基于可解释机器学习的重症监护室脓毒症患者死亡风险预测

为了有效预测重症监护室脓毒症患者的死亡风险并分析影响结局的因素,建立了脓毒症患者死亡风险预测模型,为脓毒症患者的早期预防和死亡风险控制提供科学的参考依据。本研究以重症监护医学信息市场数据库作为数据来源,从中挑选符合要求的病患,使用贝叶斯网络模型训练相关特征预测脓毒症患者的死亡风险。纳入2 352例脓毒症患者,以患者是否死亡作为最终结局建立模型,模型的风险预测准确率为78.7%,优于逻辑回归模型(72.3%)和决策树模型(71.0%)。贝叶斯网络模型相较于其他模型具有更高的信服力,能够准确预测脓毒症患者的死亡风险,模型的可解释性能够辅助医护人员进行临床决策,同时能够更加合理、科学地分配医疗资源。     

基于机器学习的软件缺陷倾向性预测研究

为了能尽早发现软件中存在的缺陷,使用传统的机器学习方法来预测软件模块的缺陷倾向性,选取了NASA公开数据集中的部分数据集,针对软件缺陷预测中类不平衡的问题,分别采取了随机欠采样和随机过采样的方案,再使用逻辑回归算法和随机森林算法分别对数据集进行训练和预测,使用了查准率(Precision)、查全率(Recall)、RO...     

基于机器学习的风险预测方法研究

预测是用科学的方法和手段时事物的发展趋势和未来状态进行估量的技术.为了弥补传统方法和技术的不足,各种机器学习技术越来越多地应用于预测的研究中.讨论了在风险预测这一特定领域,应用基于案例的推理(CBR,Case based Reasoning)、支持向量机(SVM,Support Vectot Machine)以及人工神经网络(ANN,Artificial Neural Network)等机器学习方法来进行预测的技术.同时,以我们的工作为基础,详细论述了在信贷风险预测和工程评标中基于机器学习预测模型的应用.     

基于机器学习的硬盘故障预测研究

硬盘故障所致的数据丢失和损坏给企业和用户带来重大损失,硬盘故障预测也因此引起了学术界和企业界的高度重视,涌现了不少基于机器学习的故障预测方法,但由于存在机器学习算法模型的样本数据差异、性能指标不一致等原因,无法合理评估预测方法的优劣。鉴于此,建立了基于机器学习的硬盘故障检测评估平台,在统一的实验平台中对随机森林、逻辑回归、多层感知神经网络、决策树、朴素贝叶斯、极端梯度提升树、梯度提升决策树和AdaBoost算法模型进行故障预测性能比较,主要针对相同样本集和同一性能度量进行预测对比研究,还对同一预测模型在不同大小样本集上的预测效果进行了对比。实验结果表明：随机森林模型和梯度提升决策树模型不仅预测精度很高而且对不同规模的样本集具有很强的泛化性。     

基于因果贝叶斯网络的急性肾损伤患者死亡风险预测

为了及早发现重症监护室中的急性肾损伤高危患者,为其提供适当的护理,实现医疗资源的合理利用,研究建立因果贝叶斯网络模型进行急性肾损伤高危患者死亡风险预测。从重症监护医学信息市场(Medical Information Mart for Intensive CareⅢ, MIMIC-Ⅲ)数据库中筛选了25个研究变量和3 870条患者数据,使用因果发现算法进行特征降维。通过NO TEARS算法构建因果图并建立因果贝叶斯网络进行实验,通过机器学习算法验证重要特征的合理性,并对网络结构进行因果效应估计,模型具有最高的受试者工作特征曲线下面积(Area Under the Receiver Operating Characteristic, AUROC)分数,为81.7%,优于逻辑回归(Logistic Regression, LR)、随机森林(Random Forest, RF)和极端梯度提升树(eXtreme Gradient Boosting, XGBoost)。此外,模型的重要特征预测能力在各种建模中都很稳健,构建的因果贝叶斯网络具有更好的预测效果并具备良好的解释能力。     

