Search Results - data processing methods

Advanced Wind Speed Forecasting: A Hybrid Framework Integrating Ensemble Methods and Deep Neural Networks for Meteorological Data by Daniel Díaz-Bedoya, Mario González-Rodríguez, Oscar Gonzales-Zurita, Xavier Serrano-Guerrero, Jean-Michel Clairand

“…Validated with real-world data from Cuenca, Ecuador, the LSTM model achieves superior accuracy across all targets, demonstrating robust performance for real-world deployment. …”
Get full text

Abnormal behavior detection method of fish school under low dissolved oxygen stress based on image processing and compressed sensing by LU Huanda, YU Xin, LIU Guangqiang

“…In order to overcome the time-consuming and laborious problems of artificial observation, we proposed an automatic detection method of abnormal behavior of fish school under low dissolved oxygen stress based on image processing and compressed sensing algorithm. …”
Get full text

DiffGAN: A Fault Diagnosis Data Augmentation Method for Hydropower Units Based on Adversarial Training and Diffusion Model by Hongwei Zhang, Zhao Liu, Hansong Si, Zhongzhi Chen, Huiping Xie

“…However, in practical production scenarios, fault data is difficult to obtain, and traditional fault diagnosis methods require a large quantity of high-quality data, severely limiting their diagnostic performance. …”
Get full text

A decoupling method for wheel-rail contact forces of heavy-duty trains based on big data and neural networks by ZHANG Zhenhui, WEI Kai, PENG Shenyou, YIN Shengwen, WANG Zhonggang

“…To accurately identify and predict wheel-rail contact forces during the operation of heavy-duty trains, this paper proposes a novel method of decoupling and predicting these forces based on big data related to non-contact strain at the wheel periphery and a neural network. …”
Get full text

A Consistency Evaluation Method for Digital Twins in Manufacturing by Li Sun, Ziyiming Jiao, Shihao Wang, Feng Jiang, Xianghui Li

“…With the development of emerging technologies such as the Internet of Things and big data, Digital Twin (DT) is increasingly used in manufacturing, and their consistency directly affects the efficiency, quality and reliability of the manufacturing process. …”
Get full text

Research by the method of an extended systematical literature review E-SLR the problem of ensuring the security of personal data when using OSINT by N. N. Romanova, V. V. Gryzunov

“…The amount of personal data in open sources increases, which makes it possible for third parties to access it using open source intelligence (OSINT) methods, which can be used for malicious purposes. …”
Get full text

An inverse problem of differential equation systems in connection with the study of semiconductor materials and biomedical processes by Golovitskii Alexander

“…This paper puts forward a new method of solving the problem for calculating the unknown and non-measurable parameters, that are included in a system of differential equations, whose solution adequately reproduces the given experimental data, but has no analytical form. …”
Get full text

Micromechanics of Localized Fracture Phenomena in Inelastic Solids Generated by Impact-Loaded Adiabatic Processes by P. PERZYNA

“…This procedure of investigation is based on utilization the finite difference method for regularized thermo-elasto-viscoplastic constitutive model of damaged material. …”
Get full text

Forecasting Transmission Line Loss Using a Cluster-Based Refinement Framework and Scheduled Outage Data by Gideon Egharevba, Arne Dankers, Hamidreza Zareipour

“…Transmission line loss forecasting is an important power system forecasting task, yet, existing methods often overlook qualitative operational data such as scheduled outages, which directly impact network topology and losses. …”
Get full text

A Rule-Based Predictive Model for Estimating Human Impact Data in Natural Onset Disasters—The Case of a PRED Model by Sara Rye, Emel Aktas

“…The framework can be used for disaster human impact assessment based on the socio-economic characteristics of the affected countries. <i>Methods</i>: A panel data of 4252 natural onset disasters between 1980 to 2020 is processed through concept drift phenomenon and rule-based classifiers, namely the Moving Average (MA). …”
Get full text

Risk Mitigation Analysis for Tofu Production Process to Minimize Product Defects Using House of Risk Approach by Hadi Susanto, Sheila Amalia Salma, Hanifa Rahmani

Get full text

Analyzing large text data for vocabulary profiling in corpus-based studies of academic discourse by Ismail Xodabande, Mahmood Reza Atai, Mohammad R. Hashemi

Get full text

Main directions in combining digitization and geoinformation methods for supporting mining production by S. V. Kornilkov, P. А. Rybnikov, L. S. Rybnikova

“…The combined use of digital twins and geoinformation monitoring data on hazardous phenomena and processes and their further analysis contributes to increasing the efficiency of mining production.…”
Get full text

Multi-Source Heterogeneous Data-Driven Digital Delivery System for Oil and Gas Surface Engineering by Wei Zhang, Zhixiang Dai, Taiwu Xia, Gangping Chen, Yihua Zhang, Jun Zhou, Cui Liu

“…Utilizing a layered collaborative framework, the system combines optimization algorithms and anomaly detection methods during data processing to enhance the relevance and reliability of high-dimensional data. …”
Get full text

Research of food security problems of the war-torn regions of Ukraine using geomatics methods by Михайло Згуровський, Костянтин Єфремов, Сергій Гапон, Іван Пишнограєв

Get full text

A conceptual approach to digital transformation of the educational process at a higher education institution by A. A. Kytmanov, Yu. N. Gorelova, T. V. Zykova, O. A. Pikhtilkova, E. V. Pronina

“…The development of a data-driven educational process management system is based on digital culture principles of process management, which imply that the data collected in university systems are consistent, organized into a single structure. and stored in a form convenient for the development of new digital services. …”
Get full text

Optimising Sensor Placement in Heritage Buildings: A Comparison of Model-Based and Data-Driven Approaches by Estefanía Chaves, Alberto Barontini, Nuno Mendes, Víctor Compán

“…The results underscore the decisive impact of the input data on the optimisation process. Although calibrated models may improve certain modal parameters, they do not necessarily translate into better sensor configurations. …”
Get full text

Estimation of the average time to failure of the turning steps according to the operation data by M. V. Belousova, V. V. Bulatov

“…Authors suggest using the maximum likelihood method to identify Weibull distribution parameters, on the basis of which the value of the point estimate of the mean time to failure is calculated.Based on the research, it is concluded that this type of distribution law and the process of finding its parameters should be introduced into the program and methodology for assessing the operational reliability of the turning steps, when calculating the average time to failure of the steps, and consider the possibility of applying this law for analogous products.In conclusion, calculation of the pointed estimation of the average time to failure of the closed turning step was made on the basis of operational tests for one year in accordance with the adopted distribution law.…”
Get full text

Methodology for determining the reactive parameters of aviation electrical energy consumers based on voltage and current data in transients by V. I. Pavlova, I. E. Starostin

“…This method is proposed to be used for diagnosing electrical equipment during its operation on board the aircraft. …”
Get full text

METHODS OF MANAGING TRAFFIC DISTRIBUTION IN INFORMATION AND COMMUNICATION NETWORKS OF CRITICAL INFRASTRUCTURE SYSTEMS by Viktor Kosenko, Elena Persiyanova, Oleksiy Belotskyy, Olga Malyeyeva

“…The goal of the work is to create methods for managing the data flows and resources of the ICN of CIS to improve the efficiency of information processing. …”
Get full text