The Recommendation Algorithm Based on Improved Conditional Variational Autoencoder and Constrained Probabilistic Matrix Factorization
An improved recommendation algorithm based on Conditional Variational Autoencoder (CVAE) and Constrained Probabilistic Matrix Factorization (CPMF) is proposed to address the issues of poor recommendation performance in traditional user-based collaborative filtering algorithms caused by data sparsity...
Uloženo v:
| Vydáno v: | Applied sciences Ročník 13; číslo 21; s. 12027 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Basel
MDPI AG
01.11.2023
|
| Témata: | |
| ISSN: | 2076-3417, 2076-3417 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | An improved recommendation algorithm based on Conditional Variational Autoencoder (CVAE) and Constrained Probabilistic Matrix Factorization (CPMF) is proposed to address the issues of poor recommendation performance in traditional user-based collaborative filtering algorithms caused by data sparsity and suboptimal feature extraction. Firstly, in the data preprocessing stage, a hidden layer is added to CVAE, and random noise is introduced into the hidden layer to constrain the data features, thereby obtaining more accurate latent features and improving the model’s robustness and generative capability. Secondly, the category of items is incorporated as auxiliary information in CVAE to supervise the encoding and decoding of item data. By learning the distribution characteristics of the data, missing values in the rating data can be effectively reconstructed, thereby reducing the sparsity of the rating matrix. Subsequently, the reconstructed data is processed using CPMF, which optimizes the feature extraction performance by imposing constraints on user features. Finally, the prediction rating of a user for an item can be obtained through the matrix product of user and item feature matrices. Experimental results on the MovieLens-100K and MovieLens-1M datasets demonstrate the effectiveness and superiority of the proposed algorithm over four comparative algorithms, as it exhibits significant advantages in terms of root mean square error and mean absolute error metrics. |
|---|---|
| AbstractList | An improved recommendation algorithm based on Conditional Variational Autoencoder (CVAE) and Constrained Probabilistic Matrix Factorization (CPMF) is proposed to address the issues of poor recommendation performance in traditional user-based collaborative filtering algorithms caused by data sparsity and suboptimal feature extraction. Firstly, in the data preprocessing stage, a hidden layer is added to CVAE, and random noise is introduced into the hidden layer to constrain the data features, thereby obtaining more accurate latent features and improving the model’s robustness and generative capability. Secondly, the category of items is incorporated as auxiliary information in CVAE to supervise the encoding and decoding of item data. By learning the distribution characteristics of the data, missing values in the rating data can be effectively reconstructed, thereby reducing the sparsity of the rating matrix. Subsequently, the reconstructed data is processed using CPMF, which optimizes the feature extraction performance by imposing constraints on user features. Finally, the prediction rating of a user for an item can be obtained through the matrix product of user and item feature matrices. Experimental results on the MovieLens-100K and MovieLens-1M datasets demonstrate the effectiveness and superiority of the proposed algorithm over four comparative algorithms, as it exhibits significant advantages in terms of root mean square error and mean absolute error metrics. |
