K-Anonymization-Based Temporal Attack Risk Detection Using Machine Learning Paradigms

Detection of visual faults in photovoltaic modules using a stacking ensemble approach

Most of data in various forms contain sensitive information about individuals and so publishing such data might violate privacy. Privacy preserving data publishing (PPDP) is an essential for publishing useful data while preserving privacy. Anonymization, which is a utility based privacy preserving approach, helps hiding the identities of data subjects and also provides data utility. Since data utility is effective on the accuracy of analysis model, new anonymization algorithms to improve data utility are always required. Mondrian is one of the near‐optimal anonymization models that presents high data utility and is frequently used for PPDP. However, the upper bound problem of Mondrian causes a decrease in potential data utility. This article focuses on this problem and proposes a new utility‐aware anonymization model (u‐Mondrian). Experimental results have shown that u‐Mondrian presents an acceptable solution to the upper bound problem, increases total data utility and presents higher data utility than Mondrian for different partitioning strategies and datasets.

Ensembles need their base classifiers do not always agree for any prediction (diverse base classifiers). Disturbing Neighbors ($\mathcal{DN}$) is a method for improving the diversity of the base classifiers of any ensemble algorithm. $\mathcal{DN}$ builds for each base classifier a set of extra features based on a 1-Nearest Neighbors (1-NN) output. These 1-NN are built using a small subset of randomly selected instances from the training dataset. $\mathcal{DN}$ has already been proved successfully on unstable base classifiers (i.e. decision trees). This paper presents an experimental validation on 62 UCI datasets for standard ensemble methods using Support Vector Machines (SVM) with a linear kernel as base classifiers. SVMs are very stable, so it is hard to increase their diversity when they belong to an ensemble. However, experiments will show that $\mathcal{DN}$ usually improves ensemble accuracy and base classifiers diversity.

ABSTRACTPrivacy preservation methods for anonymizing multiple sensitive attributes (MSA) data in the field of privacy-preserving data publishing (PPDP) mostly seek enforcement of the -diversity privacy model on MSA coupled with quasi-identifier (QID) generalization and tuple suppression, resulting in high data degradation of the published releases. Most existing work produces static releases that are not dynamic and web-based. In this article, we propose KC-Slice, which is amodified LKC-privacy model and slicing technique, for anonymizing MSA data dynamically, to produce releases that preserve the dataset content from most attack models and reduce data degradation, through cell suppression and QID random permutation. Experimental results and evaluation using data metrics and information entropy show remarkable reduction in data degradation and suppression ratio.

With the rising demand for integrated and autonomous systems in the field of engineering, efficient frameworks for instant detection of performance anomalies are imperative for improved productivity and cost-effectiveness. This study proposes a systematic predictive maintenance framework based on the hybrid multisensor fusion technique of fuzzy rough set feature selection and stacked ensemble for the efficient classification of fault conditions characterised by uncertainties. First, a feature vector of time-domain features was extracted from 17 multiple sensor signals. Then, a comparative study of six different Fuzzy Rough Set Feature Selection (FRFS) methods was employed to select the various combinations of optimal feature subsets for various faults classification tasks. The determined optimal feature subsets then served as inputs for training the stacked ensemble (ESB(STK)). In the ESB(STK), Support Vector Machine (SVM), Multilayer Perceptron (MLP), k -Nearest Neighbour ( k -NN), C4.5 Decision Tree (C4.5 DT), Logistic Regression (LR), and Linear Discriminant Analysis (LDA) served as the base classifiers while the LR was selected to be the metaclassifier. The proposed hybrid framework (FRFS-ESB(STK)) improved the classification accuracy with the selected combinations of optimal feature subset size whiles reducing the computational cost, overfitting, training runtime, and uncertainty in modelling. Overall analyses showed that the FRFS-ESB(STK) proved to be generalisable and versatile in the classification of all conditions of four monitored hydraulic components (i.e., cooler, valve, accumulator, and internal pump leakage) when compared with the six base classifiers (standalone) and three existing ensemble classifiers (Stochastic Gradient Boosting (SGB), Ada Boost (ADB), and Bagging (BAG)). The proposed FRFS-ESB(STK) showed an average improvement of 11.28% and 0.88% test accuracies when classifying accumulator and pump conditions, respectively, whiles 100% classification rates were obtained for both cooler and valve.

