Search

Missing or unavailable data (NA) in multivariate data analysis is often treated with imputation methods and, in some cases, records containing NA are eliminated, leading to the loss of information. This paper addresses the problem of NA in multiple factor analysis (MFA) without resorting to eliminating records or using imputation techniques. For this purpose, the nonlinear iterative partial least squares (NIPALS) algorithm is proposed based on the principle of available data. NIPALS presents a good alternative when data imputation is not feasible. Our proposed method is called MFA-NIPALS and, based on simulation scenarios, we recommend its use until 15% of NAs of total observations. A case of groups of quantitative variables is studied and the proposed NIPALS algorithm is compared with the regularized iterative MFA algorithm for several percentages of NA. [ABSTRACT FROM AUTHOR]

Ground meteorological observation data (GMOD) are the core of research on earth-related disciplines and an important reference for societal production and life. Unfortunately, due to operational issues or equipment failures, missing values may occur in GMOD. Hence, the imputation of missing data is a prevalent issue during the pre-processing of GMOD. Although a large number of machine-learning methods have been applied to the field of meteorological missing value imputation and have achieved good results, they are usually aimed at specific meteorological elements, and few studies discuss imputation when multiple elements are randomly missing in the dataset. This paper designed a machine-learning-based multidimensional meteorological data imputation framework (MMDIF), which can use the predictions of machine-learning methods to impute the GMOD with random missing values in multiple attributes, and tested the effectiveness of 20 machine-learning methods on imputing missing values within 124 meteorological stations across six different climatic regions based on the MMDIF. The results show that MMDIF-RF was the most effective missing value imputation method; it is better than other methods for imputing 11 types of hourly meteorological elements. Although this paper applied MMDIF to the imputation of missing values in meteorological data, the method can also provide guidance for dataset reconstruction in other industries. [ABSTRACT FROM AUTHOR]

In recent years, the development of computer technology has promoted the informatization and intelligentization of hospital management systems and thus produced a large amount of medical data. These medical data are valuable resources for research. We can obtain inducers and unknown symptoms that can help discover diseases and make earlier diagnoses. Hypertensive disorder in pregnancy (HDP) is a common obstetric complication in pregnant women, which has severe adverse effects on the life safety of pregnant women and fetuses. However, the early and mid-term symptoms of HDP are not obvious, and there is no effective solution for it except for terminating the pregnancy. Therefore, detecting and preventing HDP is of great importance. This study aims at the preprocessing of pregnancy examination data, which serves as a part of HDP prediction. We found that the problem of missing data has a large impact on HDP prediction. Unlike general data, pregnancy examination data have high dimension and a high missing rate, are in a time series, and often have many non-linear relations. Current methods are not able to process the data effectively. To this end, we propose an improved bi-LSTM-based missing value imputation approach. It combines traditional machine learning and bidirectional LSTM to deal with missing data of pregnancy examination data. Our missing value imputation method obtains a good effect and improves the accuracy of the later prediction of HDP using examination data. [ABSTRACT FROM AUTHOR]

Missing observations in time series will distort the data characteristics, change the dataset expectations, high-order distances, and other statistics, and increase the difficulty of data analysis. Therefore, data imputation needs to be performed first. Generally, data imputation methods include statistical imputation, regression imputation, multiple imputation, and imputation based on machine learning methods. However, these methods currently have problems such as insufficient utilization of time characteristics, low imputation efficiency, and poor performance under high missing rates. In response to these problems, we propose the informer-WGAN, a network model based on adversarial training and a self-attention mechanism. With the help of the discriminator network and the random missing rate training method, the informer-WGAN can efficiently solve the problem of multidimensional time series imputation. According to the experimental results under different missing rates, the informer-WGAN model achieves better imputation results than the original informer on two datasets. Our model also shows excellent performance on time series imputation of the key parameters of a spacecraft control moment gyroscope (CMG). [ABSTRACT FROM AUTHOR]

Granular computing techniques are a huge discipline in which the basic component is to operate on groups of similar objects according to a fixed similarity measure. The first references to the granular computing can be seen in the works of Zadeh in fuzzy set theory. Granular computing allows for a very natural modelling of the world. It is very likely that the human brain, while solving problems, performs granular calculations on data collected from the senses. The researchers of this paradigm have proven the unlimited possibilities of granular computing. Among other things, they are used in the processes of classification, regression, missing values handling, for feature selection, and as mechanisms of data approximation. It is impossible to quote all methods based on granular computing—we can only discuss a selected group of techniques. In the article, we have presented a review of recently developed granulation techniques belonging to the family of approximation algorithms founded by Polkowski—in the framework of rough set theory. Starting from the basic Polkowski's standard granulation, we have described further developed by us concept dependent, layered, and epsilon variants, and our recent homogeneous granulation. We are presenting simple numerical examples and samples of research results. The effectiveness of these methods in terms of decision system size reduction and maintenance of the internal knowledge from the original data are presented. The reduction in the number of objects in our techniques while maintaining classification efficiency reaches 90 percent—for standard granulation with usage of a kNN classifier (we achieve similar efficiency for the concept-dependent technique for the Naive Bayes classifier). The largest reduction achieved in the number of exhaustive set of rules at the efficiency level to the original data are 99 percent—it is for concept-dependent granulation. In homogeneous variants, the reduction is less than 60 percent, but the advantage of these techniques is that it is not necessary to look for optimal granulation parameters, which are selected dynamically. We also describe potential directions of development of granular computing techniques by prism of described methods. [ABSTRACT FROM AUTHOR]