Exploring Ensemble-Based Class Imbalance Learners for Intrusion Detection in Industrial Control Networks

Classifier ensembles have been utilized in the industrial cybersecurity sector for many years. However, their efficacy and reliability for intrusion detection systems remain questionable in current research, owing to the particularly imbalanced data issue. The purpose of this article is to address a gap in the literature by illustrating the benefits of ensemble-based models for identifying threats and attacks in a cyber-physical power grid. We provide a framework that compares nine cost-sensitive individual and ensemble models designed specifically for handling imbalanced data, including cost-sensitive C4.5, roughly balanced bagging, random oversampling bagging, random undersampling bagging, synthetic minority oversampling bagging, random undersampling boosting, synthetic minority oversampling boosting, AdaC2, and EasyEnsemble. Each ensemble’s performance is tested against a range of benchmarked power system datasets utilizing balanced accuracy, Kappa statistics, and AUC metrics. Our findings demonstrate that EasyEnsemble outperformed significantly in comparison to its rivals across the board. Furthermore, undersampling and oversampling strategies were effective in a boosting-based ensemble but not in a bagging-based ensemble.

Hybrid Swarm Enhanced Classifier Ensembles

Os Sistemas de Multi-Classificadores (MCSs) constituem um dos paradigmas mais competitivos para a obtenção de classificações precisas no campo do aprendizado de máquina. Este artigo busca avaliar se a utilização de algoritmos híbridos de enxames pode melhorar a performance dos MCSs por meio da otimização de pesos em combinações por voto majoritário ponderado. A metodologia proposta rendeu resultados competitivos em 25 conjuntos de dados de referência. Adotou-se a acurácia como função objetivo a ser maximizada pelas seguintes meta-heurísticas: otimização do exame de partículas (PSO), a colônia artificial de abelhas (ABC), e a alternativa híbrida das anteriores usando a técnica de multi enxames dinâmicos (DM-PSO-ABC).

Continuous Stress Detection of Hospital Staff Using Smartwatch Sensors and Classifier Ensemble

High stress levels among hospital workers could be harmful to both workers and the institution. Enabling the workers to monitor their stress level has many advantages. Knowing their own stress level can help them to stay aware and feel more in control of their response to situations and know when it is time to relax or take some actions to treat it properly. This monitoring task can be enabled by using wearable devices to measure physiological responses related to stress. In this work, we propose a smartwatch sensors based continuous stress detection method using some individual classifiers and classifier ensembles. The experiment results show that all of the classifiers work quite well to detect stress with an accuracy of more than 70%. The results also show that the ensemble method obtained higher accuracy and F1-measure compared to all of the individual classifiers. The best accuracy was obtained by the ensemble with soft voting strategy (ES) with 87.10% while the hard voting strategy (EH) achieved the best F1-measure with 77.45%.

Ensemble Learning Using Matrices of Classifier Interactions and Decision Profiles on Riemannian and Grassmann Manifolds

This paper introduces a new topic and research of geometric classifier ensemble learning using two types of objects: classifier prediction pairwise matrix (CPPM) and decision profiles (DPs). Learning from CPPM requires using Riemannian manifolds (R-manifolds) of symmetric positive definite (SPD) matrices. DPs can be used to build a Grassmann manifold (G-manifold). Experimental results show that classifier ensembles and their cascades built using R-manifolds are less dependent on some properties of individual classifiers (e.g. depth of decision trees in random forests (RFs) or extra trees (ETs)) in comparison to G-manifolds and Euclidean geometry. More independent individual classifiers allow obtaining R-manifolds with better properties for classification. Generally, the accuracy of classification in nonlinear geometry is higher than in Euclidean one. For multi-class problems, G-manifolds perform similarly to stacking-based classifiers built on R-manifolds of SPD matrices in terms of classification accuracy.

Dynamic Nearest Neighbor: An Improved Machine Learning Classifier and Its Application in Finances

The presence of machine learning, data mining and related disciplines is increasingly evident in everyday environments. The support for the applications of learning techniques in topics related to economic risk assessment, among other financial topics of interest, is relevant for us as human beings. The content of this paper consists of a proposal of a new supervised learning algorithm and its application in real world datasets related to finance, called D1-NN (Dynamic 1-Nearest Neighbor). The D1-NN performance is competitive against the main state of the art algorithms in solving finance-related problems. The effectiveness of the new D1-NN classifier was compared against five supervised classifiers of the most important approaches (Bayes, nearest neighbors, support vector machines, classifier ensembles, and neural networks), with superior results overall.

