Evaluation of Survival Outcomes of Endovascular Versus Open Aortic Repair for Abdominal Aortic Aneurysms with a Big Data Approach

Abdominal aortic aneurysm (AAA) is a localized enlargement of the abdominal aorta. Once ruptured AAA (rAAA) happens, repairing procedures need to be applied immediately, for which there are two main options: open aortic repair (OAR) and endovascular aortic repair (EVAR). It is of great clinical significance to objectively compare the survival outcomes of OAR versus EVAR using randomized clinical trials; however, this has serious feasibility issues. In this study, with the Medicare data, we conduct an emulation analysis and explicitly “assemble” a clinical trial with rigorously defined inclusion/exclusion criteria. A total of 7826 patients are “recruited”, with 3866 and 3960 in the OAR and EVAR arms, respectively. Mimicking but significantly advancing from the regression-based literature, we adopt a deep learning-based analysis strategy, which consists of a propensity score step, a weighted survival analysis step, and a bootstrap step. The key finding is that for both short- and long-term mortality, EVAR has survival advantages. This study delivers a new big data strategy for addressing critical clinical problems and provides valuable insights into treating rAAA using OAR and EVAR.     

Data-Driven Corrections of Partial Lotka–Volterra Models

In many applications of interacting systems, we are only interested in the dynamic behavior of a subset of all possible active species. For example, this is true in combustion models (many transient chemical species are not of interest in a given reaction) and in epidemiological models (only certain subpopulations are consequential). Thus, it is common to use greatly reduced or partial models in which only the interactions among the species of interest are known. In this work, we explore the use of an embedded, sparse, and data-driven discrepancy operator to augment these partial interaction models. Preliminary results show that the model error caused by severe reductions—e.g., elimination of hundreds of terms—can be captured with sparse operators, built with only a small fraction of that number. The operator is embedded within the differential equations of the model, which allows the action of the operator to be interpretable. Moreover, it is constrained by available physical information and calibrated over many scenarios. These qualities of the discrepancy model—interpretability, physical consistency, and robustness to different scenarios—are intended to support reliable predictions under extrapolative conditions.     

Training Multilayer Perceptron with Genetic Algorithms and Particle Swarm Optimization for Modeling Stock Price Index Prediction

Predicting stock market (SM) trends is an issue of great interest among researchers, investors and traders since the successful prediction of SMs’ direction may promise various benefits. Because of the fairly nonlinear nature of the historical data, accurate estimation of the SM direction is a rather challenging issue. The aim of this study is to present a novel machine learning (ML) model to forecast the movement of the Borsa Istanbul (BIST) 100 index. Modeling was performed by multilayer perceptron–genetic algorithms (MLP–GA) and multilayer perceptron–particle swarm optimization (MLP–PSO) in two scenarios considering Tanh (x) and the default Gaussian function as the output function. The historical financial time series data utilized in this research is from 1996 to 2020, consisting of nine technical indicators. Results are assessed using Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and correlation coefficient values to compare the accuracy and performance of the developed models. Based on the results, the involvement of the Tanh (x) as the output function, improved the accuracy of models compared with the default Gaussian function, significantly. MLP–PSO with population size 125, followed by MLP–GA with population size 50, provided higher accuracy for testing, reporting RMSE of 0.732583 and 0.733063, MAPE of 28.16%, 29.09% and correlation coefficient of 0.694 and 0.695, respectively. According to the results, using the hybrid ML method could successfully improve the prediction accuracy.     

A Bayesian-neural-network prediction for fragment production in proton induced spallation reaction

Fragment production in spallation reactions yields key infrastructure data for various applications. Based on the empirical SPACS parameterizations, a Bayesian-neural-network (BNN) approach is established to predict the fragment cross sections in proton-induced spallation reactions. A systematic investigation has been performed for the measured proton-induced spallation reactions of systems ranging from intermediate to heavy nuclei systems and incident energies ranging from 168 MeV/u to 1500 MeV/u. By learning the residuals between the experimental measurements and SPACS predictions, it is found that the BNN-predicted results are in good agreement with the measured results. The established method is suggested to benefit the related research on nuclear astrophysics, nuclear radioactive beam sources, accelerator driven systems, proton therapy, etc.     

