关键词： 机器学习   宏观审慎   多层次资本市场  

摘要： 相较于国际社会当前对于"宏观审慎"工具最新发展要求,我国对于宏观审慎监管的实践仍有需要完善的部分。在本项研究中,我们试图完善宏观审慎预警体系并建立多层次资本市场定价行为的评估机制,引入模糊数理论量化场外资本市场报价行为,通过区间支持向量回归模型(F-SVR)建立起一套对于多层次资本市场的报价行为评估体系,进一步丰富宏观审慎监管工具箱。

关键词： 娱乐新闻   朴素贝叶斯   逻辑回归   集成学习   lightGBM   异质集成学习   分类  

摘要： 娱乐新闻是腾讯新闻重要组成部分,根据娱乐文章的文本信息将文章归类是娱乐新闻处理工作中很重要的一部分。人工智能中的机器学习方法在经济生活中有着十分广泛的应用。根据娱乐新闻分类这一问题实例,分别采用了传统的机器学习方法,包括朴素贝叶斯,逻辑回归,基于集成学习的方法lightGBM,对这一分类问题进行探索。最后采用异质集成学习方法对最终结果进行集成。不同的模型在不同的问题中具有不同的效果,本文依据娱乐新闻分类这一具体问题,采用了上述几种算法模型进行预测,综合了不同模型的预测情况得出最后的预测结果。对算法模型进行了原理分析,比较了不同的分类模型解决该问题的效果,横向对比了不同模型的优缺点,并对造成结果差异的原因进行了总结。

关键词： No free lunch theorem   Random forests   River discharge   Stochastic hydrology   Support vector machines   Time series  

摘要： Research within the field of hydrology often focuses on the statistical problem of comparing stochastic to machine learning (ML) forecasting methods. The performed comparisons are based on case studies, while a study providing large-scale results on the subject is missing. Herein, we compare 11 stochastic and 9 ML methods regarding their multi-step ahead forecasting properties by conducting 12 extensive computational experiments based on simulations. Each of these experiments uses 2000 time series generated by linear stationary stochastic processes. We conduct each simulation experiment twice;the first time using time series of 100 values and the second time using time series of 300 values. Additionally, we conduct a real-world experiment using 405 mean annual river discharge time series of 100 values. We quantify the forecasting performance of the methods using 18 metrics. The results indicate that stochastic and ML methods may produce equally useful forecasts.

摘要： Background Existing universal and procedure-specific surgical risk prediction models of death and major complications after elective total joint arthroplasty (TJA) have limitations including poor transparency, poor to modest accuracy, and insufficient validation to establish performance across diverse settings. Thus, the need remains for accurate and validated prediction models for use in pre-operative management, informed consent, shared decision-making, and risk adjustment for reimbursement. Questions/purposes The purpose of this study was to use machine learning methods and large national databases to develop and validate (both internally and externally) parsimonious risk-prediction models for mortality and complications after TJA. Methods Preoperative demographic and clinical variables from all 107,792 nonemergent primary THAs and TKAs in the 2013 to 2014 American College of Surgeons-National Surgical Quality Improvement Program (ACS-NSQIP) were evaluated as predictors of 30-day death and major complications. The NSQIP database was chosen for its high-quality data on important outcomes and rich characterization of preoperative demographic and clinical predictors for demographically and geographically diverse patients. Least absolute shrinkage and selection operator (LASSO) regression, a type of machine learning that optimizes accuracy and parsimony, was used for model development. Tenfold validation was used to produce C-statistics, a measure of how well models discriminate patients who experience an outcome from those who do not. External validation, which evaluates the generalizability of the models to new data sources and patient groups, was accomplished using data from the Veterans Affairs Surgical Quality Improvement Program (VASQIP). Models previously developed from VASQIP data were also externally validated using NSQIP data to examine the generalizability of their performance with a different group of patients outside the VASQIP context. Results The model

