The proposed algorithm of the outlier detection method.
<p>The proposed algorithm of the outlier detection method.</p>
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , , , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852019833763266560 |
|---|---|
| author | Sunil Kumar (102321) |
| author2 | Sudeep Varshney (21453384) Usha Jain (21453387) Prashant Johri (21453390) Abdulaziz S. Almazyad (21453393) Ali Wagdy Mohamed (21453396) Mehdi Hosseinzadeh (8383239) Mohammad Shokouhifar (20547564) |
| author2_role | author author author author author author author |
| author_facet | Sunil Kumar (102321) Sudeep Varshney (21453384) Usha Jain (21453387) Prashant Johri (21453390) Abdulaziz S. Almazyad (21453393) Ali Wagdy Mohamed (21453396) Mehdi Hosseinzadeh (8383239) Mohammad Shokouhifar (20547564) |
| author_role | author |
| dc.creator.none.fl_str_mv | Sunil Kumar (102321) Sudeep Varshney (21453384) Usha Jain (21453387) Prashant Johri (21453390) Abdulaziz S. Almazyad (21453393) Ali Wagdy Mohamed (21453396) Mehdi Hosseinzadeh (8383239) Mohammad Shokouhifar (20547564) |
| dc.date.none.fl_str_mv | 2025-05-30T17:41:33Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0322738.g002 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/The_proposed_algorithm_of_the_outlier_detection_method_/29200713 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Biotechnology Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified nearest neighbors algorithm nearest neighbor search nearest neighbor identification identifying unusual patterns gained significant attention disrupt system modeling 53 %, outperforming 07 %, recall rf feature selection learning repository datasets named eoda ), 49 %, parameter selection deep learning significantly deviate shadow features second stage results demonstrate relevant attributes rapid growth random forest parameter estimation often limited normal behavior inaccurate results highest z first stage existing techniques eoda approach enhanced knn data size data science clustering phase boruta method |
| dc.title.none.fl_str_mv | The proposed algorithm of the outlier detection method. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <p>The proposed algorithm of the outlier detection method.</p> |
| eu_rights_str_mv | openAccess |
| id | Manara_3adf8ea293d858d2278d97e98be0ec83 |
| identifier_str_mv | 10.1371/journal.pone.0322738.g002 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/29200713 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | The proposed algorithm of the outlier detection method.Sunil Kumar (102321)Sudeep Varshney (21453384)Usha Jain (21453387)Prashant Johri (21453390)Abdulaziz S. Almazyad (21453393)Ali Wagdy Mohamed (21453396)Mehdi Hosseinzadeh (8383239)Mohammad Shokouhifar (20547564)BiotechnologySpace ScienceBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiednearest neighbors algorithmnearest neighbor searchnearest neighbor identificationidentifying unusual patternsgained significant attentiondisrupt system modeling53 %, outperforming07 %, recallrf feature selectionlearning repository datasetsnamed eoda ),49 %,parameter selectiondeep learningsignificantly deviateshadow featuressecond stageresults demonstraterelevant attributesrapid growthrandom forestparameter estimationoften limitednormal behaviorinaccurate resultshighest zfirst stageexisting techniqueseoda approachenhanced knndata sizedata scienceclustering phaseboruta method<p>The proposed algorithm of the outlier detection method.</p>2025-05-30T17:41:33ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0322738.g002https://figshare.com/articles/figure/The_proposed_algorithm_of_the_outlier_detection_method_/29200713CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/292007132025-05-30T17:41:33Z |
| spellingShingle | The proposed algorithm of the outlier detection method. Sunil Kumar (102321) Biotechnology Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified nearest neighbors algorithm nearest neighbor search nearest neighbor identification identifying unusual patterns gained significant attention disrupt system modeling 53 %, outperforming 07 %, recall rf feature selection learning repository datasets named eoda ), 49 %, parameter selection deep learning significantly deviate shadow features second stage results demonstrate relevant attributes rapid growth random forest parameter estimation often limited normal behavior inaccurate results highest z first stage existing techniques eoda approach enhanced knn data size data science clustering phase boruta method |
| status_str | publishedVersion |
| title | The proposed algorithm of the outlier detection method. |
| title_full | The proposed algorithm of the outlier detection method. |
| title_fullStr | The proposed algorithm of the outlier detection method. |
| title_full_unstemmed | The proposed algorithm of the outlier detection method. |
| title_short | The proposed algorithm of the outlier detection method. |
| title_sort | The proposed algorithm of the outlier detection method. |
| topic | Biotechnology Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified nearest neighbors algorithm nearest neighbor search nearest neighbor identification identifying unusual patterns gained significant attention disrupt system modeling 53 %, outperforming 07 %, recall rf feature selection learning repository datasets named eoda ), 49 %, parameter selection deep learning significantly deviate shadow features second stage results demonstrate relevant attributes rapid growth random forest parameter estimation often limited normal behavior inaccurate results highest z first stage existing techniques eoda approach enhanced knn data size data science clustering phase boruta method |