The core of dropout prediction lies in the selection of predictive models and feature tables. Machine learning models have been shown to predict student dropouts accurately. Because students may drop out of school in any semester, the student history data recorded in the academic management system would have a different length. The different length of student history data poses a challenge for generating feature tables. Most current studies predict student dropouts in the first academic year and therefore avoid discussing this issue. The central assumption of these studies is that more than 50% of dropouts will leave school in the first academic year. However, in our study, we found the distribution of dropouts is evenly distributed in all academic years based on the dataset from a Korean university. This result suggests that Korean students’ data characteristics included in our dataset may differ from those of other developed countries. More specifically, the result that dropouts are evenly distributed throughout the academic years indicates the importance of a dropout prediction for the students in any academic year. Based on this, we explore the universal feature tables applicable to dropout prediction for university students in any academic year. We design several feature tables and compare the performance of six machine learning models on these feature tables. We find that the mean value-based feature table exhibits better generalization, and the model based on the gradient boosting technique performs better than other models. This result reveals the importance of students’ historical information in predicting dropout.

Cryptocurrencies are highly volatile investment assets and are difficult to predict. In this study, various cryptocurrency data are used as features to predict the log-return price of major cryptocurrencies. The original contribution of this study is the selection of the most influential major features for each cryptocurrency using the volatility features of cryptocurrency, derived from the autoregressive conditional heteroskedasticity (ARCH) and generalized autoregressive conditional heteroskedasticity (GARCH) models, along with the closing price of the cryptocurrency. In addition, we sought to predict the log-return price of cryptocurrencies by implementing various types of time-series model. Based on the selected major features, the log-return price of cryptocurrency was predicted through the autoregressive integrated moving average (ARIMA) time-series prediction model and the artificial neural network-based time-series prediction model. As a result of log-return price prediction, the neural-network-based time-series prediction models showed superior predictive power compared to the traditional time-series prediction model.

Through innovation in the data collection environment, data-driven fault diagnosis has become increasingly important. This study aims to develop an algorithm to improve the accuracy of fault diagnosis based on Internet of Things (IoT) sensor data. In this research, current data collected through IoT sensors is utilized, focusing on diagnosing four states: bearing defects, shaft misalignment, rotor imbalance, and belt looseness. Additionally, to enhance the efficiency of the fault diagnosis algorithm, we introduce a preprocessing technique that utilizes descriptive statistics to reduce the data dimensionality. The experiments are conducted based on current data and vibration data, ensuring reliability from both types of data. The experimental results indicate a significant improvement in the accuracy and computational time of the fault diagnosis algorithm. After experimenting with various candidate algorithms, XGBoost version 1.7.6 exhibited the highest performance of classification. This research contributes to enhancing safety and reliability based on IoT sensors and suggests potential applications in the field of fault diagnosis.

Along with the fourth industrial revolution, research in the biomedical engineering field is being actively conducted. Among these research fields, the brain–computer interface (BCI) research, which studies the direct interaction between the brain and external devices, is in the spotlight. However, in the case of electroencephalograph (EEG) data measured through BCI, there are a huge number of features, which can lead to many difficulties in analysis because of complex relationships between features. For this reason, research on BCIs using EEG data is often insufficient. Therefore, in this study, we develop the methodology for selecting features for a specific type of BCI that predicts whether a person correctly detects facial expression changes or not by classifying EEG-based features. We also investigate whether specific EEG features affect expression change detection. Various feature selection methods were used to check the influence of each feature on expression change detection, and the best combination was selected using several machine learning classification techniques. As a best result of the classification accuracy, 71% of accuracy was obtained with XGBoost using 52 features. EEG topography was confirmed using the selected major features, showing that the detection of changes in facial expression largely engages brain activity in the frontal regions.

Alzheimer’s disease (AD) and Parkinson’s disease (PD) are prevalent neurodegenerative disorders among the elderly, leading to cognitive decline and motor impairments. As the population ages, the prevalence of these neurodegenerative disorders is increasing, providing motivation for active research in this area. However, most studies are conducted using brain imaging, with relatively few studies utilizing voice data. Using voice data offers advantages in accessibility compared to brain imaging analysis. This study introduces a novel ensemble-based classification model that utilizes Mel spectrograms and Convolutional Neural Networks (CNNs) to distinguish between healthy individuals (NM), AD, and PD patients. A total of 700 voice samples were collected under standardized conditions, ensuring data reliability and diversity. The proposed ternary classification algorithm integrates the predictions of binary CNN classifiers through a majority voting ensemble strategy. ResNet, DenseNet, and EfficientNet architectures were employed for model development. The experimental results show that the ensemble model based on ResNet achieves a weighted F1 score of 91.31%, demonstrating superior performance compared to existing approaches. To the best of our knowledge, this is the first large-scale study to perform three-class classification of neurodegenerative diseases using voice data.

As the population ages, Alzheimer’s disease (AD) and Parkinson’s disease (PD) are increasingly common neurodegenerative diseases among the elderly. Human voice signals contain various characteristics, and the voice recording signals with time-series properties include key information such as pitch, tremor, and breathing cycle. Therefore, this study aims to propose an algorithm to classify normal individuals, Alzheimer’s patients, and Parkinson’s patients using these voice signal characteristics. The study subjects consist of a total of 700 individuals, who provided data by uttering 40 predetermined sentences. To extract the main characteristics of the recorded voices, a Mel–spectrogram was used, and these features were analyzed using a Convolutional Neural Network (CNN). The analysis results showed that the classification based on DenseNet exhibited the best performance. This study suggests the potential for classification of cognitive impairment through voice signal analysis.