关键词： Fine particulate matter   Satellite remote sensing   Aerosol optical depth   Machine learning  

摘要： Ambient exposure to fine particulate matter (PM2.5) is known to harm public health in China. Satellite remote sensing measurements of aerosol optical depth (AOD) were statistically associated with in-situ observations after 2013 to predict PM2.5 concentrations nationwide, while the lack of surface monitoring data before 2013 have created difficulties in historical PM2.5 exposure estimates. Hindcast approaches using statistical models or chemical transport models (CTMs) were developed to overcome this limitation, while those approaches still suffer from incomplete daily coverage due to missing AOD data or limited accuracy due to uncertainties of CTMs. Here we developed a new machine learning (ML) model with high-dimensional expansion (HD-expansion) of numerous predictors (including AOD and other satellite covariates, meteorological variables and CTM simulations). Through comprehensive characterization of the nonlinear effects of, and interactions among different predictors, the HD-expansion parameterized the association between PM2.5 and AOD as a nonlinear function of space and time covariates (e.g., planetary boundary layer height and relative humidity). In this way, the PM2.5-AOD association can vary spatiotemporally. We trained the model with data from 2013 to 2016 and evaluated its performance using annually-iterated cross-validation, which iteratively held out the in-situ observations for a whole calendar year (as testing data) to examine the predictions from a model trained by the rest of the observations. Our estimates were found to be in good agreement with in-situ observations, with correlation coefficients (R-2) of 0.61, 0.68, and 0.75 for daily, monthly and annual averages, respectively. To interpolate the missing predictions due to incomplete AOD data, we incorporated a generalized additive model into the ML model. The two-stage estimates of PM2.5 sacrificed the prediction accuracy on a daily timescale (R-2 = 0.55), but achieved complete spatiotemporal co

关键词： Thermal comfort prediction   Feedback technology   Thermographic camera   HVAC control   Building automation  

摘要： This work introduces a new technique that provides real-time feedback to a Heating, Ventilation, and Air Conditioning (HVAC) system controller with respect to the occupants' thermal preferences to avoid space overheating. We propose a non-invasive approach for automatic prediction of personal thermal comfort and mean time to warm discomfort using machine learning. The prediction framework described uses temperature information extracted from multiple local body parts to model an individual's thermal preference, with sensing measurements that capture local body part variance as well as differences between body parts. We compared the efficacy of using machine learning with classical measurements such as skin temperature along with our approach of using multi-part measurements and derived data. An analysis of the performance of machine learning shows that our method improved the accuracy of personal thermal comfort prediction by an average of 60%, and the accuracy of mean time to warm discomfort prediction by an average of 40%. The proposed thermal models were tested on subjects' data extracted from an office setup with room temperature varying from low (21.11 degrees C) to high (27.78 degrees C). When all proposed features were used, personal thermal comfort was predicted with an accuracy higher than 80% and mean time to warm discomfort with more than 85% accuracy. Further analysis of the machine learning efficacy showed that temperature differences had the highest impact on performance of individual thermal preference prediction, while the proposed approach was found not sensitive to the actual machine learning algorithm.

关键词： Algorithms   Applied mathematics   Artificial intelligence   Biology and life sciences   Body temperature   Computer and information sciences   Dementia   Health care   Health care facilities   Hospitals   Machine learning   Machine learning algorithms   Mathematics   Medicine and health sciences   Mental health and psychiatry   Neurology   Physical sciences   Physiological parameters   Physiological processes   Physiology   Research and analysis methods   Research Article   Simulation and modeling   Sleep   Sleep disorders   Urinary tract infections   Urology  

