Distributed Self-Localization with Improved Optimization with Machine Learning in IoT Applications

The Internet of things (IoT) is one of the most trending technologies which is used to monitor a huge number of devices worldwide. Device localization and optimal path selection is very essential in this technology to maintain the communication standard of the devices. To reduce the delay and power utilization of the devices and to attend high efficiency these parameters are needed to get concentrated. For that in this article distributed self-localization with an improved optimization model is developed using machine learning (DSLIOM) algorithms. The core modules of this article are efficient data processing analysis and improved optimization algorithm. The parameters which are calculated to analyses the performance are data success rate, network throughput, routing overhead, data loss rate and delay. From the result it is proven that this DSLIOM attends better performance than earlier works in terms of data success rate and the network throughput.