Zaporizhia National Technical University

About: Zaporizhia National Technical University is a education organization based out in Zaporizhia, Ukraine. It is known for research contribution in the topics: Higher education & The Internet. The organization has 550 authors who have published 462 publications receiving 1487 citations.

Methods of sampling based on exhaustive and evolutionary search

Abstract: The development of mathematical software for training sampling is considered. Exhaustive and evolutionary sampling methods are developed. Criteria for selection, censoring, and pseudoclustering of instances are introduce in these methods. This makes it possible to speed up the sampling process and to ensure the compliance of the samples with the limited size. The proposed methods allow for the automatic allocation of a subset of instances with the minimal size from the original sample. The subset contains the most important instances for the model’s construction. The complexity estimates of the developed methods are defined. Experiments to determine the practical applicability of the methods are conducted. The use of the proposed estimates and identified dependences makes it possible to take into account the available computer resources during the sampling.

Application of Fuzzy Decision Tree for Signal Classification

Abstract: A typical algorithm for signal classification consists of two steps: signal preliminary transformation and classification itself. The procedures of preliminary transformation are used to extract specific features of the initial signal and reduce its dimension for effective classification. The result of this transformation is information loss of initial signal, which implies uncertainty of data used in classification. This uncertainty can be taken into account by the application of fuzzy classifiers. In this paper, a new algorithm with application of fuzzy classifier is proposed for signal classification. A new procedure of fuzzification is added into the preliminary transformation and fuzzy decision tree is used for classification. The efficiency of this algorithm is examined based on the problem of detection of defective blades of an aircraft engine gas turbine. The experiments showed that the accuracy of the classification for the considered example is 0.989. This is the best result in comparison with other classification methods used to solve this problem.

Flexible technologies for smart campus

Abstract: The article considers an example of the advertisement network based on the BLE 4.0, and its facilities for creating the infrastructure for a Smart Campus, where dynamic information is provided for the target audience. The authors provide an analysis of the characteristics and experimental implementation of this system. Moreover, the practical usage of a popular vendor and the needed back-end to provide dynamic usages of the network, both in appearance and content is described. In the paper different wireless technologies are compared in regards to their main feature and field of application. In general the characteristics of a Blue Tooth Low Energy, BLE, are highlighted. This is elaborated upon in the Smart Campus example. The Smart Campus is an indoor wireless network to deliver location and user based dynamic information to the different visitors, teacher or students of a university campus, both for day-to-day use as for specific events. To keep the system interesting and to augment ease-of-use for all kind of users and content providers, a dedicated content management system is developed within the Smart Campus case. The complete system consists of a set of beacons, an application on a smartphone, a database with the related CMS. All is developed in an international cooperation between different universities.