FIGAN: A Missing Industrial Data Imputation Method Customized for Soft Sensor Application

A missing manufacturing process data imputation framework for nonlinear dynamic soft sensor modeling and its application

In practice, missing data in pavement condition databases have been one of the most prevalent problems in airport pavement management systems. Missing data present problems in pavement performance analysis and uncertainties in pavement management decision making. A number of data imputation approaches are available for handling missing data. This paper examines the limitations of the conventional data imputation methods and proposes a stochastic multiple imputation (MI) approach to overcome major limitations associated with conventional data imputation methods. A case study is presented to appraise the effectiveness of the proposed approach against three conventional data imputation methods, namely, substitution by mean, substitution by interpolation, and substitution by regression methods. The roughness and friction data of a 4-km-long runway pavement and the roughness data of a 4-km-long taxiway pavement were considered in the study. The effectiveness of auxiliary variables in data imputation models was also demonstrated. Results from the performance appraisal indicated that the proposed stochastic MI method yielded the smallest errors for the roughness as well as friction data. Furthermore, the substitution by mean method resulted in imputed values with the highest amount of deviations from the observed values, followed by the substitution by regression method, and the substitution by interpolation method. Therefore, it is concluded that the proposed stochastic MI method outperformed conventional methods in handling missing runway and taxiway pavement roughness and friction data and provides an effective approach to impute missing data required in an airport pavement management system.

Neural-network-based soft sensors are widely employed in the industrial process. Such models have great significance to smart manufacturing. Considering the strict requirements of industrial production, it is vital to ensure the safety and robustness of these models in their actual deployment. However, recent research has shown that neural networks are quite vulnerable to adversarial attacks. By imposing tiny perturbation to the original sample, the fabricated adversarial sample can cheat these models to make wrong decisions. Such a phenomenon may bring serious trouble to the practical application of soft sensors. This article focuses on the adversarial attacks on industrial soft sensors. For the first time, we verify and analyze the effectiveness and deficiencies of the existing attack methods in the industrial soft sensor scenario. Based on solving these defects, this article proposes a novel perspective for attacking soft sensors. We analyze the optimization mechanism behind this new idea and then design two algorithms to perform attacks. The proposed methods more conform to the actual situation. Besides, compared with the existing approaches, the proposed methods have potentials to cause severer damages since their attacks are not only more concealed but also more likely to cheat the technicians to execute wrong operations. The research and analyses of the proposed methods lay a solid foundation for more thorough defenses against various attacks, which is quite necessary for making the deployed soft sensors more robust and secure.

Soft sensor plays a key role in the safe operation of industrial processes and product quality control. Affected by closed-loop feedback, process data often demonstrate certain dynamic characteristics. In addition, traditional soft sensor methods are often based on the assumption of completeness. Once part of the data is missing, the above methods will collapse. In this paper, we propose a Spatio-Temporal view Generative Adversarial Imputation Network (GAIN) for data imputation and apply dynamic soft sensor for block missing accompanied with completely random missing data. Initially, a data pre-imputed strategy is designed to first impute the missing data through GAIN from the perspective of data distribution. Secondly, on the basis of pre-imputation, a data imputation strategy that integrates time and space information is proposed to impute the data precisely, which can comprehensively consider the time series of process data and the correlation between variables, and further improve the accuracy of data imputation. Finally, we propose a dynamic soft sensor method to make real-time predictions of the data. The effectiveness of the proposed method is verified by the Tennessee Eastman (TE) process.

The prevalence of apathy is high after stroke, but its subsequent course remains unclear. We sought to determine the longitudinal course and predictors of apathy after stroke. Eligible patients admitted after a stroke and healthy control participants who were rated at least once on the Apathy Evaluation Scale were assessed over 5 years. Rates and levels of apathy in patients rose over 5 years. Significant risk factors for apathy were dementia, interval cerebrovascular events, poor physical functioning, and high depression scores. Apathy is common after stroke and becomes more prevalent with time, especially in those who show evidence of cognitive and functional decline.

