Applying quantum autoencoders for time series anomaly detection
Anomaly detection is an important problem with applications in various domains such as fraud detection, pattern recognition, or medical diagnosis. Several algorithms have been introduced using classical computing approaches. However, using quantum computing for solving anomaly detection problems in...
Uloženo v:
| Vydáno v: | Quantum machine intelligence Ročník 7; číslo 1 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Cham
Springer International Publishing
01.06.2025
|
| Témata: | |
| ISSN: | 2524-4906, 2524-4914 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Anomaly detection is an important problem with applications in various domains such as fraud detection, pattern recognition, or medical diagnosis. Several algorithms have been introduced using classical computing approaches. However, using quantum computing for solving anomaly detection problems in time series data is a widely unexplored research field. This paper explores the application of quantum autoencoders to time series anomaly detection. We investigate two primary techniques for classifying anomalies: (1) Analyzing the reconstruction error generated by the quantum autoencoder and (2) latent representation analysis. Our simulated experimental results, conducted across various ansaetze, demonstrate that quantum autoencoders consistently outperform classical deep learning-based autoencoders across multiple datasets. Specifically, quantum autoencoders achieve superior anomaly detection performance while utilizing 60–230 times fewer parameters and requiring five times fewer training iterations. In addition, we implement our quantum encoder on real quantum hardware. Our experimental results demonstrate that quantum autoencoders achieve anomaly detection performance on par with their simulated counterparts. |
|---|---|
| AbstractList | Anomaly detection is an important problem with applications in various domains such as fraud detection, pattern recognition, or medical diagnosis. Several algorithms have been introduced using classical computing approaches. However, using quantum computing for solving anomaly detection problems in time series data is a widely unexplored research field. This paper explores the application of quantum autoencoders to time series anomaly detection. We investigate two primary techniques for classifying anomalies: (1) Analyzing the reconstruction error generated by the quantum autoencoder and (2) latent representation analysis. Our simulated experimental results, conducted across various ansaetze, demonstrate that quantum autoencoders consistently outperform classical deep learning-based autoencoders across multiple datasets. Specifically, quantum autoencoders achieve superior anomaly detection performance while utilizing 60–230 times fewer parameters and requiring five times fewer training iterations. In addition, we implement our quantum encoder on real quantum hardware. Our experimental results demonstrate that quantum autoencoders achieve anomaly detection performance on par with their simulated counterparts. |
| ArticleNumber | 59 |
| Author | Frehner, Robin Stockinger, Kurt |
| Author_xml | – sequence: 1 givenname: Robin surname: Frehner fullname: Frehner, Robin email: frehner.robin@gmail.com organization: Zurich University of Applied Sciences – sequence: 2 givenname: Kurt surname: Stockinger fullname: Stockinger, Kurt organization: Zurich University of Applied Sciences |