| Audience | Academic |
| Author | Zhang, Yunfei Xu, Hongzhen Yu, Xiaojun |
| Author_xml | – sequence: 1 givenname: Yunfei surname: Zhang fullname: Zhang, Yunfei – sequence: 2 givenname: Hongzhen surname: Xu fullname: Xu, Hongzhen – sequence: 3 givenname: Xiaojun surname: Yu fullname: Yu, Xiaojun |
| BookMark | eNptUU1vEzEQtVCRKKU3fsBKXEnx2N619xgiCpGKQKhwtfwxmzraXQfbqYA7_xsnKVKFsA9-Gr33xvPmOTmb44yEvAR6xXlP35jdDjgDYJTJJ-ScUdktuAB59gg_I5c5b2k9PXAF9Jz8vr3D5gu6OE04e1NCnJvluIkplLupeWsy-qaW1tMuxfuKV3H24cAyY_PNpGAe8HJfIs4uekyNmY-8XJIJc9V8TtEaG8aQS3DNR1NS-NFcG1dql19Hgxfk6WDGjJcP7wX5ev3udvVhcfPp_Xq1vFk4QbuywFZQ8AocKN5jnaLrnG8BByVQUcMkU9xxr6wFOihvLW-lBUCPA3fGcn5B1idfH81W71KYTPqpown6WIhpo02qnxxRd6zzPW2xE8ILOdDeopNDLzhYxbpOVq9XJ6-azPc95qK3cZ9qFlkzpRSAZOLQ8erE2phqGuYh1lRcvR6n4OoGh1DrSylZy6GlogrYSeBSzDnhoF0ox5AOcY4aqD6sWz9edxW9_kf0d7b_0v8A85musg |
| CitedBy_id | crossref_primary_10_1049_cit2_12408 crossref_primary_10_3390_computers13110275 crossref_primary_10_3390_app15052761 |
| Cites_doi | 10.1007/s10489-021-02207-7 10.1007/s00521-020-05085-1 10.1109/ACCESS.2021.3074365 10.1145/1273496.1273596 10.1145/2647868.2654940 10.1016/j.inffus.2023.101903 10.1145/3077136.3080697 10.1145/2783258.2783273 10.1145/2835776.2835837 10.1016/j.ins.2020.12.001 10.1155/2021/6610645 10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00201 10.1007/s11280-020-00793-z 10.5565/rev/elcvia.1232 10.1016/j.asoc.2022.108971 10.1145/3097983.3098077 10.1016/j.neucom.2019.01.028 10.1145/2020408.2020480 10.1109/TCSS.2022.3170691 10.1109/ACCESS.2023.3246060 10.3390/electronics10101215 |
| ContentType | Journal Article |
| Copyright | COPYRIGHT 2023 MDPI AG 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: COPYRIGHT 2023 MDPI AG – notice: 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | AAYXX CITATION ABUWG AFKRA AZQEC BENPR CCPQU DWQXO PHGZM PHGZT PIMPY PKEHL PQEST PQQKQ PQUKI DOA |
| DOI | 10.3390/app132112027 |
| DatabaseName | CrossRef ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials - QC ProQuest Central ProQuest One ProQuest Central ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef Publicly Available Content Database ProQuest Central ProQuest One Academic Middle East (New) ProQuest One Academic UKI Edition ProQuest Central Essentials ProQuest Central Korea ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New) |
| DatabaseTitleList | Publicly Available Content Database CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Sciences (General) |
| EISSN | 2076-3417 |
| ExternalDocumentID | oai_doaj_org_article_626d905e644d47f09bec7f9431b82667 A772531504 10_3390_app132112027 |
| GeographicLocations | New York |
| GeographicLocations_xml | – name: New York |
| GroupedDBID | .4S 2XV 5VS 7XC 8CJ 8FE 8FG 8FH AADQD AAFWJ AAYXX ADBBV ADMLS AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS APEBS ARCSS BCNDV BENPR CCPQU CITATION CZ9 D1I D1J D1K GROUPED_DOAJ IAO IGS ITC K6- K6V KC. KQ8 L6V LK5 LK8 M7R MODMG M~E OK1 P62 PHGZM PHGZT PIMPY PROAC TUS ABUWG AZQEC DWQXO PKEHL PQEST PQQKQ PQUKI |
| ID | FETCH-LOGICAL-c406t-e5401d81c1839e00066cd51ef84e80a27283c3d8bb10f8dbb357b11edef3cab33 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001100460400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2076-3417 |
