关键词： 侧支根管   根尖解剖   下颌第二磨牙   LASSO回归分析   机器学习  

摘要： 目的:侧支根管是发自主根管,贯穿牙本质和牙骨质,联通牙周和牙髓组织的细小分支,常发生在根尖1/3,其结构细小,利于细菌的藏匿和繁殖,也是牙髓和牙周细菌及其代谢产物的通道,是牙周牙髓联合病变和根管治疗失败的重要原因之一。有文献报道根管治疗后1年的失败率为1.7%,2年失败率3.2%,3年及以上失败率3.2%-19%,随着时间的延长,根管治疗的失败率明显增加。造成根管治疗失败的牙位中,下颌磨牙位居第二,占20%。下颌第二磨牙的根管系统尤其复杂,中国人下颌第二磨牙C型根管的发生率大于30%,其复杂的解剖结构增加了根管治疗的难度。因此,本研究的目的是深入认识下颌第二磨牙根尖1/3的解剖特点,研究影响下颌第二磨牙根尖1/3侧支根管（lateral canal,LC）发生的解剖因素,提高根管治疗和根管再治疗的成功率。 材料和方法:于天津医科大学口腔医院口腔颌面外科收集2018年至2020年因牙周病拔除的完整下颌第二磨牙60颗,经根尖片初步排除后剩余39颗,将清理后的离体牙常温置于0.9%生理盐水中,送北京大学口腔医院实验中心行微计算机断层成像（micro-computed tomography,Micro-CT）扫描,利用可视化软件Inveon Research Workplace（SIEMENS,Munich,Germany）中的General Analysis功能进行根尖1/3根管长度和根管弯曲度测量,用Mutimodal 3D Visualization功能进行根尖1/3根管形态重建,观察是否为融合根根管、根尖孔的位置、是否为复杂根管、根管分型、LC的数量和位置分布。 本研究提出2个概念用于统计:（1）观察单位:如果一个根管发生融合或分裂,但与同一牙根内其他根管不发生融合,则将该根管独立作为一个观察单位,即一个根管,每一个观察单位对应各自的解剖数据;（2）融合根单根管:根管在融合根内,该融合根内只有一个观察单位,不区分是否是C型根管。 测量并记录根尖1/3根管解剖形态的数据具体如下:（1）根尖1/3根管长度;（2）是否是融合根根管;（3）根尖孔开口是否在根侧;（4）根尖1/3根管弯曲度（Schneider法）;（5）先确定是简单根管还是复杂根管,如果是复杂根管,还需确定根管分型,分型标准参考修改后的Vertucci根管分型。复杂根管的评判标准:根管1/3横截面到根尖孔之间发生融合或分裂;简单根管的评判标准:根管1/3横截面到根尖孔之间没有发生融合或分裂,始终呈1-1型。（6）确定有无LC、LC的数量和位置分布。侧支根管的纳入标注:从主根管呈水平向或斜向延伸至牙周的细小分支,贯穿牙根的牙本质和根面牙骨质,通向牙周膜;LC的位置分布记录为主根管的颊侧、近中、舌侧和远中。 每一个观察单位测量以上6个数据,将（1）5定为可能影响下颌第二磨牙根尖1/3侧支根管发生的因素,分别设为X1、X2……至X5,将根尖1/3有无侧支根管设为结果Y。 用R软件进行LASSO回归（Least absolute shrinkage and selection operator,LASSO）分析,筛选影响下颌第二磨牙根尖1/3出现侧支根管的变量组合。LASSO回归模型的评价:绘制受试者工作特征曲线（receiver operating characteristic curve,ROC）并计算曲线下面积（area under the cure,AUC）评价模型的区分度,检验能否使用建立的回归模型进行诊断。 结果:收集符合纳排标准的下颌第二磨牙离体牙共39颗,其中20颗为非融合根（双根）,19颗为融合根,共72个根管,通过Micro-CT继续排除因根尖片未发现的钙化根管、有隐裂纹的根管和根内吸收的根管共7个,最终确定符合纳排标准的根管数量共65个。 下颌第二磨牙根尖1/3根管解剖形态的数据结果: （1）是否是融合根根管（X2）:融合根根管有22个,双根牙根管有43个; （2）根尖孔开口是否在根侧（X3）:45个（65,69.2%）根尖孔开口在根侧,20个根尖孔开口（65,30.8%）位于解剖根尖; （3）根尖1/3根管弯曲度（X4）:直根管有10（65,15.3%）个,轻度弯曲根管4（65,6.2%）个,中度弯曲根管32（65,49.2%）个,重度弯曲根管19（65,29.2%）个; （4）是否为复杂根管（X5）和根管分型:65个根管中,简单根管38个（65,58.5%）,复杂根管27个（65,41.5%）。38个简单根管中,双根牙远中根管有16个（38,42.1%）,其次为双根牙近中根管有13个（38,34.2%）。27个复杂根管中,近中根管（非融合根近中根管和融合根近中根管）有14个（28,50%）,远中根管（非融合根远中根管和融合根远中根管）有3个（21,14

