基于文本分类的Fisher Score快速多标记特征选择算法

Fisher Score （FS）是一种快速高效的评价特征分类能力的指标,但传统的FS指标既无法直接应用于多标记学习,也不能有效处理样本极值导致的类中心与实际类中心的误差。提出一种结合中心偏移和多标记集合关联性的FS多标记特征选择算法,找出不同标记下每类样本的极值点,以极值点到该类样本的中心距离乘以半径系数筛选新的样本,从而获得分布更为密集的样本集合,以此计算特征的FS得分,通过整体遍历全体样本的标记集合中的每个标记,并在遍历过程中针对具有更多标记数量的样本自适应地赋以标记权值,得到整体特征的平均FS得分,以特征的FS得分进行排序过滤出目标子集实现特征选择目标。在8个公开的多标记文本数据集上进行参数分析及5种指标性能比较,结果表明,该算法具有一定的有效性和鲁棒性,在多数指标上优于MLNB、MLRF、PMU、MLACO等多标记特征选择算法。     

基于Fisher Score与最大信息系数的齿轮箱故障特征选择方法

因果网络定向问题实质是一个“多对多”因果关系发现过程,传统的V-结构定向方法只能确定一组马尔可夫等价类而非最终的因果关系.为解决该问题,从柯氏复杂度的因果推断原理视角出发,利用贝叶斯链式法则推导出局部网络因果定向规则,并在此基础上提出高维全局网络因果定向方法.同时,将前者运用于改进基于局部条件独立信息搜索学习马尔可夫毯典型算法,后者运用于改进基于约束的因果网络结构学习典型算法.实验结果表明,改进后算法在保证较高准确率的同时可有效提升执行效率.     

Datification,Organizational Strategy,and IS Research: What’s the Score?

This commentary on the JSIS Special Issue on datification focuses on two key themes selected from among the many topics discussed by Special Issue authors: 1) the debate over algorithmic intelligence versus human intelligence, and 2) the consequences of strategic performance systems.The current algorithmic versus human intelligence debate echoes earlier discussions in our field about whether expert systems should replace or support human experts. As appealing as it is to assume that algorithms support expert workers, research suggests that people are not very effective at monitoring and overriding automation. In addition, post-automation work tends to evolve toward lower human knowledge and skill. These observations should caution datification researchers against simplistic theories and should guide researchers to study the multilevel sociotechnical conditions and stakeholders involved in the design, use, and consequences of algorithms in organizations.Strategic performance measurement and ranking systems are also not new, but what is new is the belief that they will not just inform, but also transform, human behavior. In this respect, performance systems resemble the career tournaments that promote intense competition and create great inequality in executive pay and promotion. In addition, performance systems increasing serve as infrastructures, operating at multiple levels of analysis simultaneously. These observations imply that designing and studying such systems involve ethical choices, intensifying the demands on datification researchers.