| BookMark | eNp9kD1PwzAQhi0EEqX0DzD5Dxj8ldqZUFXxJVVigdlynHOVKrGL7Qz996QUMTD0lrvhfU53zw26DDEAQneM3jNK1UOWXGpJKK8IpVxXhF2gGa-4JLJm8vJvpstrtMh5R6eUElLT5Qw9rvb7_tCFLf4abSjjgO1YIgQXW0gZ-5hw6QbAGVIHGdsQB9sfcAsFXOliuEVX3vYZFr99jj6fnz7Wr2Tz_vK2Xm2IE0IV0nBZtVooy2njLYATSgguGk2V9pWQlFtPxbG8ktCIuqpbrmu3bFvPGuvEHOnTXpdizgm8cV2xxwtKsl1vGDVHF-bkwkwuzI8LwyaU_0P3qRtsOpyHxAnKUzhsIZldHFOYXjxHfQPsWnPY |
| CitedBy_id | crossref_primary_10_1007_s11227_025_07714_9 |
| Cites_doi | 10.1038/s41598-023-38558-z 10.1063/5.0082975 10.1109/TSMC.2020.2968516 10.1145/3444690 10.1088/2058-9565/abe458 10.1109/ACCESS.2024.3371891 10.1103/PhysRevA.109.032623 10.1109/JIOT.2019.2958185 10.1038/s41467-021-22539-9 10.1145/2689746.2689747 10.1109/ACCESS.2023.3236409 10.1109/ACCESS.2021.3107975 10.1007/s42484-022-00075-z 10.1038/s41467-023-36159-y 10.1038/s41586-023-06096-3 10.21203/rs.3.rs-2310685/v1 10.1140/epjqt/s40507-021-00091-1 10.1088/2632-2153/ac0616 10.1103/physrevresearch.4.023136 10.1088/2058-9565/aa8072 10.1103/PhysRevD.105.095004 10.1038/s41467-018-07090-4 10.1007/s42484-023-00112-5 10.1007/s42484-023-00133-0 10.1145/3665225.3665444 10.3390/e25030427 10.1109/TKDE.2021.3112126 |
| ContentType | Journal Article |
| Copyright | The Author(s) 2025 |
| Copyright_xml | – notice: The Author(s) 2025 |
| DBID | C6C AAYXX CITATION |
| DOI | 10.1007/s42484-025-00285-1 |
| DatabaseName | Springer Nature OA Free Journals CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2524-4914 |
| ExternalDocumentID | 10_1007_s42484_025_00285_1 |
| GrantInformation_xml | – fundername: ZHAW Zurich University of Applied Sciences |
| GroupedDBID | 0R~ 406 AACDK AAHNG AAJBT AASML AATNV AAUYE ABAKF ABBRH ABDBE ABDZT ABECU ABFSG ABFTV ABJNI ABKCH ABMQK ABTEG ABTKH ABTMW ABXPI ACAOD ACDTI ACHSB ACMLO ACOKC ACPIV ACSTC ACZOJ ADKNI ADTPH ADURQ ADYFF AEFQL AEJRE AEMSY AESKC AEZWR AFBBN AFDZB AFHIU AFOHR AFQWF AGDGC AGJBK AGMZJ AGQEE AGRTI AHPBZ AHWEU AIGIU AILAN AITGF AIXLP AJZVZ ALMA_UNASSIGNED_HOLDINGS AMKLP AMXSW AMYLF ATHPR AXYYD AYFIA BGNMA C6C DPUIP EBLON EBS EJD FIGPU FINBP FNLPD FSGXE GGCAI H13 IKXTQ IWAJR J-C JZLTJ KOV LLZTM M4Y NPVJJ NQJWS NU0 PT4 ROL RSV SJYHP SNE SNPRN SOHCF SOJ SRMVM SSLCW STPWE TSG UOJIU UTJUX VEKWB VFIZW ZMTXR AAYXX ABRTQ CITATION |
| ID | FETCH-LOGICAL-c337t-b245d837a20bfaeec373323b8078f53402af033333f74eb3959d289c6ddf1bac3 |
| IEDL.DBID | RSV |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001482754500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2524-4906 |
| IngestDate | Tue Nov 18 22:32:07 EST 2025 Sat Nov 29 07:48:22 EST 2025 Fri Jun 27 01:51:16 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Keywords | Quantum computing Quantum machine learning Time series anomaly detection Quantum autoencoder |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c337t-b245d837a20bfaeec373323b8078f53402af033333f74eb3959d289c6ddf1bac3 |
| OpenAccessLink | https://link.springer.com/10.1007/s42484-025-00285-1 |
| ParticipantIDs | crossref_citationtrail_10_1007_s42484_025_00285_1 crossref_primary_10_1007_s42484_025_00285_1 springer_journals_10_1007_s42484_025_00285_1 |
| PublicationCentury | 2000 |
| PublicationDate | 20250600 2025-06-00 |
| PublicationDateYYYYMMDD | 2025-06-01 |
| PublicationDate_xml | – month: 6 year: 2025 text: 20250600 |
| PublicationDecade | 2020 |
| PublicationPlace | Cham |
