关键词： bidirectional reflectance normalization   Gaussian process   angle normalization  

摘要： Data from Landsat-8 and Sentinel-2A/2B are often combined for terrestrial monitoring because of their similar spectral bands. The bidirectional reflectance distribution function (BRDF) effect has been observed in both Landsat-8 and Sentinel-2A/2B reflectance data. However, there is currently no definition of solar zenith angle (theta(sz)) that is suitable for the normalization of the BRDF-adjusted reflectance from the three sensors' combined data. This paper describes the use of four machine learning (ML) models to predict a global theta(sz) that is suitable for the normalization of bidirectional reflectance from the combined data in 2018. The observed theta(sz) collected globally, and the three locations in the Democratic Republic of Congo (26.622 degrees E, 0.356 degrees N), Texas in the USA (99.406 degrees W 30.751 degrees N), and Finland (25.194 degrees E, 61.653 degrees N), are chosen to compare the performance of the ML models. At a global scale, the ML models of Support Vector Regression (SVR), Multi-Layer Perception (MLP), and Gaussian Process Regression (GPR) exhibit comparably good performance to that of polynomial regression, considering center latitude as the input to predict the global theta(sz). GPR achieves the best overall performance considering the center latitude and acquisition time as inputs, with a root mean square error (RMSE) of 1.390 degrees, a mean absolute error (MAE) of 0.689 degrees, and a coefficient of determination (R-2) of 0.994. SVR shows an RMSE of 1.396 degrees, an MAE of 0.638 degrees, and an R-2 of 0.994, following GPR. For a specific location, the SVR and GPR models have higher accuracy than the polynomial regression, with GPR exhibiting the best performance, when center latitude and acquisition time are considered as inputs. GPR is recommended for predicting the global theta(sz) using the three sensors' combined data.

关键词： machine learning   deep learning   mobile computing   smoking   smoking cessation   smoking cessation apps  

摘要： Smoking cessation apps provide efficient, low-cost and accessible support to smokers who are trying to quit smoking. This article focuses on how up-to-date machine learning algorithms, combined with the improvement of mobile phone technology, can enhance our understanding of smoking behaviour and support the development of advanced smoking cessation apps. In particular, we focus on the pros and cons of existing approaches that have been used in the design of smoking cessation apps to date, highlighting the need to improve the performance of these apps by minimizing reliance on self-reporting of environmental conditions (e.g., location), craving status and/or smoking events as a method of data collection. Lastly, we propose that making use of more advanced machine learning methods while enabling the processing of information about the user's circumstances in real time is likely to result in dramatic improvement in our understanding of smoking behaviour, while also increasing the effectiveness and ease-of-use of smoking cessation apps, by enabling the provision of timely, targeted and personalised intervention.

关键词： Stainless steel   Capacity prediction   Machine learning   Cold-formed   Tubular columns  

摘要： Current methods of designing cold-formed stainless-steel tubular columns provide a series of design formulae for columns to adapt to various grades of materials and failure modes. In this study, machine learning algorithms were used to establish a unified capacity prediction method. Test data on cold-formed stainless-steel tubular columns were collected from the literature, and Pearson correlation analysis was performed to establish the relations among the design parameters. Seven classical machine learning algorithms were introduced and developed to predict column capacity in a variety of cases used for the analysis. The results show that the random forest performs the best, followed by another gradient boosted tree-based ensemble algorithm, XGBoost. The non-dimensional slenderness of the member and of the cross-section (denoted as comprehensive parameters) are the two key parameters for capacity prediction in the current design methods, and are used as the feature input to acquire the base machine learning model. More models are evaluated by adding one or more material and geometric variables into the feature input. The analysis results show that the performance of the random forest algorithm can be significantly improved by considering the comprehensive parameters together with the member slenderness, ratio of tensile strength to yield strength, and strain hardening exponent. The predictions of the machine learning-based method were compared with those of the current design method in Eurocode. It is concluded that the proposed unified machine learning model provides more accurate results owing to the consideration of the diversities of both material properties and member failure modes. (c) 2021 Elsevier Ltd. All rights reserved.

