[HTML][HTML] An approach towards increasing prediction accuracy for the recovery of missing IoT data based on the GRNN-SGTM ensemble

R Tkachenko, I Izonin, N Kryvinska, I Dronyuk, K Zub - Sensors, 2020 - mdpi.com
The purpose of this paper is to improve the accuracy of solving prediction tasks of the
missing IoT data recovery. To achieve this, the authors have developed a new ensemble of …

Recovery of missing sensor data with GRNN-based cascade scheme

R Tkachenko, I Izonin, I Dronyuk… - … Journal of Sensors …, 2021 - ingentaconnect.com
Background: Today, IoT-based systems are widely used in various applications. Intellectual
analysis of the data collected by IoT devices is an important task for the efficient and …

Software architecture design of the real-time processes monitoring platform

A Batyuk, V Voityshyn, V Verhun - 2018 IEEE Second …, 2018 - ieeexplore.ieee.org
Understanding of how business processes are executed in real-life is vitally important for a
company. Any process leaves a digital footprint that can be transformed into so-called event …

[PDF][PDF] Small-Batteries Utilization Analysis Based on Mathematical Statistics Methods in Challenges of Circular Economy.

M Bublyk, Y Matseliukh - COLINS, 2021 - ceur-ws.org
The paper contains an analysis of the possibilities of mathematical statistics as a section of
mathematics for solving the applied ecological and economic problem: utilization of small …

The correlates of energy management practices and sales performance of small family food firms in Turkey

AKE Onjewu, E Puntaier, S Hussain - British Food Journal, 2022 - emerald.com
Purpose While pursuing energy management, firms simultaneously strive to boost sales as a
path towards economic performance. Also, the literature suggests that family firms exhibit …

New approaches in the learning of complex-valued neural networks

V Kotsovsky, A Batyuk… - 2020 IEEE Third …, 2020 - ieeexplore.ieee.org
We consider neural networks with complex weights and continuous activation functions. The
complex generalization of the backpropagation learning algorithm is studied in the paper …

Bithreshold neural network classifier

V Kotsovsky, F Geche, A Batyuk - 2020 IEEE 15th international …, 2020 - ieeexplore.ieee.org
The fully connected 2-layer feedforward network architecture with the hidden layer
consisting of bithreshold neurons is considered in the paper. We design the neural network …

Analysis of the Interrelations Between Elements of Geoinformation System Structure

N Stupen, Z Ryzhok, M Stupen… - 2020 IEEE 15th …, 2020 - ieeexplore.ieee.org
In the article one has conducted a system analysis that quantitatively evaluated the various
properties, characteristics, factors for choosing the best model of geoinformation system …

The computation power and capacity of bithreshold neurons

V Kotsovsky, A Batyuk, I Mykoriak - 2020 IEEE 15th …, 2020 - ieeexplore.ieee.org
The paper deals with the issues concerning the expressive power of bithreshold neurons.
We study how many Boolean functions of n variables can be computed by using bithreshold …

Representational capabilities and learning of bithreshold neural networks

V Kotsovsky, A Batyuk - … “Intellectual Systems of Decision Making and …, 2020 - Springer
The paper deals with questions related to the ability of real-weighted bithreshold neurons
and neural networks to solve the classification tasks. We study how many partitions of a finite …