Reconstruction of missing data using compressed sensing techniques with adaptive dictionary

Perepu, Satheesh K.; Tangirala, Arun K.

doi:10.1016/j.jprocont.2016.08.008

Cited by 16 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gondek, Hafner, and Sampson [12] Missing value imputation using random forest and feature engineering Perepu and Tangirala [13] Missing value estimation using a CS method with adaptive dictionary Chodosh, Wang, and Lucey [14] Estimating a dense depth map using a CS method and alternating direction neural networks Most research methods resort to data imputation, where a data set with missing values is ignored. However, these kinds of methods cause distortion of the captured data-based probability distribution.…”

Section: Estimationmentioning

confidence: 99%

“…In Equation (12), is an input vector with attributes and is the missing index among these attributes. Equation (13) is the distribution of the latent variables in the attribute where the missing value occurs, and the missing value correction value using GPR is the same as Equation (13). Then, the is transformed to using Equation (14).…”

Section: Generative Adversarial Network-based Missing Value Estimatiomentioning

confidence: 99%

“…This situation makes missing value estimations the most important preprocessing steps. A number of existing studies [2][3][4][5][6][7][8][9][10][11][12][13] have proposed methods to overcome this data imbalance issue. Table 1 summarizes several existing missing value estimation methods and their applications.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Imbalanced Data Handling Framework for Industrial Big Data Using a Gaussian Process Regression-Based Generative Adversarial Network

Lee

2020

Symmetry

View full text Add to dashboard Cite

The developments in the fields of industrial Internet of Things (IIoT) and big data technologies have made it possible to collect a lot of meaningful industrial process and quality-based data. The gathered data are analyzed using contemporary statistical methods and machine learning techniques. Then, the extracted knowledge can be used for predictive maintenance or prognostic health management. However, it is difficult to gather complete data due to several issues in IIoT, such as devices breaking down, running out of battery, or undergoing scheduled maintenance. Data with missing values are often ignored, as they may contain insufficient information from which to draw conclusions. In order to overcome these issues, we propose a novel, effective missing data handling mechanism for the concepts of symmetry principles. While other existing methods only attempt to estimate missing parts, the proposed method generates a whole set of data set using Gaussian process regression and a generative adversarial network. In order to prove the effectiveness of the proposed framework, we examine a real-world, industrial case involving an air pressure system (APS), where we use the proposed method to make quality predictions and compare the results with existing state-of-the-art estimation methods.

show abstract

Section: Estimationmentioning

confidence: 99%

Section: Generative Adversarial Network-based Missing Value Estimatiomentioning

confidence: 99%

See 1 more Smart Citation

An Imbalanced Data Handling Framework for Industrial Big Data Using a Gaussian Process Regression-Based Generative Adversarial Network

Lee

2020

Symmetry

View full text Add to dashboard Cite

show abstract

“…However, only a few studies used CS in the packet-drop processing literatures. [1] uses the CS technique as a new predictive method to compensate the missing data, but its proposed algorithm only can estimate the missing data of single-output system. In the actual engineering environment, most systems have multiple sensors to get more outputs, that is, multi-output system.…”

Section: Introductionmentioning

confidence: 99%

A compensated method for Networked Control System with packet drops based on Compressed Sensing

Fan¹,

Yin²,

Liang³

2018

Proceedings of the 2018 3rd International Conference on Advances in Materials, Mechatronics and Civil Engineering (ICAMMCE 2018

View full text Add to dashboard Cite

Due to unreliable and bandwidth-limited characteristics of communication link in networked control systems, a real-time compensated method for multi-output system is presented in this paper based on Compressed Sensing and sliding window, by which estimates of dropping data packets in feedback channel is obtained and the performance degradation induced by packet drops is reduced. The merits of the compensated method are that it can compensate the dropping entire data packet and make the measurement matrix always keep instant in the whole process of Compressed Sensing which reduces the memory requirements of the buffer. Finally, simulation results illustrate that the proposed method could perform well when packet-drop occurs.

show abstract

“…In the air pollution, the future scenarios are always important to tackle with this global scale problem [2]. The statistical, mathematical or graphical approach can be used for data analyses [6,11]. The biggest problem in time series analyses is the missing data.…”

Section: Introductionmentioning

confidence: 99%

Time Series Analysis of Air Pollutants for Karabük Province

Can

2017

ITM Web Conf.

View full text Add to dashboard Cite

Abstract. The air is polluted and the atmospheric pollution has becoming a great problem for human beings due to the high rate consumption of energy. Most of the scientists dealing with the air pollution state that the first reason of all environmental problems is the population increase. Depending on population, the high consumption of energy (including heating purposes, electricity production, transportation and industries) agricultural activities, waste disposal and the pressure for destroying forest areas create air pollution problem. The atmosphere is polluted and the concentrations of pollutants have increased tremendously. Karabük Province is one of the famous provinces of heavy industries. There are 3 air quality measurement stations. In this study, the last 2 years hourly and daily air pollutants (PM10, SO 2 , NO, NO x , NO 2 , O 3 and CO) were studied as a time series by using graphical and statistical approaches. The results were considered seasonally and annually. The meteorological condition is also very effective in atmospheric pollution. Moreover, the industrial production and consumption of energy are also high pressure on Karabük province. The concentrations in each station are also showing different characteristics during two years' period. The highest concentrations (such as PM10, SO 2 , NO, NO x ) are, as usual, seen in winter season due to industrial usage of energy for production and household consumption of energy for heating. However, for O 3 , the highest concentration is observed in summer season, because the atmospheric ozone trend is supposed to show an opposite trend compared with NO due to photochemical reaction with these gases. For CO, the maximum concentration is recorded as 4779 μg/m3 in august in 2015. The analyses of data have shown that, the atmosphere is polluted highly with PM10, SO 2 , NO, NO x , NO 2 , and CO during winter season. The households are very effective using high coal for heating purposes in Karabük Province.

show abstract

Reconstruction of missing data using compressed sensing techniques with adaptive dictionary

Cited by 16 publications

References 29 publications

An Imbalanced Data Handling Framework for Industrial Big Data Using a Gaussian Process Regression-Based Generative Adversarial Network

An Imbalanced Data Handling Framework for Industrial Big Data Using a Gaussian Process Regression-Based Generative Adversarial Network

A compensated method for Networked Control System with packet drops based on Compressed Sensing

Time Series Analysis of Air Pollutants for Karabük Province

Contact Info

Product

Resources

About