the aforementioned technical issues. To validate the effectiveness of our proposed IM-GAN, we conduct comprehensive experiments on two public IAQ datasets GAMS and Gainesville. Results show that our IM-GAN achieves the new state-of-the-art performance in accurately estimating missing values in indoor air quality time series data, with the average performance of 0.1566 and 0.0789 in terms of Mean Relative Error, and 17.2884 and 2.7434 in terms of Mean Absolute Error on GAMS and Gainesville respectively at different missing rates. Our ablation study and visualization also validate that IM-GAN effectively overcomes the aforementioned technical issues by capturing data distribution, eliminating network saturation, and so on for IAQ data imputation.
Highlights Four key technical issues are identified for indoor air quality data imputation. A novel model named IM-GAN is proposed to impute incomplete indoor air quality data. IM-GAN significantly outperforms the baselines in comprehensive experiments.
Imputing missing indoor air quality data with inverse mapping generative adversarial network
https://orcid.org/0000-0001-7864-9297
https://orcid.org/0000-0002-7443-6267
https://orcid.org/0000-0002-2044-0965
https://orcid.org/0000-0001-9897-1953
https://orcid.org/0000-0003-1237-0079
https://orcid.org/0000-0001-6279-2988
Abstract Sensors deployed all over the buildings are nowadays collecting a large amount of data, such as the Indoor Air Quality (IAQ) data which can provide valuable suggestions on improving indoor environments and energy consumption strategies. However, as treated as Multivariate Time Series (MTS), IAQ data often contain missing values that severely limit further analysis on them. Unfortunately, most of the existing methods fail to handle a couple of technical issues due to the complexity of MTS data, such as data distribution approximation, removing the redundancy, and so on. In this paper, we formulate the IAQ missing data imputation problem and propose an Inverse Mapping Generative Adversarial Network (IM-GAN) to tackle that problem. IM-GAN takes advantage of Bi-directional Recurrent Neural Network (BRNN), Denoising Auto-Encoder (DAE), and Generative Adversarial Network (GAN) to overcome the aforementioned technical issues. To validate the effectiveness of our proposed IM-GAN, we conduct comprehensive experiments on two public IAQ datasets GAMS and Gainesville. Results show that our IM-GAN achieves the new state-of-the-art performance in accurately estimating missing values in indoor air quality time series data, with the average performance of 0.1566 and 0.0789 in terms of Mean Relative Error, and 17.2884 and 2.7434 in terms of Mean Absolute Error on GAMS and Gainesville respectively at different missing rates. Our ablation study and visualization also validate that IM-GAN effectively overcomes the aforementioned technical issues by capturing data distribution, eliminating network saturation, and so on for IAQ data imputation.
Highlights Four key technical issues are identified for indoor air quality data imputation. A novel model named IM-GAN is proposed to impute incomplete indoor air quality data. IM-GAN significantly outperforms the baselines in comprehensive experiments.
Imputing missing indoor air quality data with inverse mapping generative adversarial network
https://orcid.org/0000-0001-7864-9297
https://orcid.org/0000-0002-7443-6267
https://orcid.org/0000-0002-2044-0965
https://orcid.org/0000-0001-9897-1953
https://orcid.org/0000-0003-1237-0079
https://orcid.org/0000-0001-6279-2988
Abstract Sensors deployed all over the buildings are nowadays collecting a large amount of data, such as the Indoor Air Quality (IAQ) data which can provide valuable suggestions on improving indoor environments and energy consumption strategies. However, as treated as Multivariate Time Series (MTS), IAQ data often contain missing values that severely limit further analysis on them. Unfortunately, most of the existing methods fail to handle a couple of technical issues due to the complexity of MTS data, such as data distribution approximation, removing the redundancy, and so on. In this paper, we formulate the IAQ missing data imputation problem and propose an Inverse Mapping Generative Adversarial Network (IM-GAN) to tackle that problem. IM-GAN takes advantage of Bi-directional Recurrent Neural Network (BRNN), Denoising Auto-Encoder (DAE), and Generative Adversarial Network (GAN) to overcome the aforementioned technical issues. To validate the effectiveness of our proposed IM-GAN, we conduct comprehensive experiments on two public IAQ datasets GAMS and Gainesville. Results show that our IM-GAN achieves the new state-of-the-art performance in accurately estimating missing values in indoor air quality time series data, with the average performance of 0.1566 and 0.0789 in terms of Mean Relative Error, and 17.2884 and 2.7434 in terms of Mean Absolute Error on GAMS and Gainesville respectively at different missing rates. Our ablation study and visualization also validate that IM-GAN effectively overcomes the aforementioned technical issues by capturing data distribution, eliminating network saturation, and so on for IAQ data imputation.
Highlights Four key technical issues are identified for indoor air quality data imputation. A novel model named IM-GAN is proposed to impute incomplete indoor air quality data. IM-GAN significantly outperforms the baselines in comprehensive experiments.
Imputing missing indoor air quality data with inverse mapping generative adversarial network
Wu, Zejun (author) / Ma, Chao (author) / Shi, Xiaochuan (author) / Wu, Libing (author) / Dong, Yi (author) / Stojmenovic, Milos (author)
Building and Environment ; 215
2022-02-10
Article (Journal)
Electronic Resource
English
Detecting Errors and Imputing Missing Data for Single-Loop Surveillance Systems
| British Library Online Contents | 2003
A Spatial‐Bayesian Technique for Imputing Pavement Network Repair Data
| Online Contents | 2012