RepuTE: A soft voting ensemble learning framework for reputation-based attack detection in fog-IoT milieu

Verma, Richa; Chandra, Shalini

doi:10.1016/j.engappai.2022.105670

Cited by 17 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Verma and Chandra [20] developed an algorithm called RepuTE for the IoT, which enables the detection of DoS/DDoS and Sybil attacks. In the presented RepuTe algorithm, live traffic coming from the IoT layer is transferred to the fog layer and the traffic data is first pre-processed in this layer.…”

Section: Related Workmentioning

confidence: 99%

IoT-Based Intrusion Detection System Using New Hybrid Deep Learning Algorithm

Yaras,

Dener

2024

Electronics

View full text Add to dashboard Cite

The most significant threat that networks established in IoT may encounter is cyber attacks. The most commonly encountered attacks among these threats are DDoS attacks. After attacks, the communication traffic of the network can be disrupted, and the energy of sensor nodes can quickly deplete. Therefore, the detection of occurring attacks is of great importance. Considering numerous sensor nodes in the established network, analyzing the network traffic data through traditional methods can become impossible. Analyzing this network traffic in a big data environment is necessary. This study aims to analyze the obtained network traffic dataset in a big data environment and detect attacks in the network using a deep learning algorithm. This study is conducted using PySpark with Apache Spark in the Google Colaboratory (Colab) environment. Keras and Scikit-Learn libraries are utilized in the study. ‘CICIoT2023’ and ‘TON_IoT’ datasets are used for training and testing the model. The features in the datasets are reduced using the correlation method, ensuring the inclusion of significant features in the tests. A hybrid deep learning algorithm is designed using one-dimensional CNN and LSTM. The developed method was compared with ten machine learning and deep learning algorithms. The model’s performance was evaluated using accuracy, precision, recall, and F1 parameters. Following the study, an accuracy rate of 99.995% for binary classification and 99.96% for multiclassification is achieved in the ‘CICIoT2023’ dataset. In the ‘TON_IoT’ dataset, a binary classification success rate of 98.75% is reached.

show abstract

Section: Related Workmentioning

confidence: 99%

IoT-Based Intrusion Detection System Using New Hybrid Deep Learning Algorithm

Yaras,

Dener

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…On the other hand, Decision Tree is a classification model that understands the relationships between attributes in data and is used to make decisions based on the constructed decision tree (Pasha et al, 2023;Pratama et al, 2022). The soft voting method combines the outputs of multiple classification algorithms to improve accuracy (Kumari et al, 2021;Verma et al, 2023). Previous research has shown that combining Gaussian Naive Bayes and Decision Tree using the soft voting method can produce more accurate predictions regarding soil fertility.…”

Section: Literature Reviewmentioning

confidence: 99%

Optimization Accuracy Value of Agricultural Land Fertility Classification Using Soft Voting Method

Pradana,

Budiman

2024

SinkrOn

View full text Add to dashboard Cite

Soil fertility on an agricultural land is very influential with agricultural yields, where plants can grow well and fertile if nutrient intake is met. The purpose of this research is to improve the accuracy in predicting soil fertility by utilizing machine learning by combining two classification algorithms using soft voting methods in the classification of agricultural land fertility. In this research, one of the ensemble learning methods called soft voting is employed. Soft voting is used to enhance accuracy by optimizing the combination of algorithms based on the highest probability provided by each model. The Gaussian Naive Bayes algorithm is used to predict classes in the sample data based on the Gaussian distribution of numerical data, while the decision tree is utilized to predict classes by constructing a decision tree using soil content attributes for the classification of fertile or infertile soil. The use of the Gaussian Naive Bayes algorithm in identifying fertile and infertile soil based on existing attributes achieved an accuracy rate of 87.2%. The decision tree algorithm, based on decision tree modeling, helped identify important attributes for decision-making with an accuracy rate of 88.3%. The soft voting method played a crucial role in improving accuracy by combining both algorithms, resulting in an accuracy rate of 88.8%. Based on the accuracy results obtained, the use of soft voting optimization in predicting soil fertility has the highest accuracy because it combines the Gaussian naïve bayes algorithm and the decision tree algorithm.

show abstract

“…Verma and Chandra [ 24 ] proposed a RepuTE Framework tailored to bolster trust in the fog computing layer near users. This framework deploys a soft-voting ensemble learning model to classify and predict DoS/DDoS and Sybil attacks.…”

Section: Related Studiesmentioning

confidence: 99%

Credit Card Fraud Detection: An Improved Strategy for High Recall Using KNN, LDA, and Linear Regression

Chung,

Lee

2023

Sensors

View full text Add to dashboard Cite

Efficiently and accurately identifying fraudulent credit card transactions has emerged as a significant global concern along with the growth of electronic commerce and the proliferation of Internet of Things (IoT) devices. In this regard, this paper proposes an improved algorithm for highly sensitive credit card fraud detection. Our approach leverages three machine learning models: K-nearest neighbor, linear discriminant analysis, and linear regression. Subsequently, we apply additional conditional statements, such as “IF” and “THEN”, and operators, such as “>“ and “<“, to the results. The features extracted using this proposed strategy achieved a recall of 1.0000, 0.9701, 1.0000, and 0.9362 across the four tested fraud datasets. Consequently, this methodology outperforms other approaches employing single machine learning models in terms of recall.

show abstract

RepuTE: A soft voting ensemble learning framework for reputation-based attack detection in fog-IoT milieu

Cited by 17 publications

References 38 publications

IoT-Based Intrusion Detection System Using New Hybrid Deep Learning Algorithm

IoT-Based Intrusion Detection System Using New Hybrid Deep Learning Algorithm

Optimization Accuracy Value of Agricultural Land Fertility Classification Using Soft Voting Method

Credit Card Fraud Detection: An Improved Strategy for High Recall Using KNN, LDA, and Linear Regression

Contact Info

Product

Resources

About