基于一元线性回归的中国煤炭行业年死亡人数与年煤炭产量的预测研究

为了预测我国煤炭行业未来安全形势的发展状况,建立了我国煤炭行业年死亡人数与年煤炭产量的一元线性回归预测模型,采用该模型对我国未来3年煤炭行业年死亡人数与年煤炭产量的发展趋势进行了预测。预测结果表明,该模型具有一定的可行性,为预测我国煤炭行业的安全形势提供了可靠的理论依据。     

在线广告点击率预测方法的研究综述

在在线广告和推荐系统中,准确预测点击率(Click-Through Rate, CTR)是至关重要的。CTR是广告被点击次数与广告被展示次数的比值。过去,许多传统的机器学习算法,如逻辑回归、支持向量机,因为简单且易于实现而被广泛地应用于广告点击率预测工作。然而,这些传统算法往往需要复杂的特征工程。相较之下,深度学习模型能够有效自动提取高阶特征,可以较好地解决这一问题。此外,为了实现更高效、更准确的性能,融合了嵌入式和钦层感知器(Multilayer Perceptron, MLP)的优点的混合架构近年来被广泛地应用。该文对预测点击率的方法进行了全面的研究,不仅根据现有解决方案的架构将其分为三类,而且对每一类进行了详细的概述。最后,该文指出了该领域存在的挑战和未来发展方向,为进一步研究指明可能的途径。     

工业物联网中基于机器学习方法的预测技术

随着传感器网络等技术在工业领域的不断拓展,工业物联网技术得到了长足发展。工业物联网及基于工业物联网的数据分析与预测是工业智能系统的基础。文中关注在工业互联网环境下,工业智能系统在训练阶段利用有监督的机器学习方法,将工艺参数以及环境参数作为输入,将生产过程关注的关键性能指标作为输出,从而对生产线复杂系统进行建模;在生产阶段利用训练阶段的系统模型及当前输入对关键性能指标进行预测。分别利用多元线性回归和非线性BP神经网络方法建模,并利用当前输入对输出结果进行预测,从而对关键性能指标进行预警及预处理操作。同时还利用真实的工业物联网数据进行了仿真和验证,证明了基于BP神经网络的预测方法性能优于线性预测技术。     

基于软件信息库挖掘的软件缺陷预测方法

通过软件缺陷预测可以指导软件开发过程中资源的分配,提高软件质量和软件可靠性。为了更好地利用软件开发过程中产生的数据,指导软件的开发,在介绍了软件缺陷管理,数据挖掘,软件开发信息库知识的基础上,将数据挖掘的知识应用到软件开发信息库中,从版本信息库和缺陷跟踪系统中提取相关数据,经过预处理后这些数据就成数据挖掘技术的研究对象,通过选取合适的软件度量元,利用这些度量元建立新的软件缺陷预测模型并验证了该模型的有效性。     

基于Relief特征选择的心衰死亡率预测

提出心衰死亡率预测系统,预测心衰病人本次住院后30天内死亡率。基于上海曙光医院提供的心衰病人信息,首先对原始数据和特征进行预处理。由于特征的冗余性,再选用经典的Relief特征选择算法筛选出重要的心衰特征,最后选用bp-SVM算法来实现死亡率预测。实验结果证明,死亡率预测系统可以达到较高的性能并通过提供决策信息,辅助医生治疗病人。医生可以根据系统预测的病人死亡率的高低,采取不同的治疗方式,提高临床诊断结果和医院的资源分配。     

Using meta-learning to predict performance metrics in machine learning problems

Machine learning has been facing significant challenges over the last years, much of which stem from the new characteristics of machine learning problems, such as learning from streaming data or incorporating human feedback into existing datasets and models. In these dynamic scenarios, data change over time and models must adapt. However, new data do not necessarily mean new patterns. The main goal of this paper is to devise a method to predict a model's performance metrics before it is trained, in order to decide whether it is worth it to train it or not. That is, will the model hold significantly better results than the current one? To address this issue, we propose the use of meta-learning. Specifically, we evaluate two different meta-models, one built for a specific machine learning problem, and another built based on many different problems, meant to be a generic meta-model, applicable to virtually any problem. In this paper, we focus only on the prediction of the root mean square error (RMSE). Results show that it is possible to accurately predict the RMSE of future models, event in streaming scenarios. Moreover, results also show that it is possible to reduce the need for re-training models between 60% and 98%, depending on the problem and on the threshold used.     