关键词： 晶界铁素体   定量分析   扭转   图像处理  

摘要： 钢丝从普通强度逐步发展到高强度,超高强度,甚至特高强度以来,钢丝的塑性在生产过程中得到的挑战越来越大。高强度的钢丝在后续拉拔过程中面临着显著增高的断丝率,在成型过程中的扭转分层等问题。针对当前主流应用的80C钢丝,学者们通过热处理工艺和工程控制实现对80C钢丝的组织调控,进而提高塑性。研究主要集中在细片状珠光体率和晶粒度大小等方面,而对晶界铁素体则较少关注。主要原因是晶界铁素体含量低且目前行业内缺少晶界铁素体定量分析的方法。80C钢丝中晶界铁素体弱化了晶界,在扭转过程中,协同变形能力差,恶化了钢丝的塑性。为了满足钢丝强度提高的需求,结合单丝扭转测试的晶界铁素体的定量分析,对生产高强度的钢丝十分重要。数字图像处理技术和机器学习提取组织特征参数并建立大量数据库,实现了晶界铁素体的定量分析。这为以后智能识别材料性能提供强有力的基础。本论文研究了80C钢丝热处理过程中影响晶界铁素体形成的关键工艺因素。数字图像处理技术和机器学习对晶界铁素体进行定量分析,建立了晶界铁素体与单丝扭转结果的关系。结论如下:80C钢丝中不同含量的晶界铁素体取决于在相同生产速度下炉温的设定以及冷却淬火工艺中组织开始转变的温度。在本论文的工艺条件下,当晶界铁素体长度大于20±0.5um,面积率大于0.02%时,钢丝的扭转分层次数下降幅度超过20%,导致了钢丝在最后一道工序成型过程中分层的发生。

关键词： 数字货币   机器学习   量化投资  

摘要： 近年来，数字货币投资逐渐引起广大投资者的关注，由于其具有低交易成本、高换手率、广阔的交易覆盖面、低交易门槛等特点，大量散户投资者和部分机构投资者进入数字货币市场试图获得超额收益。但是，散户投资者容易受到各种行为偏差的影响，这便会产生各类市场异象，为量化投资策略的研究提供了可能。　　本文通过选取100种资质较好的数字货币从2016年至2020年的价量数据，以构造适用于数字货币市场的量化投资策略为主线，从因子选择、模型选择、策略构建、回测、优化到策略评价等角度展开实证研究。首先，本文针对数字市场独特的交易特征选取了常见的技术面指标组成因子集合，并结合文献综述选取了预测能力较好的8种机器学习预测算法。其次，本文结合因子和预测算法构建了由各机器学习预测算法驱动的量化投资策略。对比分析各策略的投资绩效，本文发现机器学习预测算法在数字货币市场的收益预测能力整体显著高于普通线性回归模型，非线性机器学习算法的收益预测能力优于线性机器学习预测算法。第三，通过模型筛选，本文发现基于SVR模型的量化投资策略在所有模型中预测能力最强，并通过重要因子筛选、参数优化等对策略进行了优化。最后，本文提出了基于SVR模型的适用于数字货币市场的跨币种量化投资策略。　　本文从机器学习的角度分析了数字货币市场的资产定价机制。通过将量化投资方法用于数字货币市场，丰富了数字货币市场上市场异象的研究，并提供了将机器学习算法用于数字货币市场量化投资策略研究的案例，为后续研究提供理论支持的同时为数字货币市场的量化投资提供了可行方案。