Under the intention-to-treat principle, all randomized subjects should be analyzed according to their randomly assigned treatment, regardless of treatment actually received or protocol compliance. Adherence to this principle requires that even subjects with missing outcome data be included in the analysis; in fact, the exclusion of such subjects can have important implications on power and bias. Statistical methods for dealing with missing data exist, but many questions remain unclear. Much statistical research has been devoted to the development and assessment of various methods for handling missing data.1 The choice of appropriate methodology requires assumptions on the mechanism underlying the missing data. All of these decisions should be made a priori, preferably before the trial starts but certainly before unblinding the trial. Related conversations between clinical investigators and the study statistician during the design phase often focus on more practical questions. Is there some threshold for the missing data rate below which the trial’s conclusions are unlikely to be affected? Under what circumstances can the missing data be excluded from the analysis without biasing estimation, or is imputation always the preferred approach? In this article, we discuss implications of missing outcome data from a practical standpoint. We describe potential reasons for missing data and suggest strategies to minimize its occurrence. We also present common imputation approaches and emphasize that because none of these approaches are universally preferred, the best analytic plan includes a series of sensitivity analyses. In any longitudinal trial where subjects are followed over some extensive period of time, lengthy follow-up makes missing data somewhat unavoidable. In stroke clinical trials, the primary outcome assessment often occurs at 90 days although there is evidence to suggest that additional follow-up may be beneficial. Subjects may expire, or withdraw informed consent, before primary outcome ascertainment. Subjects may become lost to the …

The paper contains a comparative analysis of the possibilities of using different software products to solve the problem of missing data on the example of the sample for which different variants of data skips are simulated. The study provided an opportunity to identify the strengths and weaknesses of these software products, as well as to determine the effectiveness of a particular method for different amounts of missed information. Thus, the easiest way to handle the situation with missing data is Statistica, but there are offered only simple methods of processing data with missing values in Statistica. So, this program will help to cope with the missed data when there is a small number of omissions (up to 10%). SPSS offers a wider range of data imputation methods than Statistica, and at the same time it offers a more user-friendly interface compared to the R or SAS programming language. In the R and SAS software environments, you can use different methods of missing data imputation from the simplest to the most complex, such as, for example, multiple imputation. Thus, R and SAS are the most powerful missing data recovery programs, but they are more complex for users because they require knowledge of the programming language. It is found out that none of the mentioned software-analytical environments has built-in procedures for processing categorical data with missing values. There are approaches that can be implemented by analogy for ordered categories in R and SAS software environments, but it does not cover all the needs of the analysis of research, which are implemented in the form of surveys with the results that are mostly presented as answers. The methods used to impute quantitative data cannot be applied to categorical data, even if numbers are used to encode responses. The study undoubtedly proved that handling the missing data, as well as the choosing of possible ways to use certain methods of data imputation in different software environments should be approached very carefully and the problem of imputation should be solved in each case based on careful analysis of the existing database, considering not only the characteristics of the data and the number of gaps, but also the specific of a particular study. Dealing with missing data involves a wide range of the issues, which includes both the exploration of the nature of gaps, the methodology for data processing and imputation, depending not only on their nature but also on the type and the use of various software environments on missing data imputation. It is planned in future research to assess the effectiveness of the recoverability of imputation methods in different software environments, as well as to develop methodological principles for restoring gaps for categorical data and implement them into practice.

Missing data is inevitable and ubiquitous in intelligent transportation systems (ITSs). A handful of completion methods have been proposed, among which the tensor-based models have been shown to be the most advantageous for missing traffic data imputation. Despite their superior imputation accuracies, the adoption of these imputed data is not uniform in modern ITSs applications. The primary goal of this paper is to explore how to use tensor completion methods to support ITSs. In particular, we study how to improve traffic flow prediction accuracy under different missing scenarios. Specifically, three common missing scenarios including element-wise random missing, time-structured missing, and space-structured missing are considered. Four classical tensor completion models including Smooth PARAFAC Decomposition based Completion (SPC), CP Decomposition-based (CP-WOPT) Completion, Tucker Decomposition-based Completion (TDI), and High-accuracy Low-rank Tensor Completion (HaLRTC) are used to impute the missing data. Four well-known prediction methods including Support Vector Regression (SVR), K-nearest Neighbor (KNN), Gradient Boost Regression Tree (GBRT), and Long Short-term Memory (LSTM) are tested. The simple mean value interpolation completed traffic data is regarded as the baseline data. The extensive experiments show that improvements of traffic flow prediction can be achieved by increasing missing traffic data imputation accuracy at most cases. Interestingly we find that prediction accuracy cannot be improved by an imputation model when the sparsely observed training datasets already provide sufficient training samples.

