Background: Data collected by an actigraphy device worn on the wrist or waist can provide objective measurements for studies related to physical activity; however, some data may contain intervals where values are missing. In previous studies, statistical methods have been applied to impute missing values on the basis of statistical assumptions. Deep learning algorithms, however, can learn features from the data without any such assumptions and may outperform previous approaches in imputation tasks. Objective: The aim of this study was to impute missing values in data using a deep learning approach. Methods: To develop an imputation model for missing values in accelerometer-based actigraphy data, a denoising convolutional autoencoder was adopted. We trained and tested our deep learning–based imputation model with the National Health and Nutrition Examination Survey data set and validated it with the external Korea National Health and Nutrition Examination Survey and the Korean Chronic Cerebrovascular Disease Oriented Biobank data sets which consist of daily records measuring activity counts. The partial root mean square error and partial mean absolute error of the imputed intervals (partial RMSE and partial MAE, respectively) were calculated using our deep learning–based imputation model (zero-inflated denoising convolutional autoencoder) as well as using other approaches (mean imputation, zero-inflated Poisson regression, and Bayesian regression). Results: The zero-inflated denoising convolutional autoencoder exhibited a partial RMSE of 839.3 counts and partial MAE of 431.1 counts, whereas mean imputation achieved a partial RMSE of 1053.2 counts and partial MAE of 545.4 counts, the zero-inflated Poisson regression model achieved a partial RMSE of 1255.6 counts and partial MAE of 508.6 counts, and Bayesian regression achieved a partial RMSE of 924.5 counts and partial MAE of 605.8 counts. Conclusions: Our deep learning–based imputation model performed better than the other methods when imputing missing values in actigraphy data.

Estimating and classifying depression status are critical in the clinical and psychological domains to map the course of treatment. Prior researchers used biosignal time-series data to reflect the variation in factors associated with depression. In addition, machine learning algorithms were applied to determine the underlying relationships between depressive symptoms and these factors. In this study, we introduce a classification framework for depression levels using actigraphy data based on machine learning algorithms. Fourteen circadian rhythm features (minimum, amplitude, alpha, beta, acrotime, upmesor, downmesor, mesor, f_pseudo, interdaily stability (IS), intradaily variability (IV), relative amplitude (RA), M10, and L5) extracted from accelerometer-based actigraphy data were used to model depression status with survey variables. Six evaluation metrics (accuracy, precision, recall, F1-score, receiver operating characteristic curve, and area under the curve) were applied to validate the performance of the proposed framework. Among the four candidate classifiers (XGBoost classifier, support vector classifier, multilayer perceptron, and logistic regression), the XGBoost classifier was the best at classifying depression levels. Moreover, we confirmed that the actigraphy data of two days were optimal for feature extraction and classification. The results of this study provide novel insights into the relationship between depression and physical activity in terms of both identification of depression and application of actigraphy data.

The planning and execution of a business strategy are important aspects of the strategic human resource management of a company. In previous studies, machine learning algorithms were used to determine the main factors correlating employees with company performance. In this study, we introduced a method based on machine-learning algorithms for the classification of company revenue. Both annual and integrated datasets were examined to evaluate the classification performance of the framework under both binary and multiclass conditions. The performance of the proposed method was validated using six evaluation metrics: accuracy, precision, recall, F1-score, receiver operating characteristic curve, and area under the curve. As the experimental results indicate, the XGBoost classifier displayed the best classification performance among the three algorithms (XGBoost classifier, stochastic gradient descent classifier, and logistic regression) used in this study. Moreover, we confirmed the important features of the trained XGBoost model in accordance with variables focusing on human resource management studies. These results demonstrate that the proposed framework has strength in terms of both classification and practical implementation. This study provides novel insights into the relationship between employees and the revenue levels of their employer.

Classifying emotional states is critical for brain–computer interfaces and psychology-related domains. In previous studies, researchers have tried to identify emotions using neural data such as electroencephalography (EEG) signals or brain functional magnetic resonance imaging (fMRI). In this study, we propose a machine learning framework for emotion state classification using EEG signals in virtual reality (VR) environments. To arouse emotional neural states in brain signals, we provided three VR stimuli scenarios to 15 participants. Fifty-four features were extracted from the collected EEG signals under each scenario. To find the optimal classification in our research design, three machine learning algorithms (XGBoost classifier, support vector classifier, and logistic regression) were applied. Additionally, various class conditions were used in machine learning classifiers to validate the performance of our framework. To evaluate the classification performance, we utilized five evaluation metrics (precision, recall, f1-score, accuracy, and AUROC). Among the three classifiers, the XGBoost classifiers showed the best performance under all experimental conditions. Furthermore, the usability of features, including differential asymmetry and frequency band pass categories, were checked from the feature importance of XGBoost classifiers. We expect that our framework can be applied widely not only to psychological research but also to mental health-related issues.

Background. Proper management of hyperkalemia that leads to fatal cardiac arrhythmia has become more important because of the increased prevalence of hyperkalemia-prone diseases. Although T-wave changes in hyperkalemia are well known, their usefulness is debatable. We evaluated how well T-wave-based features of electrocardiograms (ECGs) are correlated with estimated serum potassium levels using ECG data from real-world clinical practice.Methods. We collected ECGs from a local ECG repository (MUSE™) from 1994 to 2017 and extracted the ECG waveforms. Of about 1 million reports, 124,238 were conducted within 5 minutes before or after blood collection for serum potassium estimation. We randomly selected 500 ECGs and two evaluators measured the amplitude (T-amp) and right slope of the T-wave (T-right slope) on five lead waveforms (V3, V4, V5, V6, and II). Linear correlations of T-amp, T-right slope, and their normalized feature (T-norm) with serum potassium levels were evaluated using Pearson correlation coefficient analysis.Results. Pearson correlation coefficients for T-wave-based features with serum potassium between the two evaluators were 0.99 for T-amp and 0.97 for T-right slope. The coefficient for the association between T-amp, T-right slope, and T-norm, and serum potassium ranged from -0.22 to 0.02. In the normal ECG subgroup (normal ECG or otherwise normal ECG), there was no correlation between T-wave-based features and serum potassium level.Conclusions. T-wave-based features were not correlated with serum potassium level, and their use in real clinical practice is currently limited.