Creation of Scenarios for Processing Multidimensional Spatial-Temporal Data under Conditions of Uncertainty

The article discusses a method for constructing scenarios in an adaptive analytical information system for classifying objects and their movement trajectories in real time based on processing information from a large number of spatially separated information sources (sensors) and analyzing dynamic arrays of distributed multidimensional data under conditions of uncertainty. Examples of scenarios that use statistical, interval, fuzzy and stochastic methods for describing uncertainty are given. When developing scenarios for adaptive data processing and analysis, integrated ontologies of the “hydroacoustics” field of knowledge, ontologies of signal processing methods, image processing methods and data analysis methods are used. Creation of scenarios for automated processing of multidimensional spatial-temporal data is carried out in the OntoMASTER network software environment based on semantic Web standards. To support scientific research, a dynamic scripting interface and their testing in a simulator environment is implemented. The learning environment based on the knowledge base is intended for training and retraining of personnel. The results of the work can be applied both in scientific research and in the process of teaching students.

[1]  Ben Y. Zhao,et al.  Complexity vs. performance: empirical analysis of machine learning as a service , 2017, Internet Measurement Conference.

[2]  María José del Jesús,et al.  KEEL 3.0: An Open Source Software for Multi-Stage Analysis in Data Mining , 2017, Int. J. Comput. Intell. Syst..

[3]  Pavel Brazdil,et al.  Metalearning and Algorithm Selection: progress, state of the art and introduction to the 2018 Special Issue , 2017, Machine Learning.

[4]  A. S. Pisarev,et al.  Numerical analysis of particle trajectories in living cells under uncertainty conditions , 2015, Biophysics.

[5]  Michael R Berthold,et al.  KNIME for reproducible cross-domain analysis of life science data. , 2017, Journal of biotechnology.

[6]  Markus Hofmann,et al.  RapidMiner: Data Mining Use Cases and Business Analytics Applications , 2013 .

[7]  Lars Kotthoff,et al.  Auto-WEKA 2.0: Automatic model selection and hyperparameter optimization in WEKA , 2017, J. Mach. Learn. Res..

[8]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[9]  Terrence J. Sejnowski,et al.  Analysis of hidden units in a layered network trained to classify sonar targets , 1988, Neural Networks.

[10]  Ivan A. Pisarev,et al.  Development of Scenarios for Automatic Processing and Data Mining in a Multi-Agent Environment , 2019, 2019 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus).

[11]  Rossitza Setchi,et al.  Feature selection using Joint Mutual Information Maximisation , 2015, Expert Syst. Appl..

[12]  Kevin Leyton-Brown,et al.  Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms , 2012, KDD.

[13]  Abraham Bernstein,et al.  Designing KDD-Workflows via HTN-Planning for Intelligent Discovery Assistance , 2012, KDD 2012.

[14]  A. S. Pisarev.  Method for the parameters estimating of microparticles motion along the trajectories under uncertainty , 2015, 2015 XVIII International Conference on Soft Computing and Measurements (SCM).

[15]  Aaron Klein,et al.  Efficient and Robust Automated Machine Learning , 2015, NIPS.

[16]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[17]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[18]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..