| IngestDate | Tue Oct 14 18:38:14 EDT 2025 Sun Nov 30 05:15:46 EST 2025 Tue Nov 04 18:38:21 EST 2025 Sat Nov 29 07:12:17 EST 2025 Tue Nov 18 21:59:59 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 21 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c406t-e5401d81c1839e00066cd51ef84e80a27283c3d8bb10f8dbb357b11edef3cab33 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| OpenAccessLink | https://doaj.org/article/626d905e644d47f09bec7f9431b82667 |
| PQID | 2888117243 |
| PQPubID | 2032433 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_626d905e644d47f09bec7f9431b82667 proquest_journals_2888117243 gale_infotracacademiconefile_A772531504 crossref_citationtrail_10_3390_app132112027 crossref_primary_10_3390_app132112027 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-11-01 |
| PublicationDateYYYYMMDD | 2023-11-01 |
| PublicationDate_xml | – month: 11 year: 2023 text: 2023-11-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Basel |
| PublicationPlace_xml | – name: Basel |
| PublicationTitle | Applied sciences |
| PublicationYear | 2023 |
| Publisher | MDPI AG |
| Publisher_xml | – name: MDPI AG |
| References | Pan (ref_18) 2020; 23 Bin (ref_24) 2021; 2021 Shi (ref_27) 2021; 47 ref_14 ref_13 ref_12 ref_11 Ortega (ref_9) 2021; 553 ref_30 Chen (ref_10) 2020; 57 Goyani (ref_4) 2020; 19 ref_17 ref_15 Qian (ref_5) 2022; 59 Zheng (ref_23) 2022; 10 Na (ref_16) 2021; 51 Wu (ref_1) 2022; 16 Liu (ref_22) 2023; 11 Zhang (ref_8) 2019; 334 Niu (ref_19) 2023; 100 Zhang (ref_25) 2021; 9 Tahmasebi (ref_20) 2021; 33 ref_2 Wang (ref_21) 2022; 123 ref_29 ref_28 ref_26 ref_7 Yimu (ref_3) 2020; 27 ref_6 |
| References_xml | – volume: 51 start-page: 7946 year: 2021 ident: ref_16 article-title: A hybrid user-based collaborative filtering algorithm with topic model publication-title: Appl. Intell. doi: 10.1007/s10489-021-02207-7 – volume: 33 start-page: 1607 year: 2021 ident: ref_20 article-title: Social movie recommender system based on deep autoencoder network using Twitter data publication-title: Neural Comput. Appl. doi: 10.1007/s00521-020-05085-1 – volume: 9 start-page: 65266 year: 2021 ident: ref_25 article-title: FeatureMF: An item feature enriched matrix factorization model for item recommendation publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3074365 – ident: ref_26 – volume: 59 start-page: 2803 year: 2022 ident: ref_5 article-title: Event Recommendation Strategy Combining User Long-Short Term Interest and Event Influence publication-title: J. Comput. Res. Dev. – ident: ref_6 doi: 10.1145/1273496.1273596 – ident: ref_7 doi: 10.1145/2647868.2654940 – volume: 100 start-page: 101903 year: 2023 ident: ref_19 article-title: Deep adversarial autoencoder recommendation algorithm based on group influence publication-title: Inf. Fusion doi: 10.1016/j.inffus.2023.101903 – ident: ref_15 doi: 10.1145/3077136.3080697 – ident: ref_28 doi: 10.1145/2783258.2783273 – ident: ref_13 doi: 10.1145/2835776.2835837 – volume: 57 start-page: 1096 year: 2020 ident: ref_10 article-title: Collaborative filtering recommendation based on transfer learning and joint matrix decomposition publication-title: J. Sichuan Univ. (Nat. Sci. Ed.) – volume: 553 start-page: 110 year: 2021 ident: ref_9 article-title: Providing reliability in recommender systems through Bernoulli matrix factorization publication-title: Inf. Sci. doi: 10.1016/j.ins.2020.12.001 – volume: 2021 start-page: 6610645 year: 2021 ident: ref_24 article-title: Matrix factorization recommendation algorithm based on multiple social relationships publication-title: Math. Probl. Eng. doi: 10.1155/2021/6610645 – volume: 47 start-page: 2103 year: 2021 ident: ref_27 article-title: Research Advances on Stochastic Gradient Descent Algorithms publication-title: Acta Autom. Sin. – ident: