Anomaly Detection using LSTM AutoEncoder
Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Mahmoud Moallem [verfasserIn] Ali Akbar Pouyan [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Persisch |
| Erschienen: |
2019 |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
In: مجله مدل سازی در مهندسی - Semnan University, 2023, 17(2019), 56, Seite 191-211 |
|---|---|
| Übergeordnetes Werk: |
volume:17 ; year:2019 ; number:56 ; pages:191-211 |
| Links: |
Link aufrufen |
|---|
| DOI / URN: |
10.22075/jme.2018.12979.1270 |
|---|
| Katalog-ID: |
DOAJ098421425 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | DOAJ098421425 | ||
| 003 | DE-627 | ||
| 005 | 20240413223922.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240413s2019 xx |||||o 00| ||per c | ||
| 024 | 7 | |a 10.22075/jme.2018.12979.1270 |2 doi | |
| 035 | |a (DE-627)DOAJ098421425 | ||
| 035 | |a (DE-599)DOAJf1798676e15041fb988ec5113cef8a26 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a per | ||
| 100 | 0 | |a Mahmoud Moallem |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Anomaly Detection using LSTM AutoEncoder |
| 264 | 1 | |c 2019 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM). | ||
| 650 | 4 | |a anomaly detection | |
| 650 | 4 | |a autoencoder | |
| 650 | 4 | |a lstm | |
| 650 | 4 | |a deep learning | |
| 653 | 0 | |a Engineering design | |
| 653 | 0 | |a TA174 | |
| 700 | 0 | |a Ali Akbar Pouyan |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i In |t مجله مدل سازی در مهندسی |d Semnan University, 2023 |g 17(2019), 56, Seite 191-211 |w (DE-627)DOAJ090667352 |x 27832538 |7 nnns |
| 773 | 1 | 8 | |g volume:17 |g year:2019 |g number:56 |g pages:191-211 |
| 856 | 4 | 0 | |u https://doi.org/10.22075/jme.2018.12979.1270 |z kostenfrei |
| 856 | 4 | 0 | |u https://doaj.org/article/f1798676e15041fb988ec5113cef8a26 |z kostenfrei |
| 856 | 4 | 0 | |u https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf |z kostenfrei |
| 856 | 4 | 2 | |u https://doaj.org/toc/2008-4854 |y Journal toc |z kostenfrei |
| 856 | 4 | 2 | |u https://doaj.org/toc/2783-2538 |y Journal toc |z kostenfrei |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_DOAJ | ||
| 951 | |a AR | ||
| 952 | |d 17 |j 2019 |e 56 |h 191-211 | ||
| author_variant |
m m mm a a p aap |
|---|---|
| matchkey_str |
article:27832538:2019----::nmldtcinsnlta |
| hierarchy_sort_str |
2019 |
| publishDate |
2019 |
| allfields |
10.22075/jme.2018.12979.1270 doi (DE-627)DOAJ098421425 (DE-599)DOAJf1798676e15041fb988ec5113cef8a26 DE-627 ger DE-627 rakwb per Mahmoud Moallem verfasserin aut Anomaly Detection using LSTM AutoEncoder 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM). anomaly detection autoencoder lstm deep learning Engineering design TA174 Ali Akbar Pouyan verfasserin aut In مجله مدل سازی در مهندسی Semnan University, 2023 17(2019), 56, Seite 191-211 (DE-627)DOAJ090667352 27832538 nnns volume:17 year:2019 number:56 pages:191-211 https://doi.org/10.22075/jme.2018.12979.1270 kostenfrei https://doaj.org/article/f1798676e15041fb988ec5113cef8a26 kostenfrei https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf kostenfrei https://doaj.org/toc/2008-4854 Journal toc kostenfrei https://doaj.org/toc/2783-2538 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 17 2019 56 191-211 |
| spelling |
10.22075/jme.2018.12979.1270 doi (DE-627)DOAJ098421425 (DE-599)DOAJf1798676e15041fb988ec5113cef8a26 DE-627 ger DE-627 rakwb per Mahmoud Moallem verfasserin aut Anomaly Detection using LSTM AutoEncoder 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM). anomaly detection autoencoder lstm deep learning Engineering design TA174 Ali Akbar Pouyan verfasserin aut In مجله مدل سازی در مهندسی Semnan University, 2023 17(2019), 56, Seite 191-211 (DE-627)DOAJ090667352 27832538 nnns volume:17 year:2019 number:56 pages:191-211 https://doi.org/10.22075/jme.2018.12979.1270 kostenfrei https://doaj.org/article/f1798676e15041fb988ec5113cef8a26 kostenfrei https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf kostenfrei https://doaj.org/toc/2008-4854 Journal toc kostenfrei https://doaj.org/toc/2783-2538 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 17 2019 56 191-211 |
| allfields_unstemmed |
10.22075/jme.2018.12979.1270 doi (DE-627)DOAJ098421425 (DE-599)DOAJf1798676e15041fb988ec5113cef8a26 DE-627 ger DE-627 rakwb per Mahmoud Moallem verfasserin aut Anomaly Detection using LSTM AutoEncoder 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM). anomaly detection autoencoder lstm deep learning Engineering design TA174 Ali Akbar Pouyan verfasserin aut In مجله مدل سازی در مهندسی Semnan University, 2023 17(2019), 56, Seite 191-211 (DE-627)DOAJ090667352 27832538 nnns volume:17 year:2019 number:56 pages:191-211 https://doi.org/10.22075/jme.2018.12979.1270 kostenfrei https://doaj.org/article/f1798676e15041fb988ec5113cef8a26 kostenfrei https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf kostenfrei https://doaj.org/toc/2008-4854 Journal toc kostenfrei https://doaj.org/toc/2783-2538 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 17 2019 56 191-211 |
