基于GAN数据重构的电信用户流失预测方法

用户是运营商利益的核心。随着携号转网政策的出台,运营商之间的竞争越发激烈。为了提前精准有效地预测用户流失倾向,提出了一种基于生成对抗网络（generative adversarial network,GAN）数据重构的电信用户流失预测方法。首先,利用有效的数据预处理方法电信用户流失数据中的脏数据;其次,利用GAN重构电信用户流失数据,解决电信用户流失数据不平衡问题;最后,利用极度梯度提升树（extremegradient boosting,XGBoost）算法分别训练基于GAN重构的电信用户流失预测模型和基于合成少数类过采样技术（synthetic minority oversampling technique,SMOTE）采样的电信用户流失预测模型,对比两种模型的预测精度。实验结果表明,GAN重构后的电信用户流失预测模型预测精度比未重构的预测模型的准确率提升了6.75%,查准率提升了25.91%,召回率提升了30.91%,F1值提升了28.73%。该方法能够有效提升电信用户流失预测的准确度。     

基于XGBoost-MTL的综合能源系统多元负荷预测

精确的多元负荷预测是综合能源系统(integrated energy system,IES)优化调度和稳定运行的前提。针对IES中多元负荷之间耦合关系复杂以及影响负荷预测的因素众多等问题,文中提出一种基于极限梯度提升(extreme gradient boosting,XGBoost)与多任务学习(multi task learning,MTL)的多元负荷预测方法。首先通过XGBoost重要度排序得到各影响因素对于多元负荷的贡献度,依据贡献度来选取影响负荷预测的关键性因素作为预测模型的输入,保证了输入特征对于多元负荷预测有效的修正作用;其次以门控循环单元(gated recurrent unit,GRU)作为共享层来搭建MTL预测模型,各子任务通过共享信息来有效利用各负荷之间复杂的耦合关系;最后以上海某综合能源站的负荷数据为例对文中所提模型的有效性进行验证。结果表明:该模型能够适应实际综合能源系统中各类负荷的变化,有效提高预测精度并减少训练时间。     

Effective ensemble learning approach for SST field prediction using attention-based PredRNN

Accurate prediction of sea surface temperature (SST) is extremely important for forecasting oceanic environmental events and for ocean studies. However, the existing SST prediction methods do not consider the seasonal periodicity and abnormal fluctuation characteristics of SST or the importance of historical SST data from different times; thus, these methods suffer from low prediction accuracy. To solve this problem, we comprehensively consider the effects of seasonal periodicity and abnormal fluctuation characteristics of SST data, as well as the influence of historical data in different periods, on prediction accuracy. We propose a novel ensemble learning approach that combines the Predictive Recurrent Neural Network(PredRNN) network and an attention mechanism for effective SST field prediction. In this approach, the XGBoost model is used to learn the long-period fluctuation law of SST and to extract seasonal periodic features from SST data. The exponential smoothing method is used to mitigate the impact of severely abnormal SST fluctuations and extract the a priori features of SST data. The outputs of the two aforementioned models and the original SST data are stacked and used as inputs for the next model, the PredRNN network. PredRNN is the most recently developed spatiotemporal deep learning network, which simulates both spatial and temporal representations and is capable of transferring memory across layers and time steps. Therefore, we used it to extract the spatiotemporal correlations of SST data and predict future SSTs. Finally, an attention mechanism is added to capture the importance of different historical SST data, weigh the output of each step of the PredRNN network, and improve the prediction accuracy. The experimental results on two ocean datasets confirm that the proposed approach achieves higher training efficiency and prediction accuracy than the existing SST field prediction approaches do.     

基于集成学习的N6甲基化位点预测方法研究

N6-甲基腺嘌呤(N6-methyladenine,6mA)是指腺嘌呤第6位氮原子的甲基化修饰。6mA在维持细胞正常的转录活性、DNA损伤修复、染色质重塑、遗传印记、胚胎发育和肿瘤发生等生物过程中起着非常重要的作用。通过生物实验的方法来鉴定6mA位点耗时且昂贵。近年来,研究界提出了一些基于机器学习的6mA位点预测方法,但这些预测方法过度依赖一种学习模型,导致模型的泛化能力不足以及预测的准确度不高等问题。集成学习综合多种预测模型的优点,具有较好的泛化能力及预测性能。因此,为了进一步提升6mA位点的预测准确性,提出了一种基于stacking集成学习的6mA位点预测模型Stack6mAPred。该模型由两层分类器组成,第一层集成了朴素贝叶斯、支持向量机(support vector machine,SVM)和LightGBM等三种主流分类器,第二层使用逻辑回归(logistic regression,LR)分类器。Stack6mAPred利用增强核苷酸组成等5种特征对实验已鉴定6mA序列和非6mA序列进行编码,使用XGBoost(extreme gradient boosting)算法进行特征选择,去除冗余特征。通过在水稻基准数据集上进行五折交叉验证,与目前性能最优的方法MM-6mAPred相比,Stack6mAPred在敏感性、特异性、准确度、MCC和AUC上均获得了更好的性能,分别提高了1.7%、1.36%、1.72%、0.06和0.031。     