关键词： 多因子择时选股   机器学习   超额收益   分层排序  

摘要： 如何提升多因子模型对超额收益的经济解释同时兼顾实际的投资效果一直是资产定价和投资学研究领域的热点和棘手问题之一，于是Fama和French等人提出了三因子模型，此模型在CAPM的基础上考虑其他经济效应的影响，并将这些经济效应提取为因子开展进一步的研究。后来的研究者在其基础上研究不同市场上的因子效应，其中Cakici、Hou和Liu等学者在实证研究中发现不同国家市场上的因子效应存在不同的表现。这些发现说明在针对不同市场同时保留良好的经济金融理论解释力的基础上改进模型构建、提升表现并形成投资策略上仍有诸多工作可以开展。为此本文结合机器学习中的方法改进了多因子模型的构建，提出了基于模型构建改进方案的投资策略。　　在对多因子模型的构建进行改进上，本文基于2014年至2020年9月沪深300市场上的数据，应用K-NN最邻近点算法改进了分层排序提取因子的方法，将同一效应的经济指标结合得到改进三因子模型，并将之同Fama-French三因子模型，Liu的中国三因子和四因子模型进行了对比发现改进因子提取方法后的多因子模型优于前者。然后本文在之前的工作上基于机器学习方法构建多因子模型并给出选股择时策略，利用主成分分析法确定了因子效应及经济指标的维数，计算对应的因子超额收益，结合K-NN最临近点算法进行分层排序提取因子从而构建了基于以上两种机器学习方法的多因子模型，并给出因子择时选股的权重矩阵的量化投资策略，实证说明改进后的模型对个股超额收益的解释能力更强，策略表现更优秀且保留了良好的经济金融理论解释力。　　本文研究工作的创新之处主要有三处。首先是通过K-NN最邻近点算法改进因子提取方案，在不破坏模型的经济金融理论解释力的基础上提高了多因子模型对超额收益的解释能力;其次是将主成分分析同K-NN最邻近点算法相结合构建多因子模型从而在确定因子数的同时保留了经济金融理论解释力，极大提升了模型对异象效应的解释效果;最后是基于两种机器学习方法构建因子择时选股权重矩阵的投资策略，实证表明该策略具有很好的收益风险指标表现。

关键词： 脑卒中   脑电信号   MF-DFA   分层熵   集成极限学习机  

摘要： 脑卒中又称“中风”,是一种常见的脑血管疾病,在我国居民中的发病率呈现逐年上升趋势。其发病快、病程急,在临床上具有高发病率、高致死率及高致残率等特点。脑卒中主要分为出血性及缺血性两种,二者发病机制不同。脑电信号（electroencephalogram,EEG）是脑神经细胞电生理活动的反映,包含人体大量生理信息,脑卒中发病前后EEG数据会呈现显著差异性,不同类型脑卒中其EEG数据也表现出不同特性,因此,基于EEG数据进行脑卒中发病预测是实现脑卒中高效诊断的有效措施。目前临床上依据EEG数据进行脑卒中发病风险预测的诊断主要采取人工判读的方法,极易受临床医生主观判断及已有经验的影响。近年来,随着人工智能技术在智能医学的发展,采用现代信号处理手段对EEG数据进行脑卒中发病预测成为近年研究热点,有助于加快实现脑卒中智慧医疗辅助诊断。已有研究发现,EEG数据是一种具有非线性动力学特征的非平稳时间序列,所以利用非线性动力学方法对EEG数据提取合适的特征,选取有效的分类模型,能够帮助医生迅速诊断患者的脑卒中类型,并及时采取有效治疗措施。为此,本文引入了基于多重分形去趋势波动分析（Multifractal Detrended Fluctuation Analysis,MF-DFA）和熵特征的脑卒中EEG数据特征提取方法,并对比分析了单分类器和集成分类器对提取的EEG特征进行脑卒中发病预测的性能差异,以得到较优的脑卒中分类预测结果。本文主要工作如下:第一:基于多重分形去趋势波动分析MF-DFA的脑卒中EEG数据特征提取研究。首先对脑卒中EEG数据分别求解其广义Hurst指数谱、标度指数谱以及多重分形谱。证明了脑卒中EEG数据具有多重分形特性,并从中提取了四个分形特征:广义Hurst指数谱特征hqmax、多重分形谱特征αmax与α0、标度指数谱特征τqmin。对366例脑卒中患者EEG数据分别提取四个分形特征,采用C4.5单决策树作为预测模型进行脑卒中发病风险分类预测研究,实验结果表明,四个分形特征中,广义Hurst指数hqmax可获得最优的脑卒中分类预测性能。进一步对366例患者8个导联中每个导联提取四个分形特征,依然采用C4.5单决策树进行脑卒中分类预测,实验结果表明,脑卒中患者8个导联中,对C4导联进行特征提取,脑卒中分类预测性能最优。第二:基于EEG数据多特征融合的脑卒中发病风险分类预测研究。首先引入了四种单一熵特征值对两类脑卒中EEG数据进行特征提取,然后引入小波包分层理论,将小波包分解与单一熵特征相结合来提取两类脑卒中EEG数据的四种分层熵特征值。之后将得到的单一熵特征值和分层熵特征值分别与脑卒中多重分形特征值进行融合,建立C4.5单决策树分类预测模型,进行脑卒中发病风险分类预测。实验结果表明,脑卒中EEG数据广义Hurst指数最大值、C4导联四个分形特征和分层模糊熵进行融合时脑卒中发病风险分类预测性能最优。第三:集成极限学习机在脑卒中发病风险分类预测中的应用研究。为了获得更好的脑卒中发病风险分类预测性能,引入了极限学习机预测模型和Adaboost集成分类模型,设计了基于Adaboost的集成决策树分类预测模型和集成极限学习机分类预测模型。将EEG数据单一特征和融合特征作为输入,对比分析了C4.5单决策树、极限学习机以及集成C4.5决策树分类预测模型和集成极限学习机分类预测模型性能差异。实验结果表明:基于脑卒中EEG数据单一特征和融合特征,集成极限学习机得到的脑卒中发病风险分类预测性能最优。

