Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288075232> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4288075232 endingPage "257" @default.
- W4288075232 startingPage "250" @default.
- W4288075232 abstract "With the rapid development of ambient intelligence (AmI) in the Internet of Things (IoT), many data streams are generated from sensing devices in intelligent scenarios. Due to the deployment issues of IoT devices and the system’s complexity, abnormal behavior is inevitable, resulting in imbalanced data categories. Moreover, data streams generated in IoT systems are dynamic, continuous, and as the environment changes, further increasing the difficulty of anomaly detection . Therefore, we model the monitored historical and current data from the perspective of dynamic imbalanced data streams classification to discover abnormal behaviors in IoT systems. In this paper we propose a dynamic ensemble algorithm for anomaly detection in IoT environments. First the abnormal data samples are synthesized by the borderline-synthetic minority over-sampling technique (Borderline-SMOTE) to relieve the sample imbalance problem. Then considering the dynamics and continuity of data streams we adopt a chunk-based strategy to train a LightGBM classifier for each chunk of data to adapt to the current data distribution. To improve the ensemble model’s processing efficiency and anomaly detection accuracy we adopt a dynamic weighting strategy for base classifiers and remove the classifier whose accuracy performance is lower than the threshold. Finally we evaluate our proposed algorithm by conducting comparative experiments on real-world data streams. Experimental results show that our proposed algorithm outperforms the comparative anomaly detection methods in IoT scenarios." @default.
- W4288075232 created "2022-07-28" @default.
- W4288075232 creator A5005463262 @default.
- W4288075232 creator A5010421115 @default.
- W4288075232 creator A5013230360 @default.
- W4288075232 creator A5017630170 @default.
- W4288075232 creator A5033579560 @default.
- W4288075232 creator A5033732336 @default.
- W4288075232 creator A5042452580 @default.
- W4288075232 date "2022-10-01" @default.
- W4288075232 modified "2023-10-16" @default.
- W4288075232 title "A dynamic ensemble algorithm for anomaly detection in IoT imbalanced data streams" @default.
- W4288075232 cites W2088220893 @default.
- W4288075232 cites W2113876961 @default.
- W4288075232 cites W2139327121 @default.
- W4288075232 cites W2148143831 @default.
- W4288075232 cites W2324823555 @default.
- W4288075232 cites W2338694366 @default.
- W4288075232 cites W2556758239 @default.
- W4288075232 cites W2603541315 @default.
- W4288075232 cites W2740428142 @default.
- W4288075232 cites W2795554423 @default.
- W4288075232 cites W2892374186 @default.
- W4288075232 cites W2901168797 @default.
- W4288075232 cites W2931141826 @default.
- W4288075232 cites W2947296458 @default.
- W4288075232 cites W2950361482 @default.
- W4288075232 cites W2962725067 @default.
- W4288075232 cites W2999269122 @default.
- W4288075232 cites W3005299290 @default.
- W4288075232 cites W3027164667 @default.
- W4288075232 cites W3080272186 @default.
- W4288075232 cites W3093074257 @default.
- W4288075232 cites W3156522613 @default.
- W4288075232 cites W3161257672 @default.
- W4288075232 cites W3177383533 @default.
- W4288075232 cites W4213036076 @default.
- W4288075232 doi "https://doi.org/10.1016/j.comcom.2022.07.034" @default.
- W4288075232 hasPublicationYear "2022" @default.
- W4288075232 type Work @default.
- W4288075232 citedByCount "10" @default.
- W4288075232 countsByYear W42880752322022 @default.
- W4288075232 countsByYear W42880752322023 @default.
- W4288075232 crossrefType "journal-article" @default.
- W4288075232 hasAuthorship W4288075232A5005463262 @default.
- W4288075232 hasAuthorship W4288075232A5010421115 @default.
- W4288075232 hasAuthorship W4288075232A5013230360 @default.
- W4288075232 hasAuthorship W4288075232A5017630170 @default.
- W4288075232 hasAuthorship W4288075232A5033579560 @default.
- W4288075232 hasAuthorship W4288075232A5033732336 @default.
- W4288075232 hasAuthorship W4288075232A5042452580 @default.
- W4288075232 hasConcept C11413529 @default.
- W4288075232 hasConcept C121332964 @default.
- W4288075232 hasConcept C124101348 @default.
- W4288075232 hasConcept C12997251 @default.
- W4288075232 hasConcept C154945302 @default.
- W4288075232 hasConcept C26873012 @default.
- W4288075232 hasConcept C31258907 @default.
- W4288075232 hasConcept C38652104 @default.
- W4288075232 hasConcept C41008148 @default.
- W4288075232 hasConcept C42090638 @default.
- W4288075232 hasConcept C739882 @default.
- W4288075232 hasConcept C81860439 @default.
- W4288075232 hasConcept C89198739 @default.
- W4288075232 hasConceptScore W4288075232C11413529 @default.
- W4288075232 hasConceptScore W4288075232C121332964 @default.
- W4288075232 hasConceptScore W4288075232C124101348 @default.
- W4288075232 hasConceptScore W4288075232C12997251 @default.
- W4288075232 hasConceptScore W4288075232C154945302 @default.
- W4288075232 hasConceptScore W4288075232C26873012 @default.
- W4288075232 hasConceptScore W4288075232C31258907 @default.
- W4288075232 hasConceptScore W4288075232C38652104 @default.
- W4288075232 hasConceptScore W4288075232C41008148 @default.
- W4288075232 hasConceptScore W4288075232C42090638 @default.
- W4288075232 hasConceptScore W4288075232C739882 @default.
- W4288075232 hasConceptScore W4288075232C81860439 @default.
- W4288075232 hasConceptScore W4288075232C89198739 @default.
- W4288075232 hasLocation W42880752321 @default.
- W4288075232 hasOpenAccess W4288075232 @default.
- W4288075232 hasPrimaryLocation W42880752321 @default.
- W4288075232 hasRelatedWork W1582424504 @default.
- W4288075232 hasRelatedWork W1595351371 @default.
- W4288075232 hasRelatedWork W2110365568 @default.
- W4288075232 hasRelatedWork W2313030483 @default.
- W4288075232 hasRelatedWork W2548275785 @default.
- W4288075232 hasRelatedWork W2950134958 @default.
- W4288075232 hasRelatedWork W2950753689 @default.
- W4288075232 hasRelatedWork W2984111956 @default.
- W4288075232 hasRelatedWork W3123856595 @default.
- W4288075232 hasRelatedWork W4318049614 @default.
- W4288075232 hasVolume "194" @default.
- W4288075232 isParatext "false" @default.
- W4288075232 isRetracted "false" @default.
- W4288075232 workType "article" @default.