No abstract

No abstract

Governments, companies, universities and research institutes are pushing the research and development of cyber-physical systems (CPS). However, the development of cyberphysical systems is constrained by security factors. According to this situation, this paper put forward a CPS security model, which contains security objectives, basic theories, simulation, and CPS framework, summarizes security attacks to cyber-physical systems as a theoretical reference for the study of cyber-physical systems and to provide useful security defense. Based on the cyber-physical systems framework, the paper classifies attacks for the execution layer, transport layer and control layer. The execution layer attacks include security attacks for nodes such as sensors and actuators. Transport layer attacks include data leakage or damage and security issues during massive data integration. Control layer attacks include the loss of user privacy, incorrect access control policies and inadequate security standards. This paper gives security defenses and recommendations for all types of security attacks. Finally, this paper introduces categorizations of CPS application fields and explores their relationships.

Today, cyber physical systems (CPS)

To facilitate product developers capturing the varying requirements from users to support their feature evolution process, requirements evolution prediction from massive review texts is in fact of great importance. The proposed framework combines a supervised deep learning neural network with an unsupervised hierarchical topic model to analyze user reviews automatically for product feature requirements evolution prediction. The approach is to discover hierarchical product feature requirements from the hierarchical topic model and to identify their sentiment by the Long Short-term Memory (LSTM) with word embedding, which not only models hierarchical product requirement features from general to specific, but also identifies sentiment orientation to better correspond to the different hierarchies of product features. The evaluation and experimental results show that the proposed approach is effective and feasible.