k-NN Query Optimization for High-Dimensional Index Using Machine Learning
In this study, we propose three k-nearest neighbor (k-NN) optimization techniques for a distributed, in-memory-based, high-dimensional indexing method to speed up content-based image retrieval. The proposed techniques perform distributed, in-memory, high-dimensional indexing-based k-NN query optimiz...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/11/2375 |
| _version_ | 1797597710844428288 |
|---|---|
| author | Dojin Choi Jiwon Wee Sangho Song Hyeonbyeong Lee Jongtae Lim Kyoungsoo Bok Jaesoo Yoo |
| author_facet | Dojin Choi Jiwon Wee Sangho Song Hyeonbyeong Lee Jongtae Lim Kyoungsoo Bok Jaesoo Yoo |
| author_sort | Dojin Choi |
| collection | DOAJ |
| description | In this study, we propose three k-nearest neighbor (k-NN) optimization techniques for a distributed, in-memory-based, high-dimensional indexing method to speed up content-based image retrieval. The proposed techniques perform distributed, in-memory, high-dimensional indexing-based k-NN query optimization: a density-based optimization technique that performs k-NN optimization using data distribution; a cost-based optimization technique using query processing cost statistics; and a learning-based optimization technique using a deep learning model, based on query logs. The proposed techniques were implemented on Spark, which supports a master/slave model for large-scale distributed processing. We showed the superiority and validity of the proposed techniques through various performance evaluations, based on high-dimensional data. |
| first_indexed | 2024-03-11T03:09:20Z |
| format | Article |
| id | doaj.art-3111c10d6f1c439e9d479be56b3a28d7 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T03:09:20Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-3111c10d6f1c439e9d479be56b3a28d72023-11-18T07:44:05ZengMDPI AGElectronics2079-92922023-05-011211237510.3390/electronics12112375k-NN Query Optimization for High-Dimensional Index Using Machine LearningDojin Choi0Jiwon Wee1Sangho Song2Hyeonbyeong Lee3Jongtae Lim4Kyoungsoo Bok5Jaesoo Yoo6Department of Computer Engineering, Changwon National University, Changwon 51140, Republic of KoreaDepartment of Information and Communication Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaDepartment of Information and Communication Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaDepartment of Information and Communication Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaDepartment of Information and Communication Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaDepartment of Artificial Intelligence Convergence, Wonkwang University, Iksan 54538, Republic of KoreaDepartment of Information and Communication Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaIn this study, we propose three k-nearest neighbor (k-NN) optimization techniques for a distributed, in-memory-based, high-dimensional indexing method to speed up content-based image retrieval. The proposed techniques perform distributed, in-memory, high-dimensional indexing-based k-NN query optimization: a density-based optimization technique that performs k-NN optimization using data distribution; a cost-based optimization technique using query processing cost statistics; and a learning-based optimization technique using a deep learning model, based on query logs. The proposed techniques were implemented on Spark, which supports a master/slave model for large-scale distributed processing. We showed the superiority and validity of the proposed techniques through various performance evaluations, based on high-dimensional data.https://www.mdpi.com/2079-9292/12/11/2375query optimizationdata distributionimage retrievalk-NNhigh-dimensional indexmachine learning |
| spellingShingle | Dojin Choi Jiwon Wee Sangho Song Hyeonbyeong Lee Jongtae Lim Kyoungsoo Bok Jaesoo Yoo k-NN Query Optimization for High-Dimensional Index Using Machine Learning Electronics query optimization data distribution image retrieval k-NN high-dimensional index machine learning |
| title | k-NN Query Optimization for High-Dimensional Index Using Machine Learning |
| title_full | k-NN Query Optimization for High-Dimensional Index Using Machine Learning |
| title_fullStr | k-NN Query Optimization for High-Dimensional Index Using Machine Learning |
| title_full_unstemmed | k-NN Query Optimization for High-Dimensional Index Using Machine Learning |
| title_short | k-NN Query Optimization for High-Dimensional Index Using Machine Learning |
| title_sort | k nn query optimization for high dimensional index using machine learning |
| topic | query optimization data distribution image retrieval k-NN high-dimensional index machine learning |
| url | https://www.mdpi.com/2079-9292/12/11/2375 |
| work_keys_str_mv | AT dojinchoi knnqueryoptimizationforhighdimensionalindexusingmachinelearning AT jiwonwee knnqueryoptimizationforhighdimensionalindexusingmachinelearning AT sanghosong knnqueryoptimizationforhighdimensionalindexusingmachinelearning AT hyeonbyeonglee knnqueryoptimizationforhighdimensionalindexusingmachinelearning AT jongtaelim knnqueryoptimizationforhighdimensionalindexusingmachinelearning AT kyoungsoobok knnqueryoptimizationforhighdimensionalindexusingmachinelearning AT jaesooyoo knnqueryoptimizationforhighdimensionalindexusingmachinelearning |