Student performance prediction is vital for identifying at-risk students and providing support to help them succeed academically. In this paper, we propose a feature importance-based multi-layer CatBoost approach to predict the students’ grade in the period exam. The idea is to construct a multi-layer structure with increasingly important features layer by layer. Specifically, the feature importance are first calculated and sorted in ascending order. In each layer, features with the least importance are accumulated until reaching a given threshold. Then, these selected features are used to construct the first layer by training the CatBoost. Next, this trained CatBoost is utilized to generate a feature that adds to the feature set with their importance within a threshold. After that, all these feature are used to train the CatBoost in the next layer. This process is repeated until all the features are used. The results show that the proposed model has the best performance. Moreover, the statistical test conducted based on 20-runs of experiments validates the significant superiority of our proposed model over the compared models and demonstrates the efficacy of the multi-layer structure in enhancing the proposed model. This indicates our proposed model can help decision makers in enhancing educational quality.

Happiness refers to an emotional state of well-being and contentment. Accurate prediction of happiness is important for people in promoting a healthy lifestyle, helping reduce stress, and enhancing humans' immune system. In this paper, we propose a novel fuzzy feature generation approach for happiness prediction. We design a fuzzy weighted operation based on the IF-THEN rules to generate a fuzzy feature. This generated feature (new information) is added for the model training to achieve a more accurate model. In addition, considering the high interpretability of IF-THEN rules, it can improve the interpretability of the process of fuzzy feature generation. Experimental results show that with the use of the proposed fuzzy feature generation approach, the performance of the used machine learning models can be improved for happiness prediction, outperforming the state-of-the-art models. Among all the prediction models, the FF-CatBoost has the best performance in terms of accuracy (62.75%) and F1-score (66.63%). Results based on the other data sets also confirm the effectiveness of our fuzzy generation approach. The statistical results from the Wilcoxon rank-sum test further confirm that the results can be significantly improved in terms of accuracy. With its excellent performance for happiness prediction, the FF-CatBoost can be a useful tool to help people know more about their happiness status and live a happier life.

In the Internet of Things (IoT), the online performance of many online services is determined by their distribution resources, which are connected to many different devices. The expected performance of a resource service primarily depends on the optimal use of the service in satisfying end-to-end quality requirements to support its successful execution. Therefore, the performance of a resource service is dynamic and should be discovered as a benchmark to detect a performance anomaly online. A performance anomaly is referred to as a business anomaly because it depends on its usage. The performance is measured by the quality of service (QoS) that is possessed by a resource service. In this paper, an approach based on the resource service QoS is proposed to detect a business anomaly via mining business process data in collaborative tasks in the IoT. First, a resource-service chain (RSC) is considered to be an analysis object because resource services are employed as a “service flow” by a business process. The similarity between any two RSCs is measured according to the QoS indicator values of resource services. Based on the similarity, a clustering algorithm is presented to resolve clustering centers that are considered to be QoS benchmarks. Second, according to the QoS benchmarks of RSCs, the thresholds of QoS indicators of a business anomaly are determined. Third, an algorithm is presented to detect anomalies of the business process. Finally, the proposed approach is illustrated by a simulation experiment. The experimental results show that the approach can be used to effectively detect a business anomaly online.

Concrete is a vital component in modern construction, prized for its strength, durability, and versatility. Accurately determining the quantities of concrete components is crucial in civil engineering applications to optimize resources (e.g., manpower and financial resources). In this article, we propose an unbiased Fuzzy-Weighted Relative Error Support Vector Machine (UFW-RE-SVM) for reverse prediction of concrete components. First, we add an unbiased term to the target function of UFW-RE-SVM for obtaining an unbiased model. Second, we design a fuzzy-weighted operation to indicate sample importance by incorporating the fuzzy membership values into the UFW-RE- SVM. The nth root operation is introduced to address the exponential explosion issue in the fuzzy-weighted operation. Finally, considering the UFW-RE-SVM is sensitive to its hyper-parameters for multi-output prediction, the Whale Optimization Algorithm (WOA) is utilized for hyper-parameter optimization for its effectiveness in optimization tasks. We design the fitness function based on the results from multiple components to balance the performance of multi-output predictions. Experimental results show that the performance of our proposed model outperforms existing works in predicting concrete components in terms of mean absolute relative error, standard deviation, and root mean square error. Further, the statistical test shows the WOA and two other metaheuristics can significantly improve the prediction performance. This indicates that the unbiased term, fuzzy-weighted operation, and WOA are effective for improving the proposed model for reverse prediction concrete components. With these promising results, the proposed model could provide decision-makers with a valuable tool for determining concrete component quantities based on desired concrete qualities.