A framework combines supervised learning and dense subgraphs discovery to predict protein complexes

Rapidly identifying protein complexes is significant to elucidate the mechanisms of macromolecular interactions and to further investigate the overlapping clinical manifestations of diseases.To date,existing computational methods majorly focus on developing unsupervised graph clustering algorithms,sometimes in combination with prior biological insights,to detect protein complexes from protein-protein interaction(PPI)networks.However,the outputs of these methods are potentially structural or functional modules within PPI networks.These modules do not necessarily correspond to the actual protein complexes that are formed via spatiotemporal aggregation of subunits.In this study,we propose a computational framework that combines supervised learning and dense subgraphs discovery to predict protein complexes.The proposed framework consists of two steps.The first step reconstructs genome-scale protein co-complex networks via training a supervised learning model of l2-regularized logistic regression on experimentally derived co-complexed protein pairs;and the second step infers hierarchical and balanced clusters as complexes from the co-complex networks via effective but computationally intensive k-clique graph clustering method or efficient maximum modularity clustering(MMC)algorithm.Empirical studies of cross validation and independent test show that both steps achieve encouraging performance.The proposed framework is fundamentally novel and excels over existing methods in that the complexes inferred from protein co-complex networks are more biologically relevant than those inferred from PPI networks,providing a new avenue for identifying novel protein complexes.     

几种机器学习方法在人脸识别中的性能比较

BP神经网络、RBF神经网络、支持向量机（SVM）和集成学习是目前应用最为广泛的四种机器学习方法。将这四种常用的机器学习方法分别应用于人脸识别,并利用ORL人脸图像库对各学习方法性能进行了测试和评估。测试结果表明SVM和集成学习在实验中取得了较好的性能,最适合用于人脸识别中特征分类器。     

Audibility and identification of auditory alarms in the operating room and intensive care unit

Abstract

The audibility and the identification of 23 auditory alarms in the intensive care unit (ICU) and 26 auditory alarms in the operating rooms (ORs) of a 214-bed Canadian teaching hospital were investigated. Digital tape recordings of the alarms were made and analysed using masked-threshold software developed at the Université de Montréal. The digital recordings were also presented to the hospital personnel responsible for monitoring these alarms on an individual basis in order to determine how many of the alarms they would be able to identify when they heard them. Several of the alarms in both areas of the hospital could mask other alarms in the same area, and many of the alarms in the operating rooms could be masked by the sound of a surgical saw or a surgical drill. The staff in the OR (anaesthetists, anaesthesia residents, and OR technologists) were able to identify a mean of between 10 and 15 of the 26 alarms found in their operating theatres. The ICU nurses were able to identify a mean of between 9 and 14 of the 23 alarms found in their ICU. Alarm importance was positively correlated with the frequency of alarm identification in the case of the OR, rho=0·411, but was not significantly correlated in the case of the ICU, rho=0·155. This study demonstrates the poor design of auditory warning signals in hospitals and the need for standardization of alarms on medical equipment.     

