Activity-based nutrition management model for healthcare using similar group analysis

Chung, Kyungyong; Kim, Jonghun

doi:10.3233/thc-191731

Cited by 13 publications

(20 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarity analysis is a method for determining whether parameters are positively or negatively correlated with each other. These correlations are represented within a range of −1 to +1, in which a value closer to −1 indicates that the relationship is moving more in the opposite direction, whereas a value closer to +1 indicates that the relationship is moving more in the same direction [36], [37]. Values closer to 0 indicate a lower mutual impact.…”

Section: B Evaluation Results According To Multi-modal Configurationmentioning

confidence: 99%

Multi-Modal Stacked Denoising Autoencoder for Handling Missing Data in Healthcare Big Data

Kim

Chung

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Supply and demand increase in response to healthcare trends. Moreover, personal health records (PHRs) are being managed by individuals. Such records are collected using different avenues and vary considerably in terms of their type and scope depending on the particular circumstances. As a result, some data may be missing, which has a negative effect on the data analysis, and such data should, therefore, be replaced with appropriate values. In this study, a method for estimating missing data using a multi-modal autoencoder applied to the field of healthcare big data is proposed. The proposed method uses a stacked denoising autoencoder to estimate the missing data that occur during the data collection and processing stages. Autoencoders are neural networks that output value of x^similar to an input value of x. In the present study, data from the Korean National Health Nutrition Examination Survey (KNHNES), conducted by the Korea Centers for Disease Control and Prevention (KCDC), are used. As representative healthcare data from South Korea, they contain a large number of parameters identical to those used in the PHRs. Based on this, models can be generated to estimate missing data occurring in PHRs. Furthermore, PHRs involve a multimodality that allows the data to be collected from multiple sources for a single object. Therefore, the stacked denoising autoencoder applied is configured under a multi-modal setting. Through pre-processing, a set of data without missing value in KNHNES is designed. In the data set based learning, a label is set as original data, and an autoencoder input is set as noised input that additionally has as many random zero numbers as noise factor. In this way, the autoencoder learns in the way of making the zero-based noise value similar to the original label value. When the amount of missing data in a dataset reaches approximately 25%, the accuracy of the proposed method using a multi-modal stacked denoising autoencoder is 0.9217, which is higher than that achieved by other ordinary methods. For a single-modal denoising autoencoder, the accuracy is 0.932, with a slight difference of approximately 0.01, which falls within the allowable limits in data analysis. In terms of computational performance, a single-modal autoencoder has 10,384 parameters, which is 5,594 more than those used in a multi-modal stacked autoencoder. These parameters affect the speed of the model. Both models exhibit a significant difference in the number of parameters but demonstrate a relatively small difference in accuracy, suggesting that the proposed multi-modal stacked denoising autoencoder is advantageous over a single-modal model when used on a personal device. Moreover, a multi-modal model can save additional time when processing large amounts of data in locations such as hospitals and institutions. INDEX TERMS Autoencoder, data pre-processing, data estimation, data imputation, health big data, multimodal, missing data, machine learning.

show abstract

Section: B Evaluation Results According To Multi-modal Configurationmentioning

confidence: 99%

Multi-Modal Stacked Denoising Autoencoder for Handling Missing Data in Healthcare Big Data

Kim

Chung

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Secondly, to evaluate context-DNN model, a crossvalidation test is conducted with the use of K -fold. The cross-validation technique can use all data sets as evaluation data and prevents overfitting that arises in a particular evaluation data set [44], [45]. All data sets can be used as training data.…”

Section: B Performance Evaluationmentioning

confidence: 99%

Context Deep Neural Network Model for Predicting Depression Risk Using Multiple Regression

Baek

Chung

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Depression is a mental illness influenced by various factors, including stress in everyday life, physical activities, and physical diseases. It accompanies such symptoms as continuous depression, sleep disorder, and suicide attempts. In the healthcare, it is necessary to predict diverse situations accurately. Accordingly, in order to care for mental health, it is necessary to recognize individuals' situations and continue to manage them. In the area of mental diseases and treatment, research has been conducted to find a patient's state with the use of big data and to monitor the worst situation. Mental illnesses typically have depression. Research on Mental healthcare using artificial intelligence do conduct on prediction based on patients' voice, word choice, and conversation length. However, there is not much research on situation prediction in order to prevent depression. Therefore, this study proposes the context-DNN model for predicting depression risk using multiple-regression. The context of the proposed context-DNN consists of the information to predict situations and environments influencing depression in consideration of context information. Each context information related to predictor variables of depression becomes an input of DNN, and variable for depression prediction becomes an output of DNN. For DNN connection, the regression analysis to predict the risk of depression is used so as to predict the potential context influencing the risk of depression. According to the performance evaluation, the proposed model was evaluated to have the best performance in regression analysis and comparative analysis with DNN. INDEX TERMS Deep neural network, context, depression risk, mental health, multiple regression, healthcare, deep learning, context information.

show abstract

“…Therefore, it is necessary to validate the result of the image classified on the basis of the decision boundary. For validation, precision, recall and F-measure are applied [33], [34]. Precision means a ratio of actual True data to the True data determined by the model.…”

Section: Decision Boundary Calculation Through Anomaly Score For Cmentioning

confidence: 99%

Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG Data

2020

Self Cite

View full text Add to dashboard Cite

Arrhythmia detection through deep learning is mainly classified through supervised learning. Supervised learning progresses through the labeled data. However, in the medical field, it is challenging to collect ECG data of patients with arrhythmia than ECG data of healthy people, and thus data bias occurs. Therefore, if you use a supervised learning model, there are problems with lack of data and imbalance between labels that arise during learning. Accordingly, this study proposes the decision boundary-based Anomaly detection model using improved AnoGan from ECG data. In this study, at the time of learning, the loss of the Generator does not reduce, but the loss of a Discriminator lowers. Even if the Generator and Discriminator were designed to have the same learning count, the learning competency of Generator was judged to be lowered. In repeated experiments, it was found that the best loss balance was achieved when the learning count of Discriminator was 1 and that of Generator was 4. Another problem is that the decision boundary of AnoGAN is subjective. Accordingly, the repeated experiments based on F-measure are conducted to determine a decision boundary. For performance evaluation, the accuracy of the model is evaluated on the basis of Epoch, and the goodness-of-fit of the model is evaluated on the basis of AUC and F-measure. According to the evaluation of F-measure, the model has the best performance when the decision boundary is 200. In terms of Epoch, the model has the highest accuracy when the Epoch is 10. In addition, the proposed model has better goodness-of-fit than AnoGAN.

show abstract

Activity-based nutrition management model for healthcare using similar group analysis

Cited by 13 publications

References 17 publications

Multi-Modal Stacked Denoising Autoencoder for Handling Missing Data in Healthcare Big Data

Multi-Modal Stacked Denoising Autoencoder for Handling Missing Data in Healthcare Big Data

Context Deep Neural Network Model for Predicting Depression Risk Using Multiple Regression

Decision Boundary-Based Anomaly Detection Model Using Improved AnoGAN From ECG Data

Contact Info

Product

Resources

About