关键词： ERα抑制剂   特征筛选   随机森林   支持向量机   多元线性回归  

摘要： 雌激素受体α亚型(ERα)被认为是乳腺癌内分泌疗法的重要靶标。本文采用随机森林、支持向量机和多元线性回归方法,对1974个化合物建立ERα抑制剂活性预测模型。利用方差过滤法和Lasso回归思想筛选分子描述符,使用均方误差MSE来评估模型的预测效果。采用随机森林、支持向量机和多元线性回归方法在训练集和测试集上的均方误差分别为0.475和0.553、0.653和0.792、0.709和0.801。结果表明,随机森林优于其他机器学习方法,用于ERα抑制剂的活性预测具有良好的稳健性和预测能力。

关键词： 分类预测   决策树   KNN  

摘要： 文章主要介绍了对大数据进行分类预测的深度学习算法,并使用K近邻算法(KNN)、决策树算法(CART)、支持向量机算法(SVN)、贝叶斯算法、人工神经网络算法(ANN)等对ADMET性质进行分类预测,为乳腺癌治疗效果提供了一种评价方法。

关键词： 朴素贝叶斯   桥梁   损伤状态识别  

摘要： 以简支梁、连续梁、连续刚构桥梁图片为样本数据,利用不同机器学习方法对桥梁图片数据进行分析与挖掘,识别桥梁的振动、变形、应力、裂缝等指标,比较不同挖掘算法预测的准确性。结果表明:较于其他分类器,朴素贝叶斯分类器与神经元网络分类器对桥梁状态具有较好的识别准确性。基于Weka图像数据挖掘平台对图片数据进行分类与预测具有较好的效果,可以为桥梁状态在线评估提供新的思路。

关键词： 高光谱   随机森林   可解释性   人参   中药材   产地  

摘要： 人参是传统中药材中的贵重品种,具有较高的经济价值。人参生长的地域性很强,不同产地人参有效成分含量存在差异,人参因“道地”与否,会导致其质量、医学效用和经济价值的差异,因此人参产地识别的意义重大。目前常通过磨粉提取等制备,再采用化学或光学等多种手段检验人参产地,但会造成样本破坏。而基于外观性状或芦头特征的鉴别,因主观性差异不能作为标准化的识别方法。如何用高精度、无损、快速检测识别的方法,对人参的产地进行识别分析,是该研究的主要立足点。通过采用高光谱成像技术,对已知产地信息的人参样本,通过获取从400~2 500 nm的反射光谱,经过基于白板的绝对和相对辐射校正处理,构建了高光谱反射率数据集。采用随机森林的机器学习方法,构建了基于高光谱数据的全光谱人参产地识别模型,并对不同尺度的地域划分规则分别开展了产地识别精度验证,发现不同产地的人参光谱有明显区别。其中东三省与否的产地识别精度,可以达到98.2%。同时利用随机森林基于决策树构建的优势,获得了人参产地识别的光谱重要性结果,为专用轻量化仪器研发指明特征光谱。高光谱人参产地识别研究作为严格的无损检测方式,将对人参等道地药材的产地识别、药材图谱指纹认知和挖掘、药材鉴定和质量评价等提供理论支撑和技术手段。

关键词： 农作物病虫害   安卓   MySQL   自动识别  

摘要： 为了解决农作物病虫害自动识别的问题,帮助农户提高农作物的产量,研制一款农作物病虫害识别系统是十分必要的。本文开发了一款基于安卓+MySQL的框架开发的农作物病虫害自动识别系统。该系统连接农业工作者与农业专家,可实现一对一以及多对一的人员交流。系统利用安卓界面的直观性以及MySQL的优点,提高了实时性和安全性,达到了轻松种植的目的。

关键词： 植被重建   随机森林算法   生物群区化法   孢粉   末次冰盛期   青藏高原  

摘要： 地质历史时期青藏高原的植被变化为理解高寒植被响应气候变化的机制提供重要证据.然而,由于缺少合适的利用孢粉化石等代用指标定量重建高寒植被的方法,阻碍了对青藏高原过去植被变化的深入理解.本研究基于青藏高原及其周边地区的现代孢粉数据,采用一种有监督机器学习方法——随机森林算法,构建利用孢粉数据重建青藏高原植被的模型,对比模型对现代样点的预测结果与样点实际植被及生物群区化法的重建结果,评估随机森林算法建立孢粉-植被模型的可靠性.结果显示,基于现代孢粉数据,利用随机森林模型重建的现代样点植被与实际植被有较高的一致性.与生物群区化法相比,随机森林算法重建青藏高原地区现代植被的准确性更高,可能更适用于该地区的古植被重建.基于51条孢粉化石记录,利用随机森林模型重建了青藏高原2.2万年以来的植被变化,重建的古植被格局变化大体与同时期全球气候变化和东亚季风演化趋势一致.末次冰盛期时,青藏高原大部分地区是荒漠植被,亚热带森林分布于高原东南缘.高寒草原从末次冰消期开始扩张,并且在高原中部和东部逐渐形成地带性植被.高寒草甸从早全新世开始占据高原东部和东南部,高原开始形成从东南至西北分布森林-草甸-草原-荒漠的格局.中全新世时,亚热带森林向北扩张,反映最适宜期的植被状况.之后,高寒草甸和高寒草原在晚全新世再次向南扩张.

