No abstract

Many studies utilized machine learning schemes to improve network intrusion detection systems recently. Most of the research is based on manually extracted features, but this approach not only requires a lot of labor costs but also loses a lot of information in the original data, resulting in low judgment accuracy and cannot be deployed in actual situations. This paper develops a DL-IDS (deep learning-based intrusion detection system), which uses the hybrid network of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) to extract the spatial and temporal features of network traffic data and to provide a better intrusion detection system. To reduce the influence of an unbalanced number of samples of different attack types in model training samples on model performance, DL-IDS used a category weight optimization method to improve the robustness. Finally, DL-IDS is tested on CICIDS2017, a reliable intrusion detection dataset that covers all the common, updated intrusions and cyberattacks. In the multiclassification test, DL-IDS reached 98.67% in overall accuracy, and the accuracy of each attack type was above 99.50%.

No abstract

Nowadays, as the manufacturing outsourcing activities are becoming increasingly explosive, cutting-tools are gradually being considered as a kind of strategical socialized manufacturing resource. Therefore, focusing on cutting-tools, this article proposes a novel cutting-tool service mode called industrial product service system for cutting-tools. Based on industrial product service system for cutting-tools, the methodology of cutting-tool delivery in the context of industrial product service system is further studied, which comprises two sub-models. First, a cutting-tool demand prediction model is established to obtain the types and quantities of cutting-tool demands in the next day from each industrial product service system for cutting-tool customer. Then, the second sub-model is a just-in-time cutting-tool delivery model, wherein, a modified economic order quantity model and genetic algorithm are applied to optimize the delivery time and routing constrained by the delivery time window. Finally, a comprehensive use case is studied to illustrate the feasibility and applicability of the proposed models.