多分形光谱特征增强了异常扩散的分类能力

Henrik Seckler, Ralf Metzler, Damian G. Kelty-Stephen, Madhur Mangalam
{"title":"多分形光谱特征增强了异常扩散的分类能力","authors":"Henrik Seckler, Ralf Metzler, Damian G. Kelty-Stephen, Madhur Mangalam","doi":"arxiv-2401.07646","DOIUrl":null,"url":null,"abstract":"Anomalous diffusion processes pose a unique challenge in classification and\ncharacterization. Previously (Mangalam et al., 2023, Physical Review Research\n5, 023144), we established a framework for understanding anomalous diffusion\nusing multifractal formalism. The present study delves into the potential of\nmultifractal spectral features for effectively distinguishing anomalous\ndiffusion trajectories from five widely used models: fractional Brownian\nmotion, scaled Brownian motion, continuous time random walk, annealed transient\ntime motion, and L\\'evy walk. To accomplish this, we generate extensive\ndatasets comprising $10^6$ trajectories from these five anomalous diffusion\nmodels and extract multiple multifractal spectra from each trajectory. Our\ninvestigation entails a thorough analysis of neural network performance,\nencompassing features derived from varying numbers of spectra. Furthermore, we\nexplore the integration of multifractal spectra into traditional feature\ndatasets, enabling us to assess their impact comprehensively. To ensure a\nstatistically meaningful comparison, we categorize features into concept groups\nand train neural networks using features from each designated group. Notably,\nseveral feature groups demonstrate similar levels of accuracy, with the highest\nperformance observed in groups utilizing moving-window characteristics and\n$p$-variation features. Multifractal spectral features, particularly those\nderived from three spectra involving different timescales and cutoffs, closely\nfollow, highlighting their robust discriminatory potential. Remarkably, a\nneural network exclusively trained on features from a single multifractal\nspectrum exhibits commendable performance, surpassing other feature groups. Our\nfindings underscore the diverse and potent efficacy of multifractal spectral\nfeatures in enhancing classification of anomalous diffusion.","PeriodicalId":501305,"journal":{"name":"arXiv - PHYS - Adaptation and Self-Organizing Systems","volume":"25 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multifractal-spectral features enhance classification of anomalous diffusion\",\"authors\":\"Henrik Seckler, Ralf Metzler, Damian G. Kelty-Stephen, Madhur Mangalam\",\"doi\":\"arxiv-2401.07646\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Anomalous diffusion processes pose a unique challenge in classification and\\ncharacterization. Previously (Mangalam et al., 2023, Physical Review Research\\n5, 023144), we established a framework for understanding anomalous diffusion\\nusing multifractal formalism. The present study delves into the potential of\\nmultifractal spectral features for effectively distinguishing anomalous\\ndiffusion trajectories from five widely used models: fractional Brownian\\nmotion, scaled Brownian motion, continuous time random walk, annealed transient\\ntime motion, and L\\\\'evy walk. To accomplish this, we generate extensive\\ndatasets comprising $10^6$ trajectories from these five anomalous diffusion\\nmodels and extract multiple multifractal spectra from each trajectory. Our\\ninvestigation entails a thorough analysis of neural network performance,\\nencompassing features derived from varying numbers of spectra. Furthermore, we\\nexplore the integration of multifractal spectra into traditional feature\\ndatasets, enabling us to assess their impact comprehensively. To ensure a\\nstatistically meaningful comparison, we categorize features into concept groups\\nand train neural networks using features from each designated group. Notably,\\nseveral feature groups demonstrate similar levels of accuracy, with the highest\\nperformance observed in groups utilizing moving-window characteristics and\\n$p$-variation features. Multifractal spectral features, particularly those\\nderived from three spectra involving different timescales and cutoffs, closely\\nfollow, highlighting their robust discriminatory potential. Remarkably, a\\nneural network exclusively trained on features from a single multifractal\\nspectrum exhibits commendable performance, surpassing other feature groups. Our\\nfindings underscore the diverse and potent efficacy of multifractal spectral\\nfeatures in enhancing classification of anomalous diffusion.\",\"PeriodicalId\":501305,\"journal\":{\"name\":\"arXiv - PHYS - Adaptation and Self-Organizing Systems\",\"volume\":\"25 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-01-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Adaptation and Self-Organizing Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2401.07646\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Adaptation and Self-Organizing Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2401.07646","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

反常扩散过程对分类和表征提出了独特的挑战。此前(Mangalam 等人,2023 年,《物理评论研究》5,023144),我们利用多分形形式主义建立了一个理解异常扩散的框架。本研究深入探讨了多分形谱特征在有效区分异常扩散轨迹与以下五种广泛使用的模型方面的潜力:分数布朗运动、缩放布朗运动、连续时间随机行走、退火瞬时运动和 L\'evy walk。为此,我们从这五种异常扩散模型中生成了包含 10^6$ 轨迹的扩展数据集,并从每个轨迹中提取了多个多分形谱。我们的研究包括对神经网络性能的全面分析,包括从不同数量的频谱中提取的特征。此外,我们还探索了将多分形光谱整合到传统特征集中的方法,从而能够全面评估多分形光谱的影响。为了确保进行有统计意义的比较,我们将特征分为概念组,并使用每个指定组的特征来训练神经网络。值得注意的是,几个特征组都表现出了相似的准确性水平,其中利用移动窗口特征和 P 值变化特征的组表现最好。紧随其后的是多分形光谱特征,特别是那些从涉及不同时间尺度和截点的三个光谱中提取的特征,这突出了它们强大的判别潜力。值得注意的是,专门根据单一多分形频谱特征训练的神经网络表现出令人称道的性能,超过了其他特征组。我们的发现强调了多分形频谱特征在增强异常扩散分类方面的多样性和强大功效。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Multifractal-spectral features enhance classification of anomalous diffusion
Anomalous diffusion processes pose a unique challenge in classification and characterization. Previously (Mangalam et al., 2023, Physical Review Research 5, 023144), we established a framework for understanding anomalous diffusion using multifractal formalism. The present study delves into the potential of multifractal spectral features for effectively distinguishing anomalous diffusion trajectories from five widely used models: fractional Brownian motion, scaled Brownian motion, continuous time random walk, annealed transient time motion, and L\'evy walk. To accomplish this, we generate extensive datasets comprising $10^6$ trajectories from these five anomalous diffusion models and extract multiple multifractal spectra from each trajectory. Our investigation entails a thorough analysis of neural network performance, encompassing features derived from varying numbers of spectra. Furthermore, we explore the integration of multifractal spectra into traditional feature datasets, enabling us to assess their impact comprehensively. To ensure a statistically meaningful comparison, we categorize features into concept groups and train neural networks using features from each designated group. Notably, several feature groups demonstrate similar levels of accuracy, with the highest performance observed in groups utilizing moving-window characteristics and $p$-variation features. Multifractal spectral features, particularly those derived from three spectra involving different timescales and cutoffs, closely follow, highlighting their robust discriminatory potential. Remarkably, a neural network exclusively trained on features from a single multifractal spectrum exhibits commendable performance, surpassing other feature groups. Our findings underscore the diverse and potent efficacy of multifractal spectral features in enhancing classification of anomalous diffusion.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信