Accurate ensemble pruning with PL-bagging

Ensemble pruning deals with the selection of base learners prior to combination in order to improve prediction accuracy and efficiency. In the ensemble literature, it has been pointed out that in order for an ensemble classifier to achieve higher prediction accuracy, it is critical for the ensemble classifier to consist of accurate classifiers which at the same time diverse as much as possible. In this paper, a novel ensemble pruning method, called PL-bagging, is proposed. In order to attain the balance between diversity and accuracy of base learners, PL-bagging employs positive Lasso to assign weights to base learners in the combination step. Simulation studies and theoretical investigation showed that PL-bagging filters out redundant base learners while it assigns higher weights to more accurate base learners. Such improved weighting scheme of PL-bagging further results in higher classification accuracy and the improvement becomes even more significant as the ensemble size increases. The performance of PL-bagging was compared with state-of-the-art ensemble pruning methods for aggregation of bootstrapped base learners using 22 real and 4 synthetic datasets. The results indicate that PL-bagging significantly outperforms state-of-the-art ensemble pruning methods such as Boosting-based pruning and Trimmed bagging.     

一种新型气动装袋装置研制

装袋是食用菌代替料生产过程中的一个重要环节。针对工作强度大、安全性低的现状,研发了一种新型气动工艺装袋机。实践结果表明:该设备能较好满足当前食用菌代料生产中装袋操作要求,且具有结构简单、生产率高、成本低、安全性好的特征。     

增强Fisher判决的Bagging集成分类方法

提出了一种样本间的相似性度量方法,并将这种相似性度量信息附加到Fisher线性判别的类内、类间离散度矩阵,使得Fisher判决准则在使类内距离迭最小、类间距离迭最大的同时,也使类内相似度迭最小、类间相似度达最大,获得比原始Fisher判剐更好的投影矩阵。实验证明,与Bagging集成的Fisherfaee比较,该方法显示出更好的识别率。     

基于Bagging集成学习的电力系统暂态稳定在线评估

针对传统机器学习在处理暂态稳定评估时所表现出的稳定性差、精度低等问题以及离线训练的局限性,提出一种基于多模型融合Bagging集成学习方式的电力系统暂态稳定在线评估模型。首先,结合人工智能前沿理论研究,分析了暂态稳定评估中常用的7种机器学习算法的原理及实现方式,通过Bagging方法进行集成,充分发挥各个模型的优势。其次,给出Bagging集成的数学实现方法并进行了仿真实验。当原系统拓扑结构发生改变时,采用Boosting算法和迁移成分分析,分别对原电网历史数据进行样本迁移和特征迁移,完成对所提模型的在线更新。通过采用IEEE10机39节点系统和IEEE16机68节点系统进行分析,结果表明所提方法比传统机器学习模型精度更高。当数据中掺杂噪声时能够保持稳定运行,在系统拓扑改变时能够通过迁移历史数据进行准确的暂态稳定评估。     

基于Bagging算法和遗传神经网络的交通事件检测

提出一种集成遗传神经网络的交通事件检测方法,以上下游的流量和占有率作为特征,RBF神经网络作为分类器进行交通事件的自动分类与检测。在RBF神经网络的训练过程中,采用遗传算法GA（Genetic Algorithm）对RBF神经网络的隐层中心值和宽度进行优化,用递推最小二乘法训练隐层和输出层之间的权值。为了提高神经网络的分类能力,采用Bagging算法,进行网络集成。通过Matlab仿真实验,证明该方法相对于传统的事件检测算法能更准确、快速地实现分类。     

Bagging组合的不平衡数据分类方法

提出一种基于Bagging组合的不平衡数据分类方法CombineBagging,采用少数类过抽样算法SMOTE进行数据预处理,在此基础上利用C-SVM、径向基函数神经网络、Random Forests 3种不同的基分类器学习算法,分别对采样后的数据样本进行Bagging集成学习,通过投票规则集成学习结果。实验结果表明,该方法能够提高少数类的分类准确率,有效处理不平衡数据分类问题。     

