Accuracy comparison between statistical and computational classifiers applied for predicting student performance in online higher education.

Educational institutions abruptly implemented online higher education to cope with sanitary distance restrictions in 2020, causing an increment in student failure. This negative impact attracts the analyses of online higher education as a critical issue for educational systems. The early identification of students at risk is a strategy to cope with this issue by predicting their performance. Computational techniques are projected helpful in performing this task. However, the accurateness of predictions and the best model selection are goals in progress. This work objective is to describe two experiments using student grades of an online higher education program to build and apply three classifiers to predict student performance. In the literature, the three classifiers, a Probabilistic Neural Network, a Support Vector Machine, and a Discriminant Analysis, have proved efficient. I applied the leave-one-out cross-validation method, tested their performances by five criteria, and compared their results through statistical analysis. The analyses of the five performance criteria support the decision on which model applies given particular prediction goals. The results allow timely identification of students at risk of failure for early intervention and predict which students will succeed.

Decision Support for Breast Cancer Detection: Classification Improvement Through Feature Selection.

Several statistical-based approaches have been developed to support medical personnel in early breast cancer detection. This article presents a method for feature selection aimed at classifying cases into categories based on patients' breast tissue measures and protein microarray. The effectiveness of this feature selection strategy was evaluated against the commonly used Wisconsin Breast Cancer Database-WBCD (with several patients and fewer features) and a new protein microarray data set (with several features and fewer patients). Features were ranked according to a feature importance index that combines parameters emerging from the unsupervised method of principal component analysis and the supervised method of Bhattacharyya distance. Observations of a training set were iteratively categorized into malignant and benign cases through 3 classification techniques: k-Nearest Neighbor, linear discriminant analysis, and probabilistic neural network. After each classification, the feature with the smallest importance index was removed, and a new categorization was carried out until there was only one feature left. The subset yielding maximum accuracy was used to classify observations in the testing set. Our method yielded average 99.17% accurate classifications in the testing set while retaining average 4.61 out of 9 features in the WBCD, which is comparable to the best results reported by the literature on that data set, with the advantage of relying on simple and widely available multivariate techniques. When applied to the microarray data, the method yielded average accuracy of 98.30% while retaining average 2.17% of the original features. Our results can aid health-care professionals during early diagnosis of breast cancer.

A Novel Wavelet Transform-Homogeneity Model for Sudden Cardiac Death Prediction Using ECG Signals.

Sudden cardiac death (SCD) is one of the main causes of death among people. A new methodology is presented for predicting the SCD based on ECG signals employing the wavelet packet transform (WPT), a signal processing technique, homogeneity index (HI), a nonlinear measurement for time series signals, and the Enhanced Probabilistic Neural Network classification algorithm. The effectiveness and usefulness of the proposed method is evaluated using a database of measured ECG data acquired from 20 SCD and 18 normal patients. The proposed methodology presents the following significant advantages: (1) compared with previous works, the proposed methodology achieves a higher accuracy using a single nonlinear feature, HI, thus requiring low computational resource for predicting an SCD onset in real-time, unlike other methodologies proposed in the literature where a large number of nonlinear features are used to predict an SCD event; (2) it is capable of predicting the risk of developing an SCD event up to 20 min prior to the onset with a high accuracy of 95.8%, superseding the prior 12 min prediction time reported recently, and (3) it uses the ECG signal directly without the need for transforming the signal to a heart rate variability signal, thus saving time in the processing.

Use of Savitzky-Golay Filter for Performances Improvement of SHM Systems Based on Neural Networks and Distributed PZT Sensors.

A considerable amount of research has focused on monitoring structural damage using Structural Health Monitoring (SHM) technologies, which has had recent advances. However, it is important to note the challenges and unresolved problems that disqualify currently developed monitoring systems. One of the frontline SHM technologies, the Electromechanical Impedance (EMI) technique, has shown its potential to overcome remaining problems and challenges. Unfortunately, the recently developed neural network algorithms have not shown significant improvements in the accuracy of rate and the required processing time. In order to fill this gap in advanced neural networks used with EMI techniques, this paper proposes an enhanced and reliable strategy for improving the structural damage detection via: (1) Savitzky-Golay (SG) filter, using both first and second derivatives; (2) Probabilistic Neural Network (PNN); and, (3) Simplified Fuzzy ARTMAP Network (SFAN). Those three methods were employed to analyze the EMI data experimentally obtained from an aluminum plate containing three attached PZT (Lead Zirconate Titanate) patches. In this present study, the damage scenarios were simulated by attaching a small metallic nut at three different positions in the aluminum plate. We found that the proposed method achieves a hit rate of more than 83%, which is significantly higher than current state-of-the-art approaches. Furthermore, this approach results in an improvement of 93% when considering the best case scenario.