Multiple model based LPV soft sensor development with irregular/missing process output measurement

Missing data are nearly always a problem in research, and missing values represent a serious threat to the validity of inferences drawn from findings. Increasingly, social science researchers are turning to multiple imputation to handle missing data. Multiple imputation, in which missing values are replaced by values repeatedly drawn from conditional probability distributions, is an appropriate method for handling missing data when values are not missing completely at random. However, use of this method requires developing an imputation model from the observed data. This is typically a rigorous and time-consuming process. To encourage wider adoption of multiple imputation in social work research, a simple framework for designing imputation models is presented. The framework and its ability to generate unbiased estimates are demonstrated in a simulation study. KEY WORDS: missing data; multiple imputation; nonresponse ********** Missing data are ubiquitous in social research, and missingness or nonresponse can represent a threat to the validity of inferences because of undue effects on efficiency, power, and parameter bias (Shadish, Cook, & Campbell, 2002). Social work researchers are now addressing missing data in a more rigorous manner. Recently, Saunders et al. (2006) and Choi, Golder, Gillmore, and Morrison (2005) described important data imputation methods and dispelled misunderstandings regarding popular imputation methods, such as mean substitution. Recent advances in analytic methods, such as multiple imputation (MI), are taking hold in social work research. With MI, missing values are replaced with values repeatedly drawn from simulated conditional probability distributions (Schafer, 1997), thus creating multiple versions of the data set. Each version of the data set is analyzed according to the data analysis model, and the multiple results are combined into point estimates (Rubin, 1996). A critical task in MI is to devise an imputation model (Allison, 2002) or missing data model (Graham, Olchowski, & Gilreath, 2007), which involves specifying the measures that are putatively associated with the missing values. Although this process adds additional steps, the specification of an imputation model and the creation of multiple data sets can produce less-biased estimates in the presence of missing data across a wide variety of data analysis techniques (Schafer, 1997). Besides MI, there are many other methods for addressing missing data (Schafer, 1999; Schafer & Graham, 2002). An equally rigorous method known as direct or full information maximum likelihood (FIML) estimation can produce unbiased estimates and correct standard errors in the presence of missing data. When the number of imputations is sufficiently large, identical missing data models will produce the same estimates under MI and FIML (Graham et al., 2007). Unlike MI, FIML is limited to maximum likelihood analytic techniques and the missing data model must be included in the analysis model. Although we focus on MI, the steps we describe for developing an imputation model are equally appropriate for use in the missing data model for FIML. On the basis of the MI literature, this article describes a framework for developing an imputation model for use with any free or commercial software package that performs MI. BRIEF REVIEW OF MISSING DATA CONCEPTS Generally, both MI and a broad range of missing data issues have received ample attention in the applied literature (Graham et al., 2007). We briefly discuss the three types of distributions that describe the randomness of nonresponse given that this property has consequences for the development of an imputation model. For a discussion of general missing data concepts that are not critical to understanding our discussion of imputation model development, we refer readers to Schafer and Graham (2002). Distribution of Nonresponse The probability distribution of nonresponse--more frequently referred to as the missing data or nonresponse mechanism (Rubin, 1976)--is both an important factor in the decision to impute with MI and a context for the development of an imputation model. …

Adaptive soft sensors including widely used locally weighted partial least square (LW‐PLS) have been established for online prediction, fault detection, and process monitoring. Nevertheless, majority of these existing adaptive soft sensors have zero tolerance to missing data, and the presence of missing data is inevitable due to sensor failures, routine maintenance, changes in sensor equipment over time, merging data from different system, and so forth. In the literature, limited studies could be found on the effects of missing data and the existing missing data imputation methods on the predictive performances of adaptive soft sensors. This work reports combined use of different missing data imputation techniques on LW‐PLS and the nonadaptive soft sensor, the partial least square (PLS). Well known trimmed score regression (TSR) and singular value decomposition (SVD) were employed in this study, and thus, the newly integrated TSR‐LW‐PLS and SVD‐LW‐PLS algorithms were proposed. Meanwhile, both existing TSR‐PLS and SVD‐PLS were used, and their results compared with the novel TSR‐LW‐PLS and SVD‐LW‐PLS algorithms. These algorithms were tested and evaluated using two examples having different percentages of missing data ranging from 5% to 40%. Results showed that TSR‐LW‐PLS model was superior compared with SVD‐LW‐PLS, TSR‐PLS, and SVD‐PLS as indicated by more than 100% improvements in prediction accuracy. It was also evident that TSR‐LW‐PLS is able to cope well with up to 20% of missing data.

A practical guide to multiple imputation of missing data in nephrology

Developing a Soft Sensor for an Air Separation Process Based on Variable Selection in Dynamic Partial Least Squares

Strategies for cancer clinical trials with multiple biomarkers

Estimation of missing values in heterogeneous traffic data: Application of multimodal deep learning model