关键词： Reinforcement learning   Fractional ownership of autonomous vehicles   Iterative auction   Last mile delivery  

摘要： This dissertation investigates three applications of emerging technologies for urban transportation. In the first chapter, we design a new market for fractional ownership of autonomous vehicles (AVs), in which an AV is co-leased by a group of individuals. We present a practical iterative auction based on the combinatorial clock auction to match the interested customers together and determine their payments. In designing such an auction, we consider continuous-time items (time slots) which are defined by bidders, and naturally exploit driverless mobility of AVs to form co-leasing groups. To relieve the computational burdens of both bidders and the auctioneer, we devise user agents who generate packages and bid on behalf of bidders. Through numerical experiments using the California 2010–2012 travel survey, we test the performance of the auction design. In the second chapter, we propose a reinforcement learning approach for nightly offline rebalancing operations in free-floating electric vehicle sharing systems (FFEVSS). Due to sparse demand in a network, FFEVSS requires relocation of electrical vehicles (EVs) to charging stations and demander nodes, which is typically done by a group of drivers. A shuttle is used to pick up and drop off drivers throughout the network. The objective of this study is to solve the shuttle routing problem to finish the rebalancing work in minimal time. We consider a reinforcement learning framework for the problem, in which a central controller determines the routing policies of a fleet of multiple shuttles. We deploy a policy gradient method for training recurrent neural networks and compare the obtained policy results with heuristic solutions. In the final problem, the application of the tandem of drone and truck for last mile delivery is proposed. To take advantage of the different properties of drone and truck to deliver goods to customers, an efficient routing algorithm is introduced based on reinforcement learning. The proposed met

摘要： Recent advances in machine learning (ML) hold much promise for using data to drive more effective decisions. However, many challenges remain to our realizing this decision-making potential, given the limitations of predictive algorithms and imperfections in the data available. This thesis investigates these critical challenges in the areas of data-driven optimization, causal inference, and algorithmic fairness, and develops fundamental theory and new ML methods. In Part I, we focus on data-driven optimization that involves both uncertain quantities of interest (e.g., demand) and predictive contextual features (e.g., product characteristics). Chapters 2 and 3 focus on stochastic optimization problems and investigate two popular paradigms: an "estimate-then-optimize" paradigm that first uses standard ML methods to predict the distribution of uncertain quantities given contextual features and then plugs the distributional predictions into a stochastic optimization problem to solve for decisions, and an "end-to-end" paradigm that integrates the prediction and the decision-making aspects by directly training predictive models to target good decisions. In Chapter 2, we develop an "end-to-end" stochastic optimization forest algorithm that constructs decision trees to directly optimize decision quality, which we show provides significant benefits for decision making over building trees that target prediction. In Chapter 3, we show a more nuanced landscape for the integration of estimation and optimization, by identifying many common settings where "end-to-end" approaches can actually have much slower regret-convergence rates than the far simpler "estimate-then-optimize" approach. Chapter 4 considers the online setting where we collect more data as we make decisions and studies nonparametric contextual bandits with smooth expected reward functions. We develop a novel algorithm that leverages this smoothness structure and show that its regret rate is minimax optimal. Our regr