| PublicationPlace_xml | – name: Cham |
| PublicationTitle | Quantum machine intelligence |
| PublicationTitleAbbrev | Quantum Mach. Intell |
| PublicationYear | 2025 |
| Publisher | Springer International Publishing |
| Publisher_xml | – name: Springer International Publishing |
| References | 285_CR14 285_CR12 285_CR13 285_CR18 X Vasques (285_CR27) 2023; 13 Y Zhu (285_CR32) 2023; 5 285_CR17 RDM Simões (285_CR26) 2023; 11 285_CR5 H-Y Huang (285_CR11) 2021; 12 285_CR1 285_CR2 AA Cook (285_CR7) 2020; 7 285_CR21 K Choi (285_CR6) 2021; 9 JR McClean (285_CR19) 2018; 9 285_CR22 285_CR20 MP Cuéllar (285_CR8) 2023; 5 285_CR25 S Jerbi (285_CR15) 2023; 14 285_CR24 C Bravo-Prieto (285_CR4) 2021; 2 285_CR28 C Yin (285_CR31) 2022; 52 F Bova (285_CR3) 2021; 8 J Romero (285_CR23) 2017; 2 J Wu (285_CR29) 2024; 109 S Foulds (285_CR9) 2021; 6 285_CR10 Y Kim (285_CR16) 2023; 618 285_CR30 |
| References_xml | – volume: 13 start-page: 11541 issue: 1 year: 2023 ident: 285_CR27 publication-title: Sci Reports doi: 10.1038/s41598-023-38558-z – ident: 285_CR5 doi: 10.1063/5.0082975 – volume: 52 start-page: 112 issue: 1 year: 2022 ident: 285_CR31 publication-title: IEEE Trans Syst, Man, Cybernet: Syst doi: 10.1109/TSMC.2020.2968516 – ident: 285_CR2 doi: 10.1145/3444690 – volume: 6 issue: 3 year: 2021 ident: 285_CR9 publication-title: Quantum Sci Technol doi: 10.1088/2058-9565/abe458 – ident: 285_CR10 doi: 10.1109/ACCESS.2024.3371891 – volume: 109 year: 2024 ident: 285_CR29 publication-title: Phys Rev A doi: 10.1103/PhysRevA.109.032623 – volume: 7 start-page: 6481 issue: 7 year: 2020 ident: 285_CR7 publication-title: IEEE Int Things J doi: 10.1109/JIOT.2019.2958185 – volume: 12 start-page: 2631 issue: 1 year: 2021 ident: 285_CR11 publication-title: Nature Commun doi: 10.1038/s41467-021-22539-9 – ident: 285_CR25 doi: 10.1145/2689746.2689747 – volume: 11 start-page: 6197 year: 2023 ident: 285_CR26 publication-title: IEEE Access doi: 10.1109/ACCESS.2023.3236409 – volume: 9 start-page: 120043 year: 2021 ident: 285_CR6 publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3107975 – ident: 285_CR13 – ident: 285_CR24 doi: 10.1007/s42484-022-00075-z – volume: 14 start-page: 517 issue: 1 year: 2023 ident: 285_CR15 publication-title: Nature Commun doi: 10.1038/s41467-023-36159-y – volume: 618 start-page: 500 issue: 7965 year: 2023 ident: 285_CR16 publication-title: Nature doi: 10.1038/s41586-023-06096-3 – ident: 285_CR1 doi: 10.21203/rs.3.rs-2310685/v1 – volume: 8 start-page: 2 issue: 1 year: 2021 ident: 285_CR3 publication-title: EPJ Quantum Technol doi: 10.1140/epjqt/s40507-021-00091-1 – volume: 2 issue: 3 year: 2021 ident: 285_CR4 publication-title: Mach Learning: Sci Technol doi: 10.1088/2632-2153/ac0616 – ident: 285_CR20 doi: 10.1103/physrevresearch.4.023136 – volume: 2 issue: 4 year: 2017 ident: 285_CR23 publication-title: Quantum Sci Technol doi: 10.1088/2058-9565/aa8072 – ident: 285_CR21 doi: 10.1103/PhysRevD.105.095004 – volume: 9 start-page: 4812 issue: 1 year: 2018 ident: 285_CR19 publication-title: Nat Commun doi: 10.1038/s41467-018-07090-4 – volume: 5 start-page: 27 issue: 2 year: 2023 ident: 285_CR32 publication-title: Q Mach Intell doi: 10.1007/s42484-023-00112-5 – ident: 285_CR14 – ident: 285_CR12 – volume: 5 start-page: 45 issue: 2 year: 2023 ident: 285_CR8 publication-title: Q Mach Intell doi: 10.1007/s42484-023-00133-0 – ident: 285_CR22 doi: 10.1103/PhysRevD.105.095004 – ident: 285_CR17 doi: 10.1145/3665225.3665444 – ident: 285_CR18 – ident: 285_CR28 doi: 10.3390/e25030427 – ident: 285_CR30 doi: 10.1109/TKDE.2021.3112126 |
