Prediction of rockhead using a hybrid N-XGBoost machine learning framework

The spatial information of rockhead is crucial for the design and construction of tunneling or underground excavation. Although the conventional site investigation methods (i.e. borehole drilling) could provide local engineering geological information, the accurate prediction of the rockhead position with limited borehole data is still challenging due to its spatial variation and great uncertainties involved. With the development of computer science, machine learning (ML) has been proved to be a promising way to avoid subjective judgments by human beings and to establish complex relationships with mega data automatically. However, few studies have been reported on the adoption of ML models for the prediction of the rockhead position. In this paper, we proposed a robust probabilistic ML model for predicting the rockhead distribution using the spatial geographic information. The framework of the natural gradient boosting (NGBoost) algorithm combined with the extreme gradient boosting (XGBoost) is used as the basic learner. The XGBoost model was also compared with some other ML models such as the gradient boosting regression tree (GBRT), the light gradient boosting machine (LightGBM), the multivariate linear regression (MLR), the artificial neural network (ANN), and the support vector machine (SVM). The results demonstrate that the XGBoost algorithm, the core algorithm of the probabilistic N-XGBoost model, outperformed the other conventional ML models with a coefficient of determination (R²) of 0.89 and a root mean squared error (RMSE) of 5.8 m for the prediction of rockhead position based on limited borehole data. The probabilistic N-XGBoost model not only achieved a higher prediction accuracy, but also provided a predictive estimation of the uncertainty. Thus, the proposed N-XGBoost probabilistic model has the potential to be used as a reliable and effective ML algorithm for the prediction of rockhead position in rock and geotechnical engineering.     

基于深度概率图模型的鲁棒人脸画像合成

针对基于数据驱动的人脸画像合成算法像素特征缺乏对光照变化和复杂背景的鲁棒性,常合成低质量的画像的问题,文中提出基于深度概率图模型的鲁棒人脸画像合成算法.采用预处理方法调整测试照片的光照亮度和人脸姿态,使之与训练照片一致.采用深度特征代替像素特征进行近邻匹配,采用深度概率图模型对画像重建权重和深度特征权重联合建模,得到合成画像的最佳重构表示.为了提高画像合成速度,提出快速近邻搜索方法.实验验证文中算法的鲁棒性和快速性.     

Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows

Automatic synthesis of realistic gestures promises to transform the fields of animation, avatars and communicative agents. In off-line applications, novel tools can alter the role of an animator to that of a director, who provides only high-level input for the desired animation; a learned network then translates these instructions into an appropriate sequence of body poses. In interactive scenarios, systems for generating natural animations on the fly are key to achieving believable and relatable characters. In this paper we address some of the core issues towards these ends. By adapting a deep learning-based motion synthesis method called MoGlow, we propose a new generative model for generating state-of-the-art realistic speech-driven gesticulation. Owing to the probabilistic nature of the approach, our model can produce a battery of different, yet plausible, gestures given the same input speech signal. Just like humans, this gives a rich natural variation of motion. We additionally demonstrate the ability to exert directorial control over the output style, such as gesture level, speed, symmetry and spacial extent. Such control can be leveraged to convey a desired character personality or mood. We achieve all this without any manual annotation of the data. User studies evaluating upper-body gesticulation confirm that the generated motions are natural and well match the input speech. Our method scores above all prior systems and baselines on these measures, and comes close to the ratings of the original recorded motions. We furthermore find that we can accurately control gesticulation styles without unnecessarily compromising perceived naturalness. Finally, we also demonstrate an application of the same method to full-body gesticulation, including the synthesis of stepping motion and stance.     

Multilevel approach to lifetime assessment of steam turbines

This paper presents a multilevel methodology for a steam turbine lifetime assessment based on the damage calculation, probabilistic analysis and fracture mechanics considerations. Creep-fatigue damage calculations serve as a basis for evaluating the current lifetime expenditure and for defining additional steps of analysis. The need for the use of probabilistic analysis results from the inherent uncertainty in estimating the lifetime expenditure primarily caused by scatter in material properties. Fracture mechanics considerations are helpful in determining additional safety margins for components containing cracks. This methodology has been illustrated using an example of the lifetime calculations of a high-temperature steam turbine rotor. The calculations were based on the results of 2D numerical simulations performed for steady state and transient operating conditions.     