关键词： heavy rainfall events   data merging   CoKriging   machine learning   multi-source precipitation  

摘要： Gridded precipitation data with a high spatiotemporal resolution are of great importance for studies in hydrology, meteorology, and agronomy. Observational data from meteorological stations cannot accurately reflect the spatiotemporal distribution and variations of precipitation over a large area. Meanwhile, radar-derived precipitation data are restricted by low accuracy in areas of complex terrain and satellite-based precipitation data by low spatial resolution. Therefore, hourly precipitation models were employed to merge data from meteorological stations, Radar, and satellites;the models used five machine learning algorithms (XGBoost, gradient boosting decision tree, random forests (RF), LightGBM, and multiple linear regression (MLR)), as well as the CoKriging method. In the north of Guangdong Province, data of four heavy rainfall events in 2018 were processed with geographic data to obtain merged hourly precipitation data. The CoKriging method secured the best prediction of spatial distribution of accumulated precipitation, followed by the tree-based machine learning (ML) algorithms, and significantly, the prediction of MLR deviated from the actual pattern. All machine learning methods showed poor performances for timepoints with little precipitation during the heavy rainfall events. The tree-based ML method showed poor performance at some timepoints when precipitation was over-related to latitude, longitude, and distance from the coast.

关键词： near-surface air temperature   land surface temperature   random forest model   Jingjinji area   machine learning   remote sensing  

摘要： Meteorologically observed air temperature (T-a) is limited due to low density and uneven distribution that leads to uncertain accuracy. Therefore, remote sensing data have been widely used to estimate near-surface T-a on various temporal scales due to their spatially continuous characteristics. However, few studies have focused on instantaneous T-a when satellites overpass. This study aims to produce both daily and instantaneous T-a datasets at 1 km resolution for the Jingjinji area, China during 2018-2019, using machine learning methods based on remote sensing data, dense meteorological observation station data, and auxiliary data (such as elevation and normalized difference vegetation index). Newly released Moderate Resolution Imaging Spectroradiometer (MODIS) Collection 6 surface Downward Shortwave Radiation (DSR) was introduced to improve the accuracy of T-a estimation. Five machine learning algorithms were implemented and compared so that the optimal one could be selected. The random forest (RF) algorithm outperformed the others (such as decision tree, feedforward neural network, generalized linear model) and RF obtained the highest accuracy in model validation with a daily root mean square error (RMSE) of 1.29 degrees C, mean absolute error (MAE) of 0.94 degrees C, daytime instantaneous RMSE of 1.88 degrees C, MAE of 1.35 degrees C, nighttime instantaneous RMSE of 2.47 degrees C, and MAE of 1.83 degrees C. The corresponding R-2 was 0.99 for daily average, 0.98 for daytime instantaneous, and 0.95 for nighttime instantaneous. Analysis showed that land surface temperature (LST) was the most important factor contributing to model accuracy, followed by solar declination and DSR, which implied that DSR should be prioritized when estimating T-a. Particularly, these results outperformed most models presented in previous studies. These findings suggested that RF could be used to estimate daily instantaneous T-a at unprecedented accuracy and temporal scale with proper t

关键词： Machine learning   Model interpretation   SHAP   Crash modification factor   Crash frequency   Sensitivity analysis  

摘要： Machine learning (ML) model interpretability has attracted much attention recently given the promising performance of ML methods in crash frequency studies. Extracting accurate relationship between risk factors and crash frequency is important for understanding the causal effects of risk factors and developing safety countermeasures. However, there is no study that comprehensively summarizes ML model interpretation methods and provides guidance for safety researchers and practitioners. This research aims to fill this gap. Model-based and post-hoc ML interpretation methods are critically evaluated and compared to study their suitability in crash frequency modeling. These methods include classification and regression tree (CART), multivariate adaptive regression splines (MARS), Local Interpretable Model-agnostic Explanations (LIME), Local Sensitivity Analysis (LSA), Partial Dependence Plots (PDP), Global Sensitivity Analysis (GSA), and SHapley Additive exPlanations (SHAP). Model-based interpretation methods cannot reveal the detailed interaction relationships among risk factors. LIME can only be used to analyze the effects of a risk factor at the prediction level. LSA and PDP assume that different risk factors are independently distributed. Both GSA and SHAP can account for the potential correlation among risk factors. However, only SHAP can visualize the detailed relationships between crash outcomes and risk factors. This study also demonstrates the potential and benefits of using ML and SHAP to derive Crash Modification Factors (CMF). Finally, it is emphasized that statistical and ML models may not directly differentiate causation from correlation. Understanding the differences between them is critical for developing reliable safety countermeasures.