ref_11 doi: 10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00201 – volume: 23 start-page: 2259 year: 2020 ident: ref_18 article-title: Learning social representations with deep autoencoder for recommender system publication-title: World Wide Web doi: 10.1007/s11280-020-00793-z – ident: ref_29 – volume: 16 start-page: 21 year: 2022 ident: ref_1 article-title: Survey of personalized learning recommendation publication-title: J. Front. Comput. Sci. Technol. – ident: ref_12 – volume: 27 start-page: 1 year: 2020 ident: ref_3 article-title: Collaborative filtering recommendation algorithm based on interactive data classification publication-title: J. China Univ. Posts Telecommun. – volume: 19 start-page: 0018 year: 2020 ident: ref_4 article-title: A review of movie recommendation system: Limitations, Survey and Challenges publication-title: ELCVIA Electron. Lett. Comput. Vis. Image Anal. doi: 10.5565/rev/elcvia.1232 – volume: 123 start-page: 108971 year: 2022 ident: ref_21 article-title: Research on product recommendation based on matrix factorization models fusing user reviews publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2022.108971 – ident: ref_14 doi: 10.1145/3097983.3098077 – ident: ref_17 – volume: 334 start-page: 206 year: 2019 ident: ref_8 article-title: A deep variational matrix factorization method for recommendation on large scale sparse dataset publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.01.028 – ident: ref_30 doi: 10.1145/2020408.2020480 – volume: 10 start-page: 1189 year: 2022 ident: ref_23 article-title: A Matrix Factorization Recommendation System-Based Local Differential Privacy for Protecting Users’ Sensitive Data publication-title: IEEE Trans. Comput. Soc. Syst. doi: 10.1109/TCSS.2022.3170691 – volume: 11 start-page: 16994 year: 2023 ident: ref_22 article-title: Recommendation system based on deep sentiment analysis and matrix factorization publication-title: IEEE Access doi: 10.1109/ACCESS.2023.3246060 – ident: ref_2 doi: 10.3390/electronics10101215 |
| SSID | ssj0000913810 |
| Score | 2.2856026 |
| Snippet | An improved recommendation algorithm based on Conditional Variational Autoencoder (CVAE) and Constrained Probabilistic Matrix Factorization (CPMF) is proposed... |
| SourceID | doaj proquest gale crossref |
| SourceType | Open Website Aggregation Database Enrichment Source Index Database |
| StartPage | 12027 |
| SubjectTerms | Algorithms Analysis auxiliary information Collaboration collaborative filtering conditional variational autoencoder constrained probabilistic matrix factorization feature matric Neural networks Optimization techniques Ratings & rankings Recommender systems Sparsity User behavior |
| SummonAdditionalLinks | – databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT9wwELVa6KEcoNBWXQrIh6K2qiLixCHOqdpFrHpoVyvUVtwsf9JK7AaSgPgD_d-dcbzLXuDCbZV1Ekcez7wZ2-8R8kHbUnADaSorVJZwplSi8kwnWOIHPKIhggQS1-_lZCLOz6tpLLi1cVvlwicGR21rgzXyowxSNQbRludfr64TVI3C1dUoofGcrCNTGdj5-uh0Mj1bVlmQ9VKwtN_xnkN-j-vC8HpAGSkKyazEokDZ_5BjDtFmvPXUfr4imxFn0mFvGNvkmZvvkI0V9sEdsh3ndUs_RfLpz6_JP7AbijnpbOai3hIdXl7AG7o_MzqCmGcpXOprEfD7pMY171BPpL8h7461RTq86WrkyLSuoWoe2rVBjgLumTbgRHBTLnJE0x8oEnBHx0H4J54KfUN-jU9_nnxLolRDYgARdIkD4MesYAYBlwtAxtiCOS-4E6nKSkAxJrdCa5Z6YbXOi1Iz5qzzuVE6z9-StXk9d-8ILTQ_9lWmXGkZ16kSBeeV96LS3pXOFAPyZTFo0kQec-z_pYR8BodYrg7xgBwuW1_1_B0PtBvh-C_bIOt2uFA3FzJOYgnJn63SwgGGtLz0aQUToPQVYDANWdoxPOQjWo9E3wBdMioecYAPQ5YtOYRUBnxekfIB2VtYj4xOo5X3prP7-N_vyUtUve-PRO6Rta65cfvkhbnt_rbNQZwD_wGERxJJ priority: 102 providerName: ProQuest |
