“…The following evaluation metrics are used to assess the performance of our approach as well as other comparative approaches. These are standard evaluation metrics, which have been used in several other works [8,19].…”
The application of machine learning algorithms to the detection of fraudulent credit card transactions is a challenging problem domain due to the high imbalance in the datasets and confidentiality of financial data. This implies that legitimate transactions make up a high majority of the datasets such that a weak model with 99% accuracy and faulty predictions may still be assessed as high-performing. To build optimal models, four techniques were used in this research to sample the datasets including the baseline train test split method, the class weighted hyperparameter approach, and the undersampling and oversampling techniques. Three machine learning algorithms were implemented for the development of the models including the Random Forest, XGBoost and TensorFlow Deep Neural Network (DNN). Our observation is that the DNN is more effcient than the other 2 algorithms in modelling the under-sampled dataset while overall, the three algorithms had a better performance in the oversampling technique than in the undersampling technique. However, the Random Forest performed better than the other algorithms in the baseline approach. After comparing our results with some existing state-of-the-art works, we achieved an improved performance using real-world datasets.
“…The following evaluation metrics are used to assess the performance of our approach as well as other comparative approaches. These are standard evaluation metrics, which have been used in several other works [8,19].…”
The application of machine learning algorithms to the detection of fraudulent credit card transactions is a challenging problem domain due to the high imbalance in the datasets and confidentiality of financial data. This implies that legitimate transactions make up a high majority of the datasets such that a weak model with 99% accuracy and faulty predictions may still be assessed as high-performing. To build optimal models, four techniques were used in this research to sample the datasets including the baseline train test split method, the class weighted hyperparameter approach, and the undersampling and oversampling techniques. Three machine learning algorithms were implemented for the development of the models including the Random Forest, XGBoost and TensorFlow Deep Neural Network (DNN). Our observation is that the DNN is more effcient than the other 2 algorithms in modelling the under-sampled dataset while overall, the three algorithms had a better performance in the oversampling technique than in the undersampling technique. However, the Random Forest performed better than the other algorithms in the baseline approach. After comparing our results with some existing state-of-the-art works, we achieved an improved performance using real-world datasets.
“…Additionally, the GRU method was executed for identifying the occurrence of intrusions from the industrial CPS environments. The authors in [18] primarily present a new self-learning spatial distribution technique called Euclidean distance-based between-class learning (EBC learning) that enhances between-class learning by computing the Euclidean distance (ED) amongst KNN of distinct classes. Moreover, a cognitive computing-based ID model termed order-line SMOTE and EBC learning dependent upon RF (BSBC-RF) is also presented as dependent upon EBC learning to industrial CPSs.…”
Section: Literature Reviewmentioning
confidence: 99%
“…The class with the maximum probability was assumed as the prediction label y pred of x input vector, as determined in Equation (17). The predictive error of sample dataset D(Loss(D)) is evaluated according to the true label, as demonstrated in Equation (18), where y i indicates the true label of x i . Loss(D) is minimalized by the Gradient Descent model that is the same as the procedure of minimalizing the abovementioned reconstruction error:…”
Section: Hyperparameter Tuning Using Cso Algorithmmentioning
As cyberattacks develop in volume and complexity, machine learning (ML) was extremely implemented for managing several cybersecurity attacks and malicious performance. The cyber-physical systems (CPSs) combined the calculation with physical procedures. An embedded computer and network monitor and control the physical procedure, commonly with feedback loops whereas physical procedures affect calculations and conversely, at the same time, ML approaches were vulnerable to data pollution attacks. Improving network security and attaining robustness of ML determined network schemes were the critical problems of the growth of CPS. This study develops a new Stochastic Fractal Search Algorithm with Deep Learning Driven Intrusion Detection system (SFSA-DLIDS) for a cloud-based CPS environment. The presented SFSA-DLIDS technique majorly focuses on the recognition and classification of intrusions for accomplishing security from the CPS environment. The presented SFSA-DLIDS approach primarily performs a min-max data normalization approach to convert the input data to a compatible format. In order to reduce a curse of dimensionality, the SFSA technique is applied to select a subset of features. Furthermore, chicken swarm optimization (CSO) with deep stacked auto encoder (DSAE) technique was utilized for the identification and classification of intrusions. The design of a CSO algorithm majorly focuses on the parameter optimization of the DSAE model and thereby enhances the classifier results. The experimental validation of the SFSA-DLIDS model is tested using a series of experiments. The experimental results depict the promising performance of the SFSA-DLIDS model over the recent models.
“…The selection of hyperparameters can be viewed as an optimization issue in which the objective is to maximize the accuracy of fitness functions while minimizing the inaccuracy of cost functions [6]. Manually fine-tuning these hyper-parameters is a challenging task [7].…”
<p>Deep neural networks (DNNs) are very dependent on their parameterization and require experts to determine which method to implement and modify the hyper-parameters value. This study proposes an automated-tuned hyper-parameter for DNN using a metaheuristic optimization algorithm, arithmetic optimization algorithm (AOA). AOA makes use of the distribution properties of mathematics’ primary arithmetic operators, including multiplication, division, addition, and subtraction. AOA is mathematically modeled and implemented to optimize processes across a broad range of search spaces. The performance of AOA is evaluated against 29 benchmark functions, and several real-world engineering design problems are to demonstrate AOA’s applicability. The hyper-parameter tuning framework consists of a set of Lorenz chaotic system datasets, hybrid DNN architecture, and AOA that works automatically. As a result, AOA produced the highest accuracy in the test dataset with a combination of optimized hyper-parameters for DNN architecture. The boxplot analysis also produced the ten AOA particles that are the most accurately chosen. Hence, AOA with ten particles had the smallest size of boxplot for all hyper-parameters, which concluded the best solution. In particular, the result for the proposed system is outperformed compared to the architecture tested with particle swarm optimization.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.