{"title":"Innovative Deep Learning Strategies for Chaotic Data Classification: A Multi-Algorithm Comparison in the Presence of Noise","authors":"Shih-Lin Lin","doi":"10.1142/s0219477524500251","DOIUrl":null,"url":null,"abstract":"<p>Chaos is prevalent in both nature and science, appearing in data, time series and complex systems. Chaotic systems exhibit numerous uncertainties, akin to noise, which challenge researchers to distinguish or analyze potential underlying patterns or even identify the type of system involved. However, determining the kind of chaotic system is essential, as it enables prediction, synchronization, control, treatment and application. This study employs machine learning to classify chaotic data through a simulation involving three types of research data: Lorenz data, Lorenz combined with Gaussian white noise, Gaussian white noise and pink noise, utilizing six distinct algorithms. The most effective testing results are achieved using Mobilenet, with a classification accuracy of 97.38% and a loss of 0.2680 across these six data types.</p>","PeriodicalId":55155,"journal":{"name":"Fluctuation and Noise Letters","volume":null,"pages":null},"PeriodicalIF":1.2000,"publicationDate":"2024-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fluctuation and Noise Letters","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1142/s0219477524500251","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATHEMATICS, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
Chaos is prevalent in both nature and science, appearing in data, time series and complex systems. Chaotic systems exhibit numerous uncertainties, akin to noise, which challenge researchers to distinguish or analyze potential underlying patterns or even identify the type of system involved. However, determining the kind of chaotic system is essential, as it enables prediction, synchronization, control, treatment and application. This study employs machine learning to classify chaotic data through a simulation involving three types of research data: Lorenz data, Lorenz combined with Gaussian white noise, Gaussian white noise and pink noise, utilizing six distinct algorithms. The most effective testing results are achieved using Mobilenet, with a classification accuracy of 97.38% and a loss of 0.2680 across these six data types.
期刊介绍：
Fluctuation and Noise Letters (FNL) is unique. It is the only specialist journal for fluctuations and noise, and it covers that topic throughout the whole of science in a completely interdisciplinary way. High standards of refereeing and editorial judgment are guaranteed by the selection of Editors from among the leading scientists of the field.
FNL places equal emphasis on both fundamental and applied science and the name "Letters" is to indicate speed of publication, rather than a limitation on the lengths of papers. The journal uses on-line submission and provides for immediate on-line publication of accepted papers.
FNL is interested in interdisciplinary articles on random fluctuations, quite generally. For example: noise enhanced phenomena including stochastic resonance; 1/f noise; shot noise; fluctuation-dissipation; cardiovascular dynamics; ion channels; single molecules; neural systems; quantum fluctuations; quantum computation; classical and quantum information; statistical physics; degradation and aging phenomena; percolation systems; fluctuations in social systems; traffic; the stock market; environment and climate; etc.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