可见光光谱和机器学习的温室黄瓜霜霉病严重度定量估算

温室黄瓜霜霉病严重度的准确估算是科学防治霜霉病的前提条件,对于减少农药使用量、提升温室黄瓜品质和农民经济效益具有重要意义。机器学习在植物病害诊断领域的应用越来越广泛,已经取得了丰富的研究成果,病害严重程度的估算萌发了新的思路。利用霜霉病可见光图像并结合机器学习方法,开展温室黄瓜霜霉病严重度快速准确定量估算研究。利用数码相机采集温室黄瓜霜霉病叶片图像并进行预处理,剔除病害图像的背景。以黄瓜霜霉病叶片图像为输入,构建基于卷积神经网络(CNN)的估算模型。利用可见光光谱颜色特征(CVCF)结合支持向量机进行温室黄瓜霜霉病病斑图像分割,采用SURF(speeded up robust features)特征及形态学操作对分割结果进行优化。在获取黄瓜霜霉病病斑分割图像后,提取病斑图像RGB, HSV, L~*a~*b~*, YCbCr和HSI共5个颜色空间15个颜色分量的平均值和标准差2个颜色特征,以及在此基础上结合灰度共生矩阵提取各颜色分量的对比度、相关性、熵和平稳度4个纹理特征,共计90个特征;利用Pearson相关性分析进行特征优选,采用与温室黄瓜霜霉病严重程度实际值相关性高的图像特征构建浅层机器学习估算模型,包括支持基于向量机回归(SVR)的估算模型和基于BP神经网络(BPNN)的估算模型。基于以上3种估算模型开展黄瓜霜霉病严重度定量估算,采用决定系数(R^2)和归一化均方根误差(NRMSE)对估算模型准确率进行定量评价。结果表明,模型估算的温室黄瓜霜霉病严重度与实际值之间具有良好的线性关系,其中,基于CNN的估算模型准确率最高,模型的R^2为0.919 0, NRMSE为23.33%,其次是基于BPNN的估算模型,其R^2为0.890 8, NRMSE为24.64%,基于SVR的估算模型的准确率最低,其R^2为0.8901, NRMSE为31.08%。研究结果表明,利用黄瓜霜霉病可见光图像数据,结合卷积神经网络估算模型,实现了温室黄瓜霜霉病严重度的准确估算,能够为温室黄瓜霜霉病的科学防治提供参考,提高病害防治效率,减少农药使用。     

基于字典学习的稠密光场重建算法

相机阵列是获取空间中目标光场信息的重要手段,采用大规模密集相机阵列获取高角度分辨率光场的方法增加了采样难度和设备成本,同时产生的大量数据的同步和传输需求也限制了光场采样规模.为了实现稀疏光场采样的稠密重建,本文基于稀疏光场数据,分析同一场景多视角图像的空间、角度信息的关联性和冗余性,建立有效的光场字典学习和稀疏编码数学模型,并根据稀疏编码元素间的约束关系,建立虚拟角度图像稀疏编码恢复模型,提出变换域稀疏编码恢复方法,并结合多场景稠密重建实验,验证提出方法的有效性.实验结果表明,本文方法能够对场景中的遮挡、阴影以及复杂的光影变化信息进行高质量恢复,可以用于复杂场景的稀疏光场稠密重建.本研究实现了线性采集稀疏光场的稠密重建,未来将针对非线性采集稀疏光场的稠密重建进行研究,以推进光场成像在实际工程中的应用.     

一种基于GAN和自适应迁移学习的样本生成方法

研究了基于生成式对抗网络(GAN)和跨域自适应迁移学习的样本生成和自动标注方法。该方法利用自适应迁移学习网络,基于已有的少量可见光图像样本集,挖掘目标在红外和可见光图像中特征内在相关性,构建自适应的转换迁移学习网络模型,生成标注好的目标图像。提出的方法解决了红外图像样本数量少且标注费时的问题,为后续多频段协同目标检测和识别获得了足够的样本数据。实验结果表明:自动标注算法对实际采集的装甲目标图像和生成的装甲目标图像各1 000张进行自动标注测试,对实际装甲目标图像的标注准确率达到95%以上,对生成的装甲目标标注准确率达到83%以上;利用真实图像和生成图像的混合数据集训练的分类器的性能和使用纯真实图像时基本一致。     

基于改进DeepLabv3+的无人车夜间红外图像语义分割

为了增强无人车对夜间场景的理解能力,针对无人车在夜间获取的红外图像,提出了一种基于改进DeepLabv3+网络的无人车夜间红外图像语义分割算法。由于自动驾驶场景中的对象往往显示出非常大的尺度变化,该算法在DeepLabv3+网络的基础上,通过引入密集连接的空洞卷积空间金字塔模块,使网络生成的多尺度特征能覆盖更大的尺度范围。此外,该算法将编码器模块的多层结果拼接在译码器模块中,以恢复更多在降采样过程中丢失的空间信息和低级特征。通过端到端的学习和训练,可直接用于对夜间红外图像的语义分割。实验结果表明,该算法在红外数据集上的分割精度优于原DeepLabv3+算法,平均交并比达到80.42,具有良好的实时性和准确性。     

Dynamic Topology Reconfiguration of Boltzmann Machines on Quantum Annealers

Boltzmann machines have useful roles in deep learning applications, such as generative data modeling, initializing weights for other types of networks, or extracting efficient representations from high-dimensional data. Most Boltzmann machines use restricted topologies that exclude looping connectivity, as such connectivity creates complex distributions that are difficult to sample. We have used an open-system quantum annealer to sample from complex distributions and implement Boltzmann machines with looping connectivity. Further, we have created policies mapping Boltzmann machine variables to the quantum bits of an annealer. These policies, based on correlation and entropy metrics, dynamically reconfigure the topology of Boltzmann machines during training and improve performance.     

Sequentially Estimating the Approximate Conditional Mean Using Extreme Learning Machines

This study examined the extreme learning machine (ELM) applied to the Wald test statistic for the model specification of the conditional mean, which we call the WELM testing procedure. The omnibus test statistics available in the literature weakly converge to a Gaussian stochastic process under the null that the model is correct, and this makes their application inconvenient. By contrast, the WELM testing procedure is straightforwardly applicable when detecting model misspecification. We applied the WELM testing procedure to the sequential testing procedure formed by a set of polynomial models and estimate an approximate conditional expectation. We then conducted extensive Monte Carlo experiments to evaluate the performance of the sequential WELM testing procedure and verify that it consistently estimates the most parsimonious conditional mean when the set of polynomial models contains a correctly specified model. Otherwise, it consistently rejects all the models in the set.