| Title | The Recommendation Algorithm Based on Improved Conditional Variational Autoencoder and Constrained Probabilistic Matrix Factorization |
| URI | https://www.proquest.com/docview/2888117243 https://doaj.org/article/626d905e644d47f09bec7f9431b82667 |
| Volume | 13 |
| WOSCitedRecordID | wos001100460400001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: DOA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: M~E dateStart: 20110101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: BENPR dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: PIMPY dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwEB6hwgEOqC0glj7kAwgQiogTp3aOu1VXINFVhACVk-VnQeruVrtbxB_o_2bGcatcql64JZYjO56x5xvb8w3Aa-ulEg7dVN6YqhDcmMLUlS1oix_xiEULkkhcv8jZTJ2dtd0g1RfdCevpgfuB-4iA27dlE9BueyFj2WKjMrZo9ywi46MUR17KduBMpTW45URd1d90r9Gvp_NgbBbRRUkJZAY2KFH137UgJysz3YanGR6ycd-tHXgQFrvwZEAauAs7eTqu2bvMGf3-GVyjuBm5kvN5yGmS2PjifImu_685m6Cp8gyL-i0EfD5e0lF12gZkP9BdzluCbHy1WRK1pQ8rZhap3jplkcBvuhXOfbpLS9TO7JS4_f-yacrXk4M5n8P36cm3409FzrBQODTkmyIgXuNecUc4KST84XzDQ1QiqNJUEsGHq72ylpdReWvrRlrOgw-xdsbW9QvYWiwX4SWwxoqj2FYmSM-FLY1qhGhjVK2NQQbXjODDzZhrl-nHqf8XGt0QkpAeSmgEb25rX_a0G3fUm5D4busQWXYqQBXSWYX0fSo0grckfE1TGrvkTI5MwB8jciw9Rg8El6qmFCPYv9EPnef6WldKUbRuJepX_6M3e_CYUtr38Y77sLVZXYUDeOT-bH6vV4fwcHIy674eJnXHt-7zaffzHzsvBVQ |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwELWqLRJwAFpALBTwgQoQirATp0kOFdoWVl11d7WHgsop-CulUndTkpSPH8Df6W9kxnGWvZRbD9xWWSeyk-d5M2P7DSEvlElSoSFM5bEMA8GlDGQUqgBT_OCPKGAQJ-I6TqbT9Pg4m62Ry-4sDG6r7GyiM9Sm1JgjfxtCqMaBbUX07vxbgFWjcHW1K6HRwuLQ_voBIVu9O3oP33c7DIcfjvYPAl9VINBAXk1gwUfhJuUafQPrOFebmNsiFTZlMkyAcHVkUqU4K1KjVBQninNrbBFpqTABCiZ_XQDYWY-sz0aT2edlVgdVNlPO2h32UZQxXIeG4YJXw7BwzQr3uRIBVxGBY7fh3f_tvdwjd7wfTQct8DfIml1sktsr6oqbZMPbrZq-8uLar--T3zAvKMbc87n19aTo4OwERtR8ndM94HRD4VKba4Hf-yWu6bt8Kf0kq1OfO6WDi6ZEDVBjKyoXrl3tym3APbMKjCRuOkYNbDrBIgg_6dAVNvKnXh-Qj9fych6S3qJc2EeExkrsFFkobWK4UEymsRBZUaSZKmxiddwnbzqQ5NrrtGP_z3KI1xBS-Sqk-mR72fq81Se5ot0e4m3ZBlXF3YWyOsm9kcohuDUZiy34yEYkBctggidFBj6mgih0Bx7yEtGao-2DLmnpj3DAwFBFLB9AqAY2PWaiT7Y6tObeKNb5X6g-_vffz8nNg6PJOB-PpodPyC3of9Qe_9wivaa6sE_JDf29Oa2rZ37-UfLluqH9B7C9b-M |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwELWqLUJwAFpAbCngAxUgFDVOnMY5ILTbdkXVslohQL0Zf6Wt1N2UbMrHD-BP8euYcZxlL-XWA7dV1ons5HnezNh-Q8hzbXPBDYSpLFNJxJlSkUoTHWGKH_wRDQziRVyP8vFYHB8XkxXyuzsLg9sqO5voDbWtDObItxMI1RiwLU-3y7AtYrI3envxNcIKUrjS2pXTaCFy6H5-h_Bt_uZgD771VpKM9j_uvotChYHIAJE1kQN_hVnBDPoJzvOvsRlzpeBOxCrJgXxNaoXWLC6F1TrNcs2Ys65MjdKYDAXzv5qnEPT0yOpwfzz5sMjwoOKmYHG72z5NixjXpGHo4OHEWMRmiQd9uYCrSMEz3eju__yO7pE7wb-mg3ZCrJEVN1snt5dUF9fJWrBnc_oyiG6_uk9-wXyhGItPpy7UmaKD8xMYUXM6pUPgekvhUpuDgd-7Fa71-zwq_azqs5BTpYPLpkJtUOtqqma-3dyX4YB7JjUYT9yMjNrY9D0WR_hBR77gUTgN-4B8upaX85D0ZtXMPSI003ynLBLlcsu4jpXIOC_KUhS6dLkzWZ-87gAjTdBvx_6fS4jjEF5yGV59srVofdHqllzRbojYW7RBtXF_oapPZDBeEoJeW8SZA9_Z8ryMC5j4eVmA76khOt2Bh7xA5Eq0idAlo8LRDhgYqovJAYRwYOuzmPfJZodcGYzlXP6F7ca__35GbgKe5dHB-PAxuQXdT9tToZuk19SX7gm5Yb41Z_P6aZiKlHy5bmT_AS9deH0 |
| 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=The+Recommendation+Algorithm+Based+on+Improved+Conditional+Variational+Autoencoder+and+Constrained+Probabilistic+Matrix+Factorization&rft.jtitle=Applied+sciences&rft.au=Zhang%2C+Yunfei&rft.au=Xu%2C+Hongzhen&rft.au=Yu%2C+Xiaojun&rft.date=2023-11-01&rft.pub=MDPI+AG&rft.issn=2076-3417&rft.eissn=2076-3417&rft.volume=13&rft.issue=21&rft_id=info:doi/10.3390%2Fapp132112027&rft.externalDocID=A772531504 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2076-3417&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2076-3417&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2076-3417&client=summon |