关键词： milk spectra   gradient boosting machine   phenotypic prediction   dairy cattle  

摘要： Fourier-transform infrared (FTIR) spectroscopy is a powerful high-throughput phenotyping tool for predicting traits that are expensive and difficult to measure in dairy cattle. Calibration equations are often developed using standard methods, such as partial least squares (PLS) regression. Methods that employ penalization, rank-reduction, and variable selection, as well as being able to model the nonlinear relations between phenotype and FTIR, might offer improvements in predictive ability and model robustness. This study aimed to compare the predictive ability of 2 machine learning methods, namely random forest (RF) and gradient boosting machine (GBM), and penalized regression against PLS regression for predicting 3 phenotypes differing in terms of biological meaning and relationships with milk composition (i.e., phenotypes measurable directly and not directly in milk, reflecting different biological processes which can be captured using milk spectra) in Holstein-Friesian cattle under 2 cross-validation scenarios. The data set comprised phenotypic information from 471 Holstein-Friesian cows, and 3 target phenotypes were evaluated: (1) body condition score (BCS), (2) blood beta-hydroxybutyrate (BHB, mmol/L), and (3) kappa-casein expressed as a percentage of nitrogen (kappa-CN, % N). The data set was split considering 2 cross-validation scenarios: samples-out random in which the population was randomly split into 10-folds (8-folds for training and 1-fold for validation and testing);and herd/dateout in which the population was randomly assigned to training (70% herd), validation (10%), and testing (20% herd) based on the herd and date in which the samples were collected. The random grid search was performed using the training subset for the hyperparameter optimization and the validation set was used for the generalization of prediction error. The trained model was then used to assess the final prediction in the testing subset. The grid search for penalized regression

关键词： Nonlinear dynamical systems   Intelligent systems   Computational intelligence   Recurrent neural networks   Combustion modeling & optimization   NOx emissions  

摘要： Ten established, data-driven dynamic algorithms are surveyed and a practical guide for understanding these methods generated. Existing Python programming packages for implementing each algorithm are acknowledged, and the model equations necessary for prediction are presented. A case study on a coal-fired power plant's NOx emission rates is performed, directly comparing each modeling method's performance on a mutual system. Each model is evaluated by its root mean squared error (RMSE) on out-of-sample future horizon predictions. Optimal hyperparameters are identified using either an exhaustive search or genetic algorithm. The top five model structures of each method are used to recursively predict future NOx emission rates over a 60-step time horizon. The RMSE at each future timestep is determined, and the recursive output prediction trends compared against measurements in time. The GRU neural network is identified as the best candidate for representing the system, demonstrating accurate and stable predictions across the future horizon by all considered models, while satisfactory performance was observed in several of the ARX/NARX formulations. These efforts have contributed 1) a concise resource of multiple proven dynamic machine learning methods, 2) a practical guide explaining the use of these methods, effectively lowering the "barrier-to-entry" of deploying such models in control systems, 3) a comparison study evaluating each method's performance on a mutual system, 4) demonstration of accurate multi-timestep emissions modeling suitable for systems-level control, and 5) generalizable results demonstrating the suitability of each method for prediction over a multi-step future horizon to other complex dynamic systems.

关键词： 机器学习方法   精准养猪   母猪早期选育   决策树   随机森林   支持向量机   繁殖性能   产仔数早期预测   高繁殖力   分类模型  

摘要： 为帮助猪场管理者更好地对母猪进行繁殖管理、预测母猪的高低产、及时淘汰低产母猪,收集和整理包含出生场地、分娩栏位、品种和不同胎次、初生窝重信息的3个母猪群体的生产数据集,制定母猪高低产的分类标准,使用R软件中的Boruta包筛选出影响母猪高低产的重要特征,使用4种不同的机器学习方法——逻辑回归(logistic regression,LOG)、决策树(decision tree,DT)、随机森林(random forest,RF)和支持向量机(support vector machine,SVM)构建母猪高低产的分类模型,并进行决策树视图分析探究影响母猪最高产的相关因素。结果显示:4种机器学习方法构建母猪高产分类模型的分类准确率均在71%左右,最高可达84%,并且发现SVM作为最佳建模方法在所有数据集和不同分类标准下出现的频率最高,其次是LOG和DT。决策树视图显示出生场地、品种和初生窝重是划分最高产母猪的重要叶节点,利用这些特征预测最高产母猪准确率可达73%~82%。以上结果表明在未来的养猪生产中,利用机器学习方法实现母猪高低产的早期预测将会是一个不错的选择。