| SSID | ssj0002734806 |
| Score | 2.3072138 |
| Snippet | Anomaly detection is an important problem with applications in various domains such as fraud detection, pattern recognition, or medical diagnosis. Several... |
| SourceID | crossref springer |
| SourceType | Enrichment Source Index Database Publisher |
| SubjectTerms | Artificial Intelligence Computational Intelligence Engineering Quantum Information Technology Research Article Spintronics |
| Title | Applying quantum autoencoders for time series anomaly detection |
| URI | https://link.springer.com/article/10.1007/s42484-025-00285-1 |
| Volume | 7 |
| WOSCitedRecordID | wos001482754500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 2524-4914 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002734806 issn: 2524-4906 databaseCode: RSV dateStart: 20190501 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3LSsQwFA0yutCFb3F8kYU7DbR5tOlKRBQXMoiPYXYlSVMQZjo6bQX_3txMWxyQAe06LeX0psm5ufcchM41-BpRFZE4EoxwEWgimWaQEpCRySzn3u5t-BAPBnI0Sh6bprCyrXZvjyT9n7prduOUS07AfhWIgiCO86y65U7CdHx6HnaZFS_Y4k01qaCc8CSImm6Z3x-zuCItHof6VeZu63_vt402m10lvp6HwQ5ascUu2vihNbiHrmC_CT1N-KN2aNYTrOpqCjKWUMqM3d4Vg888hpC0JVbFdKLGXzizlS_WKvbR693ty809adwTiGEsroimXGSOfioa6FxZa1jMGGUaBOZzwRxvVHnA4Mpj7ih1IpLMsS8TZVkeamXYAeoV08IeIpzLWGoa5tREkkvlpnysMsYcU5JKiVD3UdgimJpGWhwcLsZpJ4rswUkdOKkHJw376KK7530urLF09GULetpMsnLJ8KO_DT9G69R_N0iunKBeNavtKVozn9VbOTvz0fUNoRfGZQ |
| linkProvider | Springer Nature |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bS8MwFA6igvrgXZzXPPimgTaXNn0SEcfEOUTn2FtJ0hSErdO1Ffz3JllbHMhA-3xayulJz_mSc74PgAtpdY2wCFAYMIIo8yTiRBK7JcADlWhKndzboBv2enw4jJ6qobC87navjyTdn7oZdqOYcoqs_KoFCgwZzLNCTcayjXzPL4NmZ8URtjhRTcwwRTTygmpa5vfHzGek-eNQl2XaW_97v22wWVWV8GYWBjtgSWe7YOMH1-AeuLb1pp1pgh-l8WY5hqIsJpbG0rYyQ1O7QqszD21I6hyKbDIWoy-Y6MI1a2X74LV917_toEo9ASlCwgJJTFli4KfAnkyF1oqEhGAiLcF8yojBjSL1iL3SkBpIHbEoMehLBUmS-lIocgCWs0mmDwFMecgl9lOsAk65MEs-FAkhBilxIZgvW8CvPRirilrcKlyM4oYU2TknNs6JnXNivwUum3veZ8QaC62vaqfH1SLLF5gf_c38HKx1-o_duHvfezgG69h9Q7vRcgKWi2mpT8Gq-ize8umZi7Rv99vJSQ |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEF5ERfTgW6zPPXjTpc0-ks1JRC2KpRTU0lvYzSYgtGltE8F_7842DS1IQcx5EsLsJDvf7Mz3IXSlQdeIKp8EvmCEi4YmkmkGJQHpxybh3Mm9dVtBuy17vbAzN8Xvut1nR5LTmQZgacry-sik9WrwjVMuOQEpVgANglj8s8ZBNAjw-mu3qrI48hYnsEkF5YSHDb-cnPn9MYu70-LRqNtxmjv_f9ddtF1mm_huGh57aCXJ9tHWHAfhAbqFPBRmnfBnYb1cDLAq8iHQW0KLM7Y5LQb9eQyhmkywyoYD1f_GJsldE1d2iN6bj2_3T6RUVSAxY0FONOXCWFiqaEOnKkliFjBGmQbi-VQwiydV2mBwpQG3UDsUobGoLPaNST2tYnaEVrNhlhwjnMpAauqlNPYll8r-CgJlGLMISiolPF1D3sybUVxSjoPyRT-qyJKdcyLrnMg5J_Jq6Lq6ZzQl3FhqfTNbgKj8-CZLzE_-Zn6JNjoPzaj13H45RZvULSHUX87Qaj4uknO0Hn_lH5PxhQu6Hy7e0i0 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Applying+quantum+autoencoders+for+time+series+anomaly+detection&rft.jtitle=Quantum+machine+intelligence&rft.au=Frehner%2C+Robin&rft.au=Stockinger%2C+Kurt&rft.date=2025-06-01&rft.issn=2524-4906&rft.eissn=2524-4914&rft.volume=7&rft.issue=1&rft_id=info:doi/10.1007%2Fs42484-025-00285-1&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s42484_025_00285_1 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2524-4906&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2524-4906&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2524-4906&client=summon |