The increasing popularity of the Internet of Things (IoT) has significantly impacted our daily lives in the past few years. On one hand, it brings convenience, simplicity, and efficiency for us; on the other hand, the devices are susceptible to various cyber-attacks due to the lack of solid security mechanisms and hardware security support. In this paper, we present IMIDS, an intelligent intrusion detection system (IDS) to protect IoT devices. IMIDS’s core is a lightweight convolutional neural network model to classify multiple cyber threats. To mitigate the training data shortage issue, we also propose an attack data generator powered by a conditional generative adversarial network. In the experiment, we demonstrate that IMIDS could detect nine cyber-attack types (e.g., backdoors, shellcode, worms) with an average F-measure of 97.22% and outperforms its competitors. Furthermore, IMIDS’s detection performance is notably improved after being further trained by the data generated by our attack data generator. These results demonstrate that IMIDS can be a practical IDS for the IoT scenario.

No abstract

No abstract

No abstract

For cable structures, the tension force is one of the main factors showing the structure’s health. If the tension force falls below a safe level during construction or operation, it can lead to partial or complete the structural failure, posing a risk to the people’s safety. In this study, a parallel structural health monitoring approach of the vibration-based and impedance-based methods is proposed to identify the tension force in cable structures. Firstly, a cable structure including the anchorage is simulated using a finite element model to obtain the vibration and impedance responses. The numerical results are verified with the experimental ones of the previous studies. Then, the parallel approach combining the above two methods is presented to determine the tension force. For the vibration-based method, the tension force is estimated by the natural frequencies. For the impedance-based method, the tension force is estimated by the mean absolute percentage deviation (MAPD) index and the artificial neural network (ANN). Finally, the tension force estimation results are compared and assessed. By using the parallel approach, the reliability and accuracy of the tension force identification results are guaranteed.