Accurate and efficient disease diagnosis plays a crucial role in healthcare. This study proposes a novel approach to enhance disease diagnosis performance by combining bagging and Teaching-Learning-Based Optimization (TLBO). The objective is to develop an optimized ensemble model that leverages the strengths of multiple base classifiers to improve diagnostic accuracy. The proposed methodology involves several key steps. TLBO optimization process is employed to dynamically select the most informative instances (bags) from the training data. The optimization process iteratively refines the bags by considering the fitness of each ensemble model constructed using different base classifiers. The soundness of an ensemble model is evaluated based on its accuracy in predicting the target variable. To further enhance the performance of the base classifiers, hyperparameter tuning using grid search is incorporated into the model training process. This ensures that each base classifier is optimized with the best set of hyperparameters, leading to more accurate predictions. The optimized bags are then used to train the base classifiers, which include Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Gaussian Naive Bayes (GNB). The base classifiers are combined into ensemble models using a Voting Classifier, allowing them to complement each other’s strengths and improve overall prediction performance. The results indicate that the TLBO-optimized ensemble models outperform individual base classifiers and traditional ensemble methods. The diversity among classifiers plays a crucial role in influencing the performance of ensemble models, especially in the context of disease diagnosis. Evaluating dissimilarity measures between classifiers becomes a key strategy in disease diagnosis. The dynamically selected bags contribute to improved accuracy, as they contain the most relevant instances for disease diagnosis and also explore computation time and diversity proposed ensemble approach on disease datasets.

Emotion recognition plays a pivotal role in advancing Human-Computer Interaction (HCI) by enabling systems to understand and respond to human emotional states. Among various modalities, Speech Emotion Recognition (SER) stands out as a non-invasive, cost-effective, and temporally efficient approach for detecting emotions. This study leverages the RAVDESS dataset, which provides high-quality audio recordings for emotion classification. The proposed methodology involves preprocessing audio signals to remove noise, extracting temporal and spectral features in both time and frequency domains, and implementing machine learning models for multi-class emotion classification. The study evaluates and compares the performance of several classification models, including Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), Convolutional Neural Networks (CNN), and Decision Trees (DT). Experimental results demonstrate promising accuracy levels, highlighting the potential of these machine learning techniques in SER. This research contributes to the integration of SER within Brain-Computer Interfaces (BCI) and other emotion-aware applications, paving the way for enhanced interactive systems. Keywords – Speech Emotion Recognition -Machine Learning - Random Forest -Multilayer Perceptron - Support Vector Machine - Convolutional Neural Networks - Decision Tree - RAVDESS Dataset

Botnets are used for malicious activities such as cyber-attacks, spamming, and data theft and have become a significant threat to cyber security. Despite existing approaches for cyber attack detection, botnets prove to be a particularly difficult problem that calls for more advanced detection methods. In this research, a stacking classifier is proposed based on K-nearest neighbor, support vector machine, decision tree, random forest, and multilayer perceptron, called KSDRM, for botnet detection. Logistic regression acts as the meta-learner to combine the predictions from the base classifiers into the final prediction with the aim of increasing the overall accuracy and predictive performance of the ensemble. The UNSW-NB15 dataset is used to train machine learning models and evaluate their effectiveness in detecting cyber-attacks on IoT networks. The categorical features are transformed into numerical values using label encoding. Machine learning techniques are adopted to recognize botnet attacks to enhance cyber security measures. The KSDRM model successfully captures the complex patterns and traits of botnet attacks and obtains 99.99% training accuracy. The KSDRM model also performs well during testing by achieving an accuracy of 97.94%. Based on 3, 5, 7, and 10 folds, the k-fold cross-validation results show that the proposed method’s average accuracy is 99.89%, 99.88%, 99.89%, and 99.87%, respectively. Further, the demonstration of experiments and results shows the KSDRM model is an effective method to identify botnet-based cyber attacks. The findings of this study have the potential to improve cyber security controls and strengthen networks against changing threats.

Diabetes Mellitus Prediction Using Ensemble Machine Learning Techniques

With its growing emphasis on sustainability, the construction industry is increasingly interested in environmentally friendly concrete produced by using alternative and/or recycled waste materials. However, the wide application of such concrete is hindered by the lack of understanding of the impacts of these materials on concrete properties. This research investigates and compares the performance of nine data mining models in predicting the compressive strength of a new type of concrete containing three alternative materials as fly ash, Haydite lightweight aggregate, and portland limestone cement. These models include three advanced predictive models (multilayer perceptron, support vector machines, and Gaussian processes regression), four regression tree models (M5P, REPTree, M5-Rules, and decision stump), and two ensemble methods (additive regression and bagging) with each of the seven individual models used as the base classifier. The analytical results show that, with appropriate parameter settings, all of these models, except decision stump, achieved acceptable prediction performance. The ensemble methods improved the prediction accuracy of the four regression tree models but had less success on the other three advanced predictive models. The individual Gaussian processes regression model and its related ensemble models reached the highest prediction accuracy in comparison groups. The results of this paper offer valuable insights on improving the use of these models for property prediction of concrete.

