Cervical Cancer Diagnosis Using Stacked Ensemble Model and Optimized Feature Selection: An Explainable Artificial Intelligence Approach DOI Creative Commons
Abdulaziz AlMohimeed,

Hager Saleh,

Sherif Mostafa

et al.

Computers, Journal Year: 2023, Volume and Issue: 12(10), P. 200 - 200

Published: Oct. 7, 2023

Cervical cancer affects more than half a million women worldwide each year and causes over 300,000 deaths. The main goals of this paper are to study the effect applying feature selection methods with stacking models for prediction cervical cancer, propose ensemble learning that combines different meta-learners predict explore black-box model best-optimized features using explainable artificial intelligence (XAI). A dataset from machine repository (UCI) is highly imbalanced contains missing values used. Therefore, SMOTE-Tomek was used combine under-sampling over-sampling handle data, pre-processing steps implemented hold values. Bayesian optimization optimizes selects best architecture. Chi-square scores, recursive removal, tree-based three techniques applied For determining factors most crucial predicting extended multiple levels: Level 1 (multiple base learners) 2 (meta-learner). At 1, (training testing stacking) employed combining output multi-base models, while training train meta-learner at level 2. Testing evaluate models. results showed based on selected elimination (RFE), has higher accuracy, precision, recall, f1-score, AUC. Furthermore, To assure efficiency, efficacy, reliability produced model, local global explanations provided.

Language: Английский

A new cloud-based cyber-attack detection architecture for hyper-automation process in industrial internet of things DOI
Alireza Souri, Monire Norouzi, Yousef Alsenani

et al.

Cluster Computing, Journal Year: 2023, Volume and Issue: 27(3), P. 3639 - 3655

Published: Nov. 2, 2023

Language: Английский

Citations

12
Intelligent intrusion detection framework for multi-clouds – IoT environment using swarm-based deep learning classifier DOI Creative Commons
Syed Mohamed Thameem Nizamudeen

Journal of Cloud Computing Advances Systems and Applications, Journal Year: 2023, Volume and Issue: 12(1)

Published: Sept. 22, 2023

Abstract In the current era, a tremendous volume of data has been generated by using web technologies. The association between different devices and services have also explored to wisely widely use recent Due restriction in available resources, chance security violation is increasing highly on constrained devices. IoT backend with multi-cloud infrastructure extend public terms better scalability reliability. Several users might access resources that lead threats while handling user requests for services. It poses new challenge proposing functional elements schemes. This paper introduces an intelligent Intrusion Detection Framework (IDF) detect network application-based attacks. proposed framework three phases: pre-processing, feature selection classification. Initially, collected datasets are pre-processed Integer- Grading Normalization (I-GN) technique ensures fair-scaled transformation process. Secondly, Opposition-based Learning- Rat Inspired Optimizer (OBL-RIO) designed phase. progressive nature rats chooses significant features. fittest value stability features from OBL-RIO. Finally, 2D-Array-based Convolutional Neural Network (2D-ACNN) as binary class classifier. input preserved 2D-array model perform complex layers. detects normal (or) abnormal traffic. trained tested Netflow-based datasets. yields 95.20% accuracy, 2.5% false positive rate 97.24% detection rate.

Language: Английский

Citations

11
Enhanced pelican optimization algorithm with ensemble-based anomaly detection in industrial internet of things environment DOI

Nenavath Chander,

M. Upendra Kumar

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(5), P. 6491 - 6509

Published: March 2, 2024

Language: Английский

Citations

4
SACNN‐IDS: A self‐attention convolutional neural network for intrusion detection in industrial internet of things DOI Creative Commons

Mimonah Al Qathrady,

Safi Ullah, Mohammed S. Alshehri

et al.

CAAI Transactions on Intelligence Technology, Journal Year: 2024, Volume and Issue: unknown

Published: June 12, 2024

Abstract Industrial Internet of Things (IIoT) is a pervasive network interlinked smart devices that provide variety intelligent computing services in industrial environments. Several IIoT nodes operate confidential data (such as medical, transportation, military, etc.) which are reachable targets for hostile intruders due to their openness and varied structure. Intrusion Detection Systems (IDS) based on Machine Learning (ML) Deep (DL) techniques have got significant attention. However, existing ML DL‐based IDS still face number obstacles must be overcome. For instance, the DL approaches necessitate substantial quantity effective performance, not feasible run low‐power low‐memory devices. Imbalanced fewer potentially lead low performance IDS. This paper proposes self‐attention convolutional neural (SACNN) architecture detection malicious activity networks an appropriate feature extraction method extract most features. The proposed has layer calculate input attention (CNN) layers process assigned features prediction. evaluation SACNN been done with Edge‐IIoTset X‐IIoTID datasets. These datasets encompassed behaviours contemporary communication protocols, operations state‐of‐the‐art devices, various attack types, diverse scenarios.

Language: Английский

Citations

4
Cervical Cancer Diagnosis Using Stacked Ensemble Model and Optimized Feature Selection: An Explainable Artificial Intelligence Approach DOI Creative Commons
Abdulaziz AlMohimeed,

Hager Saleh,

Sherif Mostafa

et al.

Computers, Journal Year: 2023, Volume and Issue: 12(10), P. 200 - 200

Published: Oct. 7, 2023

Cervical cancer affects more than half a million women worldwide each year and causes over 300,000 deaths. The main goals of this paper are to study the effect applying feature selection methods with stacking models for prediction cervical cancer, propose ensemble learning that combines different meta-learners predict explore black-box model best-optimized features using explainable artificial intelligence (XAI). A dataset from machine repository (UCI) is highly imbalanced contains missing values used. Therefore, SMOTE-Tomek was used combine under-sampling over-sampling handle data, pre-processing steps implemented hold values. Bayesian optimization optimizes selects best architecture. Chi-square scores, recursive removal, tree-based three techniques applied For determining factors most crucial predicting extended multiple levels: Level 1 (multiple base learners) 2 (meta-learner). At 1, (training testing stacking) employed combining output multi-base models, while training train meta-learner at level 2. Testing evaluate models. results showed based on selected elimination (RFE), has higher accuracy, precision, recall, f1-score, AUC. Furthermore, To assure efficiency, efficacy, reliability produced model, local global explanations provided.

Language: Английский

Citations

11