| allfieldsGer |
10.22075/jme.2018.12979.1270 doi (DE-627)DOAJ098421425 (DE-599)DOAJf1798676e15041fb988ec5113cef8a26 DE-627 ger DE-627 rakwb per Mahmoud Moallem verfasserin aut Anomaly Detection using LSTM AutoEncoder 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM). anomaly detection autoencoder lstm deep learning Engineering design TA174 Ali Akbar Pouyan verfasserin aut In مجله مدل سازی در مهندسی Semnan University, 2023 17(2019), 56, Seite 191-211 (DE-627)DOAJ090667352 27832538 nnns volume:17 year:2019 number:56 pages:191-211 https://doi.org/10.22075/jme.2018.12979.1270 kostenfrei https://doaj.org/article/f1798676e15041fb988ec5113cef8a26 kostenfrei https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf kostenfrei https://doaj.org/toc/2008-4854 Journal toc kostenfrei https://doaj.org/toc/2783-2538 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 17 2019 56 191-211 |
| allfieldsSound |
10.22075/jme.2018.12979.1270 doi (DE-627)DOAJ098421425 (DE-599)DOAJf1798676e15041fb988ec5113cef8a26 DE-627 ger DE-627 rakwb per Mahmoud Moallem verfasserin aut Anomaly Detection using LSTM AutoEncoder 2019 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM). anomaly detection autoencoder lstm deep learning Engineering design TA174 Ali Akbar Pouyan verfasserin aut In مجله مدل سازی در مهندسی Semnan University, 2023 17(2019), 56, Seite 191-211 (DE-627)DOAJ090667352 27832538 nnns volume:17 year:2019 number:56 pages:191-211 https://doi.org/10.22075/jme.2018.12979.1270 kostenfrei https://doaj.org/article/f1798676e15041fb988ec5113cef8a26 kostenfrei https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf kostenfrei https://doaj.org/toc/2008-4854 Journal toc kostenfrei https://doaj.org/toc/2783-2538 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ AR 17 2019 56 191-211 |
| language |
Persian |
| source |
In مجله مدل سازی در مهندسی 17(2019), 56, Seite 191-211 volume:17 year:2019 number:56 pages:191-211 |
| sourceStr |
In مجله مدل سازی در مهندسی 17(2019), 56, Seite 191-211 volume:17 year:2019 number:56 pages:191-211 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
anomaly detection autoencoder lstm deep learning Engineering design TA174 |
| isfreeaccess_bool |
true |
| container_title |
مجله مدل سازی در مهندسی |
| authorswithroles_txt_mv |
Mahmoud Moallem @@aut@@ Ali Akbar Pouyan @@aut@@ |
| publishDateDaySort_date |
2019-01-01T00:00:00Z |
| hierarchy_top_id |
DOAJ090667352 |
| id |
DOAJ098421425 |
| language_de |
persisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ098421425</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413223922.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240413s2019 xx |||||o 00| ||per c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.22075/jme.2018.12979.1270</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ098421425</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJf1798676e15041fb988ec5113cef8a26</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">per</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Mahmoud Moallem</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Anomaly Detection using LSTM AutoEncoder</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM).</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">anomaly detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">autoencoder</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">lstm</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Engineering design</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">TA174</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ali Akbar Pouyan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">مجله مدل سازی در مهندسی</subfield><subfield code="d">Semnan University, 2023</subfield><subfield code="g">17(2019), 56, Seite 191-211</subfield><subfield code="w">(DE-627)DOAJ090667352</subfield><subfield code="x">27832538</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:17</subfield><subfield code="g">year:2019</subfield><subfield code="g">number:56</subfield><subfield code="g">pages:191-211</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.22075/jme.2018.12979.1270</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/f1798676e15041fb988ec5113cef8a26</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2008-4854</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2783-2538</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">17</subfield><subfield code="j">2019</subfield><subfield code="e">56</subfield><subfield code="h">191-211</subfield></datafield></record></collection>
|
| author |
Mahmoud Moallem |
| spellingShingle |