Feature selection and ensemble classification increase system efficiency and accuracy in machine learning, data mining and biomedical informatics. This research presents an analysis of the effect of removing irrelevant and redundant features with ensemble classifiers using two datasets from UCI machine learning repository. Accuracy and computational time were evaluated by four base classifiers; NaiveBayes, Multilayer Perceptron, Support Vector Machines and Decision Tree. Eliminating irrelevant features improves accuracy and reduces computational time while removing redundant features reduces computational time and reduces accuracy of the ensemble.

This study compares single and hybrid soft computing models for estimating daily solar radiation flux for two scenarios. Scenario I developed single soft computing models, including multilayer perceptron (MLP), support vector machines (SVM), adaptive neuro-fuzzy inference system (ANFIS), and multivariate adaptive regression splines (MARS), for estimating daily solar radiation flux at two stations from the USA and South Korea. The MLP model was used to evaluate the effect of factors controlling daily solar radiation flux. Using different combinations of controlling factors as input, the MLP and SVM models, based on evaluation measures, were found to be superior to the ANFIS and MARS models at Big Bend station, USA. In addition, the MLP, SVM, and MARS models performed better than did the ANFIS model at Incheon station, South Korea. Scenario II combined the discrete wavelet transform (DWT) and single soft computing models (e.g., MLP and SVM) for improved performance using 4-input combination. The wavelet-based MLP (WMLP) and SVM (WSVM) models were superior to other single soft computing models (MLP, SVM, ANFIS, and MARS) at two stations. Taylor diagrams, violin plots and point density plots were also utilized to examine the similarity between the observed and estimated solar radiation flux values. Results showed that scenarios I and II can be alternatives for estimating daily solar radiation flux based on different meteorological information, such as peninsular and continental conditions.

Abstract:Bankruptcy prediction and credit scoring are the two important problems facing financial decision support. The multilayer perceptron (MLP) network has shown its applicability to these problems and its performance is usually superior to those of other traditional statistical models. Support vector machines (SVMs) are the core machine learning techniques and have been used to compare with MLP as the benchmark. However, the performance of SVMs is not fully understood in the literature because an insufficient number of data sets is considered and different kernel functions are used to train the SVMs. In this paper, four public data sets are used. In particular, three different sizes of training and testing data in each of the four data sets are considered (i.e. 3:7, 1:1 and 7:3) in order to examine and fully understand the performance of SVMs. For SVM model construction, the linear, radial basis function and polynomial kernel functions are used to construct the SVMs. Using MLP as the benchmark, the SVM classifier only performs better in one of the four data sets. On the other hand, the prediction results of the MLP and SVM classifiers are not significantly different for the three different sizes of training and testing data.

In smart power grids, the utilization of computational infrastructures, advanced communication protocols, and automated metering systems (AMI) has led to increased efficiency and optimized energy consumption management. However, due to their heavy reliance on digital communications and the processing of large volumes of data, these grids are exposed to numerous security threats such as data tampering, unauthorized access, and measurement data manipulation. One of the most critical security threats in this domain is electricity theft through measurement data alteration or interference with smart metering systems. This paper presents a pattern recognition-based approach to enhance the accuracy of electricity theft detection in smart grids. The proposed method consists of two stages: In the first stage, anomaly detection in measurement data is performed using four base classifiers, including Support Vector Machines (SVM), Multi-Layer Perceptron (MLP), Decision Trees (DT), and the K-Nearest Neighbors (KNN) algorithm. In the second stage, the outputs of these classifiers are combined using the AdaBoost ensemble algorithm to improve detection accuracy. The proposed method is implemented in the MATLAB 2022b environment and evaluated on the CER dataset. The results indicate that the AdaBoost algorithm achieved the best results across various metrics, including accuracy (93.75%), recall (94.01%), and F -measure (93.84%). Additionally, in terms of the false positive rate (FPR), the AdaBoost algorithm demonstrated a favorable performance with a rate of $\mathbf{5. 9 2 \%}$, indicating its strong ability to correctly identify normal samples.

Zelenkov et al. [1] proposed a two-step classification method (TSCM) based on genetic algorithm to predict the bankruptcy of Russian companies. This current study was conducted to do more comprehensive evaluation than Zelenkov et al. [1] did. We involved more datasets, compared to a greater number of competitive methods, and developed the ensemble using more base classifiers. The datasets consisted of nine datasets and then the result of prediction compared to previous studies from 13 papers that were published between 1996 and 2009. In addition, the previous method using five base classifiers, this study involved seven base classifiers. The purpose of this study is to compare the accuracy of prediction from previous studies with this method. In this study, we used k-Nearest Neighbour (k-NN), Logistic Regression (LR), Naïve Bayes (NB), Decision Tree (DT), support vector machine (SVM), random forest (RF), and boosting as the base classifiers of ensemble model. Genetic algorithm is used to find the best predictor variables and the best weight for each base classifier. The result of TSCM shows that the accuracy of prediction can increase about 0-34% for some datasets compared to the previous studies.