25 posts tagged with "paper"

Abstract

Predicting future blood glucose (BG) levels for diabetic patients will help them avoid potentially critical health issues. We demonstrate the use of machine learning models to predict future blood glucose levels given a history of blood glucose values as the single input parameter. We propose an Artificial Neural Network (ANN) model with time-domain attributes to predict blood glucose levels 15, 30, 45 and 60 min in the future. Initially, the model’s features are selected based on the previous 30 min of BG measurements before a trained model is generated for each patient. These features are combined with time-domain attributes to give additional inputs to the proposed ANN. The prediction model was tested on 12 patients with Type 1 diabetes (T1D) and the results were compared with other data-driven models including the Support Vector Regression (SVR), K-Nearest Neighbor (KNN), C4.5 Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost) and eXtreme Gradient Boosting (XGBoost) models. Our results show that the proposed BG prediction model that is based on an ANN outperformed all other models with an average Root Mean Square Error (RMSE) of 2.82, 6.31, 10.65 and 15.33 mg/dL for Prediction Horizons (PHs) of 15, 30, 45 and 60 min, respectively. Our testing showed that combining time-domain attributes into the input data resulted in enhanced performance of majority of prediction models. The implementation of proposed prediction model allows patients to obtain future blood glucose levels, so that the preventive alerts can be generated before critical hypoglycemic/ hyperglycemic events occur.

Published in: Biocybernetics and Biomedical Engineering
DOI: 10.1016/j.bbe.2020.10.004

Abstract

Extracting information from individual risk factors provides an effective way to identify diabetes risk and associated complications, such as retinopathy, at an early stage. Deep learning and machine learning algorithms are being utilized to extract information from individual risk factors to improve early-stage diagnosis. This study proposes a deep neural network (DNN) combined with recursive feature elimination (RFE) to provide early prediction of diabetic retinopathy (DR) based on individual risk factors. The proposed model uses RFE to remove irrelevant features and DNN to classify the diseases. A publicly available dataset was utilized to predict DR during initial stages, for the proposed and several current best-practice models. The proposed model achieved 82.033% prediction accuracy, which was a significantly better performance than the current models. Thus, important risk factors for retinopathy can be successfully extracted using RFE. In addition, to evaluate the proposed prediction model robustness and generalization, we compared it with other machine learning models and datasets (nephropathy and hypertension–diabetes). The proposed prediction model will help improve early-stage retinopathy diagnosis based on individual risk factors.

Published in: Mathematics
DOI: 10.3390/math8091620

Abstract

Detecting self-care problems is one of important and challenging issues for occupational therapists, since it requires a complex and time-consuming process. Machine learning algorithms have been recently applied to overcome this issue. In this study, we propose a self-care prediction model called GA-XGBoost, which combines genetic algorithms (GAs) with extreme gradient boosting (XGBoost) for predicting self-care problems of children with disability. Selecting the feature subset affects the model performance; thus, we utilize GA to optimize finding the optimum feature subsets toward improving the model’s performance. To validate the effectiveness of GA-XGBoost, we present six experiments: comparing GA-XGBoost with other machine learning models and previous study results, a statistical significant test, impact analysis of feature selection and comparison with other feature selection methods, and sensitivity analysis of GA parameters. During the experiments, we use accuracy, precision, recall, and f1-score to measure the performance of the prediction models. The results show that GA-XGBoost obtains better performance than other prediction models and the previous study results. In addition, we design and develop a web-based self-care prediction to help therapist diagnose the self-care problems of children with disabilities. Therefore, appropriate treatment/therapy could be performed for each child to improve their therapeutic outcome.

Published in: Mathematics
DOI: 10.3390/math8091590

Abstract

Radio frequency identification (RFID) technology can be utilized to monitor tagged product movements and directions for the purpose of inventory management. It is important for RFID gate to identify the several RFID readings such as movement type and direction as well as the static tags (tags that accidentally read by the reader). In this study, random forest (RF) method is utilized to detect the movement type and direction of RFID passive tags. The input features are derived from received signal strength (RSS) and timestamp of tags. The result showed that machine learning models successfully distinguish direction and movement type of tag. In addition, proposed model based on random forest generated accuracy as much as 98.39% and was significantly superior to the other models considered.

Published in: IEEE Xplore
DOI: 10.1109/ICST47872.2019.9166196

Abstract

Heart disease, one of the major causes of mortality worldwide, can be mitigated by early heart disease diagnosis. A clinical decision support system (CDSS) can be used to diagnose the subjects’ heart disease status earlier. This study proposes an effective heart disease prediction model (HDPM) for a CDSS which consists of Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to detect and eliminate the outliers, a hybrid Synthetic Minority Over-sampling Technique-Edited Nearest Neighbor (SMOTE-ENN) to balance the training data distribution and XGBoost to predict heart disease. Two publicly available datasets (Statlog and Cleveland) were used to build the model and compare the results with those of other models (naive bayes (NB), logistic regression (LR), multilayer perceptron (MLP), support vector machine (SVM), decision tree (DT), and random forest (RF)) and of previous study results. The results revealed that the proposed model outperformed other models and previous study results by achieving accuracies of 95.90% and 98.40% for Statlog and Cleveland datasets, respectively. In addition, we designed and developed the prototype of the Heart Disease CDSS (HDCDSS) to help doctors/clinicians diagnose the patients’/subjects’ heart disease status based on their current condition. Therefore, early treatment could be conducted to prevent the deaths caused by late heart disease diagnosis.

Published in: IEEE Access
DOI: 10.1109/ACCESS.2020.3010511

Abstract

Predicting future blood glucose (BG) level for diabetic patients will help them to avoid critical conditions in the future. This study proposed Extreme Gradient Boosting (XGBoost), an ensemble learning model to predict the future blood glucose value of diabetic patients. The clinical dataset of Type 1 Diabetes (T1D) patients was utilized and the prediction models were generated to predict future BG of 30 and 60 minutes ahead of time. The prediction models have been tested tofive children who develop T1D and showed that BG prediction model based on XGBoost outperformed other models, with average of Root Mean Square Error (RMSE) are 23.219 mg/dL and 35.800 mg/dL for prediction horizon (PH) 30 and 60 minutes respectively. In addition, the result showed that by utilizing statistical-based features as additional attributes, most of the performance of predictions model were increased.

Published in: IOP Conference Series: Materials Science and Engineering
DOI: 10.1088/1757-899X/803/1/012012

Abstract

Understanding customer shopping behavior in retail store is important to improve the customers' relationship with the retailer, which can help to lift the revenue of the business. However, compared to online store, the customer browsing activities in the retail store is difficult to be analysed. Therefore, in this study the customer shopping behavior analysis (i.e., browsing activity) in retail store by utilizing radio frequency identification (RFID)-enabled shelf and machine learning model is proposed. First, the RFID technology is installed in the store shelf to monitor the movement tagged products. The dataset was gathered from receive signal strength (RSS) of the tags for different customer behavior scenario. The statistical features were extracted from RSS of tags. Finally, machine learning models were utilized to classify different customer shopping activities. The experiment result showed that the proposed model based on Multilayer Perceptron (MLP) outperformed other models by as much as 97.00%, 96.67%, 97.50%, and 96.57% for accuracy, precision, recall, and f-score, respectively. The proposed model can help the managers better understand what products customer interested in, so that can be utilized for product placement, promotion as well as relevant product recommendations to the customers.

Published in: IOP Conference Series: Materials Science and Engineering
DOI: 10.1088/1757-899X/803/1/012022