Visually Evaluating Generative Adversarial Networks Using Itself under Multivariate Time Series

Visually evaluating the goodness of generated Multivariate Time Series (MTS) are difficult to implement, especially in the case that the generative model is Generative Adversarial Networks (GANs). We present a general framework named Gaussian GANs to visually evaluate GANs using itself under the MTS...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Pan, Qilong
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Pan, Qilong
description Visually evaluating the goodness of generated Multivariate Time Series (MTS) are difficult to implement, especially in the case that the generative model is Generative Adversarial Networks (GANs). We present a general framework named Gaussian GANs to visually evaluate GANs using itself under the MTS generation task. Firstly, we attempt to find the transformation function in the multivariate Kolmogorov Smirnov (MKS) test by explicitly reconstructing the architecture of GANs. Secondly, we conduct the normality test of transformed MST where the Gaussian GANs serves as the transformation function in the MKS test. In order to simplify the normality test, an efficient visualization is proposed using the chi square distribution. In the experiment, we use the UniMiB dataset and provide empirical evidence showing that the normality test using Gaussian GANs and chi sqaure visualization is effective and credible.
doi_str_mv 10.48550/arxiv.2208.02649
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2208_02649</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2208_02649</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-95e54dbfbb8b37d0d040d9117c0794ed5a13dfad16ea95f88abc802e37199d443</originalsourceid><addsrcrecordid>eNotj7FOwzAURb0woMIHMOEfSLATO7bHqiqlUoGBwBo918_Iwg3ITgL9e5rCdO9wdKRDyA1npdBSsjtIP2Eqq4rpklWNMJekewt5hBiPdD1BHGEI_TvdYI_pdCekSzdhypACRPqEw_dn-sj0Nc_UdsgYPR17h4k-jvHEz9yAtA0HpC-YAuYrcuEhZrz-3wVp79ft6qHYPW-2q-WugEaZwkiUwllvrba1cswxwZzhXO2ZMgKdBF47D443CEZ6rcHuNauwVtwYJ0S9ILd_2nNh95XCAdKxm0u7c2n9C1A-UE8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Visually Evaluating Generative Adversarial Networks Using Itself under Multivariate Time Series</title><source>arXiv.org</source><creator>Pan, Qilong</creator><creatorcontrib>Pan, Qilong</creatorcontrib><description>Visually evaluating the goodness of generated Multivariate Time Series (MTS) are difficult to implement, especially in the case that the generative model is Generative Adversarial Networks (GANs). We present a general framework named Gaussian GANs to visually evaluate GANs using itself under the MTS generation task. Firstly, we attempt to find the transformation function in the multivariate Kolmogorov Smirnov (MKS) test by explicitly reconstructing the architecture of GANs. Secondly, we conduct the normality test of transformed MST where the Gaussian GANs serves as the transformation function in the MKS test. In order to simplify the normality test, an efficient visualization is proposed using the chi square distribution. In the experiment, we use the UniMiB dataset and provide empirical evidence showing that the normality test using Gaussian GANs and chi sqaure visualization is effective and credible.</description><identifier>DOI: 10.48550/arxiv.2208.02649</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Applications</subject><creationdate>2022-08</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2208.02649$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2208.02649$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Pan, Qilong</creatorcontrib><title>Visually Evaluating Generative Adversarial Networks Using Itself under Multivariate Time Series</title><description>Visually evaluating the goodness of generated Multivariate Time Series (MTS) are difficult to implement, especially in the case that the generative model is Generative Adversarial Networks (GANs). We present a general framework named Gaussian GANs to visually evaluate GANs using itself under the MTS generation task. Firstly, we attempt to find the transformation function in the multivariate Kolmogorov Smirnov (MKS) test by explicitly reconstructing the architecture of GANs. Secondly, we conduct the normality test of transformed MST where the Gaussian GANs serves as the transformation function in the MKS test. In order to simplify the normality test, an efficient visualization is proposed using the chi square distribution. In the experiment, we use the UniMiB dataset and provide empirical evidence showing that the normality test using Gaussian GANs and chi sqaure visualization is effective and credible.</description><subject>Computer Science - Learning</subject><subject>Statistics - Applications</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7FOwzAURb0woMIHMOEfSLATO7bHqiqlUoGBwBo918_Iwg3ITgL9e5rCdO9wdKRDyA1npdBSsjtIP2Eqq4rpklWNMJekewt5hBiPdD1BHGEI_TvdYI_pdCekSzdhypACRPqEw_dn-sj0Nc_UdsgYPR17h4k-jvHEz9yAtA0HpC-YAuYrcuEhZrz-3wVp79ft6qHYPW-2q-WugEaZwkiUwllvrba1cswxwZzhXO2ZMgKdBF47D443CEZ6rcHuNauwVtwYJ0S9ILd_2nNh95XCAdKxm0u7c2n9C1A-UE8</recordid><startdate>20220804</startdate><enddate>20220804</enddate><creator>Pan, Qilong</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20220804</creationdate><title>Visually Evaluating Generative Adversarial Networks Using Itself under Multivariate Time Series</title><author>Pan, Qilong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-95e54dbfbb8b37d0d040d9117c0794ed5a13dfad16ea95f88abc802e37199d443</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Applications</topic><toplevel>online_resources</toplevel><creatorcontrib>Pan, Qilong</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Pan, Qilong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Visually Evaluating Generative Adversarial Networks Using Itself under Multivariate Time Series</atitle><date>2022-08-04</date><risdate>2022</risdate><abstract>Visually evaluating the goodness of generated Multivariate Time Series (MTS) are difficult to implement, especially in the case that the generative model is Generative Adversarial Networks (GANs). We present a general framework named Gaussian GANs to visually evaluate GANs using itself under the MTS generation task. Firstly, we attempt to find the transformation function in the multivariate Kolmogorov Smirnov (MKS) test by explicitly reconstructing the architecture of GANs. Secondly, we conduct the normality test of transformed MST where the Gaussian GANs serves as the transformation function in the MKS test. In order to simplify the normality test, an efficient visualization is proposed using the chi square distribution. In the experiment, we use the UniMiB dataset and provide empirical evidence showing that the normality test using Gaussian GANs and chi sqaure visualization is effective and credible.</abstract><doi>10.48550/arxiv.2208.02649</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2208.02649
ispartof
issn
language eng
recordid cdi_arxiv_primary_2208_02649
source arXiv.org
subjects Computer Science - Learning
Statistics - Applications
title Visually Evaluating Generative Adversarial Networks Using Itself under Multivariate Time Series
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T09%3A17%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Visually%20Evaluating%20Generative%20Adversarial%20Networks%20Using%20Itself%20under%20Multivariate%20Time%20Series&rft.au=Pan,%20Qilong&rft.date=2022-08-04&rft_id=info:doi/10.48550/arxiv.2208.02649&rft_dat=%3Carxiv_GOX%3E2208_02649%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true