Identifying mortality risk factors amongst acute coronary syndrome patients admitted to Arabian Gulf hospitals using machine‐learning methods

Acute coronary syndrome (ACS) is a leading cause of mortality and morbidity in the Arabian Gulf. In this study, the in‐hospital mortality amongst patients admitted with ACS to Arabian Gulf hospitals is predicted using a comprehensive modelling framework that combines powerful machine‐learning methods such as support‐vector machine (SVM), Naïve Bayes (NB), artificial neural networks (NN), and decision trees (DT). The performance of the machine‐learning methods is compared with that of the performance of a commonly used statistical method, namely, logistic regression (LR). The study follows the current practise of computing mortality risk using risk scores such as the Global Registry of Acute Coronary Events (GRACE) score, which has not been validated for Arabian Gulf patients. Cardiac registry data of 7,000 patients from 65 hospitals located in Arabian Gulf countries are used for the study. This study is unique as it uses a contemporary data analytics framework. A k‐fold (k = 10) cross‐validation is utilized to generate training and validation samples from the GRACE dataset. The machine‐learning‐based predictive models often incur prejudgments for imbalanced training data patterns. To mitigate the data imbalance due to scarce observations for in‐hospital mortalities, we have utilized specialized methods such as random undersampling (RUS) and synthetic minority over sampling technique (SMOTE). A detailed simulation experimentation is carried out to build models with each of the five predictive methods (LR, NN, NB, SVM, and DT) for the each of the three datasets k‐fold subsamples generated. The predictive models are developed under three schemes of the k‐fold samples that include no data imbalance, RUS, and SMOTE. We have implemented an information fusion method rooted in computing weighted impact scores obtain for an individual medical history attributes from each of the predictive models simulated for a collective recommendation based on an impact score specific to a predictor. Finally, we grouped the predictors using fuzzy c‐mean clustering method into three categories, high‐, medium‐, and low‐risk factors for in‐hospital mortality due to ACS. Our study revealed that patients with medical history related to the presences of peripheral artery disease, congestive heart failure, cardiovascular transient ischemic attack valvular disease, and coronary artery bypass grafting amongst others have the most risk for in‐hospital mortality.     

基于IPSO混沌支持向量机的网络流量预测研究

针对传统混沌支持向量机参数寻优算法的不足,提出了一种改进的粒子群(IPSO)算法。该算法通过延长迭代的开始阶段和最后阶段的搜索时间,实现了算法的全局搜索与局部搜索能力之间的平衡,进而优化模型参数,建立了基于IPSO优化的混沌支持向量机预测模型。应用实例结果表明,该模型对网络流量预测是有效可行的,并具有较高的寻优效率、预测精度和较好的稳态性能。     

车间调度中的数据挖掘技术研究

基于Multi-Agent System（MAS）的人机合作技术适合于解决复杂调度问题。为了使人与机能够更好地合作来完成高效、准确的车间调度,引入C4.5算法,建立并实现了基于机器学习和MAS的人机合作车间调度系统仿真模型。在Java环境下,以Weka、JADE为开发平台,以Eclipse为开发工具,Access为后台数据库,完成了系统的开发。通过实例仿真和结果分析,运用机器学习算法动态调度的结果稍优于最佳的静态调度结果,证明了系统的正确性和优越性。     

深度学习视阈下MOOC学习者流失预测及干预研究

MOOC（Massive Open Online Courses）在为学习者提供优质课程的同时,低完成率成为影响其有效推广的重要因素。通过对edX开放数据集分析发现,学习者的逐渐流失是导致MOOC课程低完成率的因素之一,且学习行为与成绩之间存在复杂的相关性;基于线性回归和深度神经网络（Deep Neural Network,DNN）预测学习者的成绩,实验证明,DNN能够更好地拟合学习行为与成绩之间复杂的相关性,实现对成绩更加精准的预测,预警学习者流失;对预测的潜在流失学习者迭代进行个性化的教学干预,提高MOOC课程的完成率。     

HIFU治疗区域检测方法研究

提出了一种基于自适应掩模滤波和水平集方法相结合的B超图像分割方法,能较准确地从高强度聚焦超声（HIFU）辐照前后获得的B超图像的减影中检测出治疗区域。对HIFU辐照后的新鲜离体猪肉进行解剖切片,实际损伤情形基本与该方法所得结果相吻合。该方法可以帮助HIFU临床医生客观、准确地监控治疗过程,对提高HIFU疗效有实际意义。