According to the American Diabetes Association(ADA), 30.3 million people in the United States have diabetes, but only 7.2 million may be undiagnosed and unaware of their condition. Type 2 diabetes is usually diagnosed for most patients later on in life whereas the less common Type 1 diabetes is diagnosed early on in life. People can live healthy and happy lives while living with diabetes, but early detection produces a better overall outcome on most patient's health. Thus, to test the accurate prediction of Type 2 diabetes, we use the patients' information from an electronic health records company called Practice Fusion, which has about 10,000 patient records from 2009 to 2012. This data contains individual key biometrics, including age, diastolic and systolic blood pressure, gender, height, and weight. We use this data on popular machine learning algorithms and for each algorithm, we evaluate the performance of every model based on their classification accuracy, precision, sensitivity, specificity/recall, negative predictive value, and F1 score. In our study, we find that all algorithms other than Naive Bayes suffered from very low precision. Hence, we take a step further and incorporate all the algorithms into a weighted average or soft voting ensemble model where each algorithm will count towards a majority vote towards the decision outcome of whether a patient has diabetes or not. The accuracy of the Ensemble model on Practice Fusion is 85\%, by far our ensemble approach is new in this space. We firmly believe that the weighted average ensemble model not only performed well in overall metrics but also helped to recover wrong predictions and aid in accurate prediction of Type 2 diabetes. Our accurate novel model can be used as an alert for the patients to seek medical evaluation in time.
Enhancing Bagging Ensemble Regression with Data Integration for Time Series-Based Diabetes Prediction
Insight Centre for Data Analytics, School of Computing, Dublin City University, Dublin, Ireland(数据分析洞察中心、计算学院、都柏林城市大学,都柏林,爱尔兰);Faculty of Information Technology, Ho Chi Minh City Open University, Ho Chi Minh City, Vietnam(信息技术学院、胡志明市开放大学,胡志明市,越南);Faculty of Electrical and Electronic Engineering, Ho Chi Minh City University of Transport, Ho Chi Minh City, Vietnam(电气与电子工程学院、胡志明市交通大学,胡志明市,越南);School of Public Health, University College Cork, Cork, Ireland(公共卫生学院、科克大学学院,科克,爱尔兰)
SmartEdge: Smart Healthcare End-to-End Integrated Edge and Cloud Computing System for Diabetes Prediction Enabled by Ensemble Machine Learning
University of Melbourne(墨尔本大学);United Arab Emirates University(阿联酋大学);Emirates Center for Mobility Research(阿联酋交通研究中心);National Water and Energy Center(国家水资源与能源中心);UAE University(阿联酋大学)
ECO-AMLP: A Decision Support System using an Enhanced Class Outlier with Automatic Multilayer Perceptron for Diabetes Prediction
National University of Sciences & Technology(国家科学与技术大学);Manchester Metropolitan University(曼彻斯特城市大学)
随着先进的数据分析技术,为疾病预测提供更准确的决策支持系统的努力正在增加。世界卫生组织(WHO)的调查表明,糖尿病患者和相关死亡人数每年都在大幅增加。糖尿病的早期诊断是研究人员和从业人员的主要关注点。本文提出了一个应用\textit{Automatic Multilayer Perceptron },\textit{ }结合离群检测方法\textit{Enhanced Class Outlier Detection using distance based algorithm },创建一个预测框架命名为增强类离群自动多层感知器(ECO-AMLP)。一系列的实验进行公开的皮马印度糖尿病数据集比较ECO-AMLP与其他个人分类器以及集成为基础的方法。与其他预处理和分类技术相比,我们框架中使用的离群值技术得到了更好的结果。最后,将结果与文献中报道的其他最先进的方法进行比较,预测PIDD糖尿病的准确性为88.7%,优于所有其他报道的研究。
Diversified Ensemble of Independent Sub-Networks for Robust Self-Supervised Representation Learning
LMU Munich(慕尼黑大学);Munich Center for Machine Learning(慕尼黑机器学习中心);Institute of Statistics, LMU Munich(慕尼黑大学统计研究所);Institute of Informatics, LMU Munich(慕尼黑大学信息学研究所)
Detecting diabetic retinopathy severity through fundus images using an ensemble of classifiers
Technical University of Cluj-Napoca(克卢日-纳波卡技术大学);“Iuliu Hatieganu” University of Medicine and Pharmacy(“尤利乌·哈采加努”医药大学);Emergency County Hospital(急诊县医院)
Explainable Retinal Imaging for Prediction of Multi-Organ Dysfunction in Type 2 Diabetes
Faculty of Computer Science and Artificial Intelligence(计算机科学与人工智能学院);Frontier Science Computing Center(前沿科学计算中心);Chinese Academy of Sciences(中国科学院);Chinese University of Hong Kong(香港中文大学);Zhuhai People's Hospital(珠海人民医院);Beijing Institute of Technology(北京理工大学);Jinan University(暨南大学);Lampang Inter-Tech College
RADE: Resource-Efficient Supervised Anomaly Detection Using Decision Tree-Based Ensemble Methods
VMware Research(威睿研究院);Technion(以色列理工学院)
基于决策树的集成分类方法(DTEM)是一种流行的工具,监督异常检测。然而,由于数据集的持续增长,DTEM导致越来越多的缺点,例如不断增长的内存占用,更长的训练时间,以及在较低吞吐量下较慢的分类延迟。在本文中,我们提出,设计和评估RADE -一个基于DTEM的异常检测框架,它增强了标准DTEM分类器,并通过依赖两个观察来消除这些缺点:(1)我们发现,(粗粒度)DTEM模型足以正确分类大多数分类查询,使得仅当分类的对应置信度水平大于或等于预定分类置信度阈值时分类才有效;(2)我们发现,在这些较难的情况下,我们的粗粒度DTEM模型导致其分类的置信度不足,我们可以通过将分类查询转发到一个专家DTEM(细粒度)模型来改进它,该模型是针对该特定情况进行显式训练的。我们基于scikit-learn在Python中实现了RADE,并在不同的DTEM方法上进行了评估:RF,XGBoost,AdaBoost,GBDT和LightGBM,以及三个公开的数据集。我们对强大的AWS EC2实例和Raspberry Pi 3设备的评估表明,与标准DTEM方法相比,RADE提供了具有竞争力且通常更出色的异常检测功能,同时显着改善了内存占用(高达5.46倍),训练时间(高达17.2倍)和分类延迟(高达31.2倍)。
Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition
organization= The University of New South Wales , city= Sydney , country= Australia;organization= The University of New South Wales \& CSIRO , city= Sydney , country= Australia
Cross Device Matching for Online Advertising with Neural Feature Ensembles : First Place Solution at CIKM Cup 2016
Nanyang Technological University(南洋理工大学)
我们描述了CIKM Cup 2016挑战赛的第一名获胜方法。在本文中,我们提供了一种方法来合理地识别相同的用户在多个设备上的浏览日志的基础上。我们的方法将候选人排序问题视为成对分类,并利用无监督的神经特征集成方法来学习用户的潜在特征。结合传统的手工制作的功能,每个用户对功能被送入一个监督分类器,以执行成对分类。最后,我们提出了监督和无监督推理技术。