Supervised Classification of Diseases Based on an Improved Associative Algorithm

The linear associator is a classic associative memory model. However, due to its low performance, it is pertinent to note that very few linear associator applications have been published. The reason for this is that this model requires the vectors representing the patterns to be orthonormal, which is a big restriction. Some researchers have tried to create orthogonal projections to the vectors to feed the linear associator. However, this solution has serious drawbacks. This paper presents a proposal that effectively improves the performance of the linear associator when acting as a pattern classifier. For this, the proposal involves transforming the dataset using a powerful mathematical tool: the singular value decomposition. To perform the experiments, we selected fourteen medical datasets of two classes. All datasets exhibit balance, so it is possible to use accuracy as a performance measure. The effectiveness of our proposal was compared against nine supervised classifiers of the most important approaches (Bayes, nearest neighbors, decision trees, support vector machines, and neural networks), including three classifier ensembles. The Friedman and Holm tests show that our proposal had a significantly better performance than four of the nine classifiers. Furthermore, there are no significant differences against the other five, although three of them are ensembles.

Combining Hybrid Approach Redefinition-Multiclass Imbalance (HAR-MI) and Hybrid Sampling in Handling Multi-Class Imbalance and Overlapping

Class imbalance is one of the main problems in classification because the number of samples in majority class is far more than the number of samples in minority class. The class imbalance problem in the multi-class dataset is much more difficult to handle than the problem in the two class dataset. This multi-class imbalance problem is even more complicated if it is accompanied by overlapping. One method that has proven reliable in dealing with this problem is the Hybrid Approach Redefinition-Multiclass Imbalance (HAR-MI) method which is classified as a hybrid approach which combines sampling and classifier ensembles. However, in terms of diversity among classifiers, hybrid approach that combine sampling and classifier ensembles will give better results. HAR-MI delivers excellent results in handling multi-class imbalances. The HAR-MI method uses SMOTE to increase the number of sample in minority class. However, this SMOTE also has a weakness where if there is an extremely imbalanced dataset and a large number of attributes there will be over-fitting. To overcome the problem of over-fitting, the Hybrid Sampling method was proposed. HAR-MI combination with Hybrid Sampling is done to increase the number of samples in the minority class and at the same time reduce the number of noise samples in the majority class. The preprocessing stages at HAR-MI will use the Minimizing Overlapping Selection under Hybrid Sazmpling (MOSHS) method and the processing stages will use Different Contribution Sampling. The results obtained will be compared with the results using Neighbourhood-based undersampling. Overlapping and Classifier Performance will be measured using Augmented R-Value, the Matthews Correlation Coefficient (MCC), Precision, Recall, and F-Value. The results showed that HAR-MI with Hybrid Sampling gave better results in terms of Augmented R-Value, Precision, Recall, and F-Value.

Testing the Suitability of Automated Machine Learning for Weeds Identification

In the past years, several machine-learning-based techniques have arisen for providing effective crop protection. For instance, deep neural networks have been used to identify different types of weeds under different real-world conditions. However, these techniques usually require extensive involvement of experts working iteratively in the development of the most suitable machine learning system. To support this task and save resources, a new technique called Automated Machine Learning has started being studied. In this work, a complete open-source Automated Machine Learning system was evaluated with two different datasets, (i) The Early Crop Weeds dataset and (ii) the Plant Seedlings dataset, covering the weeds identification problem. Different configurations, such as the use of plant segmentation, the use of classifier ensembles instead of Softmax and training with noisy data, have been compared. The results showed promising performances of 93.8% and 90.74% F1 score depending on the dataset used. These performances were aligned with other related works in AutoML, but they are far from machine-learning-based systems manually fine-tuned by human experts. From these results, it can be concluded that finding a balance between manual expert work and Automated Machine Learning will be an interesting path to work in order to increase the efficiency in plant protection.