RSSI_Indoor_IICUT

The Internet of Things (IoT) technology has revolutionized every aspect of everyday life by making everything smarter. IoT became more popular in recent years due to its vast applications in many fields such as smart cities, agriculture, healthcare, ambient assisted living, animal tracking, etc. Localization of a sensor node refers to knowing a sensor node's geographical location in the IoT network. In this research, we propose a device free indoor localization mechanism based on the Received Signal Strength Indicator (RSSI), a measure of the receiving signal from the sensor nodes, and supervised Machine Learning (ML) algorithms. An experimental test-bed was implanted in a controlled environment to collect RSSI values from the sensor nodes. The RSSI levels were collected by using multiple and published to a remote MQTT server over the Internet. In this research, RSSI values were used to train supervised ML algorithms, Linear Regression (LR), Polynomial Regression (PR), Decision Tree Regression (DTR), Support Vector Regression (SVR), and Random Forest Regressor (RFR) to estimate the accurate positioning of IoT related localization applications. The error between the actual measured values of the position and the estimated values are compared to validate the system model presented

物联网（IoT）技术通过使万物更智能化，彻底革新了日常生活的各个方面。近年来，物联网因其广泛的应用领域而日益受到关注，这些领域包括智慧城市、农业、医疗保健、辅助生活环境、动物追踪等。传感器节点的本地化指的是在物联网网络中确定传感器节点的地理位置。在本研究中，我们提出了一种基于接收信号强度指示器（RSSI）的设备无关室内定位机制，RSSI是衡量从传感器节点接收到的信号的一种度量，以及监督式机器学习（ML）算法。在可控环境中构建了一个实验测试平台，用于收集传感器节点的RSSI值。通过使用多个传感器，收集到的RSSI水平被发布到互联网上的远程MQTT服务器。在本研究中，利用RSSI值训练监督式ML算法，包括线性回归（LR）、多项式回归（PR）、决策树回归（DTR）、支持向量回归（SVR）和随机森林回归器（RFR），以估计与物联网相关的定位应用的准确位置。将实际测量的位置值与估计值之间的误差进行比较，以验证所提出的系统模型。