Military tasks constitute the most important and significant applications of WSNs. In military, Sensor node deployment increases activities, efficient operation, saves loss of life, and protects national sovereignty. Usually, the main difficulties in military missions are energy consumption and security in the network. Another major security issues are hacking or masquerade attack. To overcome the limitations, the proposed method modified DBSCAN with OSPREY optimization Algorithm (OOA) using hybrid classifier Long Short-Term Memory (LSTM) with Extreme Gradient Boosting (XGBOOST) to detect attack types in the WSN military sector for enhancing security. First, nodes are deployed and modified DBSCAN algorithm is used to cluster the nodes to reduce energy consumption. To select the cluster head optimally by using the OSPREY optimization Algorithm (OOA) based on small distance and high energy for transfer data between the base station and nodes. Hybrid LSTM-XGBOOST classifier utilized to learn the parameter and predict the four assault types such as scheduling, flooding, blackhole and grayhole assault. Classification and network metrics including Packet Delivery Ratio (PDR), Throughput, Average Residual Energy (ARE), Packet Loss Ratio (PLR), Accuracy and F1_score are used to evaluate the performance of the model. Performance results show that PDR of 94.12%, 3.2 Mbps throughput at 100 nodes, ARE of 8.94J, PLR of 5.88%, accuracy of 96.14%, and F1_score of 95.04% are achieved. Hence, the designed model for assault prediction types in WSN based on modified DBSCAN clustering with a hybrid classifier yields better results.

An intelligent distributed network system is the Wireless Sensor Network (WSN), which is a strategy required to address security threats as well as energy consumption that has a direct impact on a network’s lifetime. Thus, attempting to identify malicious attacks with a low consumption of data transmission makes a lot of sense. The high energy consumption of nodes due to the transmission of data shortens the lifetime of the network. To overcome these issues, the proposed method is based on the Ordering Points to Identify Cluster Structure (OPTICS) with Bi-directional Long Short Term Memory using Differential evolution (DE-BiLSTM) classifier to detect the threats in WSN for smart building. Initial deployment of the sensor nodes (SN) and formation of the cluster nodes (CN) by employing the OPTICS density-based clustering approach that partitions clusters with different densities. In order to transport data to the base station, the cluster head (CH) nodes are chosen from the CN according to their more energy as well as shorter distance. Then, in order to forecast the threats, the size of the batch and hidden layers are set using the differential evolution method (DE) and the classification of the data is performed using BiLSTM to detect as attack or non-attack. Performance for predicting an attack is measured by network and classification parameters such as Packet Delivery Ratio (PDR), Average Residual Energy (ARE), Throughput, Accuracy and Precision. The results of the performance obtained are 91.78% for PDR, 8.56J for ARE, 2.52mbps for throughput with 100 nodes, then 93.78% for accuracy and 93.04% for precision. Thus, the designed detection of threats in WSN based on OPTICS clustering with DE-BILSTM classifier performs better for malicious attack prediction with low energy consumption sensor nodes.