Mahmoud Moallem misc anomaly detection misc autoencoder misc lstm misc deep learning misc Engineering design misc TA174 Anomaly Detection using LSTM AutoEncoder |
| authorStr |
Mahmoud Moallem |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)DOAJ090667352 |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut aut |
| collection |
DOAJ |
| remote_str |
true |
| illustrated |
Not Illustrated |
| issn |
27832538 |
| topic_title |
Anomaly Detection using LSTM AutoEncoder anomaly detection autoencoder lstm deep learning |
| topic |
misc anomaly detection misc autoencoder misc lstm misc deep learning misc Engineering design misc TA174 |
| topic_unstemmed |
misc anomaly detection misc autoencoder misc lstm misc deep learning misc Engineering design misc TA174 |
| topic_browse |
misc anomaly detection misc autoencoder misc lstm misc deep learning misc Engineering design misc TA174 |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
مجله مدل سازی در مهندسی |
| hierarchy_parent_id |
DOAJ090667352 |
| hierarchy_top_title |
مجله مدل سازی در مهندسی |
| isfreeaccess_txt |
true |
| familylinks_str_mv |
(DE-627)DOAJ090667352 |
| title |
Anomaly Detection using LSTM AutoEncoder |
| ctrlnum |
(DE-627)DOAJ098421425 (DE-599)DOAJf1798676e15041fb988ec5113cef8a26 |
| title_full |
Anomaly Detection using LSTM AutoEncoder |
| author_sort |
Mahmoud Moallem |
| journal |
مجله مدل سازی در مهندسی |
| journalStr |
مجله مدل سازی در مهندسی |
| lang_code |
per |
| isOA_bool |
true |
| recordtype |
marc |
| publishDateSort |
2019 |
| contenttype_str_mv |
txt |
| container_start_page |
191 |
| author_browse |
Mahmoud Moallem Ali Akbar Pouyan |
| container_volume |
17 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Mahmoud Moallem |
| doi_str_mv |
10.22075/jme.2018.12979.1270 |
| author2-role |
verfasserin |
| title_sort |
anomaly detection using lstm autoencoder |
| title_auth |
Anomaly Detection using LSTM AutoEncoder |
| abstract |
Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM). |
| abstractGer |
Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM). |
| abstract_unstemmed |
Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM). |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ |
| container_issue |
56 |
| title_short |
Anomaly Detection using LSTM AutoEncoder |
| url |
https://doi.org/10.22075/jme.2018.12979.1270 https://doaj.org/article/f1798676e15041fb988ec5113cef8a26 https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf https://doaj.org/toc/2008-4854 https://doaj.org/toc/2783-2538 |
| remote_bool |
true |
| author2 |
Ali Akbar Pouyan |
| author2Str |
Ali Akbar Pouyan |
| ppnlink |
DOAJ090667352 |
| mediatype_str_mv |
c |
| isOA_txt |
true |
| hochschulschrift_bool |
false |
| doi_str |
10.22075/jme.2018.12979.1270 |
| up_date |
2024-07-03T17:09:56.069Z |
| _version_ |
1803578608004890624 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ098421425</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413223922.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240413s2019 xx |||||o 00| ||per c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.22075/jme.2018.12979.1270</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ098421425</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJf1798676e15041fb988ec5113cef8a26</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">per</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Mahmoud Moallem</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Anomaly Detection using LSTM AutoEncoder</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM).</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">anomaly detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">autoencoder</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">lstm</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Engineering design</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">TA174</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ali Akbar Pouyan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">مجله مدل سازی در مهندسی</subfield><subfield code="d">Semnan University, 2023</subfield><subfield code="g">17(2019), 56, Seite 191-211</subfield><subfield code="w">(DE-627)DOAJ090667352</subfield><subfield code="x">27832538</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:17</subfield><subfield code="g">year:2019</subfield><subfield code="g">number:56</subfield><subfield code="g">pages:191-211</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.22075/jme.2018.12979.1270</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/f1798676e15041fb988ec5113cef8a26</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2008-4854</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2783-2538</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">17</subfield><subfield code="j">2019</subfield><subfield code="e">56</subfield><subfield code="h">191-211</subfield></datafield></record></collection>
|
| score |
7.4000406 |