关键词： 太阳质子事件   耀斑   日冕物质抛射   Apriori算法   机器学习  

摘要： 在耀斑伴随日冕物质抛射(CME)事件编目数据的基础上,进行太阳质子事件(SPE)匹配,构建研究数据集.利用Apriori算法挖掘SPE与耀斑级别、耀斑发生日面位置以及CME角宽度和速度的关联关系.结果表明:X级耀斑、全晕CME、高速(> 1000 km·s^(-1)) CME和日面西半球耀斑是最可能伴随质子事件的4种特征,其诱发质子事件概率依次为0.366,0.355,0.30,0.155.角宽度低于120°或速度低于400 km·s^(-1)的CME产生质子事件的概率为0.高速CME产生质子事件的概率是低速(400~1000km·s^(-1)) CME的8.6倍,X级耀斑产生质子事件的概率是M级耀斑的6.2倍,日面西部耀斑产生质子事件的概率是日面东部耀斑概率的3.9倍,全晕CME产生太阳质子事件的概率是非全晕(120°~360°) CME的3.8倍.对太阳质子事件样本进行过采样处理,利用随机森林等5种典型有监督学习算法,构建了基于第23太阳活动周耀斑和CME特征的质子事件预测模型.结果表明,该预报模型的质子事件预测准确率、精确率和召回率均控制在91%以上.

关键词： 北半球环状模(NAM)   重建   代用指标   机器学习  

摘要： 受限于观测资料的短缺,关于北半球主要大气环流模态(Northern Annular Mode,简称NAM)的演变规律和机理还很不明确。运用树轮、冰芯、沉积物等代用指标重建时间序列更长的NAM指数有助于加深对其演变规律和驱动机制的认识。本文通过评估多种机器学习模型在古气候重建中的适用性,基于PAGES 2k的气候代用指标重建了过去1000年高分辨率(1年)的NAM指数。研究结果表明相比普通线性回归模型和随机森林等模型,Cat Boost、极端随机树和主成分回归模型可以有效地避免过拟合,模型具有更高的稳定性和可靠性,其中Cat Boost模型的重建结果与器测时段内NAM指数的相关系数最高(R=0.93,p<0.01),能够更好地拟合NAM指数的量级和峰谷变化。分析过去1000年NAM指数的变化特征,发现NAM具有显著的百年际周期(167.5年)和多年代际周期(32.3年)波动,1950~2000年NAM由负位相转向正位相的速率在过去1000年中前所未有。进一步探究NAM与温度和海冰的关系发现,1850年之前,暖期对应NAM增强,冷期对应NAM减弱;而在1850年之后NAM的多年代际变化与巴伦支-喀拉海海冰范围的变化趋于一致,1950年之后NAM向正位相快速转变可能是温度和北极海冰异常共同影响的结果。

关键词： 溶解性有机质   有机碳标化分配系数   预测模型   紫外⁃可见光谱   机器学习  

摘要： 有机化合物在溶解性有机质(Dissolved Organic Matter,DOM)上的吸附行为显著影响其环境归趋和生物有效性.以标化的DOM紫外⁃可见光谱和有机化合物的正辛醇⁃水分配系数为特征,运用随机森林算法,建立有机碳标化分配系数(KOC)的预测模型.结果显示,随机森林模型在全部来源DOM上的预测精度显著高于目前普遍使用的线性自由能模型,但略低于两相体系模型.随机森林模型对土壤和泥炭来源的DOM吸附预测精度显著优于其他模型,说明随机森林模型具有很好的适用性.根据随机森林模型输出的特征重要性,发现模型学习到了表征DOM分子量大小、腐殖化程度以及苯环上取代基类型的光谱特征.通过特征选择,发现模型使用少数重要性较高的特征可以达到使用全谱的效果,即使在只选取两个波长时,预测精度依然显著优于线性自由能模型.由于DOM的紫外⁃可见光谱可原位实时分析,基于紫外⁃可见光谱和机器学习方法的预测模型未来可进行原位及高通量KOC时空规律解析,从而实现更准确更精细的风险评估与管理.

关键词： 高速信道   DNN   RNN   眼图   机器学习   均衡   LMS  

摘要： 随着高速信道的传输速率变快,传输长度变长,结构复杂度变高,对信道进行建模也变得复杂与艰难。将目前比较火热的机器学习方法与高速信道结合起来,提出了一个新颖的方法。利用采集的大量模拟数据,采用深度神经网络DNN与循环神经网络RNN对信道建模,模型一旦训练成功,就可以通过该仿真模型预测输出信号的眼图,快速精准地对信号完整性进行评估和分析。另外,在高速信道中,信号的严重干扰和衰减问题会限制传输距离和传输速率,给测试和信息采集带来困难。为了恢复理想信号,高速串行链路通常包含复杂的均衡摸块,采用最小均方算法LMS可以有效地消除干扰,减小误码率,提高传输速率。