一种基于束状搜索的组合分类器修剪方法

以现有组合分类器修剪方法为基础,从增大搜索空间的角度出发,提出一种基于束状搜索的组合分类器修剪方法,在每一步增加或删除一个基分类器时都保存最优的前k个组合。该方法既保持了爬山搜索算法的高效剪枝特性,又能有效减小其过快收敛到局部最优解的可能性,使修剪得到的组合基分类器更接近于全局最优。与传统组合分类器修剪方法的对比结果表明,该方法修剪所得的组合分类器具有更高的分类准确率,并且组合规模也有所降低。     

Corrective classification: Learning from data imperfections with aggressive and diverse classifier ensembling

Learning from imperfect (noisy) information sources is a challenging and reality issue for many data mining applications. Common practices include data quality enhancement by applying data preprocessing techniques or employing robust learning algorithms to avoid developing overly complicated structures that overfit the noise. The essential goal is to reduce noise impact and eventually enhance the learners built from noise-corrupted data. In this paper, we propose a novel corrective classification (C2) design, which incorporates data cleansing, error correction, Bootstrap sampling and classifier ensembling for effective learning from noisy data sources. C2 differs from existing classifier ensembling or robust learning algorithms in two aspects. On one hand, a set of diverse base learners of C2 constituting the ensemble are constructed via a Bootstrap sampling process; on the other hand, C2 further improves each base learner by unifying error detection, correction and data cleansing to reduce noise impact. Being corrective, the classifier ensemble is built from data preprocessed/corrected by the data cleansing and correcting modules. Experimental comparisons demonstrate that C2 is not only more accurate than the learner built from original noisy sources, but also more reliable than Bagging [4] or aggressive classifier ensemble (ACE) [56], which are two degenerated components/variants of C2. The comparisons also indicate that C2 is more stable than Boosting and DECORATE, which are two state-of-the-art ensembling methods. For real-world imperfect information sources (i.e. noisy training and/or test data), C2 is able to deliver more accurate and reliable prediction models than its other peers can offer.     

一种基于投票法融合的ASTER遥感影像水体提取方法

遥感影像在水资源调查和洪涝灾害监测中发挥着重要作用,但从遥感影像中提取水体通常面临着阴影和狭小水体漏提等难题。针对单一方法在水体提取中的局限性,引入分类器集成的思想,提出一种基于投票法融合的水体提取方法,首先利用Bagging、Random Forests和神经网络(NN)分类器对遥感影像进行分类,然后采用多数投票法从决策层融合3个分类结果,得到研究区水体提取结果。试验结果表明,该方法能够有效去除阴影且能较好地识别狭小水体,具有良好的应用效果。     

Analysis of physical demands during bulk bag closing and sealing

Several tools are sold and recommended for closing and sealing flexible intermediate bulk containers (bulk bags) which are used to transport product that has been mined and processed. However, there is limited information on the risks, physical demands, or the benefits of using one tool over another. The purpose of this study was to evaluate the physical demands involved with two closing methods and several sealing tools in order to provide recommendations for selecting tools to reduce exposure to risk factors for work-related musculoskeletal disorders. In this study, twelve participants completed bag closing and sealing tasks using two different closing methods and eight sealing tools on two types of bulk bags. Physical demands and performance were evaluated using muscle activity, perceived exertion, subjective ratings of use, and time. Results indicate that using the “flowering” method to close bags required on average 32% less muscle activity, 30% less perceived exertion, 42% less time, and was preferred by participants compared to using the “snaking” method. For sealing, there was no single method significantly better across all measures; however, using a pneumatic cable tie gun consistently had the lowest muscle activity and perceived exertion ratings. The pneumatic cable tie gun did require approximately 33% more time to seal the bag compared to methods without a tool, but the amount of time to seal the bag was comparable to using other tools. Further, sealing a spout bulk bag required on average 13% less muscle activity, 18% less perceived exertion, 35% less time, and was preferred by participants compared to sealing a duffle bulk bag. The current results suggest that closing the spout bag using the flowering method and sealing the bag using the pneumatic cable tie gun that is installed with a tool balancer is ergonomically advantageous. Our findings can help organizations select methods and tools that pose the lowest physical demands when closing and sealing bulk bags.