基于多粒度特征和XGBoost模型的城市日供水量预测

城市日供水量预测对供水部门具有十分重要的现实意义。为提高城市日供水量预测精度,以某市历史用水数据为基础,构建多粒度特征,并利用Pearson相关系数进行特征的筛选,基于XGBoost模型构建城市日供水量预测模型。本模型通过在训练集上进行训练和学习,在测试集上的平均绝对误差为70 571 t/d,平均相对误差为1.4%;传统的回归预测方法如随机森林法和支持向量机法,平均绝对误差分别为84 366 t/d和88 848 t/d。本模型预测精度更高,说明此模型可行、有效,具有一定的应用价值。     

基于人工智能的暂态稳定裕度精细化预测

人工智能算法在暂态稳定评估中得到了很好的应用.然而,电力系统是时变大系统,训练数据无法涵盖所有工况,模型需要在有限时间内更新;电力系统中稳定样本数远大于失稳样本数,导致模型对失稳样本学习不足.针对以上2点,提出了基于人工智能的暂态稳定裕度精细化预测方法.该方法将改进的极限梯度提升(XGBoost)树与双XGBoost回归树集成,平衡了2类样本数量差异对模型的影响,并实现了裕度预测.当运行工况变化较大时,结合增量学习技术,以较少的样本和较短的时间对模型进行有效更新.在2套IEEE系统上的实验结果表明所提方法可应用于暂态稳定评估.     

基于烧结大数据预测小于10 mm烧结矿含量模型

为了给高炉提供合格的烧结矿,提出基于烧结生产线各个环节的大量数据,将XGBoost算法、因子相关分析与深度学习算法相结合的大数据技术对烧结矿小于10 mm粒级含量进行预测。首先,对烧结厂数据库的数据进行搜集、整合和预处理;其次,进行因子分析,筛选出适合建模的14个相关变量并进行变量之间的相关性分析;最后,建立深度神经网络算法模型。通过测试并与传统算法模型进行性能比较,结果表明,模型预测效果很好,达到了精确预测烧结矿小于10 mm粒级含量的目的,对烧结实际生产具有很好的指导意义。     

基于XGBoost算法对新疆女性臀部体型判别及原型修正

为准确判断下体体型,使新疆地区女性裙装更加合体,分析了220名18~25岁的新疆地区青年女性臀部数据,通过因子分析与相关指数得到聚类指标:后臀长腰围比、后臀长臀围比,采用K-means聚类方法将臀部分为3类,使用Python软件建立XGBOOST臀部判别模型。首先对不同算法模型进行比较分析表明,运用XGBOOST方法的测试集精准度最高为98.4%。其次修正新疆地区中间体的裙装原型,发现其后臀长与标准裙装原型后臀长相差2.4 cm,说明新疆地区女性臀部相比国内其他地区偏翘。将判别算法运用到数据系统中,可提高体型判别效率,为人体相关领域提供数据支持。     

基于Apriori和GP-XGBoost的特高拱坝变形缺失数据填补方法

变形监测数据作为特高拱坝服役性态最直观的表征,蕴藏着丰富的时空信息和演变规律,对工程长治久安意义重大。然而,多源多维的变形监测数据受仪器本身及外界因素影响,往往存在数据缺失的现象,会对接下来的数据分析工作造成干扰。针对大坝变形监测序列中的缺失数据,基于Apriori关联规则算法挖掘测点变形在空间维度上的关联性,得到目标测点的强关联测点,随后以强关联测点的变形监测数据作为输入样本,利用贝叶斯优化的XGBoost回归模型填补了目标测点的空缺变形监测序列。结合锦屏一级特高拱坝工程实例表明,该填补方法实现了变形监测空缺信息的高效、精准填补,可用于类似大坝工程的变形缺失数据填补。     

Deep learning with knowledge transfer for explainable anomaly prediction in wind turbines

The last decade has witnessed an increased interest in applying machine learning techniques to predict faults and anomalies in the operation of wind turbines. These efforts have lately been dominated by deep learning techniques which, as in other fields, tend to outperform traditional machine learning algorithms given sufficient amounts of training data. An important shortcoming of deep learning models is their lack of transparency—they operate as black boxes and typically do not provide rationales for their predictions, which can lead to a lack of trust in predicted outputs. In this article, a novel hybrid model for anomaly prediction in wind farms is proposed, which combines a recurrent neural network approach for accurate classification with an XGBoost decision tree classifier for transparent outputs. Experiments with an offshore wind turbine show that our model achieves a classification accuracy of up to 97%. The model is further able to generate detailed feature importance analyses for any detected anomalies, identifying exactly those components in a wind turbine that contribute to an anomaly. Finally, the feasibility of transfer learning is demonstrated for the wind domain by porting our “offshore” model to an unseen dataset from an onshore wind farm. The latter model achieves an accuracy of 65% and is able to detect 85% of anomalies in the unseen domain. These results are encouraging for application to wind farms for which no training data are available, for example, because they have not been in operation for long.