Data Mining Approaches to the Real-Time Monitoring and Early Warning of Convective Weather Using Lightning Data

Stephany, Stephan; Strauss, Cesar; Calheiros, Alan James Peixoto; Lima, Glauston Roberto Teixeira de; Garcia, João Victor Cal; Pessoa, Alex Sandro Aguiar

doi:10.1007/978-3-030-21205-6_5

Cited by 1 publication

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, Stephany S., Strauss C., James A., Calheiros P. [11] developed a new data mining approach for near-real-time weather monitoring for such countries as Brazil, which lacks weather radar coverage. Data analysis and insights extraction from information arrays can cut down costs and increase productivity if the measures are accurate.…”

Section: Introductionmentioning

confidence: 99%

Real-Time High-Load Infrastructure Transaction Status Output Prediction Using Operational Intelligence and Big Data Technologies

2020

View full text Add to dashboard Cite

An approach to use Operational Intelligence with mathematical modeling and Machine Learning to solve industrial technology projects problems are very crucial for today’s IT (information technology) processes and operations, taking into account the exponential growth of information and the growing trend of Big Data-based projects. Monitoring and managing high-load data projects require new approaches to infrastructure, risk management, and data-driven decision support. Key difficulties that might arise when performing IT Operations are high error rates, unplanned downtimes, poor infrastructure KPIs and metrics. The methods used in the study include machine learning models, data preprocessing, missing data imputation, SRE (site reliability engineering) indicators computation, quantitative research, and a qualitative study of data project demands. A requirements analysis for the implementation of an Operational Intelligence solution with Machine learning capabilities has been conducted and represented in the study. A model based on machine learning algorithms for transaction status code and output predictions, in order to execute system load testing, risks identification and, to avoid downtimes, is developed. Metrics and indicators for determining infrastructure load are given in the paper to obtain Operational intelligence and Site reliability insights. It turned out that data mining among the set of Operational Big Data simplifies the task of getting an understanding of what is happening with requests within the data acquisition pipeline and helps identify errors before a user faces them. Transaction tracing in a distributed environment has been enhanced using machine learning and mathematical modelling. Additionally, a step-by-step algorithm for applying the application monitoring solution in a data-based project, especially when it is dealing with Big Data is described and proposed within the study.

show abstract

Section: Introductionmentioning

confidence: 99%