Search

Studies on automatically predicting student learning outcomes often focus on developing and optimizing machine learning algorithms that fit the data captured from different education systems. This approach has a fatal weakness when it is used for disadvantaged groups, such as those with academic warnings or who have dropped out, because these groups are often much smaller than other common groups in number. The imbalanced data that have class distribution skew create a big challenge to training good classification models. The significant approach to tackle this challenge is applying oversampling methods to increase the number of minor classes; however, generating good new samples from the existing instances of a minor class is still a hard issue and requires new investigation. This study presents two new methods of handling data imbalance based on the original algorithms SMOTE and adaptive synthetic sampling (ADASYN), called Improved SMOTE (I_SMOTE) and Improved ADASYN (I_ADASYN). These modifications involve a new selecting fit candidate method based on a new similarity measurement and a roulette wheel selection to generate synthetic data samples. The aim is to rebalance data and therefore improve the prediction accuracy of minor groups. The proposal methods were designed and applied to education datasets, and they were tested on public datasets and a dataset collected from a Vietnamese university for evaluation. The experimental results on learning datasets showed the high potential of novel algorithms, I_SMOTE and I_ADASYN, for student academic performance problems in general and at‐risk student groups especially. Empirical results proved that the recall, precision, and F1‐score of the minority class of I_SMOTE and I_ADASYN are strongly better than the original balancing algorithms. Besides, the I_SMOTE and I_ADASYN also improve relatively by 6.6% and 8.0% of the ROC area compared to the original SMOTE and ADASYN, respectively. [ABSTRACT FROM AUTHOR]

One of the most significant issues in wireless sensor networks (WSNs) is security, which must be addressed to keep WSNs safe from malicious attacks. An intrusion detection system (IDS) is essential in analyzing network traffic and detecting abnormal events. However, these IDSs suffer from several drawbacks that affect their effectiveness and flexibility in accuracy, so they must overcome these drawbacks to improve the performance of IDS. These drawbacks include difficulties in determining the appropriate dataset, the problem of feature selection, and the issue of the imbalanced dataset and choosing the appropriate algorithms for the classification process in WSN. In this paper, a model for an anomaly‐based IDS in WSNs is proposed. This model applied mutual information (MI) for feature selection and the synthetic minority oversampling technique (SMOTE) for solving the imbalanced dataset problem. It used different machine learning (ML) algorithms, random forest (RF), decision tree (DT), support vector machine (SVM), and K‐nearest neighbors (KNNs) to analyze network traffic and binary classification or multiclass classification. To implement and evaluate the performance of the proposed model, the standard dataset NSL‐KDD is used. Python language is used to implement the proposed model in the Anaconda platform, and many evaluation metrics are also utilized to evaluate the performance of the proposed method. Experimental results show that the proposed model can detect intrusions using different ML algorithms with high accuracy. The results of the proposed model for different ML algorithms outperform the state‐of‐the‐art algorithms, and the maximum enhancement reached 15% in the accuracy metric. [ABSTRACT FROM AUTHOR]

This research proposes a highly effective soft computing paradigm for estimating the compressive strength (CS) of metakaolin-contained cemented materials. The proposed approach is a combination of an enhanced grey wolf optimizer (EGWO) and an extreme learning machine (ELM). EGWO is an augmented form of the classic grey wolf optimizer (GWO). Compared to standard GWO, EGWO has a better hunting mechanism and produces an optimal performance. The EGWO was used to optimize the ELM structure and a hybrid model, ELM-EGWO, was built. To train and validate the proposed ELM-EGWO model, a sum of 361 experimental results featuring five influencing factors was collected. Based on sensitivity analysis, three distinct cases of influencing parameters were considered to investigate the effect of influencing factors on predictive precision. Experimental consequences show that the constructed ELM-EGWO achieved the most accurate precision in both training (RMSE = 0.0959) and testing (RMSE = 0.0912) phases. The outcomes of the ELM-EGWO are significantly superior to those of deep neural networks (DNN), k-nearest neighbors (KNN), long short-term memory (LSTM), and other hybrid ELMs constructed with GWO, particle swarm optimization (PSO), harris hawks optimization (HHO), salp swarm algorithm (SSA), marine predators algorithm (MPA), and colony predation algorithm (CPA). The overall results demonstrate that the newly suggested ELM-EGWO has the potential to estimate the CS of metakaolin-contained cemented materials with a high degree of precision and robustness. [ABSTRACT FROM AUTHOR]

The determination of subgrade/subsoil strength is one of the most important pavement design factors in transportation engineering, particularly for railways, roadways, and airport runways. The California bearing ratio (CBR) is often used to measure the strength and stiffness modulus of subgrade materials. This study presents a novel machine learning solution as an alternate approach for estimating soil CBR in soaked conditions. The present approach is an integration of an artificial neural network (ANN) and improved particle swarm optimisation (IPSO). According to experimental results during the testing phase, the proposed hybrid model, ANN-IPSO has achieved the highest predictive precision with root mean square error, RMSE = 0.0711 and mean absolute error, MAE = 0.0546. The findings of the proposed model are far superior to those of employed models including the conventional ANN, support vector machine, and group method of data handling. Six additional hybrid models of ANN and standard PSO (SPSO), PSO with time-varying accelerator coefficients, modified PSO, Harris hawks optimisation, slime mould algorithm, and colony predation algorithm were also constructed for a detailed comparison. Based on the outcomes, the newly created ANN-IPSO has the potential to be a new tool to estimate soaked CBR of fine-grained soils in civil engineering projects. [ABSTRACT FROM AUTHOR]