Monte Carlo simulation-based probabilistic assessment of DG penetration in medium voltage distribution networks

With the growing use of renewable energy sources, Distributed Generation (DG) systems are rapidly spreading. Embedding DG to the distribution network may be costly due to the grid reinforcements and control adjustments required in order to maintain the electrical network reliability. Deterministic load flow calculations are usually employed to assess the allowed DG penetration in a distribution network in order to ensure that current or voltage limits are not exceeded. However, these calculations may overlook the risk of limit violations due to uncertainties in the operating conditions of the networks. To overcome this limitation, related to both injection and demand profiles, the present paper addresses the problem of DG penetration with a Monte Carlo technique that accounts for the intrinsic variability of electric power consumption. The power absorbed by each load of a medium voltage network is characterized by a load variation curve; a probabilistic load flow is then used for computing the maximum DG power that can be connected to each bus without determining a violation of electric constraints. A distribution network is studied and a comparison is provided between the results of the deterministic load flow and probabilistic load flow analyses.     

Salmonella in table eggs from farm to retail – When is cooling required?

Storage time and temperature are known to be important factors in determining Salmonella growth in table eggs. It is assumed that growth of Salmonella within eggs starts when the egg yolk membrane breaks down, allowing Salmonella to enter and grow. The length of time for which the yolk membrane remains intact is time and temperature dependent.The present study addresses the question whether the current legal requirement in Germany to cool table eggs marketed 18 days after laying needs to be updated. Detailed data on the current storage and transport conditions in Germany were collected. On the basis of these data, typical combinations of temperature and time were selected. For these different time-temperature scenarios, the consequences regarding the probability of growth of Salmonella Enteritidis inside the eggs were calculated. A probabilistic model consisting of nine modules reflecting storage/transport stages from farm to retail in Germany was used to calculate whether the yolk membrane remains intact during the individual steps. Growth of Salmonella was simulated without cooling (room temperature) as well as with two different cooling scenarios (4–6 °C and 8–12 °C), which are temperature ranges used in Germany by various retailers. Simulations of these scenarios resulted in relative low numbers of eggs with Salmonella growth until purchase (89 out of 50,000 eggs in the uncooled scenario, 10 out of 50,000 eggs stored at 8–12 °C and 5 out of 50,000 eggs stored at 4–6 °C). These results show that for an average egg trading time of 7.5 days, as was observed for Germany, the probability for the consumer to purchase eggs where no Salmonella growth has started and yolk membrane integrity still exists is high. However, the model supports the necessity for egg cooling after the yolk membrane integrity time is exhausted. Furthermore, the model shows clearly that cooling will extend the time period before the egg yolk membrane breaks down. According to our results, the requirement to cool eggs from the 18th day onwards after laying, as required by legislation in Germany, is reasonable, as it matches the time point of the yolk membrane breakdown for the average egg kept at 18–20 °C. Therefore, continuation of this regulation is strongly supported.     

A review of topic modeling methods

Topic modeling is a popular analytical tool for evaluating data. Numerous methods of topic modeling have been developed which consider many kinds of relationships and restrictions within datasets; however, these methods are not frequently employed. Instead many researchers gravitate to Latent Dirichlet Analysis, which although flexible and adaptive, is not always suited for modeling more complex data relationships. We present different topic modeling approaches capable of dealing with correlation between topics, the changes of topics over time, as well as the ability to handle short texts such as encountered in social media or sparse text data. We also briefly review the algorithms which are used to optimize and infer parameters in topic modeling, which is essential to producing meaningful results regardless of method. We believe this review will encourage more diversity when performing topic modeling and help determine what topic modeling method best suits the user needs.     

基于概率方法的土质边坡稳定性分析

以某公路路堑边坡为例,设计了强度参数最小值组合、最大值组合、平均值组合的边坡确定性方法的计算方案,用其检验了概率方法的合理性,分析了两者的异同。设计了Monte-Carlo循环次数为5000,10000,100000,1000000和5000000等5种计算工况。发现随着循环次数的增加,安全系数的分布范围逼近最小值组合及最大值组合情况下确定值方法计算的安全系数值;安全系数的平均值与平均值组合时,确定性方法计算的结果差别不大;失效概率随循环次数的增加没有稳定趋势,可靠性指数、安全系数则逐步趋稳。     

海洋石油钢结构的疲劳寿命问题

本文归结了几种疲劳寿命的估算方法与模式,论述了估算疲劳寿命过程中不确定性的解决方法,和运用概率断裂力学方法解决的几个问题(如裂纹扩展试验、疲劳寿命的分布规律及其失效概率)以及考虑模糊性在内的模糊疲劳可靠度等高难课题。