Evaluation of Deep Learning Algorithms in Comparison for Phishing Email Identification
Applied Mathematics on Science and Engineering · 30.06.2024 · 1 (1) · 21
DOI: 10.65036/amse113 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Mathematics on Science and Engineering, online erschienen am 30.06.2024. Verfasst von Mohamed Hassan. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Using skewed sequential data, the study explores the effectiveness of numerous sequential models designed for binary classification tasks. The dataset under investigation consists of 5,595 testing samples and 13,055 training samples, a structure that presents significant difficulties because of uneven labelling. The researchers carefully go through pretreatment procedures, which include text data encoding and effective methods for handling missing information, in order to address this. The study employs and examines a wide range of algorithms, which reflects the heterogeneous sequential modelling environment. A variety of neural network architectures are included in the arsenal CNN, CNN-RNN, RCNN. The binary classification job at hand is used to thoroughly assess each architecture, revealing both its advantages and disadvantages. The study's evaluation approach, which presents a wide range of measures indicating consistently excellent performance overall, is its key component. Among these algorithms stand out as the best with an astounding 97% accuracy rate on a variety of evaluation metrics. This strong performance highlights their ability to handle sequential data with unbalanced labels and establishes a standard for further work in related fields. Beyond its empirical results, the study is important because it provides a well-designed assessment approach that may be used as a benchmark by practitioners facing similar problems. Through the clarification of important concepts related to model selection and performance evaluation, the study provides professionals and academics with crucial resources to efficiently traverse the complex terrain of sequential modelling.
Zitieren
APA
Hassan, M. (2024). Evaluation of Deep Learning Algorithms in Comparison for Phishing Email Identification. Applied Mathematics on Science and Engineering, 1(1), 21. https://doi.org/10.65036/amse113
Vancouver
Hassan M. Evaluation of Deep Learning Algorithms in Comparison for Phishing Email Identification. Applied Mathematics on Science and Engineering. 2024;1(1):21. doi:10.65036/amse113
BibTeX
@article{Hassan2024,
author = {Hassan, Mohamed},
title = {Evaluation of Deep Learning Algorithms in Comparison for Phishing Email Identification},
journal = {Applied Mathematics on Science and Engineering},
year = {2024},
volume = {1},
number = {1},
pages = {21},
doi = {10.65036/amse113}
}
EUVIMED