Monitoring the border is a very important task for national security. Wireless sensor networks (WSN) appear well suited in this application. This work aims to monitor a large-scale geographical framework that represents the borders of countries. Researchers take the Tunisian Algerian border as an example. This border is labeled by the illegal passage of intruders between the two countries. The task is to identify the intruders and study their kinematics based on speed, acceleration, and bearing. The appropriate types of sensors are determined according to the nature of intruders. Six classification techniques are compared which are: Naïve Bayes, Support Vector Machine (SVM), Multilayer Perceptron, Best First Decision Tree (BF-Tree), Logistic Alternating Decision Tree (LAD-Tree), and J48. The comparison of the performance of the classification techniques is provided in terms of correct differentiation rates, confusion matrices, and the time taken to build each model. Four different levels of cross-validation are used to validate the classifiers. The results indicate that J48 has achieved the highest correct classification rate with a relatively low model-building time.
To enhance target detection and tracking in real-world environments, it is crucial to consider the impact of weather and other environmental factors on sensor readings in addition to minimizing false alarms. This goal can be achieved through the implementation of machine learning algorithms that incorporate these parameters as predictors. To demonstrate the superiority of a machine learning-based solution in reducing false alarms and improving target detection accuracy in Wireless Sensor Networks (WSNs), the performance of algorithms such as K-Nearest Neighbors, Logistic Regression, Decision Trees, and Random Forest is compared. This paper incorporates environmental factors, such as weather, to improve target detection accuracy in real-world scenarios. The simulation results demonstrate the effectiveness of the proposed approach in reducing false alarms in WSNs using machine learning algorithms.
Coverage and connectivity in wireless sensor networks (WSN) have been greatly studied in several researches. Actually, WSN have been applied in open-pit mines and underground tunnels to detect damages at real times. In this article, we treat the case of open-pit mines in Tunisia. Health mines monitoring use largely wireless sensors. Wireless Open-pit Mines Health Monitoring (WMHM) applications have a crucial importance for the company as a whole. We aim to get a wireless sensor network with higher degree of coverage, means having well detection and achieved connectivity. Thus, it is clear that sensor arrays face a number of challenges due to coverage such as the number of sensor nodes to be deployed, the deployment method in open-pit mining and underground tunnel, the communication and detection ranges associated with the sensor nodes, etc. In this paper we address the problem of wsn connectivity and coverage in mining area and tunnels. We study and detection and their impact on coverage in wireless sensor networks. We propose models which can be used as a suitable solution for tunnels monitoring system.