2021
DOI: 10.1007/978-3-030-79725-6_24
|View full text |Cite
|
Sign up to set email alerts
|

Alexnet-Adaboost-ABC Based Hybrid Neural Network for Electricity Theft Detection in Smart Grids

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
7
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(8 citation statements)
references
References 27 publications
1
7
0
Order By: Relevance
“…Furthermore, our model's Recall score, which measures the ability to capture positive instances, is only marginally lower than the benchmark model, demonstrating that our approach maintains a high ability to detect positive instances while significantly improving other performance aspects. These compelling results underscore the novelty and superiority of our "AlexNet" model over the benchmark "AlexNet-Adaboost-ABC-Based Hybrid Neural Network" proposed in research paper [50]. The substantial performance improvements achieved by our approach validate its efficacy in addressing classification tasks on balanced datasets.…”
Section: Et Classifiermentioning
confidence: 54%
See 2 more Smart Citations
“…Furthermore, our model's Recall score, which measures the ability to capture positive instances, is only marginally lower than the benchmark model, demonstrating that our approach maintains a high ability to detect positive instances while significantly improving other performance aspects. These compelling results underscore the novelty and superiority of our "AlexNet" model over the benchmark "AlexNet-Adaboost-ABC-Based Hybrid Neural Network" proposed in research paper [50]. The substantial performance improvements achieved by our approach validate its efficacy in addressing classification tasks on balanced datasets.…”
Section: Et Classifiermentioning
confidence: 54%
“…Comparing the performance results from both tables, we observe that our proposed "AlexNet" model outperforms the benchmark model from research paper [50] across all evaluation metrics. Notably, our model achieved higher Precision, Accuracy, and F1 score values, indicating better precision-recall balance and overall classification accuracy.…”
Section: Et Classifiermentioning
confidence: 86%
See 1 more Smart Citation
“…With AlexNet, the curse of dimensionality issue has been handled, while adaptive boosting (AdaBoost) classified normal consumers and energy thieves. The tuning of hyper-parameters remain critical to achieving better prediction accuracy; hence a bee colony optimization algorithm has been used to tune the AdaBoost, and AlexNet 35 .…”
Section: Related Workmentioning
confidence: 99%
“…In our scenario, the balanced data are synthesized by six theft variants to cope with the realistic theft data. Manipulating techniques used for the synthesis of the data are as follows [ 42 , 43 , 44 , 45 , 46 ]: …”
Section: Proposed System Modelmentioning
confidence: 99%