摘要： Dementia is a neurological and cognitive condition that affects millions of people around the world. At any given time in the United Kingdom, 1 in 4 hospital beds are occupied by a person with dementia, while about 22% of these hospital admissions are due to preventable causes. In this paper we discuss using Internet of Things (IoT) technologies and in-home sensory devices in combination with machine learning techniques to monitor health and well-being of people with dementia. This will allow us to provide more effective and preventative care and reduce preventable hospital admissions. One of the unique aspects of this work is combining environmental data with physiological data collected via low cost in-home sensory devices to extract actionable information regarding the health and well-being of people with dementia in their own home environment. We have worked with clinicians to design our machine learning algorithms where we focused on developing solutions for real-world settings. In our solutions, we avoid generating too many alerts/alarms to prevent increasing the monitoring and support workload. We have designed an algorithm to detect Urinary Tract Infections (UTI) which is one of the top five reasons of hospital admissions for people with dementia (around 9% of hospital admissions for people with dementia in the UK). To develop the UTI detection algorithm, we have used a Non-negative Matrix Factorisation (NMF) technique to extract latent factors from raw observation and use them for clustering and identifying the possible UTI cases. In addition, we have designed an algorithm for detecting changes in activity patterns to identify early symptoms of cognitive decline or health decline in order to provide personalised and preventative care services. For this purpose, we have used an Isolation Forest (iForest) technique to create a holistic view of the daily activity patterns. This paper describes the algorithms and discusses the evaluation of the work using a lar

关键词： Survey   algorithmic trading   statistics   machine learning   high frequency trading   hardware implementation  

摘要： Automated trading, which is also known as algorithmic trading, is a method of using a predesigned computer program to submit a large number of trading orders to an exchange. It is substantially a real-time decision-making system which is under the scope of Enterprise Information System (EIS). With the rapid development of telecommunication and computer technology, the mechanisms underlying automated trading systems have become increasingly diversified. Considerable effort has been exerted by both academia and trading firms towards mining potential factors that may generate significantly higher profits. In this paper, we review studies on trading systems built using various methods and empirically evaluate the methods by grouping them into three types: technical analyses, textual analyses and high-frequency trading. Then, we evaluate the advantages and disadvantages of each method and assess their future prospects.

关键词： Heavy haul train   Intelligent operation   Machine learning   Air brake   Imbalanced data  

摘要： Compared with high speed trains and metro subways, heavy haul train operations are more challenging for their complex dynamic characteristics and complicated running environments. When running on a continuous and steep descent, the air brake operation strategy has become the most important issue for the safety and efficiency of heavy haul train transportation. Due to the difficulty in modeling the train's dynamics and pneumatic brake system precisely, this paper addresses the intelligent driving problem for heavy haul train based on the fusion of expert knowledge and machine learning methodologies. By considering the characteristics of manual driving on steep descent, the pneumatic brake operation problem is formulated as a multi-class classification model. To overcome the negative influences of data imbalances, EasyEnsemble for the multi-class with a KNN based Denoising (EMKD) algorithm is introduced to determine the feasible Air Pressure Reduction (APR) and the exact time for exerting and releasing the air brake. This approach utilizes the EasyEnsemble.M algorithm to moderate the class imbalanced datasets and takes advantage of the AdaBoost.M1 algorithm to ensemble weak classifiers. Specifically, the K-nearest neighbor based Denoising (KD) algorithm is elaborated to remove the possible noise data from the minority dataset. Additionally, expert knowledge is obtained by abstracting the experience of sophisticated drivers and technical specifications, which are employed as operating constraints to regulate the output of the EMKD algorithm. The operational safety in terms of the in-train forces and punctuality of the proposed algorithm are validated by a number of experiments under the real running circumstances of Shuohuang heavy haul railway. (C) 2018 Elsevier B.V. All rights reserved.

关键词： 数据挖掘   网络异常检测   入侵检测技术  

摘要： 随着信息化革命进程的不断深入,社会民众的信息交流方式呈现出明显的变化,网络不安全因素也逐渐增多,因此,做好网络异常信息的检测工作,显得十分重要。本文基于数据挖掘和机器学习方法,在对入侵检测技术的定义和方法进行综合阐述的基础上,论述了数据挖掘方法的定义和方法,以期为相关人士提供借鉴和参考。