关键词： 卵巢癌   计算机辅助诊断   机器学习   卷积神经网络   核磁共振成像  

摘要： 卵巢癌(Ovarian Cancer)是女性生殖系统常见恶性肿瘤,其致死率居妇科恶性肿瘤首位。其中,上皮性卵巢癌(Epithelial Ovarian Cancer,EOC)为主要类型(占比>90%)。术前准确评估EOC状态,可帮助患者实施个性化精准治疗,提高其生存率。相比于超声和CT等常用成像技术,核磁共振成像(Magnetic Resonance Imaging,MRI)在EOC分期及复发转移评估等方面具有明显优势,是EOC首选的影像学术前诊断方法。然而,EOC影像表现异常复杂,基于肉眼的临床诊断主观性高,极易误诊。机器学习方法可借助大量样本挖掘图像中的深层次特征,构建模型提高诊断的准确率,有效减少误诊和漏诊。本文利用机器学习方法,针对EOC分割、诊断中的一系列问题开展大规模多中心研究,主要工作如下:(1)针对EOC病灶人工标注工作量大、难度高的问题,提出一种用于EOC自动分割的多边输出全卷积神经网络。该网络使用多个边输出模块对提取到的不同层级特征进行解码,以生成包含不同尺度信息的边输出分割结果,最终将其融合并生成更为精细的最终分割结果。所提模型能够减少临床医生的工作量,提高病灶勾画的准确性和稳定性。(2)针对Ⅰ型和Ⅱ型EOC临床鉴别困难的问题,提出一种基于多模态MRI的影像组学-机器学习模型。从患者的多模态MRI(T2WIFS,DWI,ADC和CE-T1WI)数据中提取形状特征、小波特征等八类特征,并分别使用支持向量机、决策树和线性模型构建多模态的混合模型。此外,我们还使用遮挡测试对模型的重点关注区域进行识别,该方法有望用于辅助术中冰冻病理切片采样的定位。(3)提出一种用于EOC和BEOT鉴别的新型多示例卷积神经网络。所提模型能够借鉴临床医生的决策方式,自动感知不同模态对决策的重要程度,并基于其重要性实现多模态MRI特征融合。此外,该模型还将肿瘤分布的强先验知识作为决策的重要参考,在对示例进行预测时参考其邻近示例的预测值,从而实现更加精准的预测。

关键词： Biophysics   Bioengineering   Nanotechnology   Artificial intelligence  

摘要： Precision medicine promises the ability to intelligently tailor clinical interventions to individual patient needs. Personalizing clinical management will necessitate access to high quality, accurate, and functional information about disease state. However, traditional noninvasive diagnostics such as imaging rely on static measurements of tissue morphology, while molecular features of disease can often only be discerned through invasive methods like biopsy. To acquire functional, personalized information about a disease, a promising approach would be to engineer sensing probes that can directly query disease activity to generate amplified signals that can be analyzed externally. To this end, we have engineered responsive nanosensors that probe tissue microenvironments and detect dysregulated protease activity as a functional biomarker of disease. Because proteases directly contribute to multiple disease processes, including cancer, these sensing probes have the potential to enable quantitative, dynamic, and personalized monitoring of disease activity. In this thesis, we designed new classes of these protease activity sensors and machine learning methods to accurately detect cancer and to functionally profile its biology, aiming to promote the utility of these tools for precision medicine. We first established diagnostic platforms that leverage responsive nanoparticles to measure protease activity in vivo and release reporters that can be detected in the urine. We exploited this basic framework to invent a simple, fast color change urinary readout, and further demonstrated its translational potential by integrating nanosensor multiplexing and machine learning to accurately detect localized lung cancer in two genetically engineered mouse models of lung adenocarcinoma. We then sought to establish generalizable pipelines to rationally design such tools and to functionally dissect the biology of protease dysregulation in cancer. We designed an integrated suite of ex vivo

摘要： Snowfall forecasting has historically been an area of difficulty for operational meteorologists, particularly in the remote complex terrain of the Western US. Attempts at improving forecasts have been made, but skill is still poor, with snowfall routinely overpredicted. A major reason for this overprediction has been a failure to accurately predict snow-liquid ratios (SLR) ahead of major events. This research proposes, develops, and tests multiple machine learning methods for dynamic SLR prediction for the Sky Islands of southeast Arizona in the form of a simple feed-forward neural network, a support vector machine, and a k-nearest neighbor algorithm. Input parameters were chosen based on variables found by previous studies to have a regression-based relationship with SLR, with a focus on the lower-mid levels of the troposphere. These parameters were also used to construct a multiple linear regression model, and its performance was compared with the machine learning methods. Each of the machine learning methods showed significant improvement compared to the multiple linear regression. When tested on historical events, nearly 95% of the network-predicted SLR values fell within the margin of error of observed SLRs, calculated using verification data from Zeng et al (2018), with slightly higher accuracies for both the SVM and KNN algorithms. Each showed significant gain in skill compared to the multiple linear regression model. Current and future work is focusing on shifting to higher resolution data, as well as adjusting the model to look at a wider region within the mountainous Western US in order to achieve greater operational benefit.