Traditional rule-based Intrusion Detection Systems (IDS) are commonly employed owing to their simple design and ability to detect known threats. Nevertheless, as dynamic network traffic and a new degree of threats exist in IoT environments, these systems do not perform well and have elevated false positive rates—consequently decreasing detection accuracy. In this study, we try to overcome these restrictions by employing fuzzy logic and machine learning to develop an Enhanced Rule-Based Model (ERBM) to classify the packets better and identify intrusions. The ERBM developed for this approach improves data preprocessing and feature selections by utilizing fuzzy logic, where three membership functions are created to classify all the network traffic features as low, medium, or high to remain situationally aware of the environment. Such fuzzy logic sets produce adaptive detection rules by reducing data uncertainty. Also, for further classification, machine learning classifiers such as Decision Tree (DT), Random Forest (RF), and Neural Networks (NN) learn complex ways of attacks and make the detection process more precise. A thorough performance evaluation using different metrics, including accuracy, precision, recall, F1 Score, detection rate, and false-positive rate, verifies the supremacy of ERBM over classical IDS. Under extensive experiments, the ERBM enables a remarkable detection rate of 99% with considerably fewer false positives than the conventional models. Integrating the ability for uncertain reasoning with fuzzy logic and an adaptable component via machine learning solutions, the ERBM system provides a unique, scalable, data-driven approach to IoT intrusion detection. This research presents a major enhancement initiative in the context of rule-based IDS, introducing improvements in accuracy to evolving IoT threats.

In situations when the precise position of a machine is unknown, localization becomes crucial. This research focuses on improving the position prediction accuracy over long-range (LoRa) network using an optimized machine learning-based technique. In order to increase the prediction accuracy of the reference point position on the data collected using the fingerprinting method over LoRa technology, this study proposed an optimized machine learning (ML) based algorithm. Received signal strength indicator (RSSI) data from the sensors at different positions was first gathered via an experiment through the LoRa network in a multistory round layout building. The noise factor is also taken into account, and the signal-to-noise ratio (SNR) value is recorded for every RSSI measurement. This study concludes the examination of reference point accuracy with the modified KNN method (MKNN). MKNN was created to more precisely anticipate the position of the reference point. The findings showed that MKNN outperformed other algorithms in terms of accuracy and complexity.