A Novel Approach to IoT Device Identification via Anti‐Interference Dynamic Integral Neural Network and Multiobjective Fitness‐Dependent Optimizer Algorithm

ABSTRACT The Internet of Things (IoT) has observed an accelerated development in the quantity of applications due to the rapid development of information technology. It can be difficult to identify IoT devices in heterogeneous, interference‐prone networks. The accuracy, optimization, and robustness of existing techniques are insufficient for dependable classification and application detection. To overcome this complication, a novel approach for IoT device identification using an anti‐interference dynamic integral neural network (AIDINN) and a multiobjective fitness‐dependent optimizer algorithm (MOFDOA) (IoT‐DTI‐AIDINN‐MOFDOA) is proposed. The input data are collected from the Network Traffic Dataset. Then, the input data are given to feature extraction. By using the synchro‐transient‐extracting transform (STET), the features are extracted from the dataset. Then the extracted features are given to AIDINN for IoT device identification, which classifies known IoT devices and unknown IoT devices. In general, AIDINN does not adopt any optimization techniques to determine the ideal parameters for ensuring an accurate IoT device identification. Hence, an MOFDOA is proposed here to optimize the AIDINN, which precisely constructs the IoT application detection. The performance measures like accuracy, precision, recall, specificity, F measure, computational time, and computational complexity are evaluated. The proposed IoT‐DTI‐AIDINN‐MOFDOA method attains a higher accuracy of 25.23%, 16.12%, and 21.27% and a higher precision of 25.26%, 16.22%, and 26.27% when analyzed with the following existing models: IoT device type detection using deep neural network (IoT‐DTI‐DNN), adversarial attacks and IoT for long short‐term memory (AA‐IoT‐LSTM), and IoT device identification depending on fully connected neural network (IoT‐DI‐FCNN), respectively.