A novel design and data analytics for an electronic human resource management (e-HRM) system has been proposed in this article. E-HRM software is being widely used in big industries and institutions. This e-HRM is very cost-effective, competence, congruence, and commitment for the organization. At present, Internet of Things (IoT) have great impact on e-HRM, which gives various facilities and supports to e-HRM functionalities such as securities, standards, privacy, and regulations. The combination of e-HRM with IoT has wide applications for implementing policies, strategies, and practices within the organization. An e-HRM has mainly five activities: e-Selection, e-Recruitment, e-Performance, e-Compensation, and e-Learning. In this work, the proposed system has two parts. In the first part, the various e-HRM activities have been discussed and elaborated with examples. In the second part, the description of data analytics based on IoT for each e-HRM activity has been discussed and demonstrated. Here the data analytics part is divided into four components: (a) data preprocessing; (b) feature selection; (c) data classification; and (d) performance evaluation. Extensive experimentation has been performed for each e-HRM activity using four HR analytic datasets from Kaggle site, and finally, the performance with proper justifications has been exquisitely done using each dataset respect to each e-HRM activity.

中文翻译：

---

组织中通过物联网的电子人力资源管理活动的设计和数据分析

本文提出了一种用于电子人力资源管理 (e-HRM) 系统的新颖设计和数据分析。E-HRM 软件正被广泛应用于大型行业和机构。这种 e-HRM 对组织来说非常具有成本效益、能力、一致性和承诺。目前，物联网（IoT）对e-HRM的影响很大，它为e-HRM的安全、标准、隐私和法规等功能提供了各种便利和支持。e-HRM 与物联网的结合在组织内实施政策、战略和实践方面具有广泛的应用。e-HRM 主要有五种活动：e-Selection、e-Recruitment、e-Performance、e-Compensation 和 e-Learning。在这项工作中，所提出的系统有两个部分。在第一部分，已经讨论并举例说明了各种电子人力资源管理活动。在第二部分中，已经讨论和演示了基于 IoT 的每个 e-HRM 活动的数据分析的描述。这里的数据分析部分分为四个部分：(a) 数据预处理；(b) 特征选择；(c) 数据分类；(d) 绩效评估。使用来自 Kaggle 站点的四个 HR 分析数据集对每个 e-HRM 活动进行了广泛的实验，最后，使用每个 e-HRM 活动的每个数据集精心完成了具有适当理由的性能。(b) 特征选择；(c) 数据分类；(d) 绩效评估。使用来自 Kaggle 站点的四个 HR 分析数据集对每个 e-HRM 活动进行了广泛的实验，最后，使用每个 e-HRM 活动的每个数据集精心完成了具有适当理由的性能。(b) 特征选择；(c) 数据分类；(d) 绩效评估。使用来自 Kaggle 站点的四个 HR 分析数据集对每个 e-HRM 活动进行了广泛的实验，最后，使用每个 e-HRM 活动的每个数据集精心完成了具有适当理由的性能。