Silhouette score metrics results.
<div><p>Perimeter Intrusion Detection Systems (PIDS) are crucial for protecting any physical locations by detecting and responding to intrusions around its perimeter. Despite the availability of several PIDS, challenges remain in detection accuracy and precise activity classification. To...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , |
| Published: |
2024
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852024253798416384 |
|---|---|
| author | Shahneela Pitafi (20454775) |
| author2 | Toni Anwar (19999011) I Dewa Made Widia (20454778) Zubair Sharif (17767086) Boonsit Yimwadsana (614577) |
| author2_role | author author author author |
| author_facet | Shahneela Pitafi (20454775) Toni Anwar (19999011) I Dewa Made Widia (20454778) Zubair Sharif (17767086) Boonsit Yimwadsana (614577) |
| author_role | author |
| dc.creator.none.fl_str_mv | Shahneela Pitafi (20454775) Toni Anwar (19999011) I Dewa Made Widia (20454778) Zubair Sharif (17767086) Boonsit Yimwadsana (614577) |
| dc.date.none.fl_str_mv | 2024-12-19T18:32:12Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0313890.g015 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Silhouette_score_metrics_results_/28064464 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified produce similar results precise activity classification manhattan distance formula human activity recognition comparative techniques failed art techniques found based spatial clustering traditional dbscan algorithm proposed model achieved proposed model subsequent clustering model utilizes varying densities trained inceptionv3 societal security silhouette score research enhances research contributes physical locations minimal points intrusions around handling high future researchers feature extraction existing density epsilon values enhanced dbscan dimensionality reduction dimensional data determined using detection accuracy analysis reveals |
| dc.title.none.fl_str_mv | Silhouette score metrics results. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Perimeter Intrusion Detection Systems (PIDS) are crucial for protecting any physical locations by detecting and responding to intrusions around its perimeter. Despite the availability of several PIDS, challenges remain in detection accuracy and precise activity classification. To address these challenges, a new machine learning model is developed. This model utilizes the pre-trained InceptionV3 for feature extraction on PID intrusion image dataset, followed by t-SNE for dimensionality reduction and subsequent clustering. When handling high-dimensional data, the existing Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm faces efficiency issues due to its complexity and varying densities. To overcome these limitations, this research enhances the traditional DBSCAN algorithm. In the enhanced DBSCAN, distances between minimal points are determined using an estimation for the epsilon values with the Manhattan distance formula. The effectiveness of the proposed model is evaluated by comparing it to state-of-the-art techniques found in the literature. The analysis reveals that the proposed model achieved a silhouette score of 0.86, while comparative techniques failed to produce similar results. This research contributes to societal security by improving location perimeter protection, and future researchers can utilize the developed model for human activity recognition from image datasets.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_da7b874c4a13cedbbcff3ea75c9ec2cf |
| identifier_str_mv | 10.1371/journal.pone.0313890.g015 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28064464 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Silhouette score metrics results.Shahneela Pitafi (20454775)Toni Anwar (19999011)I Dewa Made Widia (20454778)Zubair Sharif (17767086)Boonsit Yimwadsana (614577)Science PolicySpace ScienceBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedproduce similar resultsprecise activity classificationmanhattan distance formulahuman activity recognitioncomparative techniques failedart techniques foundbased spatial clusteringtraditional dbscan algorithmproposed model achievedproposed modelsubsequent clusteringmodel utilizesvarying densitiestrained inceptionv3societal securitysilhouette scoreresearch enhancesresearch contributesphysical locationsminimal pointsintrusions aroundhandling highfuture researchersfeature extractionexisting densityepsilon valuesenhanced dbscandimensionality reductiondimensional datadetermined usingdetection accuracyanalysis reveals<div><p>Perimeter Intrusion Detection Systems (PIDS) are crucial for protecting any physical locations by detecting and responding to intrusions around its perimeter. Despite the availability of several PIDS, challenges remain in detection accuracy and precise activity classification. To address these challenges, a new machine learning model is developed. This model utilizes the pre-trained InceptionV3 for feature extraction on PID intrusion image dataset, followed by t-SNE for dimensionality reduction and subsequent clustering. When handling high-dimensional data, the existing Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm faces efficiency issues due to its complexity and varying densities. To overcome these limitations, this research enhances the traditional DBSCAN algorithm. In the enhanced DBSCAN, distances between minimal points are determined using an estimation for the epsilon values with the Manhattan distance formula. The effectiveness of the proposed model is evaluated by comparing it to state-of-the-art techniques found in the literature. The analysis reveals that the proposed model achieved a silhouette score of 0.86, while comparative techniques failed to produce similar results. This research contributes to societal security by improving location perimeter protection, and future researchers can utilize the developed model for human activity recognition from image datasets.</p></div>2024-12-19T18:32:12ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0313890.g015https://figshare.com/articles/figure/Silhouette_score_metrics_results_/28064464CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/280644642024-12-19T18:32:12Z |
| spellingShingle | Silhouette score metrics results. Shahneela Pitafi (20454775) Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified produce similar results precise activity classification manhattan distance formula human activity recognition comparative techniques failed art techniques found based spatial clustering traditional dbscan algorithm proposed model achieved proposed model subsequent clustering model utilizes varying densities trained inceptionv3 societal security silhouette score research enhances research contributes physical locations minimal points intrusions around handling high future researchers feature extraction existing density epsilon values enhanced dbscan dimensionality reduction dimensional data determined using detection accuracy analysis reveals |
| status_str | publishedVersion |
| title | Silhouette score metrics results. |
| title_full | Silhouette score metrics results. |
| title_fullStr | Silhouette score metrics results. |
| title_full_unstemmed | Silhouette score metrics results. |
| title_short | Silhouette score metrics results. |
| title_sort | Silhouette score metrics results. |
| topic | Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified produce similar results precise activity classification manhattan distance formula human activity recognition comparative techniques failed art techniques found based spatial clustering traditional dbscan algorithm proposed model achieved proposed model subsequent clustering model utilizes varying densities trained inceptionv3 societal security silhouette score research enhances research contributes physical locations minimal points intrusions around handling high future researchers feature extraction existing density epsilon values enhanced dbscan dimensionality reduction dimensional data determined using detection accuracy analysis reveals |