The expansion in the Internet of Things (IoT) has led to a shift towards smart technologies. IoT focuses on integrating networks to facilitate smooth services to humans. The interface between the mobility patterns and the routing protocols is considered to increase the performance of the network. However, incorporating security in the IoT network has been a major issue that continues to nurture with increasing IoT devices. This article addresses this issue by developing a novel technique, namely energy harvesting trust aware routing algorithm (EHTARA) for initiating a trust-based routing model in the IoT network in the presence of ambient energy sources. The cost metric is newly devised by considering energy, distance, and trust parameters for determining the best path. At the base station, big data classification is performed using the adaptive exponential-Bat (adaptive E-Bat) algorithm based deep belief network (DBN). The training of DBN is performed using the adaptive E-Bat algorithm, which is the combination of adaptive concept, exponential weighted moving average (EWMA), and Bat algorithm (BA). Here, the optimization-based map-reduce framework helps to deal with the imbalanced data by adapting the deep learning in classification. The proposed EHTARA outperformed other methods with a maximal energy of 0.927.

中文翻译：

---

物联网网络的信任和能量感知路由算法

物联网 (IoT) 的扩展导致向智能技术的转变。物联网专注于整合网络以促进为人类提供顺畅的服务。移动模式和路由协议之间的接口被认为可以提高网络的性能。然而，在物联网网络中加入安全性一直是一个主要问题，随着物联网设备的增加而不断发展。本文通过开发一种新技术来解决这个问题，即能量收集信任感知路由算法 (EHTARA)，用于在存在环境能源的情况下在物联网网络中启动基于信任的路由模型。成本度量是通过考虑用于确定最佳路径的能量、距离和信任参数而新设计的。在基站，大数据分类使用基于深度信念网络 (DBN) 的自适应指数蝙蝠 (adaptive E-Bat) 算法执行。DBN 的训练使用自适应 E-Bat 算法进行，该算法是自适应概念、指数加权移动平均 (EWMA) 和 Bat 算法 (BA) 的结合。在这里，基于优化的 map-reduce 框架通过在分类中适应深度学习来帮助处理不平衡的数据。提出的 EHTARA 以 0.927 的最大能量优于其他方法。基于优化的 map-reduce 框架通过在分类中适应深度学习来帮助处理不平衡的数据。提出的 EHTARA 以 0.927 的最大能量优于其他方法。基于优化的 map-reduce 框架通过在分类中适应深度学习来帮助处理不平衡的数据。提出的 EHTARA 以 0.927 的最大能量优于其他方法。