Work

Editorial

Year: 2021
Type: editorial
Abstract: This issue of the IDA journal is the fifth issue for our 25 th year of publication.It contains fourteen articles representing a wide range of topics related to the theoretical and applied research in the field of Intelligent Data Analysis.The first group of articles are about advanced data preprocessing and data understanding.Noering et al. in the first article of this group present an approach for improving discretization based pattern discovery for multivariate time series.The authors argue that load situations in engineering applications are challenging to be defined by hand.In other words, they need to be discovered as recurrent patterns within multivariate time series data of the system under consideration.They propose a series of preprocessing steps for symbolic representation of time series aiming for enhanced multivariate pattern discovery.They also show the performance of their proposed algorithms in a synthetic test data set as well as in a real life example with 100 million time points.Miswan et al. in the next article of this issue present a predictive modelling approach for different preprocessing techniques on machine learning classifiers.Their research is about preprocessing applied by previous hospital readmission that are compared, and the most common approaches highlighted such as missing value imputation, feature selection, data balancing, and feature scaling.Their results indicated that the preprocessing approaches helped improve the model's prediction of hospital readmission.Chen et al. in the third article of this issue present a non-binary hierarchical tree overlapping community detection that is based on multi-dimensional similarity.The authors argue that overlapping communities exist in real networks, where the communities represent hierarchical community structures, such as schools and government departments.The authors further explain that a non-binary tree would allow a vertex to belong to multiple communities to obtain a more realistic overlapping community structure.They propose a non-binary hierarchical tree overlapping community detection that is based on multi-dimensional similarity.Their experiments on real-world networks demonstrate that their proposed algorithm is superior to other representative algorithms in terms of the quality of overlapping community detection.Wan et al. in the last article of this group discuss an attribute interaction aware matrix factorization (MF) method for recommendation tasks.The authors argue that when the original rating matrix is particularly large, the training time complexity of the MF-based model becomes higher and the update cost of the model is also higher.They partition the original rating matrix into different sub-matrices according to the attribute interactions, train each submatrix independently, and merge all the latent vectors to generate the final score.Their experimental results on the two classic public datasets show that their approach can not only effectively improve the accuracy of recommendation, but also make full use of parallel computing technology to improve training efficiency without modifying the matrix factorization model.The second group of articles in this issue are about learning methods in IDA.Srivastava and Mittal in the first article of this group present an age decay accuracy weighted ensemble method for drifting data stream mining.The authors explain that a data source of a dynamic environment generates data streams in which the underlying data distribution changes very frequently with respect to time and
Author: A. Famili
Language: Spanish
Open Access status: bronze
OpenAlex ID: W4